{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 7132, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00014022295449765126, "grad_norm": 41.75437927246094, "learning_rate": 0.0, "loss": 2.027681350708008, "step": 1 }, { "epoch": 0.0002804459089953025, "grad_norm": 35.45913314819336, "learning_rate": 4.672897196261682e-08, "loss": 1.8763107061386108, "step": 2 }, { "epoch": 0.0004206688634929538, "grad_norm": 45.003238677978516, "learning_rate": 9.345794392523364e-08, "loss": 1.8533108234405518, "step": 3 }, { "epoch": 0.000560891817990605, "grad_norm": 42.53562927246094, "learning_rate": 1.4018691588785048e-07, "loss": 1.7366639375686646, "step": 4 }, { "epoch": 0.0007011147724882563, "grad_norm": 81.45015716552734, "learning_rate": 1.8691588785046729e-07, "loss": 2.3943405151367188, "step": 5 }, { "epoch": 0.0008413377269859076, "grad_norm": 33.350826263427734, "learning_rate": 2.3364485981308412e-07, "loss": 1.8055672645568848, "step": 6 }, { "epoch": 0.0009815606814835588, "grad_norm": 37.4820442199707, "learning_rate": 2.8037383177570096e-07, "loss": 1.6457951068878174, "step": 7 }, { "epoch": 0.00112178363598121, "grad_norm": 46.69675827026367, "learning_rate": 3.2710280373831776e-07, "loss": 1.855057954788208, "step": 8 }, { "epoch": 0.0012620065904788613, "grad_norm": 40.395286560058594, "learning_rate": 3.7383177570093457e-07, "loss": 1.7073394060134888, "step": 9 }, { "epoch": 0.0014022295449765125, "grad_norm": 42.43779373168945, "learning_rate": 4.2056074766355143e-07, "loss": 1.8145322799682617, "step": 10 }, { "epoch": 0.001542452499474164, "grad_norm": 82.55043029785156, "learning_rate": 4.6728971962616824e-07, "loss": 1.7282485961914062, "step": 11 }, { "epoch": 0.0016826754539718152, "grad_norm": 49.17936325073242, "learning_rate": 5.140186915887851e-07, "loss": 1.7214298248291016, "step": 12 }, { "epoch": 0.0018228984084694665, "grad_norm": 48.93755340576172, "learning_rate": 5.607476635514019e-07, "loss": 2.008028745651245, "step": 13 }, { "epoch": 0.0019631213629671177, "grad_norm": 32.49382400512695, "learning_rate": 6.074766355140187e-07, "loss": 1.6834228038787842, "step": 14 }, { "epoch": 0.002103344317464769, "grad_norm": 37.4005012512207, "learning_rate": 6.542056074766355e-07, "loss": 1.4686461687088013, "step": 15 }, { "epoch": 0.00224356727196242, "grad_norm": 33.60232925415039, "learning_rate": 7.009345794392523e-07, "loss": 1.5762226581573486, "step": 16 }, { "epoch": 0.0023837902264600714, "grad_norm": 31.391386032104492, "learning_rate": 7.476635514018691e-07, "loss": 1.6166822910308838, "step": 17 }, { "epoch": 0.0025240131809577226, "grad_norm": 40.99386215209961, "learning_rate": 7.94392523364486e-07, "loss": 1.610270380973816, "step": 18 }, { "epoch": 0.002664236135455374, "grad_norm": 32.285972595214844, "learning_rate": 8.411214953271029e-07, "loss": 1.5368175506591797, "step": 19 }, { "epoch": 0.002804459089953025, "grad_norm": 33.43672180175781, "learning_rate": 8.878504672897197e-07, "loss": 1.2177274227142334, "step": 20 }, { "epoch": 0.0029446820444506768, "grad_norm": 30.572528839111328, "learning_rate": 9.345794392523365e-07, "loss": 1.2340996265411377, "step": 21 }, { "epoch": 0.003084904998948328, "grad_norm": 35.078208923339844, "learning_rate": 9.813084112149534e-07, "loss": 1.3235970735549927, "step": 22 }, { "epoch": 0.0032251279534459792, "grad_norm": 35.90279769897461, "learning_rate": 1.0280373831775702e-06, "loss": 1.349792718887329, "step": 23 }, { "epoch": 0.0033653509079436305, "grad_norm": 20.7570743560791, "learning_rate": 1.074766355140187e-06, "loss": 1.3107020854949951, "step": 24 }, { "epoch": 0.0035055738624412817, "grad_norm": 38.34511184692383, "learning_rate": 1.1214953271028038e-06, "loss": 1.3046934604644775, "step": 25 }, { "epoch": 0.003645796816938933, "grad_norm": 22.82797622680664, "learning_rate": 1.1682242990654206e-06, "loss": 1.1309937238693237, "step": 26 }, { "epoch": 0.003786019771436584, "grad_norm": 20.907651901245117, "learning_rate": 1.2149532710280374e-06, "loss": 1.2902169227600098, "step": 27 }, { "epoch": 0.003926242725934235, "grad_norm": 15.745122909545898, "learning_rate": 1.2616822429906543e-06, "loss": 1.0385704040527344, "step": 28 }, { "epoch": 0.004066465680431887, "grad_norm": 23.951025009155273, "learning_rate": 1.308411214953271e-06, "loss": 1.0527769327163696, "step": 29 }, { "epoch": 0.004206688634929538, "grad_norm": 11.67510986328125, "learning_rate": 1.3551401869158879e-06, "loss": 1.0014690160751343, "step": 30 }, { "epoch": 0.0043469115894271895, "grad_norm": 20.033222198486328, "learning_rate": 1.4018691588785047e-06, "loss": 0.9132629632949829, "step": 31 }, { "epoch": 0.00448713454392484, "grad_norm": 13.379271507263184, "learning_rate": 1.4485981308411215e-06, "loss": 0.9409018754959106, "step": 32 }, { "epoch": 0.004627357498422492, "grad_norm": 17.33014678955078, "learning_rate": 1.4953271028037383e-06, "loss": 0.8403022885322571, "step": 33 }, { "epoch": 0.004767580452920143, "grad_norm": 7.492353439331055, "learning_rate": 1.542056074766355e-06, "loss": 0.8468807339668274, "step": 34 }, { "epoch": 0.0049078034074177945, "grad_norm": 11.740361213684082, "learning_rate": 1.588785046728972e-06, "loss": 0.8744781017303467, "step": 35 }, { "epoch": 0.005048026361915445, "grad_norm": 13.542364120483398, "learning_rate": 1.6355140186915887e-06, "loss": 0.9327365756034851, "step": 36 }, { "epoch": 0.005188249316413097, "grad_norm": 15.039802551269531, "learning_rate": 1.6822429906542057e-06, "loss": 0.8858104348182678, "step": 37 }, { "epoch": 0.005328472270910748, "grad_norm": 18.740005493164062, "learning_rate": 1.7289719626168225e-06, "loss": 0.8500158786773682, "step": 38 }, { "epoch": 0.005468695225408399, "grad_norm": 7.143667221069336, "learning_rate": 1.7757009345794394e-06, "loss": 0.8495869636535645, "step": 39 }, { "epoch": 0.00560891817990605, "grad_norm": 6.515839099884033, "learning_rate": 1.8224299065420562e-06, "loss": 0.8435910940170288, "step": 40 }, { "epoch": 0.005749141134403702, "grad_norm": 10.410655975341797, "learning_rate": 1.869158878504673e-06, "loss": 0.9758667945861816, "step": 41 }, { "epoch": 0.0058893640889013535, "grad_norm": 14.952445983886719, "learning_rate": 1.9158878504672898e-06, "loss": 0.9568907022476196, "step": 42 }, { "epoch": 0.006029587043399004, "grad_norm": 9.571800231933594, "learning_rate": 1.962616822429907e-06, "loss": 0.7570854425430298, "step": 43 }, { "epoch": 0.006169809997896656, "grad_norm": 26.06985092163086, "learning_rate": 2.0093457943925234e-06, "loss": 0.8385471701622009, "step": 44 }, { "epoch": 0.006310032952394307, "grad_norm": 9.937033653259277, "learning_rate": 2.0560747663551404e-06, "loss": 0.8587227463722229, "step": 45 }, { "epoch": 0.0064502559068919585, "grad_norm": 8.588506698608398, "learning_rate": 2.102803738317757e-06, "loss": 0.7549892067909241, "step": 46 }, { "epoch": 0.006590478861389609, "grad_norm": 20.336130142211914, "learning_rate": 2.149532710280374e-06, "loss": 0.8323598504066467, "step": 47 }, { "epoch": 0.006730701815887261, "grad_norm": 6.515740871429443, "learning_rate": 2.1962616822429906e-06, "loss": 0.6833214163780212, "step": 48 }, { "epoch": 0.006870924770384912, "grad_norm": 5.2175493240356445, "learning_rate": 2.2429906542056077e-06, "loss": 0.6960177421569824, "step": 49 }, { "epoch": 0.007011147724882563, "grad_norm": 10.722951889038086, "learning_rate": 2.2897196261682247e-06, "loss": 0.8222728371620178, "step": 50 }, { "epoch": 0.007151370679380214, "grad_norm": 10.205052375793457, "learning_rate": 2.3364485981308413e-06, "loss": 0.8136335015296936, "step": 51 }, { "epoch": 0.007291593633877866, "grad_norm": 13.582768440246582, "learning_rate": 2.3831775700934583e-06, "loss": 0.7290695905685425, "step": 52 }, { "epoch": 0.007431816588375517, "grad_norm": 5.564488887786865, "learning_rate": 2.429906542056075e-06, "loss": 0.7481948137283325, "step": 53 }, { "epoch": 0.007572039542873168, "grad_norm": 5.5864763259887695, "learning_rate": 2.476635514018692e-06, "loss": 0.8280171751976013, "step": 54 }, { "epoch": 0.00771226249737082, "grad_norm": 5.6350202560424805, "learning_rate": 2.5233644859813085e-06, "loss": 0.7321093082427979, "step": 55 }, { "epoch": 0.00785248545186847, "grad_norm": 7.056332588195801, "learning_rate": 2.570093457943925e-06, "loss": 0.7492762804031372, "step": 56 }, { "epoch": 0.007992708406366122, "grad_norm": 8.158387184143066, "learning_rate": 2.616822429906542e-06, "loss": 0.627120852470398, "step": 57 }, { "epoch": 0.008132931360863774, "grad_norm": 4.903497695922852, "learning_rate": 2.6635514018691587e-06, "loss": 0.7976604700088501, "step": 58 }, { "epoch": 0.008273154315361424, "grad_norm": 7.031196117401123, "learning_rate": 2.7102803738317757e-06, "loss": 0.6955508589744568, "step": 59 }, { "epoch": 0.008413377269859076, "grad_norm": 5.546510219573975, "learning_rate": 2.7570093457943923e-06, "loss": 0.8266729116439819, "step": 60 }, { "epoch": 0.008553600224356727, "grad_norm": 5.674646854400635, "learning_rate": 2.8037383177570094e-06, "loss": 0.7578063011169434, "step": 61 }, { "epoch": 0.008693823178854379, "grad_norm": 6.366845607757568, "learning_rate": 2.8504672897196264e-06, "loss": 0.8715668320655823, "step": 62 }, { "epoch": 0.008834046133352029, "grad_norm": 18.185630798339844, "learning_rate": 2.897196261682243e-06, "loss": 0.7191293239593506, "step": 63 }, { "epoch": 0.00897426908784968, "grad_norm": 4.142700672149658, "learning_rate": 2.94392523364486e-06, "loss": 0.7828853130340576, "step": 64 }, { "epoch": 0.009114492042347332, "grad_norm": 6.930135726928711, "learning_rate": 2.9906542056074766e-06, "loss": 0.7844122052192688, "step": 65 }, { "epoch": 0.009254714996844984, "grad_norm": 5.968459129333496, "learning_rate": 3.0373831775700936e-06, "loss": 0.6368163228034973, "step": 66 }, { "epoch": 0.009394937951342636, "grad_norm": 7.025407791137695, "learning_rate": 3.08411214953271e-06, "loss": 0.7469204664230347, "step": 67 }, { "epoch": 0.009535160905840286, "grad_norm": 8.731856346130371, "learning_rate": 3.1308411214953272e-06, "loss": 0.6620163917541504, "step": 68 }, { "epoch": 0.009675383860337937, "grad_norm": 5.243095874786377, "learning_rate": 3.177570093457944e-06, "loss": 0.8362154960632324, "step": 69 }, { "epoch": 0.009815606814835589, "grad_norm": 3.988215446472168, "learning_rate": 3.224299065420561e-06, "loss": 0.6443442106246948, "step": 70 }, { "epoch": 0.00995582976933324, "grad_norm": 11.115423202514648, "learning_rate": 3.2710280373831774e-06, "loss": 0.7106008529663086, "step": 71 }, { "epoch": 0.01009605272383089, "grad_norm": 8.018771171569824, "learning_rate": 3.3177570093457945e-06, "loss": 0.829011082649231, "step": 72 }, { "epoch": 0.010236275678328542, "grad_norm": 3.764375686645508, "learning_rate": 3.3644859813084115e-06, "loss": 0.6206546425819397, "step": 73 }, { "epoch": 0.010376498632826194, "grad_norm": 11.42310619354248, "learning_rate": 3.411214953271028e-06, "loss": 0.6857424974441528, "step": 74 }, { "epoch": 0.010516721587323846, "grad_norm": 8.590436935424805, "learning_rate": 3.457943925233645e-06, "loss": 0.6488102674484253, "step": 75 }, { "epoch": 0.010656944541821495, "grad_norm": 7.661379814147949, "learning_rate": 3.5046728971962617e-06, "loss": 0.6866803765296936, "step": 76 }, { "epoch": 0.010797167496319147, "grad_norm": 6.1490864753723145, "learning_rate": 3.5514018691588787e-06, "loss": 0.855787456035614, "step": 77 }, { "epoch": 0.010937390450816799, "grad_norm": 5.787054538726807, "learning_rate": 3.5981308411214953e-06, "loss": 0.7099299430847168, "step": 78 }, { "epoch": 0.01107761340531445, "grad_norm": 6.2028093338012695, "learning_rate": 3.6448598130841123e-06, "loss": 0.7097862958908081, "step": 79 }, { "epoch": 0.0112178363598121, "grad_norm": 6.913258075714111, "learning_rate": 3.691588785046729e-06, "loss": 0.7781422138214111, "step": 80 }, { "epoch": 0.011358059314309752, "grad_norm": 4.637197017669678, "learning_rate": 3.738317757009346e-06, "loss": 0.7103097438812256, "step": 81 }, { "epoch": 0.011498282268807404, "grad_norm": 25.62066078186035, "learning_rate": 3.785046728971963e-06, "loss": 0.763434648513794, "step": 82 }, { "epoch": 0.011638505223305055, "grad_norm": 5.851142406463623, "learning_rate": 3.8317757009345796e-06, "loss": 0.7044357061386108, "step": 83 }, { "epoch": 0.011778728177802707, "grad_norm": 25.18638801574707, "learning_rate": 3.878504672897196e-06, "loss": 0.6218277215957642, "step": 84 }, { "epoch": 0.011918951132300357, "grad_norm": 5.505525588989258, "learning_rate": 3.925233644859814e-06, "loss": 0.6292622685432434, "step": 85 }, { "epoch": 0.012059174086798009, "grad_norm": 7.808413028717041, "learning_rate": 3.97196261682243e-06, "loss": 0.6420274972915649, "step": 86 }, { "epoch": 0.01219939704129566, "grad_norm": 4.1569647789001465, "learning_rate": 4.018691588785047e-06, "loss": 0.679512619972229, "step": 87 }, { "epoch": 0.012339619995793312, "grad_norm": 8.610003471374512, "learning_rate": 4.065420560747663e-06, "loss": 0.6741341948509216, "step": 88 }, { "epoch": 0.012479842950290962, "grad_norm": 21.578176498413086, "learning_rate": 4.112149532710281e-06, "loss": 0.7360944747924805, "step": 89 }, { "epoch": 0.012620065904788614, "grad_norm": 6.585391044616699, "learning_rate": 4.1588785046728974e-06, "loss": 0.7122312188148499, "step": 90 }, { "epoch": 0.012760288859286265, "grad_norm": 8.91394329071045, "learning_rate": 4.205607476635514e-06, "loss": 0.6889052391052246, "step": 91 }, { "epoch": 0.012900511813783917, "grad_norm": 14.799596786499023, "learning_rate": 4.2523364485981315e-06, "loss": 0.7649226188659668, "step": 92 }, { "epoch": 0.013040734768281567, "grad_norm": 13.776300430297852, "learning_rate": 4.299065420560748e-06, "loss": 0.7840640544891357, "step": 93 }, { "epoch": 0.013180957722779219, "grad_norm": 16.466203689575195, "learning_rate": 4.345794392523365e-06, "loss": 0.6336718797683716, "step": 94 }, { "epoch": 0.01332118067727687, "grad_norm": 4.586424827575684, "learning_rate": 4.392523364485981e-06, "loss": 0.7490583658218384, "step": 95 }, { "epoch": 0.013461403631774522, "grad_norm": 6.355332374572754, "learning_rate": 4.439252336448599e-06, "loss": 0.7025411128997803, "step": 96 }, { "epoch": 0.013601626586272174, "grad_norm": 6.864720344543457, "learning_rate": 4.485981308411215e-06, "loss": 0.7148688435554504, "step": 97 }, { "epoch": 0.013741849540769823, "grad_norm": 6.384853839874268, "learning_rate": 4.532710280373832e-06, "loss": 0.6906647682189941, "step": 98 }, { "epoch": 0.013882072495267475, "grad_norm": 5.293791770935059, "learning_rate": 4.579439252336449e-06, "loss": 0.6485897302627563, "step": 99 }, { "epoch": 0.014022295449765127, "grad_norm": 5.7502241134643555, "learning_rate": 4.626168224299066e-06, "loss": 0.6811102032661438, "step": 100 }, { "epoch": 0.014162518404262778, "grad_norm": 6.302574157714844, "learning_rate": 4.6728971962616825e-06, "loss": 0.7220103740692139, "step": 101 }, { "epoch": 0.014302741358760428, "grad_norm": 10.062765121459961, "learning_rate": 4.719626168224299e-06, "loss": 0.5926655530929565, "step": 102 }, { "epoch": 0.01444296431325808, "grad_norm": 8.343512535095215, "learning_rate": 4.766355140186917e-06, "loss": 0.6174185276031494, "step": 103 }, { "epoch": 0.014583187267755732, "grad_norm": 6.299063205718994, "learning_rate": 4.813084112149533e-06, "loss": 0.7111942768096924, "step": 104 }, { "epoch": 0.014723410222253383, "grad_norm": 6.964920520782471, "learning_rate": 4.85981308411215e-06, "loss": 0.7406825423240662, "step": 105 }, { "epoch": 0.014863633176751033, "grad_norm": 8.127129554748535, "learning_rate": 4.906542056074766e-06, "loss": 0.5645974278450012, "step": 106 }, { "epoch": 0.015003856131248685, "grad_norm": 4.806131362915039, "learning_rate": 4.953271028037384e-06, "loss": 0.8974952101707458, "step": 107 }, { "epoch": 0.015144079085746337, "grad_norm": 5.087182998657227, "learning_rate": 5e-06, "loss": 0.6305274963378906, "step": 108 }, { "epoch": 0.015284302040243988, "grad_norm": 5.620641708374023, "learning_rate": 5.046728971962617e-06, "loss": 0.6390151381492615, "step": 109 }, { "epoch": 0.01542452499474164, "grad_norm": 5.71720552444458, "learning_rate": 5.0934579439252344e-06, "loss": 0.6751503348350525, "step": 110 }, { "epoch": 0.01556474794923929, "grad_norm": 9.750357627868652, "learning_rate": 5.14018691588785e-06, "loss": 0.6204992532730103, "step": 111 }, { "epoch": 0.01570497090373694, "grad_norm": 11.4663667678833, "learning_rate": 5.186915887850468e-06, "loss": 0.7168265581130981, "step": 112 }, { "epoch": 0.01584519385823459, "grad_norm": 14.351362228393555, "learning_rate": 5.233644859813084e-06, "loss": 0.6051616668701172, "step": 113 }, { "epoch": 0.015985416812732245, "grad_norm": 6.239736080169678, "learning_rate": 5.280373831775702e-06, "loss": 0.6749290227890015, "step": 114 }, { "epoch": 0.016125639767229895, "grad_norm": 18.0993595123291, "learning_rate": 5.3271028037383174e-06, "loss": 0.6684108376502991, "step": 115 }, { "epoch": 0.016265862721727548, "grad_norm": 4.9435014724731445, "learning_rate": 5.373831775700935e-06, "loss": 0.6347384452819824, "step": 116 }, { "epoch": 0.016406085676225198, "grad_norm": 5.390393257141113, "learning_rate": 5.4205607476635515e-06, "loss": 0.6121516227722168, "step": 117 }, { "epoch": 0.016546308630722848, "grad_norm": 6.367030620574951, "learning_rate": 5.467289719626169e-06, "loss": 0.7230445146560669, "step": 118 }, { "epoch": 0.0166865315852205, "grad_norm": 7.24412202835083, "learning_rate": 5.514018691588785e-06, "loss": 0.6087905168533325, "step": 119 }, { "epoch": 0.01682675453971815, "grad_norm": 9.204792022705078, "learning_rate": 5.560747663551402e-06, "loss": 0.6784247159957886, "step": 120 }, { "epoch": 0.016966977494215805, "grad_norm": 7.823343753814697, "learning_rate": 5.607476635514019e-06, "loss": 0.8288732171058655, "step": 121 }, { "epoch": 0.017107200448713455, "grad_norm": 4.103150367736816, "learning_rate": 5.654205607476636e-06, "loss": 0.6458917856216431, "step": 122 }, { "epoch": 0.017247423403211105, "grad_norm": 6.367490768432617, "learning_rate": 5.700934579439253e-06, "loss": 0.5782976150512695, "step": 123 }, { "epoch": 0.017387646357708758, "grad_norm": 10.215524673461914, "learning_rate": 5.747663551401869e-06, "loss": 0.585402250289917, "step": 124 }, { "epoch": 0.017527869312206408, "grad_norm": 7.348824977874756, "learning_rate": 5.794392523364486e-06, "loss": 0.6707977056503296, "step": 125 }, { "epoch": 0.017668092266704058, "grad_norm": 5.20811653137207, "learning_rate": 5.841121495327103e-06, "loss": 0.6559058427810669, "step": 126 }, { "epoch": 0.01780831522120171, "grad_norm": 7.12399435043335, "learning_rate": 5.88785046728972e-06, "loss": 0.7571951746940613, "step": 127 }, { "epoch": 0.01794853817569936, "grad_norm": 6.554798603057861, "learning_rate": 5.9345794392523374e-06, "loss": 0.7012773752212524, "step": 128 }, { "epoch": 0.018088761130197015, "grad_norm": 5.707541465759277, "learning_rate": 5.981308411214953e-06, "loss": 0.6071768999099731, "step": 129 }, { "epoch": 0.018228984084694665, "grad_norm": 7.75826358795166, "learning_rate": 6.028037383177571e-06, "loss": 0.6935689449310303, "step": 130 }, { "epoch": 0.018369207039192315, "grad_norm": 3.4938888549804688, "learning_rate": 6.074766355140187e-06, "loss": 0.7081989049911499, "step": 131 }, { "epoch": 0.018509429993689968, "grad_norm": 7.85988187789917, "learning_rate": 6.121495327102805e-06, "loss": 0.878288209438324, "step": 132 }, { "epoch": 0.018649652948187618, "grad_norm": 6.085755825042725, "learning_rate": 6.16822429906542e-06, "loss": 0.6697049140930176, "step": 133 }, { "epoch": 0.01878987590268527, "grad_norm": 5.85064697265625, "learning_rate": 6.214953271028038e-06, "loss": 0.7410085201263428, "step": 134 }, { "epoch": 0.01893009885718292, "grad_norm": 5.102226734161377, "learning_rate": 6.2616822429906544e-06, "loss": 0.6420471668243408, "step": 135 }, { "epoch": 0.01907032181168057, "grad_norm": 4.922510147094727, "learning_rate": 6.308411214953272e-06, "loss": 0.7647600173950195, "step": 136 }, { "epoch": 0.019210544766178225, "grad_norm": 6.128218650817871, "learning_rate": 6.355140186915888e-06, "loss": 0.7159332036972046, "step": 137 }, { "epoch": 0.019350767720675875, "grad_norm": 8.620444297790527, "learning_rate": 6.401869158878505e-06, "loss": 0.7087379693984985, "step": 138 }, { "epoch": 0.019490990675173524, "grad_norm": 8.706990242004395, "learning_rate": 6.448598130841122e-06, "loss": 0.6811858415603638, "step": 139 }, { "epoch": 0.019631213629671178, "grad_norm": 6.660795211791992, "learning_rate": 6.495327102803739e-06, "loss": 0.6679391860961914, "step": 140 }, { "epoch": 0.019771436584168828, "grad_norm": 5.035619735717773, "learning_rate": 6.542056074766355e-06, "loss": 0.6788004636764526, "step": 141 }, { "epoch": 0.01991165953866648, "grad_norm": 8.871026039123535, "learning_rate": 6.588785046728972e-06, "loss": 0.728473961353302, "step": 142 }, { "epoch": 0.02005188249316413, "grad_norm": 6.170507431030273, "learning_rate": 6.635514018691589e-06, "loss": 0.6331366300582886, "step": 143 }, { "epoch": 0.02019210544766178, "grad_norm": 4.726235866546631, "learning_rate": 6.682242990654206e-06, "loss": 0.7211220264434814, "step": 144 }, { "epoch": 0.020332328402159434, "grad_norm": 6.967743396759033, "learning_rate": 6.728971962616823e-06, "loss": 0.5559762716293335, "step": 145 }, { "epoch": 0.020472551356657084, "grad_norm": 4.762149333953857, "learning_rate": 6.77570093457944e-06, "loss": 0.7399042248725891, "step": 146 }, { "epoch": 0.020612774311154734, "grad_norm": 5.218959331512451, "learning_rate": 6.822429906542056e-06, "loss": 0.6573964953422546, "step": 147 }, { "epoch": 0.020752997265652388, "grad_norm": 12.30506706237793, "learning_rate": 6.869158878504674e-06, "loss": 0.5471721887588501, "step": 148 }, { "epoch": 0.020893220220150038, "grad_norm": 7.169048309326172, "learning_rate": 6.91588785046729e-06, "loss": 0.5636089444160461, "step": 149 }, { "epoch": 0.02103344317464769, "grad_norm": 5.859265327453613, "learning_rate": 6.962616822429908e-06, "loss": 0.5645543336868286, "step": 150 }, { "epoch": 0.02117366612914534, "grad_norm": 6.638420104980469, "learning_rate": 7.009345794392523e-06, "loss": 0.6556246876716614, "step": 151 }, { "epoch": 0.02131388908364299, "grad_norm": 6.665639400482178, "learning_rate": 7.056074766355141e-06, "loss": 0.6224002242088318, "step": 152 }, { "epoch": 0.021454112038140644, "grad_norm": 5.802305221557617, "learning_rate": 7.1028037383177574e-06, "loss": 0.6161412000656128, "step": 153 }, { "epoch": 0.021594334992638294, "grad_norm": 5.02898645401001, "learning_rate": 7.149532710280375e-06, "loss": 0.7277558445930481, "step": 154 }, { "epoch": 0.021734557947135948, "grad_norm": 9.253006935119629, "learning_rate": 7.196261682242991e-06, "loss": 0.6803451776504517, "step": 155 }, { "epoch": 0.021874780901633598, "grad_norm": 6.625620365142822, "learning_rate": 7.242990654205608e-06, "loss": 0.7115730047225952, "step": 156 }, { "epoch": 0.022015003856131247, "grad_norm": 9.679130554199219, "learning_rate": 7.289719626168225e-06, "loss": 0.7407569885253906, "step": 157 }, { "epoch": 0.0221552268106289, "grad_norm": 7.318441867828369, "learning_rate": 7.336448598130842e-06, "loss": 0.7514153122901917, "step": 158 }, { "epoch": 0.02229544976512655, "grad_norm": 9.377775192260742, "learning_rate": 7.383177570093458e-06, "loss": 0.6292873620986938, "step": 159 }, { "epoch": 0.0224356727196242, "grad_norm": 7.048178195953369, "learning_rate": 7.429906542056075e-06, "loss": 0.5685185790061951, "step": 160 }, { "epoch": 0.022575895674121854, "grad_norm": 6.917372226715088, "learning_rate": 7.476635514018692e-06, "loss": 0.7073736190795898, "step": 161 }, { "epoch": 0.022716118628619504, "grad_norm": 8.271458625793457, "learning_rate": 7.523364485981309e-06, "loss": 0.6299194097518921, "step": 162 }, { "epoch": 0.022856341583117157, "grad_norm": 3.9339160919189453, "learning_rate": 7.570093457943926e-06, "loss": 0.5987552404403687, "step": 163 }, { "epoch": 0.022996564537614807, "grad_norm": 9.447490692138672, "learning_rate": 7.616822429906543e-06, "loss": 0.6619658470153809, "step": 164 }, { "epoch": 0.023136787492112457, "grad_norm": 4.299883842468262, "learning_rate": 7.663551401869159e-06, "loss": 0.6636252403259277, "step": 165 }, { "epoch": 0.02327701044661011, "grad_norm": 9.854989051818848, "learning_rate": 7.710280373831777e-06, "loss": 0.5614457130432129, "step": 166 }, { "epoch": 0.02341723340110776, "grad_norm": 6.699087142944336, "learning_rate": 7.757009345794392e-06, "loss": 0.5720765590667725, "step": 167 }, { "epoch": 0.023557456355605414, "grad_norm": 6.51131534576416, "learning_rate": 7.80373831775701e-06, "loss": 0.5866494178771973, "step": 168 }, { "epoch": 0.023697679310103064, "grad_norm": 13.039170265197754, "learning_rate": 7.850467289719627e-06, "loss": 0.7280548214912415, "step": 169 }, { "epoch": 0.023837902264600714, "grad_norm": 5.600376605987549, "learning_rate": 7.897196261682244e-06, "loss": 0.603405237197876, "step": 170 }, { "epoch": 0.023978125219098367, "grad_norm": 7.5504469871521, "learning_rate": 7.94392523364486e-06, "loss": 0.7165837287902832, "step": 171 }, { "epoch": 0.024118348173596017, "grad_norm": 4.259058952331543, "learning_rate": 7.990654205607477e-06, "loss": 0.7055143117904663, "step": 172 }, { "epoch": 0.024258571128093667, "grad_norm": 36.114376068115234, "learning_rate": 8.037383177570094e-06, "loss": 0.6370686292648315, "step": 173 }, { "epoch": 0.02439879408259132, "grad_norm": 8.89880084991455, "learning_rate": 8.084112149532712e-06, "loss": 0.6250158548355103, "step": 174 }, { "epoch": 0.02453901703708897, "grad_norm": 12.194146156311035, "learning_rate": 8.130841121495327e-06, "loss": 0.811434805393219, "step": 175 }, { "epoch": 0.024679239991586624, "grad_norm": 7.877242565155029, "learning_rate": 8.177570093457945e-06, "loss": 0.7128852009773254, "step": 176 }, { "epoch": 0.024819462946084274, "grad_norm": 6.1277756690979, "learning_rate": 8.224299065420562e-06, "loss": 0.5934735536575317, "step": 177 }, { "epoch": 0.024959685900581924, "grad_norm": 4.839795112609863, "learning_rate": 8.271028037383178e-06, "loss": 0.6326809525489807, "step": 178 }, { "epoch": 0.025099908855079577, "grad_norm": 7.746187210083008, "learning_rate": 8.317757009345795e-06, "loss": 0.7292517423629761, "step": 179 }, { "epoch": 0.025240131809577227, "grad_norm": 7.159272193908691, "learning_rate": 8.364485981308411e-06, "loss": 0.5798690319061279, "step": 180 }, { "epoch": 0.02538035476407488, "grad_norm": 8.11306095123291, "learning_rate": 8.411214953271028e-06, "loss": 0.5837739109992981, "step": 181 }, { "epoch": 0.02552057771857253, "grad_norm": 8.59046459197998, "learning_rate": 8.457943925233646e-06, "loss": 0.6870864033699036, "step": 182 }, { "epoch": 0.02566080067307018, "grad_norm": 8.418621063232422, "learning_rate": 8.504672897196263e-06, "loss": 0.6201134920120239, "step": 183 }, { "epoch": 0.025801023627567834, "grad_norm": 6.045348644256592, "learning_rate": 8.55140186915888e-06, "loss": 0.6891505718231201, "step": 184 }, { "epoch": 0.025941246582065484, "grad_norm": 6.580827236175537, "learning_rate": 8.598130841121496e-06, "loss": 0.6276957988739014, "step": 185 }, { "epoch": 0.026081469536563134, "grad_norm": 5.468252182006836, "learning_rate": 8.644859813084113e-06, "loss": 0.5829881429672241, "step": 186 }, { "epoch": 0.026221692491060787, "grad_norm": 5.884418964385986, "learning_rate": 8.69158878504673e-06, "loss": 0.6291450262069702, "step": 187 }, { "epoch": 0.026361915445558437, "grad_norm": 17.98995590209961, "learning_rate": 8.738317757009348e-06, "loss": 0.6134465932846069, "step": 188 }, { "epoch": 0.02650213840005609, "grad_norm": 6.500589847564697, "learning_rate": 8.785046728971963e-06, "loss": 0.7071872353553772, "step": 189 }, { "epoch": 0.02664236135455374, "grad_norm": 6.7586283683776855, "learning_rate": 8.83177570093458e-06, "loss": 0.6091735363006592, "step": 190 }, { "epoch": 0.02678258430905139, "grad_norm": 4.29121208190918, "learning_rate": 8.878504672897197e-06, "loss": 0.5853902697563171, "step": 191 }, { "epoch": 0.026922807263549044, "grad_norm": 5.531899929046631, "learning_rate": 8.925233644859814e-06, "loss": 0.7131562829017639, "step": 192 }, { "epoch": 0.027063030218046694, "grad_norm": 12.293463706970215, "learning_rate": 8.97196261682243e-06, "loss": 0.6198933124542236, "step": 193 }, { "epoch": 0.027203253172544347, "grad_norm": 10.03479290008545, "learning_rate": 9.018691588785047e-06, "loss": 0.6482654213905334, "step": 194 }, { "epoch": 0.027343476127041997, "grad_norm": 10.459707260131836, "learning_rate": 9.065420560747664e-06, "loss": 0.7387464642524719, "step": 195 }, { "epoch": 0.027483699081539647, "grad_norm": 11.791081428527832, "learning_rate": 9.112149532710282e-06, "loss": 0.6833959221839905, "step": 196 }, { "epoch": 0.0276239220360373, "grad_norm": 8.44423770904541, "learning_rate": 9.158878504672899e-06, "loss": 0.6335874199867249, "step": 197 }, { "epoch": 0.02776414499053495, "grad_norm": 5.4756245613098145, "learning_rate": 9.205607476635515e-06, "loss": 0.6131185293197632, "step": 198 }, { "epoch": 0.0279043679450326, "grad_norm": 6.216544151306152, "learning_rate": 9.252336448598132e-06, "loss": 0.5499069690704346, "step": 199 }, { "epoch": 0.028044590899530254, "grad_norm": 11.594731330871582, "learning_rate": 9.299065420560748e-06, "loss": 0.6739356517791748, "step": 200 }, { "epoch": 0.028184813854027903, "grad_norm": 6.429089069366455, "learning_rate": 9.345794392523365e-06, "loss": 0.6454058885574341, "step": 201 }, { "epoch": 0.028325036808525557, "grad_norm": 15.343890190124512, "learning_rate": 9.392523364485983e-06, "loss": 0.6490234136581421, "step": 202 }, { "epoch": 0.028465259763023207, "grad_norm": 8.35794734954834, "learning_rate": 9.439252336448598e-06, "loss": 0.6029407382011414, "step": 203 }, { "epoch": 0.028605482717520857, "grad_norm": 9.695300102233887, "learning_rate": 9.485981308411217e-06, "loss": 0.5473890900611877, "step": 204 }, { "epoch": 0.02874570567201851, "grad_norm": 5.5189900398254395, "learning_rate": 9.532710280373833e-06, "loss": 0.7319609522819519, "step": 205 }, { "epoch": 0.02888592862651616, "grad_norm": 6.042965412139893, "learning_rate": 9.57943925233645e-06, "loss": 0.6998810768127441, "step": 206 }, { "epoch": 0.029026151581013813, "grad_norm": 5.075780391693115, "learning_rate": 9.626168224299066e-06, "loss": 0.7290840148925781, "step": 207 }, { "epoch": 0.029166374535511463, "grad_norm": 5.432959079742432, "learning_rate": 9.672897196261683e-06, "loss": 0.6074272394180298, "step": 208 }, { "epoch": 0.029306597490009113, "grad_norm": 5.198263168334961, "learning_rate": 9.7196261682243e-06, "loss": 0.692758321762085, "step": 209 }, { "epoch": 0.029446820444506767, "grad_norm": 3.9537038803100586, "learning_rate": 9.766355140186918e-06, "loss": 0.6501717567443848, "step": 210 }, { "epoch": 0.029587043399004417, "grad_norm": 3.933346748352051, "learning_rate": 9.813084112149533e-06, "loss": 0.5942485332489014, "step": 211 }, { "epoch": 0.029727266353502067, "grad_norm": 7.28522253036499, "learning_rate": 9.859813084112151e-06, "loss": 0.7026945352554321, "step": 212 }, { "epoch": 0.02986748930799972, "grad_norm": 4.82488489151001, "learning_rate": 9.906542056074768e-06, "loss": 0.5588880181312561, "step": 213 }, { "epoch": 0.03000771226249737, "grad_norm": 7.881717681884766, "learning_rate": 9.953271028037384e-06, "loss": 0.7599740624427795, "step": 214 }, { "epoch": 0.030147935216995023, "grad_norm": 4.881436347961426, "learning_rate": 1e-05, "loss": 0.7671527862548828, "step": 215 }, { "epoch": 0.030288158171492673, "grad_norm": 3.6180875301361084, "learning_rate": 9.999999484440694e-06, "loss": 0.5135117769241333, "step": 216 }, { "epoch": 0.030428381125990323, "grad_norm": 7.592401027679443, "learning_rate": 9.999997937762879e-06, "loss": 0.5953478813171387, "step": 217 }, { "epoch": 0.030568604080487977, "grad_norm": 5.414005279541016, "learning_rate": 9.999995359966877e-06, "loss": 0.5151708126068115, "step": 218 }, { "epoch": 0.030708827034985627, "grad_norm": 5.064849853515625, "learning_rate": 9.999991751053216e-06, "loss": 0.6111670732498169, "step": 219 }, { "epoch": 0.03084904998948328, "grad_norm": 8.373117446899414, "learning_rate": 9.999987111022642e-06, "loss": 0.6976425051689148, "step": 220 }, { "epoch": 0.03098927294398093, "grad_norm": 8.476304054260254, "learning_rate": 9.999981439876113e-06, "loss": 0.7109944224357605, "step": 221 }, { "epoch": 0.03112949589847858, "grad_norm": 4.927362442016602, "learning_rate": 9.999974737614798e-06, "loss": 0.7152681946754456, "step": 222 }, { "epoch": 0.03126971885297623, "grad_norm": 4.597576141357422, "learning_rate": 9.999967004240078e-06, "loss": 0.6380909085273743, "step": 223 }, { "epoch": 0.03140994180747388, "grad_norm": 4.746475696563721, "learning_rate": 9.999958239753547e-06, "loss": 0.6141610145568848, "step": 224 }, { "epoch": 0.03155016476197153, "grad_norm": 5.026106357574463, "learning_rate": 9.999948444157017e-06, "loss": 0.6559513807296753, "step": 225 }, { "epoch": 0.03169038771646918, "grad_norm": 8.696361541748047, "learning_rate": 9.999937617452504e-06, "loss": 0.6041470766067505, "step": 226 }, { "epoch": 0.03183061067096684, "grad_norm": 5.116116523742676, "learning_rate": 9.999925759642241e-06, "loss": 0.6692550182342529, "step": 227 }, { "epoch": 0.03197083362546449, "grad_norm": 6.046142101287842, "learning_rate": 9.999912870728674e-06, "loss": 0.5631998181343079, "step": 228 }, { "epoch": 0.03211105657996214, "grad_norm": 15.147046089172363, "learning_rate": 9.999898950714463e-06, "loss": 0.54451584815979, "step": 229 }, { "epoch": 0.03225127953445979, "grad_norm": 5.9075117111206055, "learning_rate": 9.999883999602474e-06, "loss": 0.6608651876449585, "step": 230 }, { "epoch": 0.03239150248895744, "grad_norm": 13.763612747192383, "learning_rate": 9.999868017395795e-06, "loss": 0.6953121423721313, "step": 231 }, { "epoch": 0.032531725443455096, "grad_norm": 6.862777233123779, "learning_rate": 9.99985100409772e-06, "loss": 0.704451322555542, "step": 232 }, { "epoch": 0.032671948397952746, "grad_norm": 4.697068214416504, "learning_rate": 9.999832959711758e-06, "loss": 0.6637392044067383, "step": 233 }, { "epoch": 0.032812171352450396, "grad_norm": 7.6166815757751465, "learning_rate": 9.999813884241627e-06, "loss": 0.6746041774749756, "step": 234 }, { "epoch": 0.032952394306948046, "grad_norm": 6.469725131988525, "learning_rate": 9.999793777691265e-06, "loss": 0.5857585668563843, "step": 235 }, { "epoch": 0.033092617261445696, "grad_norm": 8.174189567565918, "learning_rate": 9.999772640064818e-06, "loss": 0.5201676487922668, "step": 236 }, { "epoch": 0.03323284021594335, "grad_norm": 4.309478759765625, "learning_rate": 9.999750471366642e-06, "loss": 0.6384282112121582, "step": 237 }, { "epoch": 0.033373063170441, "grad_norm": 18.512786865234375, "learning_rate": 9.999727271601313e-06, "loss": 0.6633030772209167, "step": 238 }, { "epoch": 0.03351328612493865, "grad_norm": 5.869555473327637, "learning_rate": 9.999703040773611e-06, "loss": 0.6678977012634277, "step": 239 }, { "epoch": 0.0336535090794363, "grad_norm": 5.668227672576904, "learning_rate": 9.999677778888537e-06, "loss": 0.6074270009994507, "step": 240 }, { "epoch": 0.03379373203393395, "grad_norm": 4.826259136199951, "learning_rate": 9.999651485951299e-06, "loss": 0.6714292764663696, "step": 241 }, { "epoch": 0.03393395498843161, "grad_norm": 4.423330307006836, "learning_rate": 9.999624161967317e-06, "loss": 0.6890945434570312, "step": 242 }, { "epoch": 0.03407417794292926, "grad_norm": 5.890592098236084, "learning_rate": 9.999595806942229e-06, "loss": 0.6121131181716919, "step": 243 }, { "epoch": 0.03421440089742691, "grad_norm": 4.5478034019470215, "learning_rate": 9.999566420881881e-06, "loss": 0.6000597476959229, "step": 244 }, { "epoch": 0.03435462385192456, "grad_norm": 6.883039951324463, "learning_rate": 9.999536003792332e-06, "loss": 0.570275068283081, "step": 245 }, { "epoch": 0.03449484680642221, "grad_norm": 4.398484230041504, "learning_rate": 9.999504555679857e-06, "loss": 0.6493523120880127, "step": 246 }, { "epoch": 0.03463506976091986, "grad_norm": 10.1190824508667, "learning_rate": 9.999472076550941e-06, "loss": 0.5825449228286743, "step": 247 }, { "epoch": 0.034775292715417516, "grad_norm": 9.084763526916504, "learning_rate": 9.99943856641228e-06, "loss": 0.6087126731872559, "step": 248 }, { "epoch": 0.034915515669915166, "grad_norm": 6.160186290740967, "learning_rate": 9.999404025270788e-06, "loss": 0.6618340015411377, "step": 249 }, { "epoch": 0.035055738624412816, "grad_norm": 5.355075836181641, "learning_rate": 9.999368453133584e-06, "loss": 0.6514903903007507, "step": 250 }, { "epoch": 0.035195961578910466, "grad_norm": 7.6793437004089355, "learning_rate": 9.999331850008007e-06, "loss": 0.6721071004867554, "step": 251 }, { "epoch": 0.035336184533408116, "grad_norm": 9.79814338684082, "learning_rate": 9.999294215901605e-06, "loss": 0.60922771692276, "step": 252 }, { "epoch": 0.03547640748790577, "grad_norm": 9.158773422241211, "learning_rate": 9.999255550822137e-06, "loss": 0.6949451565742493, "step": 253 }, { "epoch": 0.03561663044240342, "grad_norm": 4.9596638679504395, "learning_rate": 9.99921585477758e-06, "loss": 0.6269016265869141, "step": 254 }, { "epoch": 0.03575685339690107, "grad_norm": 5.416591167449951, "learning_rate": 9.999175127776117e-06, "loss": 0.5822302103042603, "step": 255 }, { "epoch": 0.03589707635139872, "grad_norm": 7.480010509490967, "learning_rate": 9.999133369826148e-06, "loss": 0.5165606737136841, "step": 256 }, { "epoch": 0.03603729930589637, "grad_norm": 6.638649940490723, "learning_rate": 9.999090580936286e-06, "loss": 0.6500223875045776, "step": 257 }, { "epoch": 0.03617752226039403, "grad_norm": 5.976089954376221, "learning_rate": 9.999046761115352e-06, "loss": 0.6627307534217834, "step": 258 }, { "epoch": 0.03631774521489168, "grad_norm": 10.644956588745117, "learning_rate": 9.999001910372387e-06, "loss": 0.6557222008705139, "step": 259 }, { "epoch": 0.03645796816938933, "grad_norm": 5.364903450012207, "learning_rate": 9.998956028716636e-06, "loss": 0.6079579591751099, "step": 260 }, { "epoch": 0.03659819112388698, "grad_norm": 6.446866989135742, "learning_rate": 9.998909116157563e-06, "loss": 0.6488662958145142, "step": 261 }, { "epoch": 0.03673841407838463, "grad_norm": 7.412497043609619, "learning_rate": 9.998861172704843e-06, "loss": 0.7011802196502686, "step": 262 }, { "epoch": 0.036878637032882286, "grad_norm": 9.03597640991211, "learning_rate": 9.998812198368361e-06, "loss": 0.6468762159347534, "step": 263 }, { "epoch": 0.037018859987379936, "grad_norm": 6.535673141479492, "learning_rate": 9.998762193158218e-06, "loss": 0.5594191551208496, "step": 264 }, { "epoch": 0.037159082941877586, "grad_norm": 5.144454002380371, "learning_rate": 9.998711157084726e-06, "loss": 0.7500815391540527, "step": 265 }, { "epoch": 0.037299305896375236, "grad_norm": 9.042792320251465, "learning_rate": 9.998659090158411e-06, "loss": 0.6994221210479736, "step": 266 }, { "epoch": 0.037439528850872886, "grad_norm": 9.570676803588867, "learning_rate": 9.99860599239001e-06, "loss": 0.6431000232696533, "step": 267 }, { "epoch": 0.03757975180537054, "grad_norm": 6.088304042816162, "learning_rate": 9.998551863790471e-06, "loss": 0.6963359117507935, "step": 268 }, { "epoch": 0.03771997475986819, "grad_norm": 5.145269870758057, "learning_rate": 9.998496704370957e-06, "loss": 0.6223165988922119, "step": 269 }, { "epoch": 0.03786019771436584, "grad_norm": 4.548379898071289, "learning_rate": 9.998440514142846e-06, "loss": 0.6208646297454834, "step": 270 }, { "epoch": 0.03800042066886349, "grad_norm": 5.339493751525879, "learning_rate": 9.998383293117724e-06, "loss": 0.5655364990234375, "step": 271 }, { "epoch": 0.03814064362336114, "grad_norm": 5.753556251525879, "learning_rate": 9.99832504130739e-06, "loss": 0.6586032509803772, "step": 272 }, { "epoch": 0.03828086657785879, "grad_norm": 5.3541789054870605, "learning_rate": 9.99826575872386e-06, "loss": 0.5404495000839233, "step": 273 }, { "epoch": 0.03842108953235645, "grad_norm": 3.9043898582458496, "learning_rate": 9.998205445379357e-06, "loss": 0.44940078258514404, "step": 274 }, { "epoch": 0.0385613124868541, "grad_norm": 4.980262756347656, "learning_rate": 9.99814410128632e-06, "loss": 0.5667526125907898, "step": 275 }, { "epoch": 0.03870153544135175, "grad_norm": 6.825993537902832, "learning_rate": 9.9980817264574e-06, "loss": 0.7182760238647461, "step": 276 }, { "epoch": 0.0388417583958494, "grad_norm": 6.2545342445373535, "learning_rate": 9.998018320905458e-06, "loss": 0.7190155982971191, "step": 277 }, { "epoch": 0.03898198135034705, "grad_norm": 3.988173007965088, "learning_rate": 9.997953884643571e-06, "loss": 0.6910338401794434, "step": 278 }, { "epoch": 0.039122204304844706, "grad_norm": 6.224934101104736, "learning_rate": 9.99788841768503e-06, "loss": 0.5611162781715393, "step": 279 }, { "epoch": 0.039262427259342356, "grad_norm": 5.242640018463135, "learning_rate": 9.997821920043332e-06, "loss": 0.6603567600250244, "step": 280 }, { "epoch": 0.039402650213840006, "grad_norm": 5.9749884605407715, "learning_rate": 9.997754391732191e-06, "loss": 0.697981059551239, "step": 281 }, { "epoch": 0.039542873168337656, "grad_norm": 15.268977165222168, "learning_rate": 9.997685832765534e-06, "loss": 0.6607248187065125, "step": 282 }, { "epoch": 0.039683096122835305, "grad_norm": 5.912014007568359, "learning_rate": 9.9976162431575e-06, "loss": 0.579423189163208, "step": 283 }, { "epoch": 0.03982331907733296, "grad_norm": 4.749676704406738, "learning_rate": 9.99754562292244e-06, "loss": 0.5860832929611206, "step": 284 }, { "epoch": 0.03996354203183061, "grad_norm": 8.459124565124512, "learning_rate": 9.997473972074915e-06, "loss": 0.7079553008079529, "step": 285 }, { "epoch": 0.04010376498632826, "grad_norm": 4.89307165145874, "learning_rate": 9.997401290629704e-06, "loss": 0.526929497718811, "step": 286 }, { "epoch": 0.04024398794082591, "grad_norm": 9.958710670471191, "learning_rate": 9.997327578601795e-06, "loss": 0.5955215096473694, "step": 287 }, { "epoch": 0.04038421089532356, "grad_norm": 9.543437957763672, "learning_rate": 9.997252836006386e-06, "loss": 0.5379416942596436, "step": 288 }, { "epoch": 0.04052443384982122, "grad_norm": 4.499966621398926, "learning_rate": 9.997177062858896e-06, "loss": 0.5644838809967041, "step": 289 }, { "epoch": 0.04066465680431887, "grad_norm": 4.592108249664307, "learning_rate": 9.997100259174948e-06, "loss": 0.6806083917617798, "step": 290 }, { "epoch": 0.04080487975881652, "grad_norm": 3.67696475982666, "learning_rate": 9.997022424970381e-06, "loss": 0.5496447682380676, "step": 291 }, { "epoch": 0.04094510271331417, "grad_norm": 6.436710834503174, "learning_rate": 9.996943560261247e-06, "loss": 0.5276438593864441, "step": 292 }, { "epoch": 0.04108532566781182, "grad_norm": 5.897743225097656, "learning_rate": 9.99686366506381e-06, "loss": 0.7448580265045166, "step": 293 }, { "epoch": 0.04122554862230947, "grad_norm": 9.629523277282715, "learning_rate": 9.996782739394544e-06, "loss": 0.616775393486023, "step": 294 }, { "epoch": 0.041365771576807125, "grad_norm": 4.958767414093018, "learning_rate": 9.996700783270142e-06, "loss": 0.6557762026786804, "step": 295 }, { "epoch": 0.041505994531304775, "grad_norm": 6.251393795013428, "learning_rate": 9.9966177967075e-06, "loss": 0.6294379234313965, "step": 296 }, { "epoch": 0.041646217485802425, "grad_norm": 10.782068252563477, "learning_rate": 9.996533779723737e-06, "loss": 0.6898412704467773, "step": 297 }, { "epoch": 0.041786440440300075, "grad_norm": 4.796201705932617, "learning_rate": 9.996448732336175e-06, "loss": 0.6036866903305054, "step": 298 }, { "epoch": 0.041926663394797725, "grad_norm": 3.6381819248199463, "learning_rate": 9.996362654562354e-06, "loss": 0.6440974473953247, "step": 299 }, { "epoch": 0.04206688634929538, "grad_norm": 4.965101718902588, "learning_rate": 9.996275546420029e-06, "loss": 0.6085952520370483, "step": 300 }, { "epoch": 0.04220710930379303, "grad_norm": 5.184587001800537, "learning_rate": 9.996187407927158e-06, "loss": 0.6420971155166626, "step": 301 }, { "epoch": 0.04234733225829068, "grad_norm": 4.8051347732543945, "learning_rate": 9.996098239101921e-06, "loss": 0.7080218195915222, "step": 302 }, { "epoch": 0.04248755521278833, "grad_norm": 6.532549858093262, "learning_rate": 9.996008039962705e-06, "loss": 0.6365444660186768, "step": 303 }, { "epoch": 0.04262777816728598, "grad_norm": 6.1506524085998535, "learning_rate": 9.995916810528113e-06, "loss": 0.6034393310546875, "step": 304 }, { "epoch": 0.04276800112178364, "grad_norm": 3.6740682125091553, "learning_rate": 9.995824550816958e-06, "loss": 0.712794303894043, "step": 305 }, { "epoch": 0.04290822407628129, "grad_norm": 9.426552772521973, "learning_rate": 9.995731260848265e-06, "loss": 0.6229634284973145, "step": 306 }, { "epoch": 0.04304844703077894, "grad_norm": 9.522850036621094, "learning_rate": 9.995636940641274e-06, "loss": 0.6024234890937805, "step": 307 }, { "epoch": 0.04318866998527659, "grad_norm": 6.391870498657227, "learning_rate": 9.995541590215434e-06, "loss": 0.5459619760513306, "step": 308 }, { "epoch": 0.04332889293977424, "grad_norm": 5.97572660446167, "learning_rate": 9.995445209590409e-06, "loss": 0.652113676071167, "step": 309 }, { "epoch": 0.043469115894271895, "grad_norm": 6.0114593505859375, "learning_rate": 9.995347798786079e-06, "loss": 0.5537327527999878, "step": 310 }, { "epoch": 0.043609338848769545, "grad_norm": 4.749156475067139, "learning_rate": 9.995249357822527e-06, "loss": 0.6531245112419128, "step": 311 }, { "epoch": 0.043749561803267195, "grad_norm": 3.4917962551116943, "learning_rate": 9.995149886720057e-06, "loss": 0.6325230598449707, "step": 312 }, { "epoch": 0.043889784757764845, "grad_norm": 4.250181198120117, "learning_rate": 9.995049385499181e-06, "loss": 0.5521203279495239, "step": 313 }, { "epoch": 0.044030007712262495, "grad_norm": 4.386589527130127, "learning_rate": 9.994947854180626e-06, "loss": 0.633989155292511, "step": 314 }, { "epoch": 0.04417023066676015, "grad_norm": 5.458956718444824, "learning_rate": 9.994845292785327e-06, "loss": 0.5366339087486267, "step": 315 }, { "epoch": 0.0443104536212578, "grad_norm": 6.971571922302246, "learning_rate": 9.994741701334439e-06, "loss": 0.6477446556091309, "step": 316 }, { "epoch": 0.04445067657575545, "grad_norm": 4.128116607666016, "learning_rate": 9.994637079849324e-06, "loss": 0.5237785577774048, "step": 317 }, { "epoch": 0.0445908995302531, "grad_norm": 4.899281024932861, "learning_rate": 9.994531428351553e-06, "loss": 0.6807914972305298, "step": 318 }, { "epoch": 0.04473112248475075, "grad_norm": 4.935632705688477, "learning_rate": 9.99442474686292e-06, "loss": 0.6303986310958862, "step": 319 }, { "epoch": 0.0448713454392484, "grad_norm": 10.7448091506958, "learning_rate": 9.994317035405422e-06, "loss": 0.6047718524932861, "step": 320 }, { "epoch": 0.04501156839374606, "grad_norm": 5.771068572998047, "learning_rate": 9.99420829400127e-06, "loss": 0.48328322172164917, "step": 321 }, { "epoch": 0.04515179134824371, "grad_norm": 4.036205291748047, "learning_rate": 9.994098522672894e-06, "loss": 0.6638779044151306, "step": 322 }, { "epoch": 0.04529201430274136, "grad_norm": 10.81441879272461, "learning_rate": 9.993987721442929e-06, "loss": 0.6961871385574341, "step": 323 }, { "epoch": 0.04543223725723901, "grad_norm": 8.746245384216309, "learning_rate": 9.993875890334221e-06, "loss": 0.6651788949966431, "step": 324 }, { "epoch": 0.04557246021173666, "grad_norm": 11.039877891540527, "learning_rate": 9.993763029369839e-06, "loss": 0.5967457294464111, "step": 325 }, { "epoch": 0.045712683166234315, "grad_norm": 24.4334659576416, "learning_rate": 9.993649138573053e-06, "loss": 0.6584869623184204, "step": 326 }, { "epoch": 0.045852906120731965, "grad_norm": 7.32485818862915, "learning_rate": 9.99353421796735e-06, "loss": 0.6528759002685547, "step": 327 }, { "epoch": 0.045993129075229615, "grad_norm": 5.198447227478027, "learning_rate": 9.993418267576433e-06, "loss": 0.5698654651641846, "step": 328 }, { "epoch": 0.046133352029727265, "grad_norm": 6.3438568115234375, "learning_rate": 9.99330128742421e-06, "loss": 0.8276619911193848, "step": 329 }, { "epoch": 0.046273574984224915, "grad_norm": 5.072625637054443, "learning_rate": 9.993183277534809e-06, "loss": 0.7040266990661621, "step": 330 }, { "epoch": 0.04641379793872257, "grad_norm": 4.892005443572998, "learning_rate": 9.993064237932562e-06, "loss": 0.6964032649993896, "step": 331 }, { "epoch": 0.04655402089322022, "grad_norm": 6.160145282745361, "learning_rate": 9.99294416864202e-06, "loss": 0.6806238293647766, "step": 332 }, { "epoch": 0.04669424384771787, "grad_norm": 3.508089303970337, "learning_rate": 9.992823069687943e-06, "loss": 0.5241220593452454, "step": 333 }, { "epoch": 0.04683446680221552, "grad_norm": 4.812159061431885, "learning_rate": 9.992700941095306e-06, "loss": 0.6447612047195435, "step": 334 }, { "epoch": 0.04697468975671317, "grad_norm": 3.744760274887085, "learning_rate": 9.992577782889294e-06, "loss": 0.6207246780395508, "step": 335 }, { "epoch": 0.04711491271121083, "grad_norm": 3.5448312759399414, "learning_rate": 9.992453595095304e-06, "loss": 0.612108588218689, "step": 336 }, { "epoch": 0.04725513566570848, "grad_norm": 6.399518966674805, "learning_rate": 9.99232837773895e-06, "loss": 0.6070353984832764, "step": 337 }, { "epoch": 0.04739535862020613, "grad_norm": 4.99271297454834, "learning_rate": 9.992202130846051e-06, "loss": 0.6012741923332214, "step": 338 }, { "epoch": 0.04753558157470378, "grad_norm": 7.817624092102051, "learning_rate": 9.992074854442643e-06, "loss": 0.5771042108535767, "step": 339 }, { "epoch": 0.04767580452920143, "grad_norm": 5.866034507751465, "learning_rate": 9.991946548554977e-06, "loss": 0.728326141834259, "step": 340 }, { "epoch": 0.047816027483699085, "grad_norm": 6.810055732727051, "learning_rate": 9.991817213209507e-06, "loss": 0.5472403764724731, "step": 341 }, { "epoch": 0.047956250438196735, "grad_norm": 5.009106636047363, "learning_rate": 9.99168684843291e-06, "loss": 0.5667133331298828, "step": 342 }, { "epoch": 0.048096473392694385, "grad_norm": 6.166308403015137, "learning_rate": 9.991555454252067e-06, "loss": 0.6672385334968567, "step": 343 }, { "epoch": 0.048236696347192035, "grad_norm": 4.922038555145264, "learning_rate": 9.991423030694074e-06, "loss": 0.7609614133834839, "step": 344 }, { "epoch": 0.048376919301689685, "grad_norm": 5.516350269317627, "learning_rate": 9.991289577786242e-06, "loss": 0.5991281270980835, "step": 345 }, { "epoch": 0.048517142256187334, "grad_norm": 23.97130584716797, "learning_rate": 9.991155095556094e-06, "loss": 0.5057817697525024, "step": 346 }, { "epoch": 0.04865736521068499, "grad_norm": 5.666988372802734, "learning_rate": 9.99101958403136e-06, "loss": 0.650926947593689, "step": 347 }, { "epoch": 0.04879758816518264, "grad_norm": 4.135570049285889, "learning_rate": 9.990883043239988e-06, "loss": 0.5768991708755493, "step": 348 }, { "epoch": 0.04893781111968029, "grad_norm": 6.327651023864746, "learning_rate": 9.990745473210132e-06, "loss": 0.581996500492096, "step": 349 }, { "epoch": 0.04907803407417794, "grad_norm": 9.897063255310059, "learning_rate": 9.990606873970167e-06, "loss": 0.6473736763000488, "step": 350 }, { "epoch": 0.04921825702867559, "grad_norm": 4.99374532699585, "learning_rate": 9.990467245548673e-06, "loss": 0.6297944784164429, "step": 351 }, { "epoch": 0.04935847998317325, "grad_norm": 4.837751388549805, "learning_rate": 9.990326587974445e-06, "loss": 0.5386931896209717, "step": 352 }, { "epoch": 0.0494987029376709, "grad_norm": 5.4067277908325195, "learning_rate": 9.99018490127649e-06, "loss": 0.5558749437332153, "step": 353 }, { "epoch": 0.04963892589216855, "grad_norm": 8.233312606811523, "learning_rate": 9.990042185484028e-06, "loss": 0.5918351411819458, "step": 354 }, { "epoch": 0.0497791488466662, "grad_norm": 7.953436851501465, "learning_rate": 9.989898440626489e-06, "loss": 0.6687642335891724, "step": 355 }, { "epoch": 0.04991937180116385, "grad_norm": 5.300974369049072, "learning_rate": 9.989753666733518e-06, "loss": 0.5860857963562012, "step": 356 }, { "epoch": 0.050059594755661505, "grad_norm": 8.932915687561035, "learning_rate": 9.98960786383497e-06, "loss": 0.6035829782485962, "step": 357 }, { "epoch": 0.050199817710159154, "grad_norm": 9.777947425842285, "learning_rate": 9.989461031960911e-06, "loss": 0.6988755464553833, "step": 358 }, { "epoch": 0.050340040664656804, "grad_norm": 3.8696842193603516, "learning_rate": 9.989313171141623e-06, "loss": 0.6278740167617798, "step": 359 }, { "epoch": 0.050480263619154454, "grad_norm": 4.938533306121826, "learning_rate": 9.989164281407602e-06, "loss": 0.5692856311798096, "step": 360 }, { "epoch": 0.050620486573652104, "grad_norm": 3.660844564437866, "learning_rate": 9.989014362789546e-06, "loss": 0.5944745540618896, "step": 361 }, { "epoch": 0.05076070952814976, "grad_norm": 4.342620849609375, "learning_rate": 9.988863415318378e-06, "loss": 0.6630439758300781, "step": 362 }, { "epoch": 0.05090093248264741, "grad_norm": 5.916039943695068, "learning_rate": 9.988711439025223e-06, "loss": 0.5523799061775208, "step": 363 }, { "epoch": 0.05104115543714506, "grad_norm": 6.069456577301025, "learning_rate": 9.988558433941423e-06, "loss": 0.754270076751709, "step": 364 }, { "epoch": 0.05118137839164271, "grad_norm": 5.075040340423584, "learning_rate": 9.988404400098528e-06, "loss": 0.7112393379211426, "step": 365 }, { "epoch": 0.05132160134614036, "grad_norm": 10.724635124206543, "learning_rate": 9.98824933752831e-06, "loss": 0.5744898915290833, "step": 366 }, { "epoch": 0.05146182430063802, "grad_norm": 6.654784202575684, "learning_rate": 9.988093246262745e-06, "loss": 0.6390070915222168, "step": 367 }, { "epoch": 0.05160204725513567, "grad_norm": 5.669426441192627, "learning_rate": 9.987936126334019e-06, "loss": 0.7852742671966553, "step": 368 }, { "epoch": 0.05174227020963332, "grad_norm": 4.910593509674072, "learning_rate": 9.987777977774536e-06, "loss": 0.6398310661315918, "step": 369 }, { "epoch": 0.05188249316413097, "grad_norm": 8.255945205688477, "learning_rate": 9.987618800616909e-06, "loss": 0.648237943649292, "step": 370 }, { "epoch": 0.05202271611862862, "grad_norm": 9.085831642150879, "learning_rate": 9.987458594893967e-06, "loss": 0.6248641014099121, "step": 371 }, { "epoch": 0.05216293907312627, "grad_norm": 6.4399309158325195, "learning_rate": 9.987297360638747e-06, "loss": 0.5733931064605713, "step": 372 }, { "epoch": 0.052303162027623924, "grad_norm": 3.851530075073242, "learning_rate": 9.987135097884495e-06, "loss": 0.5639608502388, "step": 373 }, { "epoch": 0.052443384982121574, "grad_norm": 4.770305156707764, "learning_rate": 9.98697180666468e-06, "loss": 0.7149243354797363, "step": 374 }, { "epoch": 0.052583607936619224, "grad_norm": 5.91831111907959, "learning_rate": 9.986807487012974e-06, "loss": 0.5837751030921936, "step": 375 }, { "epoch": 0.052723830891116874, "grad_norm": 4.476146697998047, "learning_rate": 9.98664213896326e-06, "loss": 0.5587503910064697, "step": 376 }, { "epoch": 0.052864053845614524, "grad_norm": 7.311237335205078, "learning_rate": 9.986475762549642e-06, "loss": 0.6611186265945435, "step": 377 }, { "epoch": 0.05300427680011218, "grad_norm": 8.80649185180664, "learning_rate": 9.986308357806429e-06, "loss": 0.5887116193771362, "step": 378 }, { "epoch": 0.05314449975460983, "grad_norm": 7.467635154724121, "learning_rate": 9.986139924768142e-06, "loss": 0.6539685726165771, "step": 379 }, { "epoch": 0.05328472270910748, "grad_norm": 12.939316749572754, "learning_rate": 9.985970463469519e-06, "loss": 0.603256106376648, "step": 380 }, { "epoch": 0.05342494566360513, "grad_norm": 3.9105136394500732, "learning_rate": 9.985799973945504e-06, "loss": 0.5807961821556091, "step": 381 }, { "epoch": 0.05356516861810278, "grad_norm": 14.366250991821289, "learning_rate": 9.985628456231257e-06, "loss": 0.5345735549926758, "step": 382 }, { "epoch": 0.05370539157260044, "grad_norm": 15.38187313079834, "learning_rate": 9.985455910362151e-06, "loss": 0.6330976486206055, "step": 383 }, { "epoch": 0.05384561452709809, "grad_norm": 13.898154258728027, "learning_rate": 9.985282336373766e-06, "loss": 0.5965760946273804, "step": 384 }, { "epoch": 0.05398583748159574, "grad_norm": 5.031282424926758, "learning_rate": 9.9851077343019e-06, "loss": 0.5043273568153381, "step": 385 }, { "epoch": 0.05412606043609339, "grad_norm": 5.216378688812256, "learning_rate": 9.984932104182556e-06, "loss": 0.5371794104576111, "step": 386 }, { "epoch": 0.05426628339059104, "grad_norm": 16.070907592773438, "learning_rate": 9.984755446051956e-06, "loss": 0.5928857326507568, "step": 387 }, { "epoch": 0.054406506345088694, "grad_norm": 7.890944480895996, "learning_rate": 9.984577759946532e-06, "loss": 0.6446906924247742, "step": 388 }, { "epoch": 0.054546729299586344, "grad_norm": 5.662290096282959, "learning_rate": 9.984399045902926e-06, "loss": 0.6793045997619629, "step": 389 }, { "epoch": 0.054686952254083994, "grad_norm": 5.034042835235596, "learning_rate": 9.984219303957992e-06, "loss": 0.5824986696243286, "step": 390 }, { "epoch": 0.054827175208581644, "grad_norm": 6.445096492767334, "learning_rate": 9.984038534148797e-06, "loss": 0.5111008882522583, "step": 391 }, { "epoch": 0.054967398163079294, "grad_norm": 6.801855564117432, "learning_rate": 9.983856736512623e-06, "loss": 0.7002434730529785, "step": 392 }, { "epoch": 0.05510762111757695, "grad_norm": 4.088385105133057, "learning_rate": 9.983673911086958e-06, "loss": 0.6368874311447144, "step": 393 }, { "epoch": 0.0552478440720746, "grad_norm": 3.9916698932647705, "learning_rate": 9.983490057909506e-06, "loss": 0.7237595319747925, "step": 394 }, { "epoch": 0.05538806702657225, "grad_norm": 3.875688076019287, "learning_rate": 9.983305177018182e-06, "loss": 0.6231204867362976, "step": 395 }, { "epoch": 0.0555282899810699, "grad_norm": 5.075631141662598, "learning_rate": 9.983119268451112e-06, "loss": 0.7296997308731079, "step": 396 }, { "epoch": 0.05566851293556755, "grad_norm": 4.129025459289551, "learning_rate": 9.982932332246634e-06, "loss": 0.6897695064544678, "step": 397 }, { "epoch": 0.0558087358900652, "grad_norm": 3.7566707134246826, "learning_rate": 9.982744368443302e-06, "loss": 0.6265806555747986, "step": 398 }, { "epoch": 0.05594895884456286, "grad_norm": 3.6371684074401855, "learning_rate": 9.982555377079876e-06, "loss": 0.6087244749069214, "step": 399 }, { "epoch": 0.05608918179906051, "grad_norm": 5.004859447479248, "learning_rate": 9.982365358195331e-06, "loss": 0.575169026851654, "step": 400 }, { "epoch": 0.05622940475355816, "grad_norm": 10.045495986938477, "learning_rate": 9.982174311828853e-06, "loss": 0.6741524934768677, "step": 401 }, { "epoch": 0.05636962770805581, "grad_norm": 7.043858528137207, "learning_rate": 9.981982238019842e-06, "loss": 0.6576851010322571, "step": 402 }, { "epoch": 0.05650985066255346, "grad_norm": 6.790002346038818, "learning_rate": 9.981789136807906e-06, "loss": 0.684403657913208, "step": 403 }, { "epoch": 0.056650073617051114, "grad_norm": 4.296261787414551, "learning_rate": 9.98159500823287e-06, "loss": 0.6555382013320923, "step": 404 }, { "epoch": 0.056790296571548764, "grad_norm": 5.179953575134277, "learning_rate": 9.981399852334763e-06, "loss": 0.6775506138801575, "step": 405 }, { "epoch": 0.056930519526046414, "grad_norm": 4.831573963165283, "learning_rate": 9.981203669153836e-06, "loss": 0.5991913080215454, "step": 406 }, { "epoch": 0.057070742480544064, "grad_norm": 3.513441324234009, "learning_rate": 9.981006458730543e-06, "loss": 0.5328248739242554, "step": 407 }, { "epoch": 0.057210965435041714, "grad_norm": 10.467926025390625, "learning_rate": 9.980808221105555e-06, "loss": 0.6347182989120483, "step": 408 }, { "epoch": 0.05735118838953937, "grad_norm": 4.862585544586182, "learning_rate": 9.980608956319755e-06, "loss": 0.6740255951881409, "step": 409 }, { "epoch": 0.05749141134403702, "grad_norm": 6.563756465911865, "learning_rate": 9.980408664414232e-06, "loss": 0.6580957174301147, "step": 410 }, { "epoch": 0.05763163429853467, "grad_norm": 6.271443843841553, "learning_rate": 9.980207345430294e-06, "loss": 0.5613722801208496, "step": 411 }, { "epoch": 0.05777185725303232, "grad_norm": 5.567136287689209, "learning_rate": 9.980004999409457e-06, "loss": 0.6063511371612549, "step": 412 }, { "epoch": 0.05791208020752997, "grad_norm": 14.415735244750977, "learning_rate": 9.979801626393448e-06, "loss": 0.6654555797576904, "step": 413 }, { "epoch": 0.05805230316202763, "grad_norm": 5.148159027099609, "learning_rate": 9.979597226424211e-06, "loss": 0.4910449683666229, "step": 414 }, { "epoch": 0.05819252611652528, "grad_norm": 4.421723365783691, "learning_rate": 9.979391799543894e-06, "loss": 0.6554110050201416, "step": 415 }, { "epoch": 0.05833274907102293, "grad_norm": 5.40390682220459, "learning_rate": 9.979185345794865e-06, "loss": 0.70440673828125, "step": 416 }, { "epoch": 0.05847297202552058, "grad_norm": 4.480751037597656, "learning_rate": 9.978977865219696e-06, "loss": 0.6865934729576111, "step": 417 }, { "epoch": 0.05861319498001823, "grad_norm": 5.817942142486572, "learning_rate": 9.978769357861176e-06, "loss": 0.66568922996521, "step": 418 }, { "epoch": 0.058753417934515884, "grad_norm": 4.035762310028076, "learning_rate": 9.978559823762305e-06, "loss": 0.7688785791397095, "step": 419 }, { "epoch": 0.058893640889013534, "grad_norm": 5.141525745391846, "learning_rate": 9.978349262966293e-06, "loss": 0.5810328722000122, "step": 420 }, { "epoch": 0.05903386384351118, "grad_norm": 3.9722959995269775, "learning_rate": 9.978137675516561e-06, "loss": 0.5899395942687988, "step": 421 }, { "epoch": 0.05917408679800883, "grad_norm": 14.898078918457031, "learning_rate": 9.977925061456746e-06, "loss": 0.7420055866241455, "step": 422 }, { "epoch": 0.05931430975250648, "grad_norm": 3.1865320205688477, "learning_rate": 9.977711420830694e-06, "loss": 0.4913870096206665, "step": 423 }, { "epoch": 0.05945453270700413, "grad_norm": 9.80923843383789, "learning_rate": 9.97749675368246e-06, "loss": 0.508360743522644, "step": 424 }, { "epoch": 0.05959475566150179, "grad_norm": 4.423038959503174, "learning_rate": 9.977281060056316e-06, "loss": 0.5609296560287476, "step": 425 }, { "epoch": 0.05973497861599944, "grad_norm": 4.436049938201904, "learning_rate": 9.977064339996743e-06, "loss": 0.521817684173584, "step": 426 }, { "epoch": 0.05987520157049709, "grad_norm": 4.593049049377441, "learning_rate": 9.976846593548433e-06, "loss": 0.648605227470398, "step": 427 }, { "epoch": 0.06001542452499474, "grad_norm": 4.411497116088867, "learning_rate": 9.97662782075629e-06, "loss": 0.5944064855575562, "step": 428 }, { "epoch": 0.06015564747949239, "grad_norm": 10.725522994995117, "learning_rate": 9.976408021665431e-06, "loss": 0.5664165019989014, "step": 429 }, { "epoch": 0.06029587043399005, "grad_norm": 3.405480146408081, "learning_rate": 9.976187196321186e-06, "loss": 0.5256993770599365, "step": 430 }, { "epoch": 0.0604360933884877, "grad_norm": 6.466279983520508, "learning_rate": 9.97596534476909e-06, "loss": 0.5162826776504517, "step": 431 }, { "epoch": 0.06057631634298535, "grad_norm": 10.353398323059082, "learning_rate": 9.975742467054894e-06, "loss": 0.6055065989494324, "step": 432 }, { "epoch": 0.060716539297482996, "grad_norm": 12.345638275146484, "learning_rate": 9.975518563224566e-06, "loss": 0.7306939363479614, "step": 433 }, { "epoch": 0.060856762251980646, "grad_norm": 4.640746593475342, "learning_rate": 9.975293633324275e-06, "loss": 0.602948784828186, "step": 434 }, { "epoch": 0.0609969852064783, "grad_norm": 8.528901100158691, "learning_rate": 9.97506767740041e-06, "loss": 0.5230056047439575, "step": 435 }, { "epoch": 0.06113720816097595, "grad_norm": 12.49643611907959, "learning_rate": 9.974840695499569e-06, "loss": 0.5777229070663452, "step": 436 }, { "epoch": 0.0612774311154736, "grad_norm": 4.985222339630127, "learning_rate": 9.974612687668557e-06, "loss": 0.6367600560188293, "step": 437 }, { "epoch": 0.06141765406997125, "grad_norm": 3.4654717445373535, "learning_rate": 9.974383653954397e-06, "loss": 0.5307585597038269, "step": 438 }, { "epoch": 0.0615578770244689, "grad_norm": 4.659060001373291, "learning_rate": 9.97415359440432e-06, "loss": 0.6971641182899475, "step": 439 }, { "epoch": 0.06169809997896656, "grad_norm": 5.101334571838379, "learning_rate": 9.973922509065774e-06, "loss": 0.6262149810791016, "step": 440 }, { "epoch": 0.06183832293346421, "grad_norm": 3.1744577884674072, "learning_rate": 9.973690397986411e-06, "loss": 0.5931658148765564, "step": 441 }, { "epoch": 0.06197854588796186, "grad_norm": 14.072529792785645, "learning_rate": 9.973457261214098e-06, "loss": 0.6061287522315979, "step": 442 }, { "epoch": 0.06211876884245951, "grad_norm": 4.313185214996338, "learning_rate": 9.973223098796913e-06, "loss": 0.6084474921226501, "step": 443 }, { "epoch": 0.06225899179695716, "grad_norm": 3.6380105018615723, "learning_rate": 9.972987910783144e-06, "loss": 0.5530780553817749, "step": 444 }, { "epoch": 0.062399214751454816, "grad_norm": 7.711920738220215, "learning_rate": 9.9727516972213e-06, "loss": 0.7066354751586914, "step": 445 }, { "epoch": 0.06253943770595247, "grad_norm": 4.175650596618652, "learning_rate": 9.972514458160084e-06, "loss": 0.5832764506340027, "step": 446 }, { "epoch": 0.06267966066045011, "grad_norm": 3.4282875061035156, "learning_rate": 9.972276193648425e-06, "loss": 0.5621979236602783, "step": 447 }, { "epoch": 0.06281988361494777, "grad_norm": 3.6471047401428223, "learning_rate": 9.972036903735461e-06, "loss": 0.5733075737953186, "step": 448 }, { "epoch": 0.06296010656944542, "grad_norm": 4.970339775085449, "learning_rate": 9.971796588470535e-06, "loss": 0.6438589692115784, "step": 449 }, { "epoch": 0.06310032952394307, "grad_norm": 6.946996212005615, "learning_rate": 9.971555247903208e-06, "loss": 0.5754209756851196, "step": 450 }, { "epoch": 0.06324055247844072, "grad_norm": 7.238966464996338, "learning_rate": 9.97131288208325e-06, "loss": 0.8161400556564331, "step": 451 }, { "epoch": 0.06338077543293837, "grad_norm": 3.969282388687134, "learning_rate": 9.971069491060641e-06, "loss": 0.5672131776809692, "step": 452 }, { "epoch": 0.06352099838743602, "grad_norm": 3.5491878986358643, "learning_rate": 9.970825074885578e-06, "loss": 0.7046453356742859, "step": 453 }, { "epoch": 0.06366122134193368, "grad_norm": 16.13649559020996, "learning_rate": 9.970579633608461e-06, "loss": 0.7377950549125671, "step": 454 }, { "epoch": 0.06380144429643132, "grad_norm": 4.317026615142822, "learning_rate": 9.970333167279907e-06, "loss": 0.5970251560211182, "step": 455 }, { "epoch": 0.06394166725092898, "grad_norm": 4.764448642730713, "learning_rate": 9.970085675950744e-06, "loss": 0.7167150974273682, "step": 456 }, { "epoch": 0.06408189020542662, "grad_norm": 7.2308268547058105, "learning_rate": 9.96983715967201e-06, "loss": 0.6242283582687378, "step": 457 }, { "epoch": 0.06422211315992428, "grad_norm": 17.153657913208008, "learning_rate": 9.969587618494955e-06, "loss": 0.5749671459197998, "step": 458 }, { "epoch": 0.06436233611442194, "grad_norm": 7.6784539222717285, "learning_rate": 9.969337052471042e-06, "loss": 0.5605655908584595, "step": 459 }, { "epoch": 0.06450255906891958, "grad_norm": 7.420315265655518, "learning_rate": 9.969085461651941e-06, "loss": 0.6798959970474243, "step": 460 }, { "epoch": 0.06464278202341724, "grad_norm": 5.232275009155273, "learning_rate": 9.968832846089538e-06, "loss": 0.45764321088790894, "step": 461 }, { "epoch": 0.06478300497791488, "grad_norm": 5.22987174987793, "learning_rate": 9.968579205835929e-06, "loss": 0.6245468854904175, "step": 462 }, { "epoch": 0.06492322793241254, "grad_norm": 4.374085903167725, "learning_rate": 9.968324540943417e-06, "loss": 0.6191644668579102, "step": 463 }, { "epoch": 0.06506345088691019, "grad_norm": 3.6580095291137695, "learning_rate": 9.968068851464521e-06, "loss": 0.6484180688858032, "step": 464 }, { "epoch": 0.06520367384140784, "grad_norm": 8.12879753112793, "learning_rate": 9.967812137451973e-06, "loss": 0.6478374004364014, "step": 465 }, { "epoch": 0.06534389679590549, "grad_norm": 2.7394251823425293, "learning_rate": 9.967554398958712e-06, "loss": 0.5295848846435547, "step": 466 }, { "epoch": 0.06548411975040314, "grad_norm": 3.820181131362915, "learning_rate": 9.96729563603789e-06, "loss": 0.6361445188522339, "step": 467 }, { "epoch": 0.06562434270490079, "grad_norm": 4.167173385620117, "learning_rate": 9.96703584874287e-06, "loss": 0.7180385589599609, "step": 468 }, { "epoch": 0.06576456565939845, "grad_norm": 6.493207931518555, "learning_rate": 9.966775037127223e-06, "loss": 0.7165268659591675, "step": 469 }, { "epoch": 0.06590478861389609, "grad_norm": 6.055527210235596, "learning_rate": 9.966513201244741e-06, "loss": 0.5819107294082642, "step": 470 }, { "epoch": 0.06604501156839375, "grad_norm": 4.815893173217773, "learning_rate": 9.966250341149417e-06, "loss": 0.6433442831039429, "step": 471 }, { "epoch": 0.06618523452289139, "grad_norm": 4.1349053382873535, "learning_rate": 9.965986456895458e-06, "loss": 0.6022370457649231, "step": 472 }, { "epoch": 0.06632545747738905, "grad_norm": 3.9278087615966797, "learning_rate": 9.965721548537286e-06, "loss": 0.6530956029891968, "step": 473 }, { "epoch": 0.0664656804318867, "grad_norm": 3.5506436824798584, "learning_rate": 9.965455616129526e-06, "loss": 0.5990254282951355, "step": 474 }, { "epoch": 0.06660590338638435, "grad_norm": 19.066173553466797, "learning_rate": 9.965188659727028e-06, "loss": 0.6791600584983826, "step": 475 }, { "epoch": 0.066746126340882, "grad_norm": 4.325262546539307, "learning_rate": 9.964920679384837e-06, "loss": 0.5007522106170654, "step": 476 }, { "epoch": 0.06688634929537965, "grad_norm": 33.31235122680664, "learning_rate": 9.964651675158223e-06, "loss": 0.5330456495285034, "step": 477 }, { "epoch": 0.0670265722498773, "grad_norm": 3.884385347366333, "learning_rate": 9.964381647102657e-06, "loss": 0.636883020401001, "step": 478 }, { "epoch": 0.06716679520437496, "grad_norm": 5.013111591339111, "learning_rate": 9.964110595273826e-06, "loss": 0.6556769013404846, "step": 479 }, { "epoch": 0.0673070181588726, "grad_norm": 6.21195125579834, "learning_rate": 9.963838519727627e-06, "loss": 0.6383062601089478, "step": 480 }, { "epoch": 0.06744724111337026, "grad_norm": 6.102434158325195, "learning_rate": 9.96356542052017e-06, "loss": 0.580763041973114, "step": 481 }, { "epoch": 0.0675874640678679, "grad_norm": 3.9408442974090576, "learning_rate": 9.963291297707773e-06, "loss": 0.5856130123138428, "step": 482 }, { "epoch": 0.06772768702236556, "grad_norm": 3.2949297428131104, "learning_rate": 9.96301615134697e-06, "loss": 0.6566022634506226, "step": 483 }, { "epoch": 0.06786790997686322, "grad_norm": 18.52948760986328, "learning_rate": 9.962739981494497e-06, "loss": 0.7234377264976501, "step": 484 }, { "epoch": 0.06800813293136086, "grad_norm": 10.835492134094238, "learning_rate": 9.96246278820731e-06, "loss": 0.6514966487884521, "step": 485 }, { "epoch": 0.06814835588585852, "grad_norm": 6.084994792938232, "learning_rate": 9.962184571542573e-06, "loss": 0.5490235686302185, "step": 486 }, { "epoch": 0.06828857884035616, "grad_norm": 3.7801859378814697, "learning_rate": 9.961905331557661e-06, "loss": 0.6021847128868103, "step": 487 }, { "epoch": 0.06842880179485382, "grad_norm": 7.668125629425049, "learning_rate": 9.96162506831016e-06, "loss": 0.6116204261779785, "step": 488 }, { "epoch": 0.06856902474935146, "grad_norm": 42.47172164916992, "learning_rate": 9.961343781857863e-06, "loss": 0.6729938983917236, "step": 489 }, { "epoch": 0.06870924770384912, "grad_norm": 7.584292411804199, "learning_rate": 9.961061472258785e-06, "loss": 0.5940409898757935, "step": 490 }, { "epoch": 0.06884947065834678, "grad_norm": 6.387086868286133, "learning_rate": 9.96077813957114e-06, "loss": 0.5283108949661255, "step": 491 }, { "epoch": 0.06898969361284442, "grad_norm": 4.657522201538086, "learning_rate": 9.96049378385336e-06, "loss": 0.6534898281097412, "step": 492 }, { "epoch": 0.06912991656734208, "grad_norm": 3.9511942863464355, "learning_rate": 9.960208405164082e-06, "loss": 0.589097261428833, "step": 493 }, { "epoch": 0.06927013952183972, "grad_norm": 3.9865427017211914, "learning_rate": 9.959922003562164e-06, "loss": 0.4983680844306946, "step": 494 }, { "epoch": 0.06941036247633738, "grad_norm": 6.108006954193115, "learning_rate": 9.959634579106663e-06, "loss": 0.6572977304458618, "step": 495 }, { "epoch": 0.06955058543083503, "grad_norm": 3.6809873580932617, "learning_rate": 9.959346131856857e-06, "loss": 0.6743654012680054, "step": 496 }, { "epoch": 0.06969080838533268, "grad_norm": 5.451274871826172, "learning_rate": 9.959056661872228e-06, "loss": 0.6108088493347168, "step": 497 }, { "epoch": 0.06983103133983033, "grad_norm": 5.464731216430664, "learning_rate": 9.958766169212476e-06, "loss": 0.7059160470962524, "step": 498 }, { "epoch": 0.06997125429432798, "grad_norm": 3.670386552810669, "learning_rate": 9.9584746539375e-06, "loss": 0.49345728754997253, "step": 499 }, { "epoch": 0.07011147724882563, "grad_norm": 6.982886791229248, "learning_rate": 9.958182116107422e-06, "loss": 0.6590996980667114, "step": 500 }, { "epoch": 0.07025170020332329, "grad_norm": 5.1592607498168945, "learning_rate": 9.957888555782571e-06, "loss": 0.5004640221595764, "step": 501 }, { "epoch": 0.07039192315782093, "grad_norm": 3.2731945514678955, "learning_rate": 9.957593973023484e-06, "loss": 0.6014691591262817, "step": 502 }, { "epoch": 0.07053214611231859, "grad_norm": 6.1956963539123535, "learning_rate": 9.957298367890914e-06, "loss": 0.6726844310760498, "step": 503 }, { "epoch": 0.07067236906681623, "grad_norm": 24.629610061645508, "learning_rate": 9.957001740445817e-06, "loss": 0.6022955179214478, "step": 504 }, { "epoch": 0.07081259202131389, "grad_norm": 8.439831733703613, "learning_rate": 9.95670409074937e-06, "loss": 0.7005314826965332, "step": 505 }, { "epoch": 0.07095281497581155, "grad_norm": 6.205200672149658, "learning_rate": 9.95640541886295e-06, "loss": 0.6657351851463318, "step": 506 }, { "epoch": 0.07109303793030919, "grad_norm": 4.072219371795654, "learning_rate": 9.956105724848153e-06, "loss": 0.7325906157493591, "step": 507 }, { "epoch": 0.07123326088480685, "grad_norm": 4.548482894897461, "learning_rate": 9.955805008766783e-06, "loss": 0.6373851299285889, "step": 508 }, { "epoch": 0.07137348383930449, "grad_norm": 4.180631637573242, "learning_rate": 9.955503270680855e-06, "loss": 0.6043422222137451, "step": 509 }, { "epoch": 0.07151370679380215, "grad_norm": 3.180394411087036, "learning_rate": 9.955200510652594e-06, "loss": 0.5249695181846619, "step": 510 }, { "epoch": 0.0716539297482998, "grad_norm": 4.306698322296143, "learning_rate": 9.954896728744438e-06, "loss": 0.5848827958106995, "step": 511 }, { "epoch": 0.07179415270279745, "grad_norm": 8.340401649475098, "learning_rate": 9.95459192501903e-06, "loss": 0.6834803819656372, "step": 512 }, { "epoch": 0.0719343756572951, "grad_norm": 3.7569329738616943, "learning_rate": 9.954286099539232e-06, "loss": 0.672645092010498, "step": 513 }, { "epoch": 0.07207459861179275, "grad_norm": 5.061008930206299, "learning_rate": 9.95397925236811e-06, "loss": 0.5824590921401978, "step": 514 }, { "epoch": 0.0722148215662904, "grad_norm": 8.191703796386719, "learning_rate": 9.953671383568946e-06, "loss": 0.6660211086273193, "step": 515 }, { "epoch": 0.07235504452078806, "grad_norm": 7.395518779754639, "learning_rate": 9.953362493205225e-06, "loss": 0.6090158820152283, "step": 516 }, { "epoch": 0.0724952674752857, "grad_norm": 9.148783683776855, "learning_rate": 9.953052581340652e-06, "loss": 0.6628241539001465, "step": 517 }, { "epoch": 0.07263549042978336, "grad_norm": 4.60103178024292, "learning_rate": 9.952741648039135e-06, "loss": 0.611519455909729, "step": 518 }, { "epoch": 0.072775713384281, "grad_norm": 3.3906545639038086, "learning_rate": 9.952429693364798e-06, "loss": 0.5691099762916565, "step": 519 }, { "epoch": 0.07291593633877866, "grad_norm": 5.056397914886475, "learning_rate": 9.952116717381974e-06, "loss": 0.6560862064361572, "step": 520 }, { "epoch": 0.07305615929327632, "grad_norm": 3.922948122024536, "learning_rate": 9.951802720155203e-06, "loss": 0.5772199630737305, "step": 521 }, { "epoch": 0.07319638224777396, "grad_norm": 4.536318302154541, "learning_rate": 9.951487701749242e-06, "loss": 0.6317373514175415, "step": 522 }, { "epoch": 0.07333660520227162, "grad_norm": 3.0007376670837402, "learning_rate": 9.951171662229053e-06, "loss": 0.6157448887825012, "step": 523 }, { "epoch": 0.07347682815676926, "grad_norm": 4.587056636810303, "learning_rate": 9.950854601659812e-06, "loss": 0.5732248425483704, "step": 524 }, { "epoch": 0.07361705111126692, "grad_norm": 4.747307300567627, "learning_rate": 9.950536520106903e-06, "loss": 0.6311491131782532, "step": 525 }, { "epoch": 0.07375727406576457, "grad_norm": 5.166335582733154, "learning_rate": 9.950217417635924e-06, "loss": 0.6145794987678528, "step": 526 }, { "epoch": 0.07389749702026222, "grad_norm": 4.622054100036621, "learning_rate": 9.94989729431268e-06, "loss": 0.6498915553092957, "step": 527 }, { "epoch": 0.07403771997475987, "grad_norm": 3.218210220336914, "learning_rate": 9.949576150203188e-06, "loss": 0.5327141284942627, "step": 528 }, { "epoch": 0.07417794292925751, "grad_norm": 4.06803560256958, "learning_rate": 9.949253985373676e-06, "loss": 0.6728668212890625, "step": 529 }, { "epoch": 0.07431816588375517, "grad_norm": 3.520692825317383, "learning_rate": 9.948930799890584e-06, "loss": 0.6392428874969482, "step": 530 }, { "epoch": 0.07445838883825283, "grad_norm": 3.6430490016937256, "learning_rate": 9.948606593820559e-06, "loss": 0.7519083023071289, "step": 531 }, { "epoch": 0.07459861179275047, "grad_norm": 5.3047966957092285, "learning_rate": 9.948281367230457e-06, "loss": 0.6568869352340698, "step": 532 }, { "epoch": 0.07473883474724813, "grad_norm": 3.742966651916504, "learning_rate": 9.94795512018735e-06, "loss": 0.5862616300582886, "step": 533 }, { "epoch": 0.07487905770174577, "grad_norm": 4.316215991973877, "learning_rate": 9.947627852758519e-06, "loss": 0.6983100771903992, "step": 534 }, { "epoch": 0.07501928065624343, "grad_norm": 4.619783878326416, "learning_rate": 9.947299565011453e-06, "loss": 0.6539978981018066, "step": 535 }, { "epoch": 0.07515950361074109, "grad_norm": 3.748999834060669, "learning_rate": 9.946970257013853e-06, "loss": 0.4527670741081238, "step": 536 }, { "epoch": 0.07529972656523873, "grad_norm": 3.4141197204589844, "learning_rate": 9.94663992883363e-06, "loss": 0.6438143849372864, "step": 537 }, { "epoch": 0.07543994951973639, "grad_norm": 4.249143123626709, "learning_rate": 9.946308580538906e-06, "loss": 0.744573712348938, "step": 538 }, { "epoch": 0.07558017247423403, "grad_norm": 3.7395946979522705, "learning_rate": 9.945976212198012e-06, "loss": 0.6188527345657349, "step": 539 }, { "epoch": 0.07572039542873168, "grad_norm": 5.403177261352539, "learning_rate": 9.945642823879491e-06, "loss": 0.6462650895118713, "step": 540 }, { "epoch": 0.07586061838322933, "grad_norm": 5.214280605316162, "learning_rate": 9.945308415652096e-06, "loss": 0.60892254114151, "step": 541 }, { "epoch": 0.07600084133772698, "grad_norm": 5.311559677124023, "learning_rate": 9.944972987584787e-06, "loss": 0.4511934518814087, "step": 542 }, { "epoch": 0.07614106429222464, "grad_norm": 5.314889907836914, "learning_rate": 9.944636539746741e-06, "loss": 0.5963155031204224, "step": 543 }, { "epoch": 0.07628128724672228, "grad_norm": 4.947086334228516, "learning_rate": 9.944299072207339e-06, "loss": 0.6501707434654236, "step": 544 }, { "epoch": 0.07642151020121994, "grad_norm": 3.9551336765289307, "learning_rate": 9.943960585036177e-06, "loss": 0.6719601154327393, "step": 545 }, { "epoch": 0.07656173315571758, "grad_norm": 15.081584930419922, "learning_rate": 9.943621078303056e-06, "loss": 0.7240875959396362, "step": 546 }, { "epoch": 0.07670195611021524, "grad_norm": 3.4313886165618896, "learning_rate": 9.943280552077993e-06, "loss": 0.6149649620056152, "step": 547 }, { "epoch": 0.0768421790647129, "grad_norm": 4.210930347442627, "learning_rate": 9.942939006431212e-06, "loss": 0.6137341856956482, "step": 548 }, { "epoch": 0.07698240201921054, "grad_norm": 4.12584114074707, "learning_rate": 9.942596441433146e-06, "loss": 0.5353789329528809, "step": 549 }, { "epoch": 0.0771226249737082, "grad_norm": 4.945748805999756, "learning_rate": 9.942252857154444e-06, "loss": 0.5923796892166138, "step": 550 }, { "epoch": 0.07726284792820584, "grad_norm": 4.39885950088501, "learning_rate": 9.941908253665957e-06, "loss": 0.6249822974205017, "step": 551 }, { "epoch": 0.0774030708827035, "grad_norm": 4.34890079498291, "learning_rate": 9.941562631038754e-06, "loss": 0.6348596215248108, "step": 552 }, { "epoch": 0.07754329383720115, "grad_norm": 7.3533525466918945, "learning_rate": 9.941215989344108e-06, "loss": 0.6613417267799377, "step": 553 }, { "epoch": 0.0776835167916988, "grad_norm": 3.032534122467041, "learning_rate": 9.940868328653504e-06, "loss": 0.5209277272224426, "step": 554 }, { "epoch": 0.07782373974619645, "grad_norm": 6.498841285705566, "learning_rate": 9.940519649038641e-06, "loss": 0.5119509100914001, "step": 555 }, { "epoch": 0.0779639627006941, "grad_norm": 3.3502848148345947, "learning_rate": 9.940169950571423e-06, "loss": 0.6883046627044678, "step": 556 }, { "epoch": 0.07810418565519175, "grad_norm": 6.251415252685547, "learning_rate": 9.939819233323968e-06, "loss": 0.5519660711288452, "step": 557 }, { "epoch": 0.07824440860968941, "grad_norm": 6.0840935707092285, "learning_rate": 9.939467497368597e-06, "loss": 0.628262996673584, "step": 558 }, { "epoch": 0.07838463156418705, "grad_norm": 4.280788898468018, "learning_rate": 9.939114742777853e-06, "loss": 0.549109935760498, "step": 559 }, { "epoch": 0.07852485451868471, "grad_norm": 3.0822994709014893, "learning_rate": 9.93876096962448e-06, "loss": 0.5820406079292297, "step": 560 }, { "epoch": 0.07866507747318235, "grad_norm": 3.54994535446167, "learning_rate": 9.938406177981432e-06, "loss": 0.6208382248878479, "step": 561 }, { "epoch": 0.07880530042768001, "grad_norm": 5.727042198181152, "learning_rate": 9.938050367921878e-06, "loss": 0.5539636611938477, "step": 562 }, { "epoch": 0.07894552338217767, "grad_norm": 3.4975993633270264, "learning_rate": 9.937693539519195e-06, "loss": 0.6461304426193237, "step": 563 }, { "epoch": 0.07908574633667531, "grad_norm": 3.6971139907836914, "learning_rate": 9.937335692846969e-06, "loss": 0.5793646574020386, "step": 564 }, { "epoch": 0.07922596929117297, "grad_norm": 6.261248588562012, "learning_rate": 9.936976827978993e-06, "loss": 0.604737401008606, "step": 565 }, { "epoch": 0.07936619224567061, "grad_norm": 3.7262754440307617, "learning_rate": 9.936616944989276e-06, "loss": 0.6667375564575195, "step": 566 }, { "epoch": 0.07950641520016827, "grad_norm": 3.3726961612701416, "learning_rate": 9.936256043952036e-06, "loss": 0.6714391112327576, "step": 567 }, { "epoch": 0.07964663815466592, "grad_norm": 4.7562665939331055, "learning_rate": 9.935894124941698e-06, "loss": 0.6467691659927368, "step": 568 }, { "epoch": 0.07978686110916357, "grad_norm": 3.8671789169311523, "learning_rate": 9.935531188032898e-06, "loss": 0.695082426071167, "step": 569 }, { "epoch": 0.07992708406366122, "grad_norm": 4.3303680419921875, "learning_rate": 9.935167233300483e-06, "loss": 0.5468542575836182, "step": 570 }, { "epoch": 0.08006730701815887, "grad_norm": 6.08967924118042, "learning_rate": 9.934802260819507e-06, "loss": 0.5847085118293762, "step": 571 }, { "epoch": 0.08020752997265652, "grad_norm": 4.607640743255615, "learning_rate": 9.934436270665237e-06, "loss": 0.5764992237091064, "step": 572 }, { "epoch": 0.08034775292715418, "grad_norm": 4.222103118896484, "learning_rate": 9.934069262913152e-06, "loss": 0.6532090902328491, "step": 573 }, { "epoch": 0.08048797588165182, "grad_norm": 3.6617014408111572, "learning_rate": 9.933701237638933e-06, "loss": 0.7446016073226929, "step": 574 }, { "epoch": 0.08062819883614948, "grad_norm": 3.6754846572875977, "learning_rate": 9.93333219491848e-06, "loss": 0.6290590763092041, "step": 575 }, { "epoch": 0.08076842179064712, "grad_norm": 5.048146724700928, "learning_rate": 9.932962134827893e-06, "loss": 0.6902691125869751, "step": 576 }, { "epoch": 0.08090864474514478, "grad_norm": 9.634787559509277, "learning_rate": 9.932591057443492e-06, "loss": 0.6505298614501953, "step": 577 }, { "epoch": 0.08104886769964244, "grad_norm": 18.75485610961914, "learning_rate": 9.9322189628418e-06, "loss": 0.6085450649261475, "step": 578 }, { "epoch": 0.08118909065414008, "grad_norm": 3.7799901962280273, "learning_rate": 9.931845851099551e-06, "loss": 0.5986554622650146, "step": 579 }, { "epoch": 0.08132931360863774, "grad_norm": 10.776008605957031, "learning_rate": 9.93147172229369e-06, "loss": 0.572857141494751, "step": 580 }, { "epoch": 0.08146953656313538, "grad_norm": 8.15047550201416, "learning_rate": 9.931096576501374e-06, "loss": 0.7008090019226074, "step": 581 }, { "epoch": 0.08160975951763304, "grad_norm": 4.642762660980225, "learning_rate": 9.930720413799963e-06, "loss": 0.6002588272094727, "step": 582 }, { "epoch": 0.0817499824721307, "grad_norm": 5.116590976715088, "learning_rate": 9.930343234267033e-06, "loss": 0.6341440081596375, "step": 583 }, { "epoch": 0.08189020542662834, "grad_norm": 4.018604278564453, "learning_rate": 9.929965037980365e-06, "loss": 0.5184764862060547, "step": 584 }, { "epoch": 0.082030428381126, "grad_norm": 4.21115779876709, "learning_rate": 9.929585825017954e-06, "loss": 0.5794234871864319, "step": 585 }, { "epoch": 0.08217065133562364, "grad_norm": 2.8548851013183594, "learning_rate": 9.929205595458002e-06, "loss": 0.5650991797447205, "step": 586 }, { "epoch": 0.0823108742901213, "grad_norm": 6.849513530731201, "learning_rate": 9.928824349378923e-06, "loss": 0.645487904548645, "step": 587 }, { "epoch": 0.08245109724461894, "grad_norm": 3.979315996170044, "learning_rate": 9.928442086859337e-06, "loss": 0.6678072214126587, "step": 588 }, { "epoch": 0.0825913201991166, "grad_norm": 5.946855545043945, "learning_rate": 9.928058807978077e-06, "loss": 0.6384561061859131, "step": 589 }, { "epoch": 0.08273154315361425, "grad_norm": 3.3898279666900635, "learning_rate": 9.927674512814182e-06, "loss": 0.5258110761642456, "step": 590 }, { "epoch": 0.0828717661081119, "grad_norm": 4.515774250030518, "learning_rate": 9.927289201446906e-06, "loss": 0.5710715055465698, "step": 591 }, { "epoch": 0.08301198906260955, "grad_norm": 4.3718647956848145, "learning_rate": 9.926902873955707e-06, "loss": 0.6048016548156738, "step": 592 }, { "epoch": 0.0831522120171072, "grad_norm": 8.257286071777344, "learning_rate": 9.926515530420255e-06, "loss": 0.6587851047515869, "step": 593 }, { "epoch": 0.08329243497160485, "grad_norm": 6.817593574523926, "learning_rate": 9.92612717092043e-06, "loss": 0.5985561013221741, "step": 594 }, { "epoch": 0.08343265792610251, "grad_norm": 5.710475921630859, "learning_rate": 9.92573779553632e-06, "loss": 0.5596511960029602, "step": 595 }, { "epoch": 0.08357288088060015, "grad_norm": 5.118454933166504, "learning_rate": 9.925347404348225e-06, "loss": 0.5430930852890015, "step": 596 }, { "epoch": 0.08371310383509781, "grad_norm": 5.252628326416016, "learning_rate": 9.924955997436653e-06, "loss": 0.6311306953430176, "step": 597 }, { "epoch": 0.08385332678959545, "grad_norm": 3.7957026958465576, "learning_rate": 9.92456357488232e-06, "loss": 0.5361001491546631, "step": 598 }, { "epoch": 0.08399354974409311, "grad_norm": 5.313753604888916, "learning_rate": 9.924170136766153e-06, "loss": 0.7035050988197327, "step": 599 }, { "epoch": 0.08413377269859076, "grad_norm": 6.649102210998535, "learning_rate": 9.92377568316929e-06, "loss": 0.6924100518226624, "step": 600 }, { "epoch": 0.08427399565308841, "grad_norm": 4.908106327056885, "learning_rate": 9.923380214173074e-06, "loss": 0.6277453899383545, "step": 601 }, { "epoch": 0.08441421860758606, "grad_norm": 8.722169876098633, "learning_rate": 9.922983729859061e-06, "loss": 0.5815671682357788, "step": 602 }, { "epoch": 0.08455444156208371, "grad_norm": 4.666173458099365, "learning_rate": 9.922586230309018e-06, "loss": 0.7461749315261841, "step": 603 }, { "epoch": 0.08469466451658136, "grad_norm": 14.146247863769531, "learning_rate": 9.922187715604915e-06, "loss": 0.5992957353591919, "step": 604 }, { "epoch": 0.08483488747107902, "grad_norm": 4.3289079666137695, "learning_rate": 9.921788185828938e-06, "loss": 0.5959436893463135, "step": 605 }, { "epoch": 0.08497511042557666, "grad_norm": 3.7790157794952393, "learning_rate": 9.921387641063478e-06, "loss": 0.5467395782470703, "step": 606 }, { "epoch": 0.08511533338007432, "grad_norm": 5.091342926025391, "learning_rate": 9.920986081391139e-06, "loss": 0.6636415719985962, "step": 607 }, { "epoch": 0.08525555633457196, "grad_norm": 4.010499954223633, "learning_rate": 9.920583506894729e-06, "loss": 0.6948680877685547, "step": 608 }, { "epoch": 0.08539577928906962, "grad_norm": 9.695919036865234, "learning_rate": 9.920179917657272e-06, "loss": 0.6246210336685181, "step": 609 }, { "epoch": 0.08553600224356728, "grad_norm": 3.0854713916778564, "learning_rate": 9.919775313761993e-06, "loss": 0.6678581237792969, "step": 610 }, { "epoch": 0.08567622519806492, "grad_norm": 4.853938579559326, "learning_rate": 9.919369695292333e-06, "loss": 0.7218306064605713, "step": 611 }, { "epoch": 0.08581644815256258, "grad_norm": 4.007169246673584, "learning_rate": 9.918963062331941e-06, "loss": 0.48036500811576843, "step": 612 }, { "epoch": 0.08595667110706022, "grad_norm": 4.085593223571777, "learning_rate": 9.918555414964675e-06, "loss": 0.6049700975418091, "step": 613 }, { "epoch": 0.08609689406155788, "grad_norm": 4.221750736236572, "learning_rate": 9.918146753274601e-06, "loss": 0.5567137002944946, "step": 614 }, { "epoch": 0.08623711701605553, "grad_norm": 7.916508197784424, "learning_rate": 9.917737077345993e-06, "loss": 0.5062789916992188, "step": 615 }, { "epoch": 0.08637733997055318, "grad_norm": 3.0645694732666016, "learning_rate": 9.917326387263338e-06, "loss": 0.4906911849975586, "step": 616 }, { "epoch": 0.08651756292505083, "grad_norm": 3.915731430053711, "learning_rate": 9.91691468311133e-06, "loss": 0.6152637004852295, "step": 617 }, { "epoch": 0.08665778587954848, "grad_norm": 3.3605406284332275, "learning_rate": 9.91650196497487e-06, "loss": 0.6508742570877075, "step": 618 }, { "epoch": 0.08679800883404613, "grad_norm": 3.2953639030456543, "learning_rate": 9.916088232939072e-06, "loss": 0.6182004809379578, "step": 619 }, { "epoch": 0.08693823178854379, "grad_norm": 4.950198173522949, "learning_rate": 9.915673487089258e-06, "loss": 0.6677792072296143, "step": 620 }, { "epoch": 0.08707845474304143, "grad_norm": 3.3659050464630127, "learning_rate": 9.915257727510956e-06, "loss": 0.5555884838104248, "step": 621 }, { "epoch": 0.08721867769753909, "grad_norm": 4.80136775970459, "learning_rate": 9.914840954289907e-06, "loss": 0.5705618858337402, "step": 622 }, { "epoch": 0.08735890065203673, "grad_norm": 5.105710506439209, "learning_rate": 9.914423167512059e-06, "loss": 0.6422220468521118, "step": 623 }, { "epoch": 0.08749912360653439, "grad_norm": 3.9849464893341064, "learning_rate": 9.914004367263572e-06, "loss": 0.6075446605682373, "step": 624 }, { "epoch": 0.08763934656103205, "grad_norm": 4.873507022857666, "learning_rate": 9.91358455363081e-06, "loss": 0.731768012046814, "step": 625 }, { "epoch": 0.08777956951552969, "grad_norm": 6.6527099609375, "learning_rate": 9.913163726700347e-06, "loss": 0.5462237000465393, "step": 626 }, { "epoch": 0.08791979247002735, "grad_norm": 4.612302303314209, "learning_rate": 9.912741886558972e-06, "loss": 0.574005663394928, "step": 627 }, { "epoch": 0.08806001542452499, "grad_norm": 4.530459403991699, "learning_rate": 9.912319033293675e-06, "loss": 0.6422786712646484, "step": 628 }, { "epoch": 0.08820023837902265, "grad_norm": 5.715070724487305, "learning_rate": 9.91189516699166e-06, "loss": 0.6740974187850952, "step": 629 }, { "epoch": 0.0883404613335203, "grad_norm": 3.5892539024353027, "learning_rate": 9.911470287740337e-06, "loss": 0.6266974806785583, "step": 630 }, { "epoch": 0.08848068428801795, "grad_norm": 5.680184364318848, "learning_rate": 9.911044395627327e-06, "loss": 0.5746881365776062, "step": 631 }, { "epoch": 0.0886209072425156, "grad_norm": 4.140415191650391, "learning_rate": 9.91061749074046e-06, "loss": 0.5421884059906006, "step": 632 }, { "epoch": 0.08876113019701325, "grad_norm": 6.057793617248535, "learning_rate": 9.910189573167772e-06, "loss": 0.5445926785469055, "step": 633 }, { "epoch": 0.0889013531515109, "grad_norm": 3.9803385734558105, "learning_rate": 9.90976064299751e-06, "loss": 0.5018185377120972, "step": 634 }, { "epoch": 0.08904157610600856, "grad_norm": 4.935637474060059, "learning_rate": 9.90933070031813e-06, "loss": 0.508137583732605, "step": 635 }, { "epoch": 0.0891817990605062, "grad_norm": 6.083460330963135, "learning_rate": 9.908899745218298e-06, "loss": 0.6031588315963745, "step": 636 }, { "epoch": 0.08932202201500386, "grad_norm": 10.32083511352539, "learning_rate": 9.908467777786884e-06, "loss": 0.6787307262420654, "step": 637 }, { "epoch": 0.0894622449695015, "grad_norm": 3.7702817916870117, "learning_rate": 9.908034798112973e-06, "loss": 0.7088563442230225, "step": 638 }, { "epoch": 0.08960246792399916, "grad_norm": 6.031447887420654, "learning_rate": 9.907600806285855e-06, "loss": 0.6482230424880981, "step": 639 }, { "epoch": 0.0897426908784968, "grad_norm": 3.7584290504455566, "learning_rate": 9.907165802395027e-06, "loss": 0.6319277286529541, "step": 640 }, { "epoch": 0.08988291383299446, "grad_norm": 4.973401069641113, "learning_rate": 9.9067297865302e-06, "loss": 0.6396020650863647, "step": 641 }, { "epoch": 0.09002313678749212, "grad_norm": 5.6374101638793945, "learning_rate": 9.90629275878129e-06, "loss": 0.6373418569564819, "step": 642 }, { "epoch": 0.09016335974198976, "grad_norm": 3.8787362575531006, "learning_rate": 9.905854719238419e-06, "loss": 0.6210743188858032, "step": 643 }, { "epoch": 0.09030358269648742, "grad_norm": 4.305442810058594, "learning_rate": 9.905415667991927e-06, "loss": 0.6022005081176758, "step": 644 }, { "epoch": 0.09044380565098506, "grad_norm": 3.3318679332733154, "learning_rate": 9.904975605132354e-06, "loss": 0.6674062013626099, "step": 645 }, { "epoch": 0.09058402860548272, "grad_norm": 3.6306896209716797, "learning_rate": 9.904534530750451e-06, "loss": 0.5826221704483032, "step": 646 }, { "epoch": 0.09072425155998037, "grad_norm": 4.714840412139893, "learning_rate": 9.904092444937178e-06, "loss": 0.6320734024047852, "step": 647 }, { "epoch": 0.09086447451447802, "grad_norm": 3.404977321624756, "learning_rate": 9.903649347783705e-06, "loss": 0.6026360988616943, "step": 648 }, { "epoch": 0.09100469746897567, "grad_norm": 6.811723232269287, "learning_rate": 9.903205239381408e-06, "loss": 0.6234848499298096, "step": 649 }, { "epoch": 0.09114492042347332, "grad_norm": 4.19528865814209, "learning_rate": 9.902760119821874e-06, "loss": 0.6490445733070374, "step": 650 }, { "epoch": 0.09128514337797097, "grad_norm": 3.5085160732269287, "learning_rate": 9.902313989196894e-06, "loss": 0.6192749738693237, "step": 651 }, { "epoch": 0.09142536633246863, "grad_norm": 4.507908344268799, "learning_rate": 9.901866847598475e-06, "loss": 0.5635737776756287, "step": 652 }, { "epoch": 0.09156558928696627, "grad_norm": 4.546689033508301, "learning_rate": 9.901418695118826e-06, "loss": 0.6483380794525146, "step": 653 }, { "epoch": 0.09170581224146393, "grad_norm": 4.912414073944092, "learning_rate": 9.900969531850364e-06, "loss": 0.5598253011703491, "step": 654 }, { "epoch": 0.09184603519596157, "grad_norm": 3.613229513168335, "learning_rate": 9.900519357885721e-06, "loss": 0.47485995292663574, "step": 655 }, { "epoch": 0.09198625815045923, "grad_norm": 5.399890422821045, "learning_rate": 9.900068173317735e-06, "loss": 0.7301974296569824, "step": 656 }, { "epoch": 0.09212648110495689, "grad_norm": 4.547125339508057, "learning_rate": 9.899615978239445e-06, "loss": 0.49698638916015625, "step": 657 }, { "epoch": 0.09226670405945453, "grad_norm": 3.2471742630004883, "learning_rate": 9.899162772744108e-06, "loss": 0.6367152333259583, "step": 658 }, { "epoch": 0.09240692701395219, "grad_norm": 3.412632942199707, "learning_rate": 9.898708556925187e-06, "loss": 0.6364507079124451, "step": 659 }, { "epoch": 0.09254714996844983, "grad_norm": 3.4041941165924072, "learning_rate": 9.898253330876351e-06, "loss": 0.592980146408081, "step": 660 }, { "epoch": 0.09268737292294749, "grad_norm": 3.5133631229400635, "learning_rate": 9.897797094691476e-06, "loss": 0.6714468002319336, "step": 661 }, { "epoch": 0.09282759587744514, "grad_norm": 3.0745596885681152, "learning_rate": 9.89733984846465e-06, "loss": 0.5954889059066772, "step": 662 }, { "epoch": 0.09296781883194279, "grad_norm": 3.987199068069458, "learning_rate": 9.896881592290172e-06, "loss": 0.6069166660308838, "step": 663 }, { "epoch": 0.09310804178644044, "grad_norm": 3.5154199600219727, "learning_rate": 9.89642232626254e-06, "loss": 0.5955907106399536, "step": 664 }, { "epoch": 0.09324826474093809, "grad_norm": 3.743354558944702, "learning_rate": 9.895962050476468e-06, "loss": 0.49834540486335754, "step": 665 }, { "epoch": 0.09338848769543574, "grad_norm": 7.066349506378174, "learning_rate": 9.895500765026873e-06, "loss": 0.5552067756652832, "step": 666 }, { "epoch": 0.0935287106499334, "grad_norm": 5.978977203369141, "learning_rate": 9.895038470008889e-06, "loss": 0.7607445120811462, "step": 667 }, { "epoch": 0.09366893360443104, "grad_norm": 4.509058952331543, "learning_rate": 9.894575165517846e-06, "loss": 0.49283790588378906, "step": 668 }, { "epoch": 0.0938091565589287, "grad_norm": 4.253340244293213, "learning_rate": 9.894110851649292e-06, "loss": 0.5910741090774536, "step": 669 }, { "epoch": 0.09394937951342634, "grad_norm": 3.754178285598755, "learning_rate": 9.893645528498978e-06, "loss": 0.598047137260437, "step": 670 }, { "epoch": 0.094089602467924, "grad_norm": 5.52562952041626, "learning_rate": 9.893179196162864e-06, "loss": 0.5147849321365356, "step": 671 }, { "epoch": 0.09422982542242166, "grad_norm": 4.149184226989746, "learning_rate": 9.89271185473712e-06, "loss": 0.5931152105331421, "step": 672 }, { "epoch": 0.0943700483769193, "grad_norm": 8.121631622314453, "learning_rate": 9.892243504318124e-06, "loss": 0.6084140539169312, "step": 673 }, { "epoch": 0.09451027133141696, "grad_norm": 7.180438041687012, "learning_rate": 9.89177414500246e-06, "loss": 0.5554623007774353, "step": 674 }, { "epoch": 0.0946504942859146, "grad_norm": 3.3352749347686768, "learning_rate": 9.89130377688692e-06, "loss": 0.6217091679573059, "step": 675 }, { "epoch": 0.09479071724041226, "grad_norm": 7.940488338470459, "learning_rate": 9.890832400068506e-06, "loss": 0.524344801902771, "step": 676 }, { "epoch": 0.09493094019490991, "grad_norm": 4.963816165924072, "learning_rate": 9.890360014644427e-06, "loss": 0.6836084723472595, "step": 677 }, { "epoch": 0.09507116314940756, "grad_norm": 3.1748597621917725, "learning_rate": 9.8898866207121e-06, "loss": 0.6730241179466248, "step": 678 }, { "epoch": 0.09521138610390521, "grad_norm": 4.496433258056641, "learning_rate": 9.88941221836915e-06, "loss": 0.5985363721847534, "step": 679 }, { "epoch": 0.09535160905840286, "grad_norm": 3.6308538913726807, "learning_rate": 9.88893680771341e-06, "loss": 0.5351805090904236, "step": 680 }, { "epoch": 0.09549183201290051, "grad_norm": 4.4656782150268555, "learning_rate": 9.88846038884292e-06, "loss": 0.5919641256332397, "step": 681 }, { "epoch": 0.09563205496739817, "grad_norm": 10.843836784362793, "learning_rate": 9.88798296185593e-06, "loss": 0.640305757522583, "step": 682 }, { "epoch": 0.09577227792189581, "grad_norm": 2.9672772884368896, "learning_rate": 9.887504526850897e-06, "loss": 0.576999306678772, "step": 683 }, { "epoch": 0.09591250087639347, "grad_norm": 5.979426860809326, "learning_rate": 9.887025083926486e-06, "loss": 0.5954378843307495, "step": 684 }, { "epoch": 0.09605272383089111, "grad_norm": 4.615646839141846, "learning_rate": 9.88654463318157e-06, "loss": 0.7422345876693726, "step": 685 }, { "epoch": 0.09619294678538877, "grad_norm": 7.462137699127197, "learning_rate": 9.886063174715225e-06, "loss": 0.5498608350753784, "step": 686 }, { "epoch": 0.09633316973988643, "grad_norm": 4.633543491363525, "learning_rate": 9.885580708626745e-06, "loss": 0.6482070684432983, "step": 687 }, { "epoch": 0.09647339269438407, "grad_norm": 5.398745059967041, "learning_rate": 9.885097235015622e-06, "loss": 0.5367079377174377, "step": 688 }, { "epoch": 0.09661361564888173, "grad_norm": 3.1904540061950684, "learning_rate": 9.884612753981561e-06, "loss": 0.5479444861412048, "step": 689 }, { "epoch": 0.09675383860337937, "grad_norm": 4.922155857086182, "learning_rate": 9.884127265624473e-06, "loss": 0.7260090708732605, "step": 690 }, { "epoch": 0.09689406155787703, "grad_norm": 5.9539289474487305, "learning_rate": 9.883640770044479e-06, "loss": 0.6589407324790955, "step": 691 }, { "epoch": 0.09703428451237467, "grad_norm": 2.9822726249694824, "learning_rate": 9.883153267341905e-06, "loss": 0.5046241283416748, "step": 692 }, { "epoch": 0.09717450746687233, "grad_norm": 4.070915222167969, "learning_rate": 9.882664757617282e-06, "loss": 0.5491104125976562, "step": 693 }, { "epoch": 0.09731473042136998, "grad_norm": 4.527677536010742, "learning_rate": 9.88217524097136e-06, "loss": 0.6234239339828491, "step": 694 }, { "epoch": 0.09745495337586763, "grad_norm": 5.105878829956055, "learning_rate": 9.88168471750508e-06, "loss": 0.7090309858322144, "step": 695 }, { "epoch": 0.09759517633036528, "grad_norm": 7.230356693267822, "learning_rate": 9.881193187319607e-06, "loss": 0.5258933901786804, "step": 696 }, { "epoch": 0.09773539928486293, "grad_norm": 6.421366214752197, "learning_rate": 9.880700650516301e-06, "loss": 0.6821361780166626, "step": 697 }, { "epoch": 0.09787562223936058, "grad_norm": 4.372302532196045, "learning_rate": 9.880207107196739e-06, "loss": 0.6772887706756592, "step": 698 }, { "epoch": 0.09801584519385824, "grad_norm": 5.196182727813721, "learning_rate": 9.879712557462699e-06, "loss": 0.5469332933425903, "step": 699 }, { "epoch": 0.09815606814835588, "grad_norm": 4.112587928771973, "learning_rate": 9.87921700141617e-06, "loss": 0.5856185555458069, "step": 700 }, { "epoch": 0.09829629110285354, "grad_norm": 3.6767706871032715, "learning_rate": 9.878720439159345e-06, "loss": 0.5640796422958374, "step": 701 }, { "epoch": 0.09843651405735118, "grad_norm": 4.0611162185668945, "learning_rate": 9.878222870794629e-06, "loss": 0.708238422870636, "step": 702 }, { "epoch": 0.09857673701184884, "grad_norm": 4.147633075714111, "learning_rate": 9.877724296424634e-06, "loss": 0.5917041301727295, "step": 703 }, { "epoch": 0.0987169599663465, "grad_norm": 17.47616195678711, "learning_rate": 9.877224716152172e-06, "loss": 0.6272401213645935, "step": 704 }, { "epoch": 0.09885718292084414, "grad_norm": 5.557182788848877, "learning_rate": 9.876724130080275e-06, "loss": 0.5806329250335693, "step": 705 }, { "epoch": 0.0989974058753418, "grad_norm": 4.055089473724365, "learning_rate": 9.876222538312173e-06, "loss": 0.5333967804908752, "step": 706 }, { "epoch": 0.09913762882983944, "grad_norm": 4.244472026824951, "learning_rate": 9.875719940951304e-06, "loss": 0.5903903245925903, "step": 707 }, { "epoch": 0.0992778517843371, "grad_norm": 3.0303478240966797, "learning_rate": 9.87521633810132e-06, "loss": 0.5940150022506714, "step": 708 }, { "epoch": 0.09941807473883475, "grad_norm": 3.9215760231018066, "learning_rate": 9.87471172986607e-06, "loss": 0.6098071336746216, "step": 709 }, { "epoch": 0.0995582976933324, "grad_norm": 3.5941972732543945, "learning_rate": 9.87420611634962e-06, "loss": 0.5185529589653015, "step": 710 }, { "epoch": 0.09969852064783005, "grad_norm": 4.795169830322266, "learning_rate": 9.873699497656242e-06, "loss": 0.5852298140525818, "step": 711 }, { "epoch": 0.0998387436023277, "grad_norm": 3.7047924995422363, "learning_rate": 9.873191873890408e-06, "loss": 0.5975520014762878, "step": 712 }, { "epoch": 0.09997896655682535, "grad_norm": 3.038114309310913, "learning_rate": 9.872683245156803e-06, "loss": 0.589898407459259, "step": 713 }, { "epoch": 0.10011918951132301, "grad_norm": 3.858931303024292, "learning_rate": 9.87217361156032e-06, "loss": 0.48470354080200195, "step": 714 }, { "epoch": 0.10025941246582065, "grad_norm": 4.059568405151367, "learning_rate": 9.871662973206057e-06, "loss": 0.675950288772583, "step": 715 }, { "epoch": 0.10039963542031831, "grad_norm": 3.6454334259033203, "learning_rate": 9.87115133019932e-06, "loss": 0.48382318019866943, "step": 716 }, { "epoch": 0.10053985837481595, "grad_norm": 3.320023775100708, "learning_rate": 9.870638682645622e-06, "loss": 0.5912976861000061, "step": 717 }, { "epoch": 0.10068008132931361, "grad_norm": 4.6197509765625, "learning_rate": 9.870125030650679e-06, "loss": 0.5733046531677246, "step": 718 }, { "epoch": 0.10082030428381127, "grad_norm": 4.249598503112793, "learning_rate": 9.869610374320424e-06, "loss": 0.6450902819633484, "step": 719 }, { "epoch": 0.10096052723830891, "grad_norm": 3.761749267578125, "learning_rate": 9.869094713760989e-06, "loss": 0.5765832662582397, "step": 720 }, { "epoch": 0.10110075019280657, "grad_norm": 3.1355724334716797, "learning_rate": 9.868578049078716e-06, "loss": 0.6019790172576904, "step": 721 }, { "epoch": 0.10124097314730421, "grad_norm": 3.1149404048919678, "learning_rate": 9.868060380380152e-06, "loss": 0.6459894180297852, "step": 722 }, { "epoch": 0.10138119610180187, "grad_norm": 5.614691257476807, "learning_rate": 9.867541707772054e-06, "loss": 0.5276470184326172, "step": 723 }, { "epoch": 0.10152141905629952, "grad_norm": 8.635942459106445, "learning_rate": 9.867022031361384e-06, "loss": 0.6139786839485168, "step": 724 }, { "epoch": 0.10166164201079717, "grad_norm": 6.644118309020996, "learning_rate": 9.866501351255312e-06, "loss": 0.5138447284698486, "step": 725 }, { "epoch": 0.10180186496529482, "grad_norm": 4.746017932891846, "learning_rate": 9.865979667561215e-06, "loss": 0.6530489921569824, "step": 726 }, { "epoch": 0.10194208791979247, "grad_norm": 3.457831382751465, "learning_rate": 9.865456980386676e-06, "loss": 0.6259087324142456, "step": 727 }, { "epoch": 0.10208231087429012, "grad_norm": 3.1501996517181396, "learning_rate": 9.864933289839485e-06, "loss": 0.5789507627487183, "step": 728 }, { "epoch": 0.10222253382878778, "grad_norm": 4.712117671966553, "learning_rate": 9.864408596027639e-06, "loss": 0.6138007640838623, "step": 729 }, { "epoch": 0.10236275678328542, "grad_norm": 8.50184154510498, "learning_rate": 9.863882899059342e-06, "loss": 0.6757234930992126, "step": 730 }, { "epoch": 0.10250297973778308, "grad_norm": 3.4996886253356934, "learning_rate": 9.863356199043008e-06, "loss": 0.5244340896606445, "step": 731 }, { "epoch": 0.10264320269228072, "grad_norm": 3.7276875972747803, "learning_rate": 9.862828496087253e-06, "loss": 0.685560941696167, "step": 732 }, { "epoch": 0.10278342564677838, "grad_norm": 3.4421896934509277, "learning_rate": 9.862299790300904e-06, "loss": 0.6209076642990112, "step": 733 }, { "epoch": 0.10292364860127604, "grad_norm": 3.3585305213928223, "learning_rate": 9.86177008179299e-06, "loss": 0.6392334699630737, "step": 734 }, { "epoch": 0.10306387155577368, "grad_norm": 5.167480945587158, "learning_rate": 9.861239370672747e-06, "loss": 0.5406172275543213, "step": 735 }, { "epoch": 0.10320409451027134, "grad_norm": 3.3780412673950195, "learning_rate": 9.860707657049628e-06, "loss": 0.5528277158737183, "step": 736 }, { "epoch": 0.10334431746476898, "grad_norm": 5.527729034423828, "learning_rate": 9.860174941033279e-06, "loss": 0.550168514251709, "step": 737 }, { "epoch": 0.10348454041926664, "grad_norm": 3.0739924907684326, "learning_rate": 9.85964122273356e-06, "loss": 0.6017082333564758, "step": 738 }, { "epoch": 0.10362476337376429, "grad_norm": 7.141872406005859, "learning_rate": 9.859106502260537e-06, "loss": 0.5326378345489502, "step": 739 }, { "epoch": 0.10376498632826194, "grad_norm": 6.061246395111084, "learning_rate": 9.85857077972448e-06, "loss": 0.6574026346206665, "step": 740 }, { "epoch": 0.10390520928275959, "grad_norm": 20.461490631103516, "learning_rate": 9.858034055235871e-06, "loss": 0.5046627521514893, "step": 741 }, { "epoch": 0.10404543223725723, "grad_norm": 13.79686164855957, "learning_rate": 9.857496328905393e-06, "loss": 0.5020259618759155, "step": 742 }, { "epoch": 0.10418565519175489, "grad_norm": 4.0406389236450195, "learning_rate": 9.85695760084394e-06, "loss": 0.6470078229904175, "step": 743 }, { "epoch": 0.10432587814625253, "grad_norm": 3.5050816535949707, "learning_rate": 9.85641787116261e-06, "loss": 0.6529454588890076, "step": 744 }, { "epoch": 0.10446610110075019, "grad_norm": 4.812593936920166, "learning_rate": 9.855877139972703e-06, "loss": 0.6971196532249451, "step": 745 }, { "epoch": 0.10460632405524785, "grad_norm": 9.207745552062988, "learning_rate": 9.855335407385738e-06, "loss": 0.5756423473358154, "step": 746 }, { "epoch": 0.10474654700974549, "grad_norm": 17.173799514770508, "learning_rate": 9.854792673513429e-06, "loss": 0.6539644002914429, "step": 747 }, { "epoch": 0.10488676996424315, "grad_norm": 4.972723960876465, "learning_rate": 9.8542489384677e-06, "loss": 0.5525243282318115, "step": 748 }, { "epoch": 0.10502699291874079, "grad_norm": 5.704021453857422, "learning_rate": 9.853704202360685e-06, "loss": 0.48295682668685913, "step": 749 }, { "epoch": 0.10516721587323845, "grad_norm": 2.636357069015503, "learning_rate": 9.853158465304721e-06, "loss": 0.6819614171981812, "step": 750 }, { "epoch": 0.1053074388277361, "grad_norm": 6.694390773773193, "learning_rate": 9.852611727412349e-06, "loss": 0.7373083233833313, "step": 751 }, { "epoch": 0.10544766178223375, "grad_norm": 3.2602832317352295, "learning_rate": 9.852063988796324e-06, "loss": 0.6096307635307312, "step": 752 }, { "epoch": 0.1055878847367314, "grad_norm": 2.8756215572357178, "learning_rate": 9.851515249569596e-06, "loss": 0.4611685276031494, "step": 753 }, { "epoch": 0.10572810769122905, "grad_norm": 3.680004596710205, "learning_rate": 9.850965509845335e-06, "loss": 0.6122156381607056, "step": 754 }, { "epoch": 0.1058683306457267, "grad_norm": 4.2071943283081055, "learning_rate": 9.850414769736906e-06, "loss": 0.6581944823265076, "step": 755 }, { "epoch": 0.10600855360022436, "grad_norm": 4.074195384979248, "learning_rate": 9.849863029357887e-06, "loss": 0.7234476208686829, "step": 756 }, { "epoch": 0.106148776554722, "grad_norm": 15.764034271240234, "learning_rate": 9.84931028882206e-06, "loss": 0.5900081396102905, "step": 757 }, { "epoch": 0.10628899950921966, "grad_norm": 3.7826757431030273, "learning_rate": 9.84875654824341e-06, "loss": 0.6007471084594727, "step": 758 }, { "epoch": 0.1064292224637173, "grad_norm": 4.5432233810424805, "learning_rate": 9.848201807736135e-06, "loss": 0.5840638279914856, "step": 759 }, { "epoch": 0.10656944541821496, "grad_norm": 6.068451881408691, "learning_rate": 9.847646067414634e-06, "loss": 0.5430034399032593, "step": 760 }, { "epoch": 0.10670966837271262, "grad_norm": 3.3073031902313232, "learning_rate": 9.847089327393514e-06, "loss": 0.5977644920349121, "step": 761 }, { "epoch": 0.10684989132721026, "grad_norm": 4.992469310760498, "learning_rate": 9.846531587787588e-06, "loss": 0.5235145092010498, "step": 762 }, { "epoch": 0.10699011428170792, "grad_norm": 3.6016273498535156, "learning_rate": 9.845972848711877e-06, "loss": 0.5462108254432678, "step": 763 }, { "epoch": 0.10713033723620556, "grad_norm": 2.8485829830169678, "learning_rate": 9.845413110281604e-06, "loss": 0.60466468334198, "step": 764 }, { "epoch": 0.10727056019070322, "grad_norm": 4.29490852355957, "learning_rate": 9.844852372612199e-06, "loss": 0.7092806100845337, "step": 765 }, { "epoch": 0.10741078314520087, "grad_norm": 2.806035280227661, "learning_rate": 9.844290635819303e-06, "loss": 0.5320806503295898, "step": 766 }, { "epoch": 0.10755100609969852, "grad_norm": 2.7278575897216797, "learning_rate": 9.843727900018757e-06, "loss": 0.5367614030838013, "step": 767 }, { "epoch": 0.10769122905419617, "grad_norm": 2.9982082843780518, "learning_rate": 9.843164165326612e-06, "loss": 0.5737758278846741, "step": 768 }, { "epoch": 0.10783145200869382, "grad_norm": 8.84177303314209, "learning_rate": 9.842599431859122e-06, "loss": 0.5974776148796082, "step": 769 }, { "epoch": 0.10797167496319147, "grad_norm": 3.6223647594451904, "learning_rate": 9.842033699732749e-06, "loss": 0.4547591507434845, "step": 770 }, { "epoch": 0.10811189791768913, "grad_norm": 6.512843608856201, "learning_rate": 9.841466969064162e-06, "loss": 0.5472344160079956, "step": 771 }, { "epoch": 0.10825212087218677, "grad_norm": 5.885802268981934, "learning_rate": 9.840899239970233e-06, "loss": 0.681588888168335, "step": 772 }, { "epoch": 0.10839234382668443, "grad_norm": 2.725595474243164, "learning_rate": 9.840330512568039e-06, "loss": 0.6464037895202637, "step": 773 }, { "epoch": 0.10853256678118207, "grad_norm": 7.440967559814453, "learning_rate": 9.839760786974868e-06, "loss": 0.49553075432777405, "step": 774 }, { "epoch": 0.10867278973567973, "grad_norm": 6.791769504547119, "learning_rate": 9.83919006330821e-06, "loss": 0.5624386072158813, "step": 775 }, { "epoch": 0.10881301269017739, "grad_norm": 4.559317111968994, "learning_rate": 9.838618341685761e-06, "loss": 0.5265123844146729, "step": 776 }, { "epoch": 0.10895323564467503, "grad_norm": 3.9502475261688232, "learning_rate": 9.838045622225425e-06, "loss": 0.681350827217102, "step": 777 }, { "epoch": 0.10909345859917269, "grad_norm": 4.382779598236084, "learning_rate": 9.837471905045311e-06, "loss": 0.6286919713020325, "step": 778 }, { "epoch": 0.10923368155367033, "grad_norm": 5.023923873901367, "learning_rate": 9.836897190263731e-06, "loss": 0.6588431000709534, "step": 779 }, { "epoch": 0.10937390450816799, "grad_norm": 4.2628560066223145, "learning_rate": 9.836321477999207e-06, "loss": 0.6606655716896057, "step": 780 }, { "epoch": 0.10951412746266564, "grad_norm": 4.972975730895996, "learning_rate": 9.835744768370461e-06, "loss": 0.5855675935745239, "step": 781 }, { "epoch": 0.10965435041716329, "grad_norm": 3.088926076889038, "learning_rate": 9.835167061496427e-06, "loss": 0.5715600848197937, "step": 782 }, { "epoch": 0.10979457337166094, "grad_norm": 3.537303924560547, "learning_rate": 9.834588357496242e-06, "loss": 0.5630470514297485, "step": 783 }, { "epoch": 0.10993479632615859, "grad_norm": 5.022487640380859, "learning_rate": 9.834008656489246e-06, "loss": 0.4918098747730255, "step": 784 }, { "epoch": 0.11007501928065624, "grad_norm": 3.224168062210083, "learning_rate": 9.83342795859499e-06, "loss": 0.6526966094970703, "step": 785 }, { "epoch": 0.1102152422351539, "grad_norm": 3.9990124702453613, "learning_rate": 9.832846263933226e-06, "loss": 0.5490628480911255, "step": 786 }, { "epoch": 0.11035546518965154, "grad_norm": 2.681119918823242, "learning_rate": 9.832263572623915e-06, "loss": 0.6868915557861328, "step": 787 }, { "epoch": 0.1104956881441492, "grad_norm": 4.235092639923096, "learning_rate": 9.83167988478722e-06, "loss": 0.5606788396835327, "step": 788 }, { "epoch": 0.11063591109864684, "grad_norm": 3.0809154510498047, "learning_rate": 9.831095200543512e-06, "loss": 0.6680677533149719, "step": 789 }, { "epoch": 0.1107761340531445, "grad_norm": 5.179124355316162, "learning_rate": 9.830509520013365e-06, "loss": 0.6538060307502747, "step": 790 }, { "epoch": 0.11091635700764216, "grad_norm": 2.6950531005859375, "learning_rate": 9.829922843317565e-06, "loss": 0.6205816864967346, "step": 791 }, { "epoch": 0.1110565799621398, "grad_norm": 3.545706272125244, "learning_rate": 9.829335170577092e-06, "loss": 0.5719349384307861, "step": 792 }, { "epoch": 0.11119680291663746, "grad_norm": 15.487460136413574, "learning_rate": 9.828746501913143e-06, "loss": 0.6386479139328003, "step": 793 }, { "epoch": 0.1113370258711351, "grad_norm": 3.770392417907715, "learning_rate": 9.828156837447114e-06, "loss": 0.5928773880004883, "step": 794 }, { "epoch": 0.11147724882563276, "grad_norm": 4.694217681884766, "learning_rate": 9.827566177300607e-06, "loss": 0.6617640852928162, "step": 795 }, { "epoch": 0.1116174717801304, "grad_norm": 3.042860984802246, "learning_rate": 9.826974521595431e-06, "loss": 0.5622719526290894, "step": 796 }, { "epoch": 0.11175769473462806, "grad_norm": 3.2998876571655273, "learning_rate": 9.8263818704536e-06, "loss": 0.7081747651100159, "step": 797 }, { "epoch": 0.11189791768912571, "grad_norm": 4.054560661315918, "learning_rate": 9.825788223997333e-06, "loss": 0.5672070980072021, "step": 798 }, { "epoch": 0.11203814064362336, "grad_norm": 6.219020843505859, "learning_rate": 9.825193582349052e-06, "loss": 0.49279001355171204, "step": 799 }, { "epoch": 0.11217836359812101, "grad_norm": 2.9293510913848877, "learning_rate": 9.824597945631386e-06, "loss": 0.589134931564331, "step": 800 }, { "epoch": 0.11231858655261866, "grad_norm": 4.271163463592529, "learning_rate": 9.824001313967174e-06, "loss": 0.5171965956687927, "step": 801 }, { "epoch": 0.11245880950711631, "grad_norm": 4.640100479125977, "learning_rate": 9.82340368747945e-06, "loss": 0.6750030517578125, "step": 802 }, { "epoch": 0.11259903246161397, "grad_norm": 3.7500545978546143, "learning_rate": 9.82280506629146e-06, "loss": 0.555412769317627, "step": 803 }, { "epoch": 0.11273925541611161, "grad_norm": 3.4642903804779053, "learning_rate": 9.822205450526656e-06, "loss": 0.5987652540206909, "step": 804 }, { "epoch": 0.11287947837060927, "grad_norm": 6.2390313148498535, "learning_rate": 9.821604840308692e-06, "loss": 0.4922180771827698, "step": 805 }, { "epoch": 0.11301970132510691, "grad_norm": 8.725983619689941, "learning_rate": 9.821003235761429e-06, "loss": 0.501544713973999, "step": 806 }, { "epoch": 0.11315992427960457, "grad_norm": 3.2115440368652344, "learning_rate": 9.820400637008929e-06, "loss": 0.5067477822303772, "step": 807 }, { "epoch": 0.11330014723410223, "grad_norm": 4.156521320343018, "learning_rate": 9.819797044175466e-06, "loss": 0.6278368234634399, "step": 808 }, { "epoch": 0.11344037018859987, "grad_norm": 4.274267196655273, "learning_rate": 9.819192457385512e-06, "loss": 0.6773028373718262, "step": 809 }, { "epoch": 0.11358059314309753, "grad_norm": 5.667977809906006, "learning_rate": 9.818586876763749e-06, "loss": 0.5313711762428284, "step": 810 }, { "epoch": 0.11372081609759517, "grad_norm": 4.07375955581665, "learning_rate": 9.817980302435062e-06, "loss": 0.5353853106498718, "step": 811 }, { "epoch": 0.11386103905209283, "grad_norm": 4.839898586273193, "learning_rate": 9.817372734524541e-06, "loss": 0.6102362871170044, "step": 812 }, { "epoch": 0.11400126200659048, "grad_norm": 3.8082594871520996, "learning_rate": 9.81676417315748e-06, "loss": 0.6732835173606873, "step": 813 }, { "epoch": 0.11414148496108813, "grad_norm": 3.285416603088379, "learning_rate": 9.816154618459379e-06, "loss": 0.6341720223426819, "step": 814 }, { "epoch": 0.11428170791558578, "grad_norm": 3.585113525390625, "learning_rate": 9.815544070555945e-06, "loss": 0.5272776484489441, "step": 815 }, { "epoch": 0.11442193087008343, "grad_norm": 10.457009315490723, "learning_rate": 9.814932529573083e-06, "loss": 0.49539005756378174, "step": 816 }, { "epoch": 0.11456215382458108, "grad_norm": 5.18947696685791, "learning_rate": 9.814319995636911e-06, "loss": 0.5912858247756958, "step": 817 }, { "epoch": 0.11470237677907874, "grad_norm": 3.6648101806640625, "learning_rate": 9.813706468873747e-06, "loss": 0.6711194515228271, "step": 818 }, { "epoch": 0.11484259973357638, "grad_norm": 5.486788272857666, "learning_rate": 9.813091949410114e-06, "loss": 0.6268613338470459, "step": 819 }, { "epoch": 0.11498282268807404, "grad_norm": 7.030045032501221, "learning_rate": 9.812476437372742e-06, "loss": 0.649277925491333, "step": 820 }, { "epoch": 0.11512304564257168, "grad_norm": 2.9663548469543457, "learning_rate": 9.811859932888562e-06, "loss": 0.541581392288208, "step": 821 }, { "epoch": 0.11526326859706934, "grad_norm": 6.605481147766113, "learning_rate": 9.811242436084713e-06, "loss": 0.6135627627372742, "step": 822 }, { "epoch": 0.115403491551567, "grad_norm": 2.7751643657684326, "learning_rate": 9.810623947088538e-06, "loss": 0.5902650952339172, "step": 823 }, { "epoch": 0.11554371450606464, "grad_norm": 6.624775409698486, "learning_rate": 9.810004466027585e-06, "loss": 0.6585283875465393, "step": 824 }, { "epoch": 0.1156839374605623, "grad_norm": 3.6594080924987793, "learning_rate": 9.809383993029602e-06, "loss": 0.5334699749946594, "step": 825 }, { "epoch": 0.11582416041505994, "grad_norm": 3.445556879043579, "learning_rate": 9.808762528222549e-06, "loss": 0.6180902719497681, "step": 826 }, { "epoch": 0.1159643833695576, "grad_norm": 5.651453971862793, "learning_rate": 9.808140071734585e-06, "loss": 0.6009028553962708, "step": 827 }, { "epoch": 0.11610460632405525, "grad_norm": 3.87939715385437, "learning_rate": 9.807516623694077e-06, "loss": 0.5923426151275635, "step": 828 }, { "epoch": 0.1162448292785529, "grad_norm": 3.0052435398101807, "learning_rate": 9.806892184229592e-06, "loss": 0.5651963949203491, "step": 829 }, { "epoch": 0.11638505223305055, "grad_norm": 3.8024091720581055, "learning_rate": 9.806266753469906e-06, "loss": 0.6000843644142151, "step": 830 }, { "epoch": 0.1165252751875482, "grad_norm": 3.5365240573883057, "learning_rate": 9.805640331543997e-06, "loss": 0.6281982660293579, "step": 831 }, { "epoch": 0.11666549814204585, "grad_norm": 3.641960620880127, "learning_rate": 9.805012918581049e-06, "loss": 0.6110734343528748, "step": 832 }, { "epoch": 0.11680572109654351, "grad_norm": 2.8385682106018066, "learning_rate": 9.804384514710448e-06, "loss": 0.5521880388259888, "step": 833 }, { "epoch": 0.11694594405104115, "grad_norm": 3.407958745956421, "learning_rate": 9.803755120061787e-06, "loss": 0.6752058267593384, "step": 834 }, { "epoch": 0.11708616700553881, "grad_norm": 4.472616672515869, "learning_rate": 9.803124734764863e-06, "loss": 0.5440356731414795, "step": 835 }, { "epoch": 0.11722638996003645, "grad_norm": 2.7850916385650635, "learning_rate": 9.802493358949673e-06, "loss": 0.6001245379447937, "step": 836 }, { "epoch": 0.11736661291453411, "grad_norm": 4.3294901847839355, "learning_rate": 9.801860992746427e-06, "loss": 0.5279841423034668, "step": 837 }, { "epoch": 0.11750683586903177, "grad_norm": 4.669871807098389, "learning_rate": 9.801227636285528e-06, "loss": 0.5178468823432922, "step": 838 }, { "epoch": 0.11764705882352941, "grad_norm": 4.527777671813965, "learning_rate": 9.800593289697594e-06, "loss": 0.6198659539222717, "step": 839 }, { "epoch": 0.11778728177802707, "grad_norm": 3.3387904167175293, "learning_rate": 9.799957953113438e-06, "loss": 0.5593656301498413, "step": 840 }, { "epoch": 0.11792750473252471, "grad_norm": 6.186795711517334, "learning_rate": 9.799321626664084e-06, "loss": 0.5690863728523254, "step": 841 }, { "epoch": 0.11806772768702237, "grad_norm": 2.9597008228302, "learning_rate": 9.798684310480756e-06, "loss": 0.6428117156028748, "step": 842 }, { "epoch": 0.11820795064152002, "grad_norm": 11.121058464050293, "learning_rate": 9.798046004694888e-06, "loss": 0.5521354675292969, "step": 843 }, { "epoch": 0.11834817359601767, "grad_norm": 3.26381778717041, "learning_rate": 9.797406709438108e-06, "loss": 0.5036510229110718, "step": 844 }, { "epoch": 0.11848839655051532, "grad_norm": 3.0673985481262207, "learning_rate": 9.79676642484226e-06, "loss": 0.5981175303459167, "step": 845 }, { "epoch": 0.11862861950501297, "grad_norm": 4.044966697692871, "learning_rate": 9.796125151039379e-06, "loss": 0.5640495419502258, "step": 846 }, { "epoch": 0.11876884245951062, "grad_norm": 2.6872377395629883, "learning_rate": 9.795482888161717e-06, "loss": 0.6427510976791382, "step": 847 }, { "epoch": 0.11890906541400827, "grad_norm": 3.0793099403381348, "learning_rate": 9.79483963634172e-06, "loss": 0.5951834917068481, "step": 848 }, { "epoch": 0.11904928836850592, "grad_norm": 3.8801023960113525, "learning_rate": 9.794195395712043e-06, "loss": 0.5840035676956177, "step": 849 }, { "epoch": 0.11918951132300358, "grad_norm": 2.9393720626831055, "learning_rate": 9.793550166405544e-06, "loss": 0.6875929832458496, "step": 850 }, { "epoch": 0.11932973427750122, "grad_norm": 4.959534645080566, "learning_rate": 9.792903948555283e-06, "loss": 0.6785433292388916, "step": 851 }, { "epoch": 0.11946995723199888, "grad_norm": 7.240728378295898, "learning_rate": 9.792256742294529e-06, "loss": 0.5682670474052429, "step": 852 }, { "epoch": 0.11961018018649652, "grad_norm": 3.6160738468170166, "learning_rate": 9.791608547756749e-06, "loss": 0.6552267074584961, "step": 853 }, { "epoch": 0.11975040314099418, "grad_norm": 4.11030912399292, "learning_rate": 9.790959365075614e-06, "loss": 0.6069631576538086, "step": 854 }, { "epoch": 0.11989062609549184, "grad_norm": 5.032534599304199, "learning_rate": 9.790309194385003e-06, "loss": 0.6391358971595764, "step": 855 }, { "epoch": 0.12003084904998948, "grad_norm": 2.843860387802124, "learning_rate": 9.789658035818998e-06, "loss": 0.6279116272926331, "step": 856 }, { "epoch": 0.12017107200448714, "grad_norm": 3.404006242752075, "learning_rate": 9.789005889511881e-06, "loss": 0.6310912370681763, "step": 857 }, { "epoch": 0.12031129495898478, "grad_norm": 3.42965030670166, "learning_rate": 9.788352755598142e-06, "loss": 0.5953887701034546, "step": 858 }, { "epoch": 0.12045151791348244, "grad_norm": 3.6098649501800537, "learning_rate": 9.78769863421247e-06, "loss": 0.528213620185852, "step": 859 }, { "epoch": 0.1205917408679801, "grad_norm": 4.074160099029541, "learning_rate": 9.787043525489763e-06, "loss": 0.6732525825500488, "step": 860 }, { "epoch": 0.12073196382247774, "grad_norm": 4.301389217376709, "learning_rate": 9.78638742956512e-06, "loss": 0.6328228116035461, "step": 861 }, { "epoch": 0.1208721867769754, "grad_norm": 3.105848550796509, "learning_rate": 9.785730346573841e-06, "loss": 0.6231042146682739, "step": 862 }, { "epoch": 0.12101240973147304, "grad_norm": 2.8510613441467285, "learning_rate": 9.785072276651436e-06, "loss": 0.5829465389251709, "step": 863 }, { "epoch": 0.1211526326859707, "grad_norm": 2.7221412658691406, "learning_rate": 9.784413219933609e-06, "loss": 0.5789905786514282, "step": 864 }, { "epoch": 0.12129285564046835, "grad_norm": 3.09745717048645, "learning_rate": 9.783753176556279e-06, "loss": 0.6217948198318481, "step": 865 }, { "epoch": 0.12143307859496599, "grad_norm": 2.9532523155212402, "learning_rate": 9.783092146655558e-06, "loss": 0.6180813312530518, "step": 866 }, { "epoch": 0.12157330154946365, "grad_norm": 4.52825927734375, "learning_rate": 9.78243013036777e-06, "loss": 0.6332991719245911, "step": 867 }, { "epoch": 0.12171352450396129, "grad_norm": 2.826068878173828, "learning_rate": 9.781767127829435e-06, "loss": 0.6404145956039429, "step": 868 }, { "epoch": 0.12185374745845895, "grad_norm": 3.6366798877716064, "learning_rate": 9.781103139177281e-06, "loss": 0.6215379238128662, "step": 869 }, { "epoch": 0.1219939704129566, "grad_norm": 5.415340423583984, "learning_rate": 9.78043816454824e-06, "loss": 0.5035510659217834, "step": 870 }, { "epoch": 0.12213419336745425, "grad_norm": 2.9397122859954834, "learning_rate": 9.779772204079444e-06, "loss": 0.5824241042137146, "step": 871 }, { "epoch": 0.1222744163219519, "grad_norm": 3.7269861698150635, "learning_rate": 9.77910525790823e-06, "loss": 0.5646698474884033, "step": 872 }, { "epoch": 0.12241463927644955, "grad_norm": 2.9941627979278564, "learning_rate": 9.778437326172136e-06, "loss": 0.6532029509544373, "step": 873 }, { "epoch": 0.1225548622309472, "grad_norm": 10.941621780395508, "learning_rate": 9.777768409008909e-06, "loss": 0.6017414927482605, "step": 874 }, { "epoch": 0.12269508518544486, "grad_norm": 3.4802799224853516, "learning_rate": 9.777098506556495e-06, "loss": 0.5673375129699707, "step": 875 }, { "epoch": 0.1228353081399425, "grad_norm": 3.3491668701171875, "learning_rate": 9.776427618953043e-06, "loss": 0.6142851114273071, "step": 876 }, { "epoch": 0.12297553109444016, "grad_norm": 4.868885040283203, "learning_rate": 9.775755746336904e-06, "loss": 0.6430387496948242, "step": 877 }, { "epoch": 0.1231157540489378, "grad_norm": 3.1756067276000977, "learning_rate": 9.775082888846637e-06, "loss": 0.602158784866333, "step": 878 }, { "epoch": 0.12325597700343546, "grad_norm": 5.534069538116455, "learning_rate": 9.774409046620999e-06, "loss": 0.6974199414253235, "step": 879 }, { "epoch": 0.12339619995793312, "grad_norm": 4.648099422454834, "learning_rate": 9.773734219798954e-06, "loss": 0.5799704194068909, "step": 880 }, { "epoch": 0.12353642291243076, "grad_norm": 7.580204010009766, "learning_rate": 9.773058408519667e-06, "loss": 0.5507827997207642, "step": 881 }, { "epoch": 0.12367664586692842, "grad_norm": 3.7039029598236084, "learning_rate": 9.772381612922505e-06, "loss": 0.6853945255279541, "step": 882 }, { "epoch": 0.12381686882142606, "grad_norm": 3.642279863357544, "learning_rate": 9.77170383314704e-06, "loss": 0.5536929965019226, "step": 883 }, { "epoch": 0.12395709177592372, "grad_norm": 2.9095780849456787, "learning_rate": 9.771025069333047e-06, "loss": 0.6099637746810913, "step": 884 }, { "epoch": 0.12409731473042138, "grad_norm": 3.1745195388793945, "learning_rate": 9.770345321620502e-06, "loss": 0.5897037982940674, "step": 885 }, { "epoch": 0.12423753768491902, "grad_norm": 6.0356879234313965, "learning_rate": 9.769664590149586e-06, "loss": 0.5456855893135071, "step": 886 }, { "epoch": 0.12437776063941668, "grad_norm": 2.901566982269287, "learning_rate": 9.768982875060683e-06, "loss": 0.633963406085968, "step": 887 }, { "epoch": 0.12451798359391432, "grad_norm": 3.387202024459839, "learning_rate": 9.768300176494376e-06, "loss": 0.45048972964286804, "step": 888 }, { "epoch": 0.12465820654841198, "grad_norm": 4.172695159912109, "learning_rate": 9.767616494591457e-06, "loss": 0.5442438721656799, "step": 889 }, { "epoch": 0.12479842950290963, "grad_norm": 4.561534404754639, "learning_rate": 9.766931829492914e-06, "loss": 0.5777757167816162, "step": 890 }, { "epoch": 0.12493865245740728, "grad_norm": 4.765697479248047, "learning_rate": 9.766246181339943e-06, "loss": 0.7049243450164795, "step": 891 }, { "epoch": 0.12507887541190493, "grad_norm": 3.1878507137298584, "learning_rate": 9.765559550273942e-06, "loss": 0.599621057510376, "step": 892 }, { "epoch": 0.12521909836640258, "grad_norm": 3.5100111961364746, "learning_rate": 9.764871936436507e-06, "loss": 0.5842007398605347, "step": 893 }, { "epoch": 0.12535932132090022, "grad_norm": 4.539719581604004, "learning_rate": 9.764183339969444e-06, "loss": 0.3752601742744446, "step": 894 }, { "epoch": 0.1254995442753979, "grad_norm": 3.9101057052612305, "learning_rate": 9.763493761014757e-06, "loss": 0.6185535192489624, "step": 895 }, { "epoch": 0.12563976722989553, "grad_norm": 3.882857322692871, "learning_rate": 9.762803199714652e-06, "loss": 0.5873152613639832, "step": 896 }, { "epoch": 0.12577999018439318, "grad_norm": 4.210113525390625, "learning_rate": 9.762111656211541e-06, "loss": 0.5661259293556213, "step": 897 }, { "epoch": 0.12592021313889085, "grad_norm": 2.8604319095611572, "learning_rate": 9.761419130648037e-06, "loss": 0.5152778029441833, "step": 898 }, { "epoch": 0.1260604360933885, "grad_norm": 3.456603527069092, "learning_rate": 9.760725623166952e-06, "loss": 0.5010683536529541, "step": 899 }, { "epoch": 0.12620065904788613, "grad_norm": 2.671288251876831, "learning_rate": 9.760031133911307e-06, "loss": 0.6134538650512695, "step": 900 }, { "epoch": 0.1263408820023838, "grad_norm": 8.845980644226074, "learning_rate": 9.75933566302432e-06, "loss": 0.6307058334350586, "step": 901 }, { "epoch": 0.12648110495688145, "grad_norm": 4.404150485992432, "learning_rate": 9.758639210649415e-06, "loss": 0.5675970315933228, "step": 902 }, { "epoch": 0.1266213279113791, "grad_norm": 2.8331685066223145, "learning_rate": 9.757941776930218e-06, "loss": 0.6710779666900635, "step": 903 }, { "epoch": 0.12676155086587673, "grad_norm": 2.4684982299804688, "learning_rate": 9.757243362010553e-06, "loss": 0.585456132888794, "step": 904 }, { "epoch": 0.1269017738203744, "grad_norm": 4.486286640167236, "learning_rate": 9.756543966034452e-06, "loss": 0.6266607642173767, "step": 905 }, { "epoch": 0.12704199677487205, "grad_norm": 4.035679817199707, "learning_rate": 9.755843589146147e-06, "loss": 0.4985142648220062, "step": 906 }, { "epoch": 0.1271822197293697, "grad_norm": 5.167372703552246, "learning_rate": 9.755142231490072e-06, "loss": 0.5543290376663208, "step": 907 }, { "epoch": 0.12732244268386736, "grad_norm": 6.725209712982178, "learning_rate": 9.754439893210864e-06, "loss": 0.5585506558418274, "step": 908 }, { "epoch": 0.127462665638365, "grad_norm": 2.813385486602783, "learning_rate": 9.75373657445336e-06, "loss": 0.5753426551818848, "step": 909 }, { "epoch": 0.12760288859286265, "grad_norm": 5.362373352050781, "learning_rate": 9.753032275362604e-06, "loss": 0.5648060441017151, "step": 910 }, { "epoch": 0.12774311154736032, "grad_norm": 2.91798996925354, "learning_rate": 9.752326996083837e-06, "loss": 0.6675050258636475, "step": 911 }, { "epoch": 0.12788333450185796, "grad_norm": 4.1321892738342285, "learning_rate": 9.751620736762503e-06, "loss": 0.5212165713310242, "step": 912 }, { "epoch": 0.1280235574563556, "grad_norm": 4.483351707458496, "learning_rate": 9.750913497544254e-06, "loss": 0.5898413062095642, "step": 913 }, { "epoch": 0.12816378041085325, "grad_norm": 3.81535267829895, "learning_rate": 9.750205278574937e-06, "loss": 0.5848391652107239, "step": 914 }, { "epoch": 0.12830400336535092, "grad_norm": 4.558585166931152, "learning_rate": 9.749496080000603e-06, "loss": 0.5445305109024048, "step": 915 }, { "epoch": 0.12844422631984856, "grad_norm": 2.8270161151885986, "learning_rate": 9.748785901967506e-06, "loss": 0.5811357498168945, "step": 916 }, { "epoch": 0.1285844492743462, "grad_norm": 4.872021198272705, "learning_rate": 9.7480747446221e-06, "loss": 0.6511444449424744, "step": 917 }, { "epoch": 0.12872467222884387, "grad_norm": 4.0415472984313965, "learning_rate": 9.747362608111045e-06, "loss": 0.6945008039474487, "step": 918 }, { "epoch": 0.12886489518334152, "grad_norm": 3.122559070587158, "learning_rate": 9.746649492581199e-06, "loss": 0.5783884525299072, "step": 919 }, { "epoch": 0.12900511813783916, "grad_norm": 3.570945978164673, "learning_rate": 9.745935398179624e-06, "loss": 0.5055443048477173, "step": 920 }, { "epoch": 0.1291453410923368, "grad_norm": 4.458548545837402, "learning_rate": 9.745220325053585e-06, "loss": 0.5830663442611694, "step": 921 }, { "epoch": 0.12928556404683447, "grad_norm": 3.2575998306274414, "learning_rate": 9.744504273350543e-06, "loss": 0.5979782342910767, "step": 922 }, { "epoch": 0.12942578700133212, "grad_norm": 3.528528928756714, "learning_rate": 9.743787243218168e-06, "loss": 0.6994978189468384, "step": 923 }, { "epoch": 0.12956600995582976, "grad_norm": 3.4352681636810303, "learning_rate": 9.743069234804328e-06, "loss": 0.6910443902015686, "step": 924 }, { "epoch": 0.12970623291032743, "grad_norm": 12.712067604064941, "learning_rate": 9.742350248257091e-06, "loss": 0.6033700704574585, "step": 925 }, { "epoch": 0.12984645586482507, "grad_norm": 4.825198173522949, "learning_rate": 9.741630283724733e-06, "loss": 0.5752866864204407, "step": 926 }, { "epoch": 0.12998667881932272, "grad_norm": 4.600449085235596, "learning_rate": 9.740909341355724e-06, "loss": 0.502071738243103, "step": 927 }, { "epoch": 0.13012690177382039, "grad_norm": 9.367401123046875, "learning_rate": 9.740187421298741e-06, "loss": 0.6076347827911377, "step": 928 }, { "epoch": 0.13026712472831803, "grad_norm": 2.954745292663574, "learning_rate": 9.739464523702664e-06, "loss": 0.5212613940238953, "step": 929 }, { "epoch": 0.13040734768281567, "grad_norm": 3.3093512058258057, "learning_rate": 9.738740648716568e-06, "loss": 0.6130092144012451, "step": 930 }, { "epoch": 0.13054757063731331, "grad_norm": 8.04305648803711, "learning_rate": 9.738015796489732e-06, "loss": 0.7408157587051392, "step": 931 }, { "epoch": 0.13068779359181099, "grad_norm": 2.757657289505005, "learning_rate": 9.73728996717164e-06, "loss": 0.6145413517951965, "step": 932 }, { "epoch": 0.13082801654630863, "grad_norm": 4.173047065734863, "learning_rate": 9.736563160911975e-06, "loss": 0.6822977066040039, "step": 933 }, { "epoch": 0.13096823950080627, "grad_norm": 3.0707216262817383, "learning_rate": 9.735835377860624e-06, "loss": 0.7040765881538391, "step": 934 }, { "epoch": 0.13110846245530394, "grad_norm": 5.419007301330566, "learning_rate": 9.73510661816767e-06, "loss": 0.6544725894927979, "step": 935 }, { "epoch": 0.13124868540980159, "grad_norm": 4.041053771972656, "learning_rate": 9.7343768819834e-06, "loss": 0.6135764122009277, "step": 936 }, { "epoch": 0.13138890836429923, "grad_norm": 3.355297565460205, "learning_rate": 9.733646169458306e-06, "loss": 0.667962372303009, "step": 937 }, { "epoch": 0.1315291313187969, "grad_norm": 2.9805526733398438, "learning_rate": 9.732914480743075e-06, "loss": 0.6058170795440674, "step": 938 }, { "epoch": 0.13166935427329454, "grad_norm": 3.753824234008789, "learning_rate": 9.732181815988601e-06, "loss": 0.5722624063491821, "step": 939 }, { "epoch": 0.13180957722779219, "grad_norm": 3.2298378944396973, "learning_rate": 9.731448175345977e-06, "loss": 0.5076046586036682, "step": 940 }, { "epoch": 0.13194980018228983, "grad_norm": 3.9507081508636475, "learning_rate": 9.730713558966494e-06, "loss": 0.5948441624641418, "step": 941 }, { "epoch": 0.1320900231367875, "grad_norm": 4.416497707366943, "learning_rate": 9.72997796700165e-06, "loss": 0.5885801315307617, "step": 942 }, { "epoch": 0.13223024609128514, "grad_norm": 19.34700584411621, "learning_rate": 9.729241399603142e-06, "loss": 0.6035275459289551, "step": 943 }, { "epoch": 0.13237046904578278, "grad_norm": 5.899989604949951, "learning_rate": 9.728503856922865e-06, "loss": 0.6066931486129761, "step": 944 }, { "epoch": 0.13251069200028046, "grad_norm": 2.5293784141540527, "learning_rate": 9.72776533911292e-06, "loss": 0.5117849707603455, "step": 945 }, { "epoch": 0.1326509149547781, "grad_norm": 5.017561912536621, "learning_rate": 9.727025846325606e-06, "loss": 0.6162567138671875, "step": 946 }, { "epoch": 0.13279113790927574, "grad_norm": 3.7351932525634766, "learning_rate": 9.726285378713424e-06, "loss": 0.560686469078064, "step": 947 }, { "epoch": 0.1329313608637734, "grad_norm": 4.067128658294678, "learning_rate": 9.725543936429079e-06, "loss": 0.6471636295318604, "step": 948 }, { "epoch": 0.13307158381827106, "grad_norm": 2.8418798446655273, "learning_rate": 9.724801519625468e-06, "loss": 0.5849616527557373, "step": 949 }, { "epoch": 0.1332118067727687, "grad_norm": 4.475289821624756, "learning_rate": 9.724058128455698e-06, "loss": 0.6283936500549316, "step": 950 }, { "epoch": 0.13335202972726634, "grad_norm": 4.911685466766357, "learning_rate": 9.723313763073078e-06, "loss": 0.519153892993927, "step": 951 }, { "epoch": 0.133492252681764, "grad_norm": 7.117713451385498, "learning_rate": 9.722568423631104e-06, "loss": 0.5462661981582642, "step": 952 }, { "epoch": 0.13363247563626166, "grad_norm": 3.8722524642944336, "learning_rate": 9.721822110283492e-06, "loss": 0.5458972454071045, "step": 953 }, { "epoch": 0.1337726985907593, "grad_norm": 3.2838122844696045, "learning_rate": 9.721074823184146e-06, "loss": 0.6224359273910522, "step": 954 }, { "epoch": 0.13391292154525697, "grad_norm": 2.418092966079712, "learning_rate": 9.720326562487174e-06, "loss": 0.6821929216384888, "step": 955 }, { "epoch": 0.1340531444997546, "grad_norm": 3.8362040519714355, "learning_rate": 9.719577328346887e-06, "loss": 0.5916868448257446, "step": 956 }, { "epoch": 0.13419336745425225, "grad_norm": 2.929739475250244, "learning_rate": 9.718827120917792e-06, "loss": 0.6329548358917236, "step": 957 }, { "epoch": 0.13433359040874993, "grad_norm": 4.710273742675781, "learning_rate": 9.7180759403546e-06, "loss": 0.5280866026878357, "step": 958 }, { "epoch": 0.13447381336324757, "grad_norm": 5.786752223968506, "learning_rate": 9.717323786812224e-06, "loss": 0.653022050857544, "step": 959 }, { "epoch": 0.1346140363177452, "grad_norm": 3.5168421268463135, "learning_rate": 9.716570660445774e-06, "loss": 0.5006381273269653, "step": 960 }, { "epoch": 0.13475425927224285, "grad_norm": 3.354940414428711, "learning_rate": 9.715816561410564e-06, "loss": 0.6166254878044128, "step": 961 }, { "epoch": 0.13489448222674053, "grad_norm": 3.672194480895996, "learning_rate": 9.715061489862108e-06, "loss": 0.568871796131134, "step": 962 }, { "epoch": 0.13503470518123817, "grad_norm": 4.408318042755127, "learning_rate": 9.714305445956118e-06, "loss": 0.5736171007156372, "step": 963 }, { "epoch": 0.1351749281357358, "grad_norm": 4.011500358581543, "learning_rate": 9.713548429848508e-06, "loss": 0.6565413475036621, "step": 964 }, { "epoch": 0.13531515109023348, "grad_norm": 3.402719259262085, "learning_rate": 9.712790441695394e-06, "loss": 0.470783531665802, "step": 965 }, { "epoch": 0.13545537404473112, "grad_norm": 3.6506242752075195, "learning_rate": 9.71203148165309e-06, "loss": 0.5342254042625427, "step": 966 }, { "epoch": 0.13559559699922877, "grad_norm": 2.770308256149292, "learning_rate": 9.711271549878111e-06, "loss": 0.6241449117660522, "step": 967 }, { "epoch": 0.13573581995372644, "grad_norm": 3.1427841186523438, "learning_rate": 9.710510646527174e-06, "loss": 0.6631195545196533, "step": 968 }, { "epoch": 0.13587604290822408, "grad_norm": 4.1056976318359375, "learning_rate": 9.709748771757196e-06, "loss": 0.59004807472229, "step": 969 }, { "epoch": 0.13601626586272172, "grad_norm": 5.055574893951416, "learning_rate": 9.708985925725293e-06, "loss": 0.6116489171981812, "step": 970 }, { "epoch": 0.13615648881721937, "grad_norm": 2.6587300300598145, "learning_rate": 9.70822210858878e-06, "loss": 0.5750858783721924, "step": 971 }, { "epoch": 0.13629671177171704, "grad_norm": 3.7706377506256104, "learning_rate": 9.707457320505179e-06, "loss": 0.542985200881958, "step": 972 }, { "epoch": 0.13643693472621468, "grad_norm": 3.6069629192352295, "learning_rate": 9.706691561632202e-06, "loss": 0.6186479330062866, "step": 973 }, { "epoch": 0.13657715768071232, "grad_norm": 3.245790481567383, "learning_rate": 9.705924832127772e-06, "loss": 0.5120971202850342, "step": 974 }, { "epoch": 0.13671738063521, "grad_norm": 3.202094316482544, "learning_rate": 9.70515713215e-06, "loss": 0.6542420387268066, "step": 975 }, { "epoch": 0.13685760358970764, "grad_norm": 4.29317045211792, "learning_rate": 9.70438846185721e-06, "loss": 0.5403921604156494, "step": 976 }, { "epoch": 0.13699782654420528, "grad_norm": 4.884507179260254, "learning_rate": 9.70361882140792e-06, "loss": 0.690001904964447, "step": 977 }, { "epoch": 0.13713804949870292, "grad_norm": 2.9776456356048584, "learning_rate": 9.702848210960843e-06, "loss": 0.6117407083511353, "step": 978 }, { "epoch": 0.1372782724532006, "grad_norm": 3.501276969909668, "learning_rate": 9.702076630674899e-06, "loss": 0.6805281639099121, "step": 979 }, { "epoch": 0.13741849540769824, "grad_norm": 5.7077860832214355, "learning_rate": 9.701304080709212e-06, "loss": 0.6262012720108032, "step": 980 }, { "epoch": 0.13755871836219588, "grad_norm": 4.5639166831970215, "learning_rate": 9.700530561223092e-06, "loss": 0.550951361656189, "step": 981 }, { "epoch": 0.13769894131669355, "grad_norm": 3.4148967266082764, "learning_rate": 9.699756072376061e-06, "loss": 0.5860918760299683, "step": 982 }, { "epoch": 0.1378391642711912, "grad_norm": 3.521746873855591, "learning_rate": 9.698980614327835e-06, "loss": 0.532966136932373, "step": 983 }, { "epoch": 0.13797938722568884, "grad_norm": 5.046500205993652, "learning_rate": 9.698204187238336e-06, "loss": 0.6551814675331116, "step": 984 }, { "epoch": 0.1381196101801865, "grad_norm": 24.40800666809082, "learning_rate": 9.697426791267678e-06, "loss": 0.7111676931381226, "step": 985 }, { "epoch": 0.13825983313468415, "grad_norm": 3.8917863368988037, "learning_rate": 9.696648426576181e-06, "loss": 0.6590107679367065, "step": 986 }, { "epoch": 0.1384000560891818, "grad_norm": 24.3072566986084, "learning_rate": 9.695869093324359e-06, "loss": 0.5660170316696167, "step": 987 }, { "epoch": 0.13854027904367944, "grad_norm": 3.60336971282959, "learning_rate": 9.695088791672932e-06, "loss": 0.6050392389297485, "step": 988 }, { "epoch": 0.1386805019981771, "grad_norm": 3.8979930877685547, "learning_rate": 9.694307521782816e-06, "loss": 0.5903897285461426, "step": 989 }, { "epoch": 0.13882072495267475, "grad_norm": 2.6299009323120117, "learning_rate": 9.693525283815124e-06, "loss": 0.5558814406394958, "step": 990 }, { "epoch": 0.1389609479071724, "grad_norm": 3.85347580909729, "learning_rate": 9.692742077931178e-06, "loss": 0.6454532146453857, "step": 991 }, { "epoch": 0.13910117086167006, "grad_norm": 4.144050121307373, "learning_rate": 9.69195790429249e-06, "loss": 0.577307403087616, "step": 992 }, { "epoch": 0.1392413938161677, "grad_norm": 4.089596748352051, "learning_rate": 9.691172763060774e-06, "loss": 0.6300538778305054, "step": 993 }, { "epoch": 0.13938161677066535, "grad_norm": 3.0001401901245117, "learning_rate": 9.690386654397948e-06, "loss": 0.5378754138946533, "step": 994 }, { "epoch": 0.13952183972516302, "grad_norm": 2.8910369873046875, "learning_rate": 9.689599578466125e-06, "loss": 0.5630762577056885, "step": 995 }, { "epoch": 0.13966206267966066, "grad_norm": 3.4578380584716797, "learning_rate": 9.688811535427618e-06, "loss": 0.6245460510253906, "step": 996 }, { "epoch": 0.1398022856341583, "grad_norm": 3.1014010906219482, "learning_rate": 9.68802252544494e-06, "loss": 0.6993328332901001, "step": 997 }, { "epoch": 0.13994250858865595, "grad_norm": 4.274363040924072, "learning_rate": 9.687232548680805e-06, "loss": 0.6501848697662354, "step": 998 }, { "epoch": 0.14008273154315362, "grad_norm": 5.553936004638672, "learning_rate": 9.686441605298124e-06, "loss": 0.6801971197128296, "step": 999 }, { "epoch": 0.14022295449765126, "grad_norm": 5.372079372406006, "learning_rate": 9.68564969546001e-06, "loss": 0.5712767243385315, "step": 1000 }, { "epoch": 0.1403631774521489, "grad_norm": 2.7338407039642334, "learning_rate": 9.684856819329771e-06, "loss": 0.5720430016517639, "step": 1001 }, { "epoch": 0.14050340040664658, "grad_norm": 3.6473522186279297, "learning_rate": 9.684062977070918e-06, "loss": 0.5340458750724792, "step": 1002 }, { "epoch": 0.14064362336114422, "grad_norm": 3.109907388687134, "learning_rate": 9.68326816884716e-06, "loss": 0.6686035990715027, "step": 1003 }, { "epoch": 0.14078384631564186, "grad_norm": 5.603472709655762, "learning_rate": 9.682472394822403e-06, "loss": 0.5952277183532715, "step": 1004 }, { "epoch": 0.14092406927013953, "grad_norm": 4.3686676025390625, "learning_rate": 9.681675655160761e-06, "loss": 0.5674129724502563, "step": 1005 }, { "epoch": 0.14106429222463718, "grad_norm": 2.7143819332122803, "learning_rate": 9.680877950026534e-06, "loss": 0.631539523601532, "step": 1006 }, { "epoch": 0.14120451517913482, "grad_norm": 2.7790801525115967, "learning_rate": 9.68007927958423e-06, "loss": 0.6012330055236816, "step": 1007 }, { "epoch": 0.14134473813363246, "grad_norm": 4.4420905113220215, "learning_rate": 9.679279643998557e-06, "loss": 0.52987140417099, "step": 1008 }, { "epoch": 0.14148496108813013, "grad_norm": 6.4608683586120605, "learning_rate": 9.678479043434413e-06, "loss": 0.4609532356262207, "step": 1009 }, { "epoch": 0.14162518404262778, "grad_norm": 3.6920971870422363, "learning_rate": 9.677677478056904e-06, "loss": 0.6194107532501221, "step": 1010 }, { "epoch": 0.14176540699712542, "grad_norm": 3.392393112182617, "learning_rate": 9.676874948031332e-06, "loss": 0.5363353490829468, "step": 1011 }, { "epoch": 0.1419056299516231, "grad_norm": 5.029802322387695, "learning_rate": 9.676071453523196e-06, "loss": 0.5334221720695496, "step": 1012 }, { "epoch": 0.14204585290612073, "grad_norm": 4.31280517578125, "learning_rate": 9.675266994698197e-06, "loss": 0.5637862682342529, "step": 1013 }, { "epoch": 0.14218607586061838, "grad_norm": 3.6285009384155273, "learning_rate": 9.674461571722234e-06, "loss": 0.5792026519775391, "step": 1014 }, { "epoch": 0.14232629881511605, "grad_norm": 4.1852617263793945, "learning_rate": 9.673655184761403e-06, "loss": 0.6006520986557007, "step": 1015 }, { "epoch": 0.1424665217696137, "grad_norm": 3.1496126651763916, "learning_rate": 9.672847833982003e-06, "loss": 0.6204215884208679, "step": 1016 }, { "epoch": 0.14260674472411133, "grad_norm": 3.5161566734313965, "learning_rate": 9.672039519550525e-06, "loss": 0.5607906579971313, "step": 1017 }, { "epoch": 0.14274696767860898, "grad_norm": 3.683269500732422, "learning_rate": 9.671230241633662e-06, "loss": 0.526421070098877, "step": 1018 }, { "epoch": 0.14288719063310665, "grad_norm": 3.2847914695739746, "learning_rate": 9.670420000398312e-06, "loss": 0.5666987895965576, "step": 1019 }, { "epoch": 0.1430274135876043, "grad_norm": 4.00629186630249, "learning_rate": 9.66960879601156e-06, "loss": 0.7087507247924805, "step": 1020 }, { "epoch": 0.14316763654210193, "grad_norm": 14.177760124206543, "learning_rate": 9.6687966286407e-06, "loss": 0.6416040658950806, "step": 1021 }, { "epoch": 0.1433078594965996, "grad_norm": 3.15516996383667, "learning_rate": 9.667983498453217e-06, "loss": 0.5932939052581787, "step": 1022 }, { "epoch": 0.14344808245109725, "grad_norm": 5.257317543029785, "learning_rate": 9.6671694056168e-06, "loss": 0.6555156707763672, "step": 1023 }, { "epoch": 0.1435883054055949, "grad_norm": 2.985596179962158, "learning_rate": 9.666354350299334e-06, "loss": 0.563980221748352, "step": 1024 }, { "epoch": 0.14372852836009253, "grad_norm": 6.267075061798096, "learning_rate": 9.6655383326689e-06, "loss": 0.6222454309463501, "step": 1025 }, { "epoch": 0.1438687513145902, "grad_norm": 4.210379600524902, "learning_rate": 9.664721352893782e-06, "loss": 0.6642328500747681, "step": 1026 }, { "epoch": 0.14400897426908785, "grad_norm": 5.834435939788818, "learning_rate": 9.663903411142463e-06, "loss": 0.5205460786819458, "step": 1027 }, { "epoch": 0.1441491972235855, "grad_norm": 5.84758996963501, "learning_rate": 9.663084507583618e-06, "loss": 0.5473247766494751, "step": 1028 }, { "epoch": 0.14428942017808316, "grad_norm": 4.748032569885254, "learning_rate": 9.662264642386129e-06, "loss": 0.6053332090377808, "step": 1029 }, { "epoch": 0.1444296431325808, "grad_norm": 4.827084064483643, "learning_rate": 9.661443815719065e-06, "loss": 0.6478748917579651, "step": 1030 }, { "epoch": 0.14456986608707845, "grad_norm": 4.452394008636475, "learning_rate": 9.660622027751705e-06, "loss": 0.5911206007003784, "step": 1031 }, { "epoch": 0.14471008904157612, "grad_norm": 3.625894784927368, "learning_rate": 9.65979927865352e-06, "loss": 0.49781444668769836, "step": 1032 }, { "epoch": 0.14485031199607376, "grad_norm": 6.41507625579834, "learning_rate": 9.65897556859418e-06, "loss": 0.5558408498764038, "step": 1033 }, { "epoch": 0.1449905349505714, "grad_norm": 3.242607831954956, "learning_rate": 9.658150897743555e-06, "loss": 0.6366115212440491, "step": 1034 }, { "epoch": 0.14513075790506905, "grad_norm": 3.8066017627716064, "learning_rate": 9.65732526627171e-06, "loss": 0.7248451113700867, "step": 1035 }, { "epoch": 0.14527098085956672, "grad_norm": 2.55621337890625, "learning_rate": 9.65649867434891e-06, "loss": 0.46277981996536255, "step": 1036 }, { "epoch": 0.14541120381406436, "grad_norm": 3.3043205738067627, "learning_rate": 9.655671122145617e-06, "loss": 0.5355911254882812, "step": 1037 }, { "epoch": 0.145551426768562, "grad_norm": 2.6791269779205322, "learning_rate": 9.654842609832495e-06, "loss": 0.5505335330963135, "step": 1038 }, { "epoch": 0.14569164972305967, "grad_norm": 2.473982572555542, "learning_rate": 9.6540131375804e-06, "loss": 0.7518292665481567, "step": 1039 }, { "epoch": 0.14583187267755732, "grad_norm": 3.051013946533203, "learning_rate": 9.653182705560392e-06, "loss": 0.6279672384262085, "step": 1040 }, { "epoch": 0.14597209563205496, "grad_norm": 7.027968406677246, "learning_rate": 9.652351313943721e-06, "loss": 0.5794278383255005, "step": 1041 }, { "epoch": 0.14611231858655263, "grad_norm": 3.0932531356811523, "learning_rate": 9.651518962901842e-06, "loss": 0.6286532878875732, "step": 1042 }, { "epoch": 0.14625254154105027, "grad_norm": 3.1644668579101562, "learning_rate": 9.650685652606408e-06, "loss": 0.5270769000053406, "step": 1043 }, { "epoch": 0.14639276449554792, "grad_norm": 5.788689136505127, "learning_rate": 9.649851383229266e-06, "loss": 0.5406884551048279, "step": 1044 }, { "epoch": 0.14653298745004556, "grad_norm": 2.608898401260376, "learning_rate": 9.649016154942457e-06, "loss": 0.5113758444786072, "step": 1045 }, { "epoch": 0.14667321040454323, "grad_norm": 14.101329803466797, "learning_rate": 9.648179967918231e-06, "loss": 0.5875366926193237, "step": 1046 }, { "epoch": 0.14681343335904087, "grad_norm": 3.490874767303467, "learning_rate": 9.64734282232903e-06, "loss": 0.6361793279647827, "step": 1047 }, { "epoch": 0.14695365631353852, "grad_norm": 11.209668159484863, "learning_rate": 9.64650471834749e-06, "loss": 0.5080046653747559, "step": 1048 }, { "epoch": 0.1470938792680362, "grad_norm": 2.9581212997436523, "learning_rate": 9.645665656146448e-06, "loss": 0.629020094871521, "step": 1049 }, { "epoch": 0.14723410222253383, "grad_norm": 8.88416576385498, "learning_rate": 9.64482563589894e-06, "loss": 0.5939263105392456, "step": 1050 }, { "epoch": 0.14737432517703147, "grad_norm": 4.303815841674805, "learning_rate": 9.643984657778198e-06, "loss": 0.6648578643798828, "step": 1051 }, { "epoch": 0.14751454813152914, "grad_norm": 3.4093098640441895, "learning_rate": 9.64314272195765e-06, "loss": 0.5311036705970764, "step": 1052 }, { "epoch": 0.1476547710860268, "grad_norm": 4.010380268096924, "learning_rate": 9.642299828610926e-06, "loss": 0.5268059968948364, "step": 1053 }, { "epoch": 0.14779499404052443, "grad_norm": 5.176855087280273, "learning_rate": 9.64145597791185e-06, "loss": 0.5866283178329468, "step": 1054 }, { "epoch": 0.14793521699502207, "grad_norm": 2.5705037117004395, "learning_rate": 9.64061117003444e-06, "loss": 0.5290008783340454, "step": 1055 }, { "epoch": 0.14807543994951974, "grad_norm": 3.815253973007202, "learning_rate": 9.63976540515292e-06, "loss": 0.5981326103210449, "step": 1056 }, { "epoch": 0.1482156629040174, "grad_norm": 2.318699359893799, "learning_rate": 9.638918683441704e-06, "loss": 0.6285473108291626, "step": 1057 }, { "epoch": 0.14835588585851503, "grad_norm": 3.9915401935577393, "learning_rate": 9.638071005075409e-06, "loss": 0.5205914378166199, "step": 1058 }, { "epoch": 0.1484961088130127, "grad_norm": 3.7477426528930664, "learning_rate": 9.637222370228845e-06, "loss": 0.5673372149467468, "step": 1059 }, { "epoch": 0.14863633176751034, "grad_norm": 3.1825006008148193, "learning_rate": 9.636372779077018e-06, "loss": 0.5781776905059814, "step": 1060 }, { "epoch": 0.148776554722008, "grad_norm": 3.72837233543396, "learning_rate": 9.63552223179514e-06, "loss": 0.669052243232727, "step": 1061 }, { "epoch": 0.14891677767650566, "grad_norm": 4.133313179016113, "learning_rate": 9.634670728558607e-06, "loss": 0.6357007622718811, "step": 1062 }, { "epoch": 0.1490570006310033, "grad_norm": 2.537039041519165, "learning_rate": 9.633818269543023e-06, "loss": 0.51921546459198, "step": 1063 }, { "epoch": 0.14919722358550094, "grad_norm": 4.891012191772461, "learning_rate": 9.632964854924185e-06, "loss": 0.5314371585845947, "step": 1064 }, { "epoch": 0.1493374465399986, "grad_norm": 2.985779047012329, "learning_rate": 9.632110484878088e-06, "loss": 0.6048642992973328, "step": 1065 }, { "epoch": 0.14947766949449626, "grad_norm": 4.205300331115723, "learning_rate": 9.631255159580922e-06, "loss": 0.6365058422088623, "step": 1066 }, { "epoch": 0.1496178924489939, "grad_norm": 2.953998327255249, "learning_rate": 9.630398879209076e-06, "loss": 0.5371365547180176, "step": 1067 }, { "epoch": 0.14975811540349154, "grad_norm": 3.27205491065979, "learning_rate": 9.629541643939133e-06, "loss": 0.45897701382637024, "step": 1068 }, { "epoch": 0.1498983383579892, "grad_norm": 3.6308562755584717, "learning_rate": 9.62868345394788e-06, "loss": 0.6478779911994934, "step": 1069 }, { "epoch": 0.15003856131248686, "grad_norm": 3.525054931640625, "learning_rate": 9.627824309412293e-06, "loss": 0.6234321594238281, "step": 1070 }, { "epoch": 0.1501787842669845, "grad_norm": 3.4425508975982666, "learning_rate": 9.626964210509547e-06, "loss": 0.6322941780090332, "step": 1071 }, { "epoch": 0.15031900722148217, "grad_norm": 4.342617988586426, "learning_rate": 9.626103157417017e-06, "loss": 0.6464443206787109, "step": 1072 }, { "epoch": 0.1504592301759798, "grad_norm": 2.403395414352417, "learning_rate": 9.625241150312272e-06, "loss": 0.514664351940155, "step": 1073 }, { "epoch": 0.15059945313047746, "grad_norm": 5.04793119430542, "learning_rate": 9.624378189373077e-06, "loss": 0.5453476905822754, "step": 1074 }, { "epoch": 0.1507396760849751, "grad_norm": 2.8415634632110596, "learning_rate": 9.623514274777399e-06, "loss": 0.6538822650909424, "step": 1075 }, { "epoch": 0.15087989903947277, "grad_norm": 3.0001251697540283, "learning_rate": 9.622649406703392e-06, "loss": 0.6553704738616943, "step": 1076 }, { "epoch": 0.1510201219939704, "grad_norm": 3.3302254676818848, "learning_rate": 9.621783585329418e-06, "loss": 0.696831226348877, "step": 1077 }, { "epoch": 0.15116034494846806, "grad_norm": 3.2096362113952637, "learning_rate": 9.620916810834025e-06, "loss": 0.5791381597518921, "step": 1078 }, { "epoch": 0.15130056790296573, "grad_norm": 5.579900741577148, "learning_rate": 9.620049083395966e-06, "loss": 0.6604522466659546, "step": 1079 }, { "epoch": 0.15144079085746337, "grad_norm": 2.867774724960327, "learning_rate": 9.619180403194184e-06, "loss": 0.6566991209983826, "step": 1080 }, { "epoch": 0.151581013811961, "grad_norm": 3.0108273029327393, "learning_rate": 9.618310770407824e-06, "loss": 0.5596349239349365, "step": 1081 }, { "epoch": 0.15172123676645866, "grad_norm": 8.405828475952148, "learning_rate": 9.617440185216222e-06, "loss": 0.5930333137512207, "step": 1082 }, { "epoch": 0.15186145972095633, "grad_norm": 3.514873743057251, "learning_rate": 9.616568647798919e-06, "loss": 0.5984663963317871, "step": 1083 }, { "epoch": 0.15200168267545397, "grad_norm": 5.261846542358398, "learning_rate": 9.61569615833564e-06, "loss": 0.6581847071647644, "step": 1084 }, { "epoch": 0.1521419056299516, "grad_norm": 3.0333640575408936, "learning_rate": 9.614822717006315e-06, "loss": 0.567002534866333, "step": 1085 }, { "epoch": 0.15228212858444928, "grad_norm": 3.2334253787994385, "learning_rate": 9.613948323991072e-06, "loss": 0.6252337694168091, "step": 1086 }, { "epoch": 0.15242235153894693, "grad_norm": 3.704530715942383, "learning_rate": 9.613072979470228e-06, "loss": 0.577398419380188, "step": 1087 }, { "epoch": 0.15256257449344457, "grad_norm": 4.233881950378418, "learning_rate": 9.6121966836243e-06, "loss": 0.5471879243850708, "step": 1088 }, { "epoch": 0.15270279744794224, "grad_norm": 3.91741943359375, "learning_rate": 9.611319436634001e-06, "loss": 0.6384487152099609, "step": 1089 }, { "epoch": 0.15284302040243988, "grad_norm": 2.844177722930908, "learning_rate": 9.610441238680241e-06, "loss": 0.5596946477890015, "step": 1090 }, { "epoch": 0.15298324335693753, "grad_norm": 2.7874839305877686, "learning_rate": 9.609562089944126e-06, "loss": 0.5620879530906677, "step": 1091 }, { "epoch": 0.15312346631143517, "grad_norm": 3.210549831390381, "learning_rate": 9.608681990606958e-06, "loss": 0.6720064878463745, "step": 1092 }, { "epoch": 0.15326368926593284, "grad_norm": 3.919985055923462, "learning_rate": 9.60780094085023e-06, "loss": 0.4914821982383728, "step": 1093 }, { "epoch": 0.15340391222043048, "grad_norm": 5.070462226867676, "learning_rate": 9.606918940855638e-06, "loss": 0.6447967290878296, "step": 1094 }, { "epoch": 0.15354413517492813, "grad_norm": 11.09453010559082, "learning_rate": 9.606035990805074e-06, "loss": 0.5116429328918457, "step": 1095 }, { "epoch": 0.1536843581294258, "grad_norm": 2.905060291290283, "learning_rate": 9.605152090880619e-06, "loss": 0.5653780698776245, "step": 1096 }, { "epoch": 0.15382458108392344, "grad_norm": 2.821558713912964, "learning_rate": 9.604267241264555e-06, "loss": 0.5583072900772095, "step": 1097 }, { "epoch": 0.15396480403842108, "grad_norm": 4.540654182434082, "learning_rate": 9.603381442139362e-06, "loss": 0.6209321618080139, "step": 1098 }, { "epoch": 0.15410502699291875, "grad_norm": 4.629749298095703, "learning_rate": 9.602494693687707e-06, "loss": 0.5989269614219666, "step": 1099 }, { "epoch": 0.1542452499474164, "grad_norm": 3.416830062866211, "learning_rate": 9.601606996092465e-06, "loss": 0.5427054166793823, "step": 1100 }, { "epoch": 0.15438547290191404, "grad_norm": 3.464503049850464, "learning_rate": 9.600718349536696e-06, "loss": 0.7011531591415405, "step": 1101 }, { "epoch": 0.15452569585641168, "grad_norm": 3.097365379333496, "learning_rate": 9.599828754203661e-06, "loss": 0.7145962715148926, "step": 1102 }, { "epoch": 0.15466591881090935, "grad_norm": 3.2680273056030273, "learning_rate": 9.598938210276818e-06, "loss": 0.5427080392837524, "step": 1103 }, { "epoch": 0.154806141765407, "grad_norm": 3.283250331878662, "learning_rate": 9.598046717939816e-06, "loss": 0.47709721326828003, "step": 1104 }, { "epoch": 0.15494636471990464, "grad_norm": 3.5496978759765625, "learning_rate": 9.597154277376501e-06, "loss": 0.6293358206748962, "step": 1105 }, { "epoch": 0.1550865876744023, "grad_norm": 2.7227866649627686, "learning_rate": 9.596260888770918e-06, "loss": 0.5562384128570557, "step": 1106 }, { "epoch": 0.15522681062889995, "grad_norm": 3.2761311531066895, "learning_rate": 9.595366552307303e-06, "loss": 0.647447943687439, "step": 1107 }, { "epoch": 0.1553670335833976, "grad_norm": 4.485655784606934, "learning_rate": 9.59447126817009e-06, "loss": 0.6293278336524963, "step": 1108 }, { "epoch": 0.15550725653789527, "grad_norm": 4.18634557723999, "learning_rate": 9.593575036543909e-06, "loss": 0.6183391809463501, "step": 1109 }, { "epoch": 0.1556474794923929, "grad_norm": 4.140892028808594, "learning_rate": 9.592677857613582e-06, "loss": 0.524728536605835, "step": 1110 }, { "epoch": 0.15578770244689055, "grad_norm": 3.4933671951293945, "learning_rate": 9.591779731564128e-06, "loss": 0.6554344892501831, "step": 1111 }, { "epoch": 0.1559279254013882, "grad_norm": 3.3407042026519775, "learning_rate": 9.590880658580766e-06, "loss": 0.5292816758155823, "step": 1112 }, { "epoch": 0.15606814835588587, "grad_norm": 4.571523666381836, "learning_rate": 9.589980638848901e-06, "loss": 0.6321818828582764, "step": 1113 }, { "epoch": 0.1562083713103835, "grad_norm": 5.041693210601807, "learning_rate": 9.589079672554145e-06, "loss": 0.5888535380363464, "step": 1114 }, { "epoch": 0.15634859426488115, "grad_norm": 3.385876417160034, "learning_rate": 9.588177759882291e-06, "loss": 0.47799795866012573, "step": 1115 }, { "epoch": 0.15648881721937882, "grad_norm": 5.918146133422852, "learning_rate": 9.58727490101934e-06, "loss": 0.5884292721748352, "step": 1116 }, { "epoch": 0.15662904017387647, "grad_norm": 21.854413986206055, "learning_rate": 9.586371096151481e-06, "loss": 0.6527227163314819, "step": 1117 }, { "epoch": 0.1567692631283741, "grad_norm": 3.9858736991882324, "learning_rate": 9.585466345465102e-06, "loss": 0.5441808700561523, "step": 1118 }, { "epoch": 0.15690948608287178, "grad_norm": 3.607529640197754, "learning_rate": 9.584560649146781e-06, "loss": 0.6083487272262573, "step": 1119 }, { "epoch": 0.15704970903736942, "grad_norm": 2.7112841606140137, "learning_rate": 9.583654007383297e-06, "loss": 0.5706744194030762, "step": 1120 }, { "epoch": 0.15718993199186707, "grad_norm": 3.7084600925445557, "learning_rate": 9.582746420361618e-06, "loss": 0.6395951509475708, "step": 1121 }, { "epoch": 0.1573301549463647, "grad_norm": 3.7804017066955566, "learning_rate": 9.581837888268911e-06, "loss": 0.6562029123306274, "step": 1122 }, { "epoch": 0.15747037790086238, "grad_norm": 2.8712635040283203, "learning_rate": 9.580928411292538e-06, "loss": 0.5311943888664246, "step": 1123 }, { "epoch": 0.15761060085536002, "grad_norm": 14.166913986206055, "learning_rate": 9.580017989620056e-06, "loss": 0.5758219957351685, "step": 1124 }, { "epoch": 0.15775082380985767, "grad_norm": 3.78385329246521, "learning_rate": 9.579106623439211e-06, "loss": 0.609214186668396, "step": 1125 }, { "epoch": 0.15789104676435534, "grad_norm": 3.2875170707702637, "learning_rate": 9.578194312937953e-06, "loss": 0.49165400862693787, "step": 1126 }, { "epoch": 0.15803126971885298, "grad_norm": 7.410464763641357, "learning_rate": 9.577281058304419e-06, "loss": 0.6308246850967407, "step": 1127 }, { "epoch": 0.15817149267335062, "grad_norm": 4.609270095825195, "learning_rate": 9.576366859726946e-06, "loss": 0.6585738658905029, "step": 1128 }, { "epoch": 0.15831171562784827, "grad_norm": 3.001315116882324, "learning_rate": 9.575451717394063e-06, "loss": 0.5473814010620117, "step": 1129 }, { "epoch": 0.15845193858234594, "grad_norm": 4.625243186950684, "learning_rate": 9.57453563149449e-06, "loss": 0.5641049742698669, "step": 1130 }, { "epoch": 0.15859216153684358, "grad_norm": 4.051817417144775, "learning_rate": 9.573618602217153e-06, "loss": 0.652909517288208, "step": 1131 }, { "epoch": 0.15873238449134122, "grad_norm": 3.491800308227539, "learning_rate": 9.572700629751158e-06, "loss": 0.6143994331359863, "step": 1132 }, { "epoch": 0.1588726074458389, "grad_norm": 3.60595965385437, "learning_rate": 9.571781714285817e-06, "loss": 0.5938461422920227, "step": 1133 }, { "epoch": 0.15901283040033654, "grad_norm": 5.908801555633545, "learning_rate": 9.570861856010631e-06, "loss": 0.5986185073852539, "step": 1134 }, { "epoch": 0.15915305335483418, "grad_norm": 5.648214817047119, "learning_rate": 9.569941055115297e-06, "loss": 0.4931389093399048, "step": 1135 }, { "epoch": 0.15929327630933185, "grad_norm": 4.099295616149902, "learning_rate": 9.569019311789707e-06, "loss": 0.6293756365776062, "step": 1136 }, { "epoch": 0.1594334992638295, "grad_norm": 2.920056104660034, "learning_rate": 9.568096626223943e-06, "loss": 0.6026937961578369, "step": 1137 }, { "epoch": 0.15957372221832714, "grad_norm": 3.552135944366455, "learning_rate": 9.567172998608288e-06, "loss": 0.6380890011787415, "step": 1138 }, { "epoch": 0.15971394517282478, "grad_norm": 6.214599132537842, "learning_rate": 9.566248429133213e-06, "loss": 0.6161262392997742, "step": 1139 }, { "epoch": 0.15985416812732245, "grad_norm": 3.423828601837158, "learning_rate": 9.565322917989388e-06, "loss": 0.5425832271575928, "step": 1140 }, { "epoch": 0.1599943910818201, "grad_norm": 3.2514102458953857, "learning_rate": 9.564396465367675e-06, "loss": 0.515294075012207, "step": 1141 }, { "epoch": 0.16013461403631774, "grad_norm": 2.4844119548797607, "learning_rate": 9.563469071459133e-06, "loss": 0.6037245988845825, "step": 1142 }, { "epoch": 0.1602748369908154, "grad_norm": 3.94152569770813, "learning_rate": 9.562540736455008e-06, "loss": 0.6736660003662109, "step": 1143 }, { "epoch": 0.16041505994531305, "grad_norm": 3.2206647396087646, "learning_rate": 9.561611460546747e-06, "loss": 0.518464207649231, "step": 1144 }, { "epoch": 0.1605552828998107, "grad_norm": 3.579007148742676, "learning_rate": 9.56068124392599e-06, "loss": 0.5587483048439026, "step": 1145 }, { "epoch": 0.16069550585430836, "grad_norm": 3.668851852416992, "learning_rate": 9.559750086784568e-06, "loss": 0.625041127204895, "step": 1146 }, { "epoch": 0.160835728808806, "grad_norm": 3.3754355907440186, "learning_rate": 9.558817989314507e-06, "loss": 0.6472052335739136, "step": 1147 }, { "epoch": 0.16097595176330365, "grad_norm": 3.3584249019622803, "learning_rate": 9.55788495170803e-06, "loss": 0.5326021909713745, "step": 1148 }, { "epoch": 0.1611161747178013, "grad_norm": 4.325605869293213, "learning_rate": 9.556950974157548e-06, "loss": 0.6275140047073364, "step": 1149 }, { "epoch": 0.16125639767229896, "grad_norm": 3.107754945755005, "learning_rate": 9.556016056855672e-06, "loss": 0.6065351963043213, "step": 1150 }, { "epoch": 0.1613966206267966, "grad_norm": 3.650143623352051, "learning_rate": 9.555080199995205e-06, "loss": 0.6102283000946045, "step": 1151 }, { "epoch": 0.16153684358129425, "grad_norm": 3.46482253074646, "learning_rate": 9.554143403769142e-06, "loss": 0.5225969552993774, "step": 1152 }, { "epoch": 0.16167706653579192, "grad_norm": 3.8369641304016113, "learning_rate": 9.55320566837067e-06, "loss": 0.6231064796447754, "step": 1153 }, { "epoch": 0.16181728949028956, "grad_norm": 3.5212862491607666, "learning_rate": 9.552266993993177e-06, "loss": 0.5653254985809326, "step": 1154 }, { "epoch": 0.1619575124447872, "grad_norm": 3.3642184734344482, "learning_rate": 9.551327380830236e-06, "loss": 0.6489999294281006, "step": 1155 }, { "epoch": 0.16209773539928488, "grad_norm": 3.2597458362579346, "learning_rate": 9.55038682907562e-06, "loss": 0.5655828714370728, "step": 1156 }, { "epoch": 0.16223795835378252, "grad_norm": 11.375835418701172, "learning_rate": 9.54944533892329e-06, "loss": 0.5338989496231079, "step": 1157 }, { "epoch": 0.16237818130828016, "grad_norm": 8.267024993896484, "learning_rate": 9.548502910567407e-06, "loss": 0.5888640284538269, "step": 1158 }, { "epoch": 0.1625184042627778, "grad_norm": 5.083702087402344, "learning_rate": 9.54755954420232e-06, "loss": 0.5387700200080872, "step": 1159 }, { "epoch": 0.16265862721727548, "grad_norm": 3.050877571105957, "learning_rate": 9.546615240022575e-06, "loss": 0.49221163988113403, "step": 1160 }, { "epoch": 0.16279885017177312, "grad_norm": 5.077573776245117, "learning_rate": 9.545669998222907e-06, "loss": 0.648984432220459, "step": 1161 }, { "epoch": 0.16293907312627076, "grad_norm": 5.401425838470459, "learning_rate": 9.544723818998252e-06, "loss": 0.6562837958335876, "step": 1162 }, { "epoch": 0.16307929608076843, "grad_norm": 6.44135046005249, "learning_rate": 9.54377670254373e-06, "loss": 0.6121644973754883, "step": 1163 }, { "epoch": 0.16321951903526608, "grad_norm": 4.18745231628418, "learning_rate": 9.54282864905466e-06, "loss": 0.6164772510528564, "step": 1164 }, { "epoch": 0.16335974198976372, "grad_norm": 5.924959182739258, "learning_rate": 9.541879658726556e-06, "loss": 0.5271215438842773, "step": 1165 }, { "epoch": 0.1634999649442614, "grad_norm": 3.0034756660461426, "learning_rate": 9.54092973175512e-06, "loss": 0.593252420425415, "step": 1166 }, { "epoch": 0.16364018789875903, "grad_norm": 4.17751407623291, "learning_rate": 9.539978868336251e-06, "loss": 0.6410632133483887, "step": 1167 }, { "epoch": 0.16378041085325667, "grad_norm": 8.247206687927246, "learning_rate": 9.539027068666036e-06, "loss": 0.5844650268554688, "step": 1168 }, { "epoch": 0.16392063380775432, "grad_norm": 5.253473281860352, "learning_rate": 9.538074332940762e-06, "loss": 0.6233941316604614, "step": 1169 }, { "epoch": 0.164060856762252, "grad_norm": 5.415610313415527, "learning_rate": 9.537120661356905e-06, "loss": 0.62247234582901, "step": 1170 }, { "epoch": 0.16420107971674963, "grad_norm": 3.728804588317871, "learning_rate": 9.536166054111133e-06, "loss": 0.5247824192047119, "step": 1171 }, { "epoch": 0.16434130267124727, "grad_norm": 12.383380889892578, "learning_rate": 9.535210511400313e-06, "loss": 0.6602361798286438, "step": 1172 }, { "epoch": 0.16448152562574495, "grad_norm": 3.4792985916137695, "learning_rate": 9.534254033421495e-06, "loss": 0.5926470160484314, "step": 1173 }, { "epoch": 0.1646217485802426, "grad_norm": 3.8904197216033936, "learning_rate": 9.533296620371931e-06, "loss": 0.49067509174346924, "step": 1174 }, { "epoch": 0.16476197153474023, "grad_norm": 3.177189588546753, "learning_rate": 9.532338272449061e-06, "loss": 0.624949038028717, "step": 1175 }, { "epoch": 0.16490219448923787, "grad_norm": 4.126794338226318, "learning_rate": 9.53137898985052e-06, "loss": 0.5731418132781982, "step": 1176 }, { "epoch": 0.16504241744373555, "grad_norm": 12.69845199584961, "learning_rate": 9.530418772774135e-06, "loss": 0.617641806602478, "step": 1177 }, { "epoch": 0.1651826403982332, "grad_norm": 4.764960765838623, "learning_rate": 9.529457621417924e-06, "loss": 0.6237246990203857, "step": 1178 }, { "epoch": 0.16532286335273083, "grad_norm": 9.191183090209961, "learning_rate": 9.528495535980101e-06, "loss": 0.5123482346534729, "step": 1179 }, { "epoch": 0.1654630863072285, "grad_norm": 3.482983112335205, "learning_rate": 9.527532516659068e-06, "loss": 0.5393043756484985, "step": 1180 }, { "epoch": 0.16560330926172614, "grad_norm": 2.7135956287384033, "learning_rate": 9.526568563653427e-06, "loss": 0.5526366233825684, "step": 1181 }, { "epoch": 0.1657435322162238, "grad_norm": 6.208900451660156, "learning_rate": 9.525603677161962e-06, "loss": 0.54376220703125, "step": 1182 }, { "epoch": 0.16588375517072146, "grad_norm": 6.587334632873535, "learning_rate": 9.524637857383663e-06, "loss": 0.5471105575561523, "step": 1183 }, { "epoch": 0.1660239781252191, "grad_norm": 6.979287147521973, "learning_rate": 9.523671104517698e-06, "loss": 0.5612784624099731, "step": 1184 }, { "epoch": 0.16616420107971674, "grad_norm": 4.075492858886719, "learning_rate": 9.522703418763437e-06, "loss": 0.5507375001907349, "step": 1185 }, { "epoch": 0.1663044240342144, "grad_norm": 4.849759101867676, "learning_rate": 9.521734800320441e-06, "loss": 0.5826993584632874, "step": 1186 }, { "epoch": 0.16644464698871206, "grad_norm": 3.77335786819458, "learning_rate": 9.52076524938846e-06, "loss": 0.5937850475311279, "step": 1187 }, { "epoch": 0.1665848699432097, "grad_norm": 14.875953674316406, "learning_rate": 9.519794766167439e-06, "loss": 0.4271746873855591, "step": 1188 }, { "epoch": 0.16672509289770734, "grad_norm": 4.586952209472656, "learning_rate": 9.518823350857515e-06, "loss": 0.6276468634605408, "step": 1189 }, { "epoch": 0.16686531585220502, "grad_norm": 5.89969539642334, "learning_rate": 9.517851003659018e-06, "loss": 0.5818614959716797, "step": 1190 }, { "epoch": 0.16700553880670266, "grad_norm": 2.5660855770111084, "learning_rate": 9.516877724772468e-06, "loss": 0.5813974142074585, "step": 1191 }, { "epoch": 0.1671457617612003, "grad_norm": 6.288183689117432, "learning_rate": 9.515903514398579e-06, "loss": 0.6834735870361328, "step": 1192 }, { "epoch": 0.16728598471569797, "grad_norm": 3.3639845848083496, "learning_rate": 9.514928372738254e-06, "loss": 0.6009092330932617, "step": 1193 }, { "epoch": 0.16742620767019561, "grad_norm": 9.752592086791992, "learning_rate": 9.513952299992593e-06, "loss": 0.5873593091964722, "step": 1194 }, { "epoch": 0.16756643062469326, "grad_norm": 3.477830648422241, "learning_rate": 9.512975296362883e-06, "loss": 0.700963020324707, "step": 1195 }, { "epoch": 0.1677066535791909, "grad_norm": 3.3621370792388916, "learning_rate": 9.511997362050606e-06, "loss": 0.5674443244934082, "step": 1196 }, { "epoch": 0.16784687653368857, "grad_norm": 3.5265932083129883, "learning_rate": 9.511018497257438e-06, "loss": 0.5633003115653992, "step": 1197 }, { "epoch": 0.16798709948818621, "grad_norm": 4.896770000457764, "learning_rate": 9.51003870218524e-06, "loss": 0.5776945352554321, "step": 1198 }, { "epoch": 0.16812732244268386, "grad_norm": 4.261762619018555, "learning_rate": 9.509057977036071e-06, "loss": 0.5952615737915039, "step": 1199 }, { "epoch": 0.16826754539718153, "grad_norm": 5.17888069152832, "learning_rate": 9.508076322012181e-06, "loss": 0.534687876701355, "step": 1200 }, { "epoch": 0.16840776835167917, "grad_norm": 4.228847026824951, "learning_rate": 9.507093737316007e-06, "loss": 0.6729727387428284, "step": 1201 }, { "epoch": 0.16854799130617681, "grad_norm": 3.148183822631836, "learning_rate": 9.506110223150184e-06, "loss": 0.5037499070167542, "step": 1202 }, { "epoch": 0.16868821426067448, "grad_norm": 2.6914796829223633, "learning_rate": 9.505125779717538e-06, "loss": 0.5766435861587524, "step": 1203 }, { "epoch": 0.16882843721517213, "grad_norm": 3.049231767654419, "learning_rate": 9.504140407221081e-06, "loss": 0.5840029716491699, "step": 1204 }, { "epoch": 0.16896866016966977, "grad_norm": 6.020596981048584, "learning_rate": 9.503154105864019e-06, "loss": 0.6417860388755798, "step": 1205 }, { "epoch": 0.16910888312416741, "grad_norm": 2.5565285682678223, "learning_rate": 9.502166875849756e-06, "loss": 0.5023882985115051, "step": 1206 }, { "epoch": 0.16924910607866508, "grad_norm": 4.664072513580322, "learning_rate": 9.501178717381878e-06, "loss": 0.6907456517219543, "step": 1207 }, { "epoch": 0.16938932903316273, "grad_norm": 4.258737564086914, "learning_rate": 9.500189630664167e-06, "loss": 0.6820090413093567, "step": 1208 }, { "epoch": 0.16952955198766037, "grad_norm": 4.978160381317139, "learning_rate": 9.499199615900598e-06, "loss": 0.6233823299407959, "step": 1209 }, { "epoch": 0.16966977494215804, "grad_norm": 6.9431562423706055, "learning_rate": 9.498208673295335e-06, "loss": 0.5373968482017517, "step": 1210 }, { "epoch": 0.16980999789665568, "grad_norm": 6.610519886016846, "learning_rate": 9.497216803052732e-06, "loss": 0.5411942005157471, "step": 1211 }, { "epoch": 0.16995022085115333, "grad_norm": 4.403174877166748, "learning_rate": 9.49622400537734e-06, "loss": 0.6323665976524353, "step": 1212 }, { "epoch": 0.170090443805651, "grad_norm": 4.726617813110352, "learning_rate": 9.495230280473892e-06, "loss": 0.5878078937530518, "step": 1213 }, { "epoch": 0.17023066676014864, "grad_norm": 14.124964714050293, "learning_rate": 9.494235628547323e-06, "loss": 0.5686086416244507, "step": 1214 }, { "epoch": 0.17037088971464628, "grad_norm": 3.8345541954040527, "learning_rate": 9.49324004980275e-06, "loss": 0.4742080569267273, "step": 1215 }, { "epoch": 0.17051111266914393, "grad_norm": 3.430762529373169, "learning_rate": 9.492243544445488e-06, "loss": 0.5462942123413086, "step": 1216 }, { "epoch": 0.1706513356236416, "grad_norm": 3.970534086227417, "learning_rate": 9.491246112681038e-06, "loss": 0.5455379486083984, "step": 1217 }, { "epoch": 0.17079155857813924, "grad_norm": 14.23582649230957, "learning_rate": 9.490247754715095e-06, "loss": 0.6098936200141907, "step": 1218 }, { "epoch": 0.17093178153263688, "grad_norm": 4.476504802703857, "learning_rate": 9.489248470753543e-06, "loss": 0.6044532656669617, "step": 1219 }, { "epoch": 0.17107200448713455, "grad_norm": 3.3032238483428955, "learning_rate": 9.48824826100246e-06, "loss": 0.5631093978881836, "step": 1220 }, { "epoch": 0.1712122274416322, "grad_norm": 3.0635368824005127, "learning_rate": 9.48724712566811e-06, "loss": 0.568953812122345, "step": 1221 }, { "epoch": 0.17135245039612984, "grad_norm": 3.4733948707580566, "learning_rate": 9.486245064956955e-06, "loss": 0.6851105093955994, "step": 1222 }, { "epoch": 0.1714926733506275, "grad_norm": 4.0262274742126465, "learning_rate": 9.48524207907564e-06, "loss": 0.6767880320549011, "step": 1223 }, { "epoch": 0.17163289630512515, "grad_norm": 3.697402238845825, "learning_rate": 9.484238168231006e-06, "loss": 0.6622884273529053, "step": 1224 }, { "epoch": 0.1717731192596228, "grad_norm": 3.4877772331237793, "learning_rate": 9.483233332630084e-06, "loss": 0.5581910610198975, "step": 1225 }, { "epoch": 0.17191334221412044, "grad_norm": 3.0965449810028076, "learning_rate": 9.482227572480092e-06, "loss": 0.5810204148292542, "step": 1226 }, { "epoch": 0.1720535651686181, "grad_norm": 3.5756947994232178, "learning_rate": 9.481220887988445e-06, "loss": 0.5357301235198975, "step": 1227 }, { "epoch": 0.17219378812311575, "grad_norm": 3.272625684738159, "learning_rate": 9.480213279362742e-06, "loss": 0.6517168283462524, "step": 1228 }, { "epoch": 0.1723340110776134, "grad_norm": 3.4601433277130127, "learning_rate": 9.479204746810779e-06, "loss": 0.5953043699264526, "step": 1229 }, { "epoch": 0.17247423403211107, "grad_norm": 2.8348257541656494, "learning_rate": 9.478195290540539e-06, "loss": 0.5468628406524658, "step": 1230 }, { "epoch": 0.1726144569866087, "grad_norm": 8.486157417297363, "learning_rate": 9.477184910760194e-06, "loss": 0.5354540348052979, "step": 1231 }, { "epoch": 0.17275467994110635, "grad_norm": 3.2667698860168457, "learning_rate": 9.476173607678108e-06, "loss": 0.5265859365463257, "step": 1232 }, { "epoch": 0.172894902895604, "grad_norm": 3.6866683959960938, "learning_rate": 9.475161381502837e-06, "loss": 0.5820241570472717, "step": 1233 }, { "epoch": 0.17303512585010167, "grad_norm": 3.0538814067840576, "learning_rate": 9.474148232443126e-06, "loss": 0.5868602991104126, "step": 1234 }, { "epoch": 0.1731753488045993, "grad_norm": 5.207523822784424, "learning_rate": 9.47313416070791e-06, "loss": 0.5579203963279724, "step": 1235 }, { "epoch": 0.17331557175909695, "grad_norm": 3.1048641204833984, "learning_rate": 9.472119166506317e-06, "loss": 0.6576390266418457, "step": 1236 }, { "epoch": 0.17345579471359462, "grad_norm": 5.940628528594971, "learning_rate": 9.471103250047658e-06, "loss": 0.556777834892273, "step": 1237 }, { "epoch": 0.17359601766809227, "grad_norm": 8.368106842041016, "learning_rate": 9.470086411541443e-06, "loss": 0.695756196975708, "step": 1238 }, { "epoch": 0.1737362406225899, "grad_norm": 3.6924893856048584, "learning_rate": 9.469068651197368e-06, "loss": 0.5803869962692261, "step": 1239 }, { "epoch": 0.17387646357708758, "grad_norm": 4.020327091217041, "learning_rate": 9.468049969225318e-06, "loss": 0.5687983632087708, "step": 1240 }, { "epoch": 0.17401668653158522, "grad_norm": 6.211825370788574, "learning_rate": 9.467030365835368e-06, "loss": 0.6663666367530823, "step": 1241 }, { "epoch": 0.17415690948608287, "grad_norm": 7.963546276092529, "learning_rate": 9.466009841237787e-06, "loss": 0.5591624975204468, "step": 1242 }, { "epoch": 0.1742971324405805, "grad_norm": 4.157421112060547, "learning_rate": 9.464988395643029e-06, "loss": 0.6352024078369141, "step": 1243 }, { "epoch": 0.17443735539507818, "grad_norm": 3.739621877670288, "learning_rate": 9.463966029261744e-06, "loss": 0.5238730907440186, "step": 1244 }, { "epoch": 0.17457757834957582, "grad_norm": 3.633975028991699, "learning_rate": 9.462942742304764e-06, "loss": 0.6583111882209778, "step": 1245 }, { "epoch": 0.17471780130407347, "grad_norm": 3.0977723598480225, "learning_rate": 9.461918534983119e-06, "loss": 0.5881125926971436, "step": 1246 }, { "epoch": 0.17485802425857114, "grad_norm": 3.168883800506592, "learning_rate": 9.460893407508022e-06, "loss": 0.571588397026062, "step": 1247 }, { "epoch": 0.17499824721306878, "grad_norm": 3.4914166927337646, "learning_rate": 9.459867360090879e-06, "loss": 0.641007661819458, "step": 1248 }, { "epoch": 0.17513847016756642, "grad_norm": 3.917109727859497, "learning_rate": 9.458840392943288e-06, "loss": 0.6665345430374146, "step": 1249 }, { "epoch": 0.1752786931220641, "grad_norm": 3.7104673385620117, "learning_rate": 9.457812506277031e-06, "loss": 0.6794064044952393, "step": 1250 }, { "epoch": 0.17541891607656174, "grad_norm": 2.898684501647949, "learning_rate": 9.456783700304082e-06, "loss": 0.5183825492858887, "step": 1251 }, { "epoch": 0.17555913903105938, "grad_norm": 4.2618727684021, "learning_rate": 9.455753975236608e-06, "loss": 0.6450466513633728, "step": 1252 }, { "epoch": 0.17569936198555702, "grad_norm": 5.306547164916992, "learning_rate": 9.45472333128696e-06, "loss": 0.5742684602737427, "step": 1253 }, { "epoch": 0.1758395849400547, "grad_norm": 3.9022605419158936, "learning_rate": 9.453691768667683e-06, "loss": 0.5794419646263123, "step": 1254 }, { "epoch": 0.17597980789455234, "grad_norm": 4.08730936050415, "learning_rate": 9.45265928759151e-06, "loss": 0.5896497964859009, "step": 1255 }, { "epoch": 0.17612003084904998, "grad_norm": 4.379703044891357, "learning_rate": 9.451625888271362e-06, "loss": 0.6509850025177002, "step": 1256 }, { "epoch": 0.17626025380354765, "grad_norm": 4.350225448608398, "learning_rate": 9.450591570920352e-06, "loss": 0.616335928440094, "step": 1257 }, { "epoch": 0.1764004767580453, "grad_norm": 4.402227401733398, "learning_rate": 9.449556335751778e-06, "loss": 0.6249651908874512, "step": 1258 }, { "epoch": 0.17654069971254294, "grad_norm": 3.1600310802459717, "learning_rate": 9.448520182979133e-06, "loss": 0.5486336946487427, "step": 1259 }, { "epoch": 0.1766809226670406, "grad_norm": 5.451690196990967, "learning_rate": 9.447483112816094e-06, "loss": 0.6424086093902588, "step": 1260 }, { "epoch": 0.17682114562153825, "grad_norm": 3.9785611629486084, "learning_rate": 9.44644512547653e-06, "loss": 0.6512271761894226, "step": 1261 }, { "epoch": 0.1769613685760359, "grad_norm": 2.6187639236450195, "learning_rate": 9.4454062211745e-06, "loss": 0.6232878565788269, "step": 1262 }, { "epoch": 0.17710159153053354, "grad_norm": 3.973409414291382, "learning_rate": 9.44436640012425e-06, "loss": 0.645655632019043, "step": 1263 }, { "epoch": 0.1772418144850312, "grad_norm": 5.5509467124938965, "learning_rate": 9.443325662540215e-06, "loss": 0.6106555461883545, "step": 1264 }, { "epoch": 0.17738203743952885, "grad_norm": 4.68560266494751, "learning_rate": 9.44228400863702e-06, "loss": 0.567168116569519, "step": 1265 }, { "epoch": 0.1775222603940265, "grad_norm": 5.086545467376709, "learning_rate": 9.441241438629479e-06, "loss": 0.4501088857650757, "step": 1266 }, { "epoch": 0.17766248334852416, "grad_norm": 3.728896141052246, "learning_rate": 9.440197952732595e-06, "loss": 0.6411564350128174, "step": 1267 }, { "epoch": 0.1778027063030218, "grad_norm": 3.440293550491333, "learning_rate": 9.439153551161558e-06, "loss": 0.6008992791175842, "step": 1268 }, { "epoch": 0.17794292925751945, "grad_norm": 8.054414749145508, "learning_rate": 9.43810823413175e-06, "loss": 0.685104489326477, "step": 1269 }, { "epoch": 0.17808315221201712, "grad_norm": 5.468801021575928, "learning_rate": 9.437062001858742e-06, "loss": 0.6237162351608276, "step": 1270 }, { "epoch": 0.17822337516651476, "grad_norm": 5.050368309020996, "learning_rate": 9.436014854558287e-06, "loss": 0.7157999277114868, "step": 1271 }, { "epoch": 0.1783635981210124, "grad_norm": 3.9551405906677246, "learning_rate": 9.434966792446337e-06, "loss": 0.5879548788070679, "step": 1272 }, { "epoch": 0.17850382107551005, "grad_norm": 2.9813072681427, "learning_rate": 9.433917815739021e-06, "loss": 0.5825748443603516, "step": 1273 }, { "epoch": 0.17864404403000772, "grad_norm": 5.470280170440674, "learning_rate": 9.432867924652669e-06, "loss": 0.5796322822570801, "step": 1274 }, { "epoch": 0.17878426698450536, "grad_norm": 4.5189595222473145, "learning_rate": 9.431817119403792e-06, "loss": 0.4678191542625427, "step": 1275 }, { "epoch": 0.178924489939003, "grad_norm": 6.214998245239258, "learning_rate": 9.430765400209087e-06, "loss": 0.6794235110282898, "step": 1276 }, { "epoch": 0.17906471289350068, "grad_norm": 2.9233741760253906, "learning_rate": 9.429712767285448e-06, "loss": 0.6904299259185791, "step": 1277 }, { "epoch": 0.17920493584799832, "grad_norm": 4.697860240936279, "learning_rate": 9.428659220849951e-06, "loss": 0.6221997737884521, "step": 1278 }, { "epoch": 0.17934515880249596, "grad_norm": 3.142246961593628, "learning_rate": 9.427604761119861e-06, "loss": 0.6402015089988708, "step": 1279 }, { "epoch": 0.1794853817569936, "grad_norm": 3.5568900108337402, "learning_rate": 9.426549388312638e-06, "loss": 0.5907477736473083, "step": 1280 }, { "epoch": 0.17962560471149128, "grad_norm": 2.6605746746063232, "learning_rate": 9.425493102645918e-06, "loss": 0.6026064157485962, "step": 1281 }, { "epoch": 0.17976582766598892, "grad_norm": 3.898252487182617, "learning_rate": 9.424435904337535e-06, "loss": 0.5635831356048584, "step": 1282 }, { "epoch": 0.17990605062048656, "grad_norm": 4.608401298522949, "learning_rate": 9.42337779360551e-06, "loss": 0.6248673796653748, "step": 1283 }, { "epoch": 0.18004627357498423, "grad_norm": 4.089115619659424, "learning_rate": 9.422318770668049e-06, "loss": 0.5773910880088806, "step": 1284 }, { "epoch": 0.18018649652948188, "grad_norm": 3.3044910430908203, "learning_rate": 9.421258835743546e-06, "loss": 0.5585423707962036, "step": 1285 }, { "epoch": 0.18032671948397952, "grad_norm": 5.514541149139404, "learning_rate": 9.420197989050588e-06, "loss": 0.5536904335021973, "step": 1286 }, { "epoch": 0.1804669424384772, "grad_norm": 2.503044843673706, "learning_rate": 9.419136230807943e-06, "loss": 0.47468486428260803, "step": 1287 }, { "epoch": 0.18060716539297483, "grad_norm": 3.1522693634033203, "learning_rate": 9.418073561234575e-06, "loss": 0.552910327911377, "step": 1288 }, { "epoch": 0.18074738834747248, "grad_norm": 4.141601085662842, "learning_rate": 9.41700998054963e-06, "loss": 0.6383844614028931, "step": 1289 }, { "epoch": 0.18088761130197012, "grad_norm": 9.922538757324219, "learning_rate": 9.415945488972443e-06, "loss": 0.5691778659820557, "step": 1290 }, { "epoch": 0.1810278342564678, "grad_norm": 4.885871887207031, "learning_rate": 9.414880086722537e-06, "loss": 0.6768383979797363, "step": 1291 }, { "epoch": 0.18116805721096543, "grad_norm": 4.348736763000488, "learning_rate": 9.413813774019624e-06, "loss": 0.5905252695083618, "step": 1292 }, { "epoch": 0.18130828016546308, "grad_norm": 3.014282464981079, "learning_rate": 9.412746551083603e-06, "loss": 0.6521565318107605, "step": 1293 }, { "epoch": 0.18144850311996075, "grad_norm": 3.369516372680664, "learning_rate": 9.41167841813456e-06, "loss": 0.5624228119850159, "step": 1294 }, { "epoch": 0.1815887260744584, "grad_norm": 3.444196939468384, "learning_rate": 9.41060937539277e-06, "loss": 0.5858823657035828, "step": 1295 }, { "epoch": 0.18172894902895603, "grad_norm": 3.0799319744110107, "learning_rate": 9.409539423078695e-06, "loss": 0.5664709210395813, "step": 1296 }, { "epoch": 0.1818691719834537, "grad_norm": 3.8862993717193604, "learning_rate": 9.408468561412984e-06, "loss": 0.5496907830238342, "step": 1297 }, { "epoch": 0.18200939493795135, "grad_norm": 3.096618890762329, "learning_rate": 9.407396790616473e-06, "loss": 0.5853317379951477, "step": 1298 }, { "epoch": 0.182149617892449, "grad_norm": 5.155398368835449, "learning_rate": 9.406324110910192e-06, "loss": 0.6431755423545837, "step": 1299 }, { "epoch": 0.18228984084694663, "grad_norm": 4.2750139236450195, "learning_rate": 9.405250522515346e-06, "loss": 0.4884829521179199, "step": 1300 }, { "epoch": 0.1824300638014443, "grad_norm": 5.4236955642700195, "learning_rate": 9.404176025653338e-06, "loss": 0.5946615934371948, "step": 1301 }, { "epoch": 0.18257028675594195, "grad_norm": 5.184696674346924, "learning_rate": 9.403100620545754e-06, "loss": 0.6842204332351685, "step": 1302 }, { "epoch": 0.1827105097104396, "grad_norm": 3.585089683532715, "learning_rate": 9.402024307414369e-06, "loss": 0.507548451423645, "step": 1303 }, { "epoch": 0.18285073266493726, "grad_norm": 2.819121837615967, "learning_rate": 9.400947086481143e-06, "loss": 0.4517577886581421, "step": 1304 }, { "epoch": 0.1829909556194349, "grad_norm": 3.968982458114624, "learning_rate": 9.399868957968224e-06, "loss": 0.6308973431587219, "step": 1305 }, { "epoch": 0.18313117857393255, "grad_norm": 4.805683135986328, "learning_rate": 9.398789922097951e-06, "loss": 0.6139352321624756, "step": 1306 }, { "epoch": 0.18327140152843022, "grad_norm": 4.3750691413879395, "learning_rate": 9.397709979092842e-06, "loss": 0.5700879096984863, "step": 1307 }, { "epoch": 0.18341162448292786, "grad_norm": 2.729213237762451, "learning_rate": 9.396629129175611e-06, "loss": 0.5204042196273804, "step": 1308 }, { "epoch": 0.1835518474374255, "grad_norm": 7.217854976654053, "learning_rate": 9.395547372569151e-06, "loss": 0.6157064437866211, "step": 1309 }, { "epoch": 0.18369207039192315, "grad_norm": 3.6602783203125, "learning_rate": 9.394464709496551e-06, "loss": 0.6491937637329102, "step": 1310 }, { "epoch": 0.18383229334642082, "grad_norm": 2.690293073654175, "learning_rate": 9.393381140181076e-06, "loss": 0.6653035879135132, "step": 1311 }, { "epoch": 0.18397251630091846, "grad_norm": 19.824689865112305, "learning_rate": 9.39229666484619e-06, "loss": 0.5788978338241577, "step": 1312 }, { "epoch": 0.1841127392554161, "grad_norm": 4.223824977874756, "learning_rate": 9.391211283715531e-06, "loss": 0.5955692529678345, "step": 1313 }, { "epoch": 0.18425296220991377, "grad_norm": 4.058411598205566, "learning_rate": 9.390124997012937e-06, "loss": 0.6205534934997559, "step": 1314 }, { "epoch": 0.18439318516441142, "grad_norm": 3.9679715633392334, "learning_rate": 9.38903780496242e-06, "loss": 0.6109769940376282, "step": 1315 }, { "epoch": 0.18453340811890906, "grad_norm": 10.677204132080078, "learning_rate": 9.387949707788187e-06, "loss": 0.5388925075531006, "step": 1316 }, { "epoch": 0.18467363107340673, "grad_norm": 4.400860786437988, "learning_rate": 9.386860705714631e-06, "loss": 0.5918854475021362, "step": 1317 }, { "epoch": 0.18481385402790437, "grad_norm": 9.37708568572998, "learning_rate": 9.38577079896633e-06, "loss": 0.44317692518234253, "step": 1318 }, { "epoch": 0.18495407698240202, "grad_norm": 5.2683424949646, "learning_rate": 9.384679987768045e-06, "loss": 0.526248574256897, "step": 1319 }, { "epoch": 0.18509429993689966, "grad_norm": 4.948015213012695, "learning_rate": 9.38358827234473e-06, "loss": 0.7312185168266296, "step": 1320 }, { "epoch": 0.18523452289139733, "grad_norm": 3.454319953918457, "learning_rate": 9.382495652921524e-06, "loss": 0.6669789552688599, "step": 1321 }, { "epoch": 0.18537474584589497, "grad_norm": 5.906193733215332, "learning_rate": 9.381402129723748e-06, "loss": 0.5450254678726196, "step": 1322 }, { "epoch": 0.18551496880039262, "grad_norm": 4.228007793426514, "learning_rate": 9.380307702976914e-06, "loss": 0.5942414999008179, "step": 1323 }, { "epoch": 0.1856551917548903, "grad_norm": 3.797057867050171, "learning_rate": 9.379212372906719e-06, "loss": 0.5259652137756348, "step": 1324 }, { "epoch": 0.18579541470938793, "grad_norm": 3.594123601913452, "learning_rate": 9.378116139739045e-06, "loss": 0.5526928901672363, "step": 1325 }, { "epoch": 0.18593563766388557, "grad_norm": 3.5409746170043945, "learning_rate": 9.377019003699962e-06, "loss": 0.6303568482398987, "step": 1326 }, { "epoch": 0.18607586061838324, "grad_norm": 5.716776371002197, "learning_rate": 9.375920965015725e-06, "loss": 0.6550041437149048, "step": 1327 }, { "epoch": 0.18621608357288089, "grad_norm": 3.393555164337158, "learning_rate": 9.374822023912777e-06, "loss": 0.5869480967521667, "step": 1328 }, { "epoch": 0.18635630652737853, "grad_norm": 4.144639015197754, "learning_rate": 9.373722180617743e-06, "loss": 0.5667639970779419, "step": 1329 }, { "epoch": 0.18649652948187617, "grad_norm": 4.25665807723999, "learning_rate": 9.37262143535744e-06, "loss": 0.5769251585006714, "step": 1330 }, { "epoch": 0.18663675243637384, "grad_norm": 3.8304224014282227, "learning_rate": 9.371519788358865e-06, "loss": 0.5803157091140747, "step": 1331 }, { "epoch": 0.18677697539087149, "grad_norm": 4.771228790283203, "learning_rate": 9.370417239849206e-06, "loss": 0.5573935508728027, "step": 1332 }, { "epoch": 0.18691719834536913, "grad_norm": 3.6380932331085205, "learning_rate": 9.369313790055834e-06, "loss": 0.6676138043403625, "step": 1333 }, { "epoch": 0.1870574212998668, "grad_norm": 5.5653486251831055, "learning_rate": 9.368209439206306e-06, "loss": 0.6059081554412842, "step": 1334 }, { "epoch": 0.18719764425436444, "grad_norm": 3.221433401107788, "learning_rate": 9.367104187528364e-06, "loss": 0.5986562371253967, "step": 1335 }, { "epoch": 0.18733786720886209, "grad_norm": 5.588677406311035, "learning_rate": 9.36599803524994e-06, "loss": 0.5937603116035461, "step": 1336 }, { "epoch": 0.18747809016335973, "grad_norm": 3.3557591438293457, "learning_rate": 9.364890982599146e-06, "loss": 0.5554105043411255, "step": 1337 }, { "epoch": 0.1876183131178574, "grad_norm": 3.838358163833618, "learning_rate": 9.363783029804286e-06, "loss": 0.6416615843772888, "step": 1338 }, { "epoch": 0.18775853607235504, "grad_norm": 5.616988658905029, "learning_rate": 9.362674177093842e-06, "loss": 0.5205994248390198, "step": 1339 }, { "epoch": 0.18789875902685269, "grad_norm": 5.463278293609619, "learning_rate": 9.36156442469649e-06, "loss": 0.6468964219093323, "step": 1340 }, { "epoch": 0.18803898198135036, "grad_norm": 5.264444351196289, "learning_rate": 9.360453772841083e-06, "loss": 0.5939708948135376, "step": 1341 }, { "epoch": 0.188179204935848, "grad_norm": 4.381634712219238, "learning_rate": 9.359342221756668e-06, "loss": 0.5480613708496094, "step": 1342 }, { "epoch": 0.18831942789034564, "grad_norm": 6.476937770843506, "learning_rate": 9.358229771672469e-06, "loss": 0.5927926301956177, "step": 1343 }, { "epoch": 0.1884596508448433, "grad_norm": 4.84950590133667, "learning_rate": 9.357116422817903e-06, "loss": 0.531451940536499, "step": 1344 }, { "epoch": 0.18859987379934096, "grad_norm": 6.144168853759766, "learning_rate": 9.356002175422567e-06, "loss": 0.6733452677726746, "step": 1345 }, { "epoch": 0.1887400967538386, "grad_norm": 5.627596855163574, "learning_rate": 9.354887029716247e-06, "loss": 0.601553201675415, "step": 1346 }, { "epoch": 0.18888031970833624, "grad_norm": 3.8732316493988037, "learning_rate": 9.35377098592891e-06, "loss": 0.5312216877937317, "step": 1347 }, { "epoch": 0.1890205426628339, "grad_norm": 3.6696250438690186, "learning_rate": 9.352654044290713e-06, "loss": 0.5978401899337769, "step": 1348 }, { "epoch": 0.18916076561733156, "grad_norm": 3.670405387878418, "learning_rate": 9.351536205031994e-06, "loss": 0.45268917083740234, "step": 1349 }, { "epoch": 0.1893009885718292, "grad_norm": 4.783669471740723, "learning_rate": 9.350417468383281e-06, "loss": 0.5506709814071655, "step": 1350 }, { "epoch": 0.18944121152632687, "grad_norm": 5.1040873527526855, "learning_rate": 9.34929783457528e-06, "loss": 0.5834834575653076, "step": 1351 }, { "epoch": 0.1895814344808245, "grad_norm": 7.317417144775391, "learning_rate": 9.348177303838887e-06, "loss": 0.6398848295211792, "step": 1352 }, { "epoch": 0.18972165743532216, "grad_norm": 3.560767650604248, "learning_rate": 9.347055876405186e-06, "loss": 0.6015903353691101, "step": 1353 }, { "epoch": 0.18986188038981983, "grad_norm": 13.992892265319824, "learning_rate": 9.345933552505438e-06, "loss": 0.555009126663208, "step": 1354 }, { "epoch": 0.19000210334431747, "grad_norm": 4.725761413574219, "learning_rate": 9.344810332371093e-06, "loss": 0.6345922946929932, "step": 1355 }, { "epoch": 0.1901423262988151, "grad_norm": 3.728435516357422, "learning_rate": 9.343686216233788e-06, "loss": 0.5071033239364624, "step": 1356 }, { "epoch": 0.19028254925331275, "grad_norm": 5.582574367523193, "learning_rate": 9.342561204325337e-06, "loss": 0.5997583270072937, "step": 1357 }, { "epoch": 0.19042277220781043, "grad_norm": 7.338588714599609, "learning_rate": 9.341435296877752e-06, "loss": 0.5771870613098145, "step": 1358 }, { "epoch": 0.19056299516230807, "grad_norm": 4.4502482414245605, "learning_rate": 9.340308494123215e-06, "loss": 0.6449608206748962, "step": 1359 }, { "epoch": 0.1907032181168057, "grad_norm": 10.964690208435059, "learning_rate": 9.339180796294106e-06, "loss": 0.571108877658844, "step": 1360 }, { "epoch": 0.19084344107130338, "grad_norm": 4.896407127380371, "learning_rate": 9.338052203622977e-06, "loss": 0.4970889389514923, "step": 1361 }, { "epoch": 0.19098366402580103, "grad_norm": 7.045510768890381, "learning_rate": 9.33692271634257e-06, "loss": 0.5449931621551514, "step": 1362 }, { "epoch": 0.19112388698029867, "grad_norm": 4.762906551361084, "learning_rate": 9.33579233468582e-06, "loss": 0.5265472531318665, "step": 1363 }, { "epoch": 0.19126410993479634, "grad_norm": 4.385258197784424, "learning_rate": 9.334661058885831e-06, "loss": 0.6692297458648682, "step": 1364 }, { "epoch": 0.19140433288929398, "grad_norm": 3.889979124069214, "learning_rate": 9.333528889175902e-06, "loss": 0.5027930736541748, "step": 1365 }, { "epoch": 0.19154455584379163, "grad_norm": 4.318483829498291, "learning_rate": 9.332395825789512e-06, "loss": 0.5816067457199097, "step": 1366 }, { "epoch": 0.19168477879828927, "grad_norm": 3.89650297164917, "learning_rate": 9.331261868960326e-06, "loss": 0.501684844493866, "step": 1367 }, { "epoch": 0.19182500175278694, "grad_norm": 3.8066680431365967, "learning_rate": 9.330127018922195e-06, "loss": 0.6424583792686462, "step": 1368 }, { "epoch": 0.19196522470728458, "grad_norm": 6.001307487487793, "learning_rate": 9.328991275909146e-06, "loss": 0.6915130615234375, "step": 1369 }, { "epoch": 0.19210544766178222, "grad_norm": 4.098471641540527, "learning_rate": 9.327854640155404e-06, "loss": 0.5573183298110962, "step": 1370 }, { "epoch": 0.1922456706162799, "grad_norm": 4.964448928833008, "learning_rate": 9.326717111895365e-06, "loss": 0.5291941165924072, "step": 1371 }, { "epoch": 0.19238589357077754, "grad_norm": 6.181085109710693, "learning_rate": 9.325578691363615e-06, "loss": 0.5693984627723694, "step": 1372 }, { "epoch": 0.19252611652527518, "grad_norm": 3.3346757888793945, "learning_rate": 9.324439378794925e-06, "loss": 0.5535833835601807, "step": 1373 }, { "epoch": 0.19266633947977285, "grad_norm": 2.732182025909424, "learning_rate": 9.323299174424247e-06, "loss": 0.5128984451293945, "step": 1374 }, { "epoch": 0.1928065624342705, "grad_norm": 3.5890231132507324, "learning_rate": 9.322158078486719e-06, "loss": 0.5049577951431274, "step": 1375 }, { "epoch": 0.19294678538876814, "grad_norm": 3.870637893676758, "learning_rate": 9.32101609121766e-06, "loss": 0.5886310338973999, "step": 1376 }, { "epoch": 0.19308700834326578, "grad_norm": 26.8818302154541, "learning_rate": 9.31987321285258e-06, "loss": 0.6119564175605774, "step": 1377 }, { "epoch": 0.19322723129776345, "grad_norm": 6.809321403503418, "learning_rate": 9.31872944362716e-06, "loss": 0.6228502988815308, "step": 1378 }, { "epoch": 0.1933674542522611, "grad_norm": 3.7230420112609863, "learning_rate": 9.317584783777279e-06, "loss": 0.5198444128036499, "step": 1379 }, { "epoch": 0.19350767720675874, "grad_norm": 4.587908744812012, "learning_rate": 9.316439233538989e-06, "loss": 0.632276177406311, "step": 1380 }, { "epoch": 0.1936479001612564, "grad_norm": 4.4726057052612305, "learning_rate": 9.315292793148531e-06, "loss": 0.5885525941848755, "step": 1381 }, { "epoch": 0.19378812311575405, "grad_norm": 4.057411193847656, "learning_rate": 9.314145462842327e-06, "loss": 0.6014456152915955, "step": 1382 }, { "epoch": 0.1939283460702517, "grad_norm": 5.985547065734863, "learning_rate": 9.312997242856988e-06, "loss": 0.4763683080673218, "step": 1383 }, { "epoch": 0.19406856902474934, "grad_norm": 4.905576705932617, "learning_rate": 9.3118481334293e-06, "loss": 0.5483171939849854, "step": 1384 }, { "epoch": 0.194208791979247, "grad_norm": 7.29706335067749, "learning_rate": 9.310698134796237e-06, "loss": 0.5046655535697937, "step": 1385 }, { "epoch": 0.19434901493374465, "grad_norm": 3.0441031455993652, "learning_rate": 9.30954724719496e-06, "loss": 0.604049563407898, "step": 1386 }, { "epoch": 0.1944892378882423, "grad_norm": 9.944158554077148, "learning_rate": 9.308395470862802e-06, "loss": 0.5809003114700317, "step": 1387 }, { "epoch": 0.19462946084273997, "grad_norm": 5.129439353942871, "learning_rate": 9.30724280603729e-06, "loss": 0.6059343218803406, "step": 1388 }, { "epoch": 0.1947696837972376, "grad_norm": 3.939800500869751, "learning_rate": 9.306089252956136e-06, "loss": 0.6230046153068542, "step": 1389 }, { "epoch": 0.19490990675173525, "grad_norm": 3.4305827617645264, "learning_rate": 9.304934811857222e-06, "loss": 0.5928283929824829, "step": 1390 }, { "epoch": 0.19505012970623292, "grad_norm": 6.6618332862854, "learning_rate": 9.303779482978628e-06, "loss": 0.5554399490356445, "step": 1391 }, { "epoch": 0.19519035266073057, "grad_norm": 4.545046329498291, "learning_rate": 9.302623266558603e-06, "loss": 0.593526303768158, "step": 1392 }, { "epoch": 0.1953305756152282, "grad_norm": 3.9196629524230957, "learning_rate": 9.301466162835593e-06, "loss": 0.6628816723823547, "step": 1393 }, { "epoch": 0.19547079856972585, "grad_norm": 3.795043468475342, "learning_rate": 9.300308172048217e-06, "loss": 0.5561279058456421, "step": 1394 }, { "epoch": 0.19561102152422352, "grad_norm": 3.3377110958099365, "learning_rate": 9.29914929443528e-06, "loss": 0.48294275999069214, "step": 1395 }, { "epoch": 0.19575124447872116, "grad_norm": 20.030858993530273, "learning_rate": 9.297989530235772e-06, "loss": 0.5512053966522217, "step": 1396 }, { "epoch": 0.1958914674332188, "grad_norm": 6.755244255065918, "learning_rate": 9.296828879688861e-06, "loss": 0.5755578875541687, "step": 1397 }, { "epoch": 0.19603169038771648, "grad_norm": 17.31481170654297, "learning_rate": 9.295667343033903e-06, "loss": 0.7265300750732422, "step": 1398 }, { "epoch": 0.19617191334221412, "grad_norm": 2.694002628326416, "learning_rate": 9.294504920510433e-06, "loss": 0.506702721118927, "step": 1399 }, { "epoch": 0.19631213629671176, "grad_norm": 7.846152305603027, "learning_rate": 9.293341612358171e-06, "loss": 0.6620662212371826, "step": 1400 }, { "epoch": 0.19645235925120944, "grad_norm": 3.3166863918304443, "learning_rate": 9.292177418817017e-06, "loss": 0.6284252405166626, "step": 1401 }, { "epoch": 0.19659258220570708, "grad_norm": 4.551250457763672, "learning_rate": 9.291012340127058e-06, "loss": 0.5949904918670654, "step": 1402 }, { "epoch": 0.19673280516020472, "grad_norm": 4.86608362197876, "learning_rate": 9.28984637652856e-06, "loss": 0.5203644037246704, "step": 1403 }, { "epoch": 0.19687302811470236, "grad_norm": 4.86986780166626, "learning_rate": 9.288679528261973e-06, "loss": 0.623314380645752, "step": 1404 }, { "epoch": 0.19701325106920003, "grad_norm": 5.750778675079346, "learning_rate": 9.287511795567927e-06, "loss": 0.5112053155899048, "step": 1405 }, { "epoch": 0.19715347402369768, "grad_norm": 4.572595596313477, "learning_rate": 9.286343178687235e-06, "loss": 0.6701937913894653, "step": 1406 }, { "epoch": 0.19729369697819532, "grad_norm": 4.621781826019287, "learning_rate": 9.2851736778609e-06, "loss": 0.6193345785140991, "step": 1407 }, { "epoch": 0.197433919932693, "grad_norm": 6.166182041168213, "learning_rate": 9.284003293330092e-06, "loss": 0.6472428441047668, "step": 1408 }, { "epoch": 0.19757414288719063, "grad_norm": 3.9309656620025635, "learning_rate": 9.282832025336178e-06, "loss": 0.6537339687347412, "step": 1409 }, { "epoch": 0.19771436584168828, "grad_norm": 3.7393558025360107, "learning_rate": 9.2816598741207e-06, "loss": 0.569203794002533, "step": 1410 }, { "epoch": 0.19785458879618595, "grad_norm": 7.538661956787109, "learning_rate": 9.280486839925382e-06, "loss": 0.5841431021690369, "step": 1411 }, { "epoch": 0.1979948117506836, "grad_norm": 3.8983001708984375, "learning_rate": 9.279312922992133e-06, "loss": 0.6347852945327759, "step": 1412 }, { "epoch": 0.19813503470518123, "grad_norm": 3.0161662101745605, "learning_rate": 9.278138123563043e-06, "loss": 0.6412435173988342, "step": 1413 }, { "epoch": 0.19827525765967888, "grad_norm": 3.539109230041504, "learning_rate": 9.276962441880382e-06, "loss": 0.6814284920692444, "step": 1414 }, { "epoch": 0.19841548061417655, "grad_norm": 3.633164644241333, "learning_rate": 9.275785878186603e-06, "loss": 0.5555980205535889, "step": 1415 }, { "epoch": 0.1985557035686742, "grad_norm": 5.413309097290039, "learning_rate": 9.274608432724343e-06, "loss": 0.6239926815032959, "step": 1416 }, { "epoch": 0.19869592652317183, "grad_norm": 3.4622855186462402, "learning_rate": 9.27343010573642e-06, "loss": 0.6205792427062988, "step": 1417 }, { "epoch": 0.1988361494776695, "grad_norm": 7.297000408172607, "learning_rate": 9.272250897465829e-06, "loss": 0.6302198171615601, "step": 1418 }, { "epoch": 0.19897637243216715, "grad_norm": 2.358466386795044, "learning_rate": 9.271070808155752e-06, "loss": 0.5417373180389404, "step": 1419 }, { "epoch": 0.1991165953866648, "grad_norm": 3.2580766677856445, "learning_rate": 9.269889838049557e-06, "loss": 0.5774085521697998, "step": 1420 }, { "epoch": 0.19925681834116246, "grad_norm": 5.730299472808838, "learning_rate": 9.268707987390781e-06, "loss": 0.5483309030532837, "step": 1421 }, { "epoch": 0.1993970412956601, "grad_norm": 4.8367919921875, "learning_rate": 9.267525256423154e-06, "loss": 0.7322084903717041, "step": 1422 }, { "epoch": 0.19953726425015775, "grad_norm": 4.801534652709961, "learning_rate": 9.26634164539058e-06, "loss": 0.5852625370025635, "step": 1423 }, { "epoch": 0.1996774872046554, "grad_norm": 5.535852432250977, "learning_rate": 9.26515715453715e-06, "loss": 0.6237389445304871, "step": 1424 }, { "epoch": 0.19981771015915306, "grad_norm": 5.829016208648682, "learning_rate": 9.263971784107133e-06, "loss": 0.6428899765014648, "step": 1425 }, { "epoch": 0.1999579331136507, "grad_norm": 5.0222930908203125, "learning_rate": 9.26278553434498e-06, "loss": 0.546302080154419, "step": 1426 }, { "epoch": 0.20009815606814835, "grad_norm": 4.1302809715271, "learning_rate": 9.261598405495325e-06, "loss": 0.6749730110168457, "step": 1427 }, { "epoch": 0.20023837902264602, "grad_norm": 5.476686954498291, "learning_rate": 9.260410397802982e-06, "loss": 0.6384950876235962, "step": 1428 }, { "epoch": 0.20037860197714366, "grad_norm": 5.207214832305908, "learning_rate": 9.259221511512946e-06, "loss": 0.5834940671920776, "step": 1429 }, { "epoch": 0.2005188249316413, "grad_norm": 4.644859313964844, "learning_rate": 9.258031746870393e-06, "loss": 0.5839092135429382, "step": 1430 }, { "epoch": 0.20065904788613897, "grad_norm": 9.384655952453613, "learning_rate": 9.256841104120681e-06, "loss": 0.5695101022720337, "step": 1431 }, { "epoch": 0.20079927084063662, "grad_norm": 5.847767353057861, "learning_rate": 9.255649583509351e-06, "loss": 0.5956271290779114, "step": 1432 }, { "epoch": 0.20093949379513426, "grad_norm": 5.701272010803223, "learning_rate": 9.254457185282121e-06, "loss": 0.534738302230835, "step": 1433 }, { "epoch": 0.2010797167496319, "grad_norm": 4.440701961517334, "learning_rate": 9.253263909684892e-06, "loss": 0.6717388033866882, "step": 1434 }, { "epoch": 0.20121993970412957, "grad_norm": 5.0045270919799805, "learning_rate": 9.252069756963744e-06, "loss": 0.4992671310901642, "step": 1435 }, { "epoch": 0.20136016265862722, "grad_norm": 4.3066205978393555, "learning_rate": 9.250874727364943e-06, "loss": 0.5051549673080444, "step": 1436 }, { "epoch": 0.20150038561312486, "grad_norm": 4.397245407104492, "learning_rate": 9.249678821134929e-06, "loss": 0.5797824263572693, "step": 1437 }, { "epoch": 0.20164060856762253, "grad_norm": 4.50225305557251, "learning_rate": 9.248482038520328e-06, "loss": 0.568932056427002, "step": 1438 }, { "epoch": 0.20178083152212017, "grad_norm": 21.56277847290039, "learning_rate": 9.247284379767945e-06, "loss": 0.6184870004653931, "step": 1439 }, { "epoch": 0.20192105447661782, "grad_norm": 6.395555019378662, "learning_rate": 9.246085845124763e-06, "loss": 0.5533035397529602, "step": 1440 }, { "epoch": 0.20206127743111546, "grad_norm": 3.886991262435913, "learning_rate": 9.244886434837954e-06, "loss": 0.5639400482177734, "step": 1441 }, { "epoch": 0.20220150038561313, "grad_norm": 3.2436397075653076, "learning_rate": 9.243686149154861e-06, "loss": 0.5033146142959595, "step": 1442 }, { "epoch": 0.20234172334011077, "grad_norm": 3.7592437267303467, "learning_rate": 9.242484988323011e-06, "loss": 0.5998951196670532, "step": 1443 }, { "epoch": 0.20248194629460842, "grad_norm": 4.763084888458252, "learning_rate": 9.241282952590113e-06, "loss": 0.5465185046195984, "step": 1444 }, { "epoch": 0.2026221692491061, "grad_norm": 4.07491397857666, "learning_rate": 9.240080042204055e-06, "loss": 0.5414301753044128, "step": 1445 }, { "epoch": 0.20276239220360373, "grad_norm": 5.096684455871582, "learning_rate": 9.238876257412908e-06, "loss": 0.6299874782562256, "step": 1446 }, { "epoch": 0.20290261515810137, "grad_norm": 4.412435054779053, "learning_rate": 9.237671598464917e-06, "loss": 0.4925059974193573, "step": 1447 }, { "epoch": 0.20304283811259904, "grad_norm": 5.126253128051758, "learning_rate": 9.236466065608513e-06, "loss": 0.6562985181808472, "step": 1448 }, { "epoch": 0.2031830610670967, "grad_norm": 11.922284126281738, "learning_rate": 9.235259659092305e-06, "loss": 0.5434558987617493, "step": 1449 }, { "epoch": 0.20332328402159433, "grad_norm": 3.272289514541626, "learning_rate": 9.234052379165084e-06, "loss": 0.5941377878189087, "step": 1450 }, { "epoch": 0.20346350697609197, "grad_norm": 6.010434150695801, "learning_rate": 9.232844226075819e-06, "loss": 0.5613613128662109, "step": 1451 }, { "epoch": 0.20360372993058964, "grad_norm": 3.158586263656616, "learning_rate": 9.231635200073658e-06, "loss": 0.5223912596702576, "step": 1452 }, { "epoch": 0.2037439528850873, "grad_norm": 3.8386032581329346, "learning_rate": 9.230425301407935e-06, "loss": 0.5786624550819397, "step": 1453 }, { "epoch": 0.20388417583958493, "grad_norm": 8.156304359436035, "learning_rate": 9.229214530328156e-06, "loss": 0.5521069765090942, "step": 1454 }, { "epoch": 0.2040243987940826, "grad_norm": 5.933171272277832, "learning_rate": 9.228002887084012e-06, "loss": 0.5572235584259033, "step": 1455 }, { "epoch": 0.20416462174858024, "grad_norm": 2.887497901916504, "learning_rate": 9.226790371925371e-06, "loss": 0.5407679080963135, "step": 1456 }, { "epoch": 0.2043048447030779, "grad_norm": 5.7136549949646, "learning_rate": 9.225576985102287e-06, "loss": 0.5510904788970947, "step": 1457 }, { "epoch": 0.20444506765757556, "grad_norm": 3.212585210800171, "learning_rate": 9.224362726864983e-06, "loss": 0.6256476640701294, "step": 1458 }, { "epoch": 0.2045852906120732, "grad_norm": 3.5306143760681152, "learning_rate": 9.223147597463875e-06, "loss": 0.590111494064331, "step": 1459 }, { "epoch": 0.20472551356657084, "grad_norm": 4.3702497482299805, "learning_rate": 9.221931597149544e-06, "loss": 0.5681729912757874, "step": 1460 }, { "epoch": 0.2048657365210685, "grad_norm": 4.6978654861450195, "learning_rate": 9.220714726172763e-06, "loss": 0.5730395317077637, "step": 1461 }, { "epoch": 0.20500595947556616, "grad_norm": 3.425558090209961, "learning_rate": 9.21949698478448e-06, "loss": 0.6308867335319519, "step": 1462 }, { "epoch": 0.2051461824300638, "grad_norm": 7.073602199554443, "learning_rate": 9.218278373235818e-06, "loss": 0.5987492799758911, "step": 1463 }, { "epoch": 0.20528640538456144, "grad_norm": 8.12198543548584, "learning_rate": 9.217058891778088e-06, "loss": 0.49627697467803955, "step": 1464 }, { "epoch": 0.20542662833905911, "grad_norm": 6.952799320220947, "learning_rate": 9.215838540662771e-06, "loss": 0.6064100861549377, "step": 1465 }, { "epoch": 0.20556685129355676, "grad_norm": 3.081209659576416, "learning_rate": 9.214617320141538e-06, "loss": 0.5480146408081055, "step": 1466 }, { "epoch": 0.2057070742480544, "grad_norm": 5.310032367706299, "learning_rate": 9.21339523046623e-06, "loss": 0.6270822286605835, "step": 1467 }, { "epoch": 0.20584729720255207, "grad_norm": 3.678839921951294, "learning_rate": 9.212172271888873e-06, "loss": 0.5510762333869934, "step": 1468 }, { "epoch": 0.2059875201570497, "grad_norm": 6.32806921005249, "learning_rate": 9.210948444661668e-06, "loss": 0.6152744293212891, "step": 1469 }, { "epoch": 0.20612774311154736, "grad_norm": 6.603895664215088, "learning_rate": 9.209723749037e-06, "loss": 0.6200268268585205, "step": 1470 }, { "epoch": 0.206267966066045, "grad_norm": 3.790811538696289, "learning_rate": 9.208498185267427e-06, "loss": 0.6102851629257202, "step": 1471 }, { "epoch": 0.20640818902054267, "grad_norm": 4.352331161499023, "learning_rate": 9.207271753605692e-06, "loss": 0.5759134292602539, "step": 1472 }, { "epoch": 0.2065484119750403, "grad_norm": 3.3842408657073975, "learning_rate": 9.206044454304712e-06, "loss": 0.6101294755935669, "step": 1473 }, { "epoch": 0.20668863492953796, "grad_norm": 11.176058769226074, "learning_rate": 9.204816287617587e-06, "loss": 0.5584046840667725, "step": 1474 }, { "epoch": 0.20682885788403563, "grad_norm": 7.4031829833984375, "learning_rate": 9.203587253797594e-06, "loss": 0.6267421245574951, "step": 1475 }, { "epoch": 0.20696908083853327, "grad_norm": 5.9447197914123535, "learning_rate": 9.202357353098187e-06, "loss": 0.5633171796798706, "step": 1476 }, { "epoch": 0.2071093037930309, "grad_norm": 7.589816093444824, "learning_rate": 9.201126585773004e-06, "loss": 0.6071297526359558, "step": 1477 }, { "epoch": 0.20724952674752858, "grad_norm": 5.0357255935668945, "learning_rate": 9.199894952075854e-06, "loss": 0.5229843258857727, "step": 1478 }, { "epoch": 0.20738974970202623, "grad_norm": 5.05228328704834, "learning_rate": 9.198662452260733e-06, "loss": 0.5782996416091919, "step": 1479 }, { "epoch": 0.20752997265652387, "grad_norm": 4.484042644500732, "learning_rate": 9.197429086581811e-06, "loss": 0.6989455819129944, "step": 1480 }, { "epoch": 0.2076701956110215, "grad_norm": 5.4495625495910645, "learning_rate": 9.196194855293437e-06, "loss": 0.5290770530700684, "step": 1481 }, { "epoch": 0.20781041856551918, "grad_norm": 4.35490083694458, "learning_rate": 9.194959758650137e-06, "loss": 0.5589605569839478, "step": 1482 }, { "epoch": 0.20795064152001683, "grad_norm": 4.7822184562683105, "learning_rate": 9.19372379690662e-06, "loss": 0.6148603558540344, "step": 1483 }, { "epoch": 0.20809086447451447, "grad_norm": 2.9403347969055176, "learning_rate": 9.192486970317767e-06, "loss": 0.5482606887817383, "step": 1484 }, { "epoch": 0.20823108742901214, "grad_norm": 3.9857394695281982, "learning_rate": 9.191249279138644e-06, "loss": 0.5615280866622925, "step": 1485 }, { "epoch": 0.20837131038350978, "grad_norm": 8.003133773803711, "learning_rate": 9.190010723624491e-06, "loss": 0.5748369097709656, "step": 1486 }, { "epoch": 0.20851153333800743, "grad_norm": 5.805113315582275, "learning_rate": 9.18877130403073e-06, "loss": 0.43141838908195496, "step": 1487 }, { "epoch": 0.20865175629250507, "grad_norm": 4.512613296508789, "learning_rate": 9.187531020612955e-06, "loss": 0.597165584564209, "step": 1488 }, { "epoch": 0.20879197924700274, "grad_norm": 4.991091251373291, "learning_rate": 9.186289873626945e-06, "loss": 0.48903316259384155, "step": 1489 }, { "epoch": 0.20893220220150038, "grad_norm": 7.778926849365234, "learning_rate": 9.185047863328651e-06, "loss": 0.5789883136749268, "step": 1490 }, { "epoch": 0.20907242515599803, "grad_norm": 4.1543049812316895, "learning_rate": 9.183804989974208e-06, "loss": 0.6242262125015259, "step": 1491 }, { "epoch": 0.2092126481104957, "grad_norm": 5.941253662109375, "learning_rate": 9.182561253819924e-06, "loss": 0.5297176837921143, "step": 1492 }, { "epoch": 0.20935287106499334, "grad_norm": 4.4606451988220215, "learning_rate": 9.181316655122288e-06, "loss": 0.4889439642429352, "step": 1493 }, { "epoch": 0.20949309401949098, "grad_norm": 5.37099552154541, "learning_rate": 9.180071194137964e-06, "loss": 0.5417282581329346, "step": 1494 }, { "epoch": 0.20963331697398865, "grad_norm": 4.172370910644531, "learning_rate": 9.178824871123797e-06, "loss": 0.61602783203125, "step": 1495 }, { "epoch": 0.2097735399284863, "grad_norm": 5.133241653442383, "learning_rate": 9.177577686336808e-06, "loss": 0.6652053594589233, "step": 1496 }, { "epoch": 0.20991376288298394, "grad_norm": 6.5402936935424805, "learning_rate": 9.176329640034197e-06, "loss": 0.728238582611084, "step": 1497 }, { "epoch": 0.21005398583748158, "grad_norm": 6.132897853851318, "learning_rate": 9.17508073247334e-06, "loss": 0.5589501857757568, "step": 1498 }, { "epoch": 0.21019420879197925, "grad_norm": 3.812042236328125, "learning_rate": 9.173830963911792e-06, "loss": 0.5159799456596375, "step": 1499 }, { "epoch": 0.2103344317464769, "grad_norm": 3.7804925441741943, "learning_rate": 9.172580334607282e-06, "loss": 0.5886713862419128, "step": 1500 }, { "epoch": 0.21047465470097454, "grad_norm": 4.942094326019287, "learning_rate": 9.171328844817724e-06, "loss": 0.5826258659362793, "step": 1501 }, { "epoch": 0.2106148776554722, "grad_norm": 4.186686038970947, "learning_rate": 9.170076494801201e-06, "loss": 0.6572044491767883, "step": 1502 }, { "epoch": 0.21075510060996985, "grad_norm": 3.224085807800293, "learning_rate": 9.168823284815981e-06, "loss": 0.5827405452728271, "step": 1503 }, { "epoch": 0.2108953235644675, "grad_norm": 4.484842777252197, "learning_rate": 9.167569215120502e-06, "loss": 0.5471629500389099, "step": 1504 }, { "epoch": 0.21103554651896517, "grad_norm": 5.871079444885254, "learning_rate": 9.166314285973384e-06, "loss": 0.6326521635055542, "step": 1505 }, { "epoch": 0.2111757694734628, "grad_norm": 3.430741310119629, "learning_rate": 9.165058497633425e-06, "loss": 0.6950533390045166, "step": 1506 }, { "epoch": 0.21131599242796045, "grad_norm": 7.434078693389893, "learning_rate": 9.163801850359596e-06, "loss": 0.5903252959251404, "step": 1507 }, { "epoch": 0.2114562153824581, "grad_norm": 5.7675323486328125, "learning_rate": 9.162544344411048e-06, "loss": 0.5636942982673645, "step": 1508 }, { "epoch": 0.21159643833695577, "grad_norm": 3.0023796558380127, "learning_rate": 9.16128598004711e-06, "loss": 0.6216515302658081, "step": 1509 }, { "epoch": 0.2117366612914534, "grad_norm": 9.71866226196289, "learning_rate": 9.160026757527286e-06, "loss": 0.5877793431282043, "step": 1510 }, { "epoch": 0.21187688424595105, "grad_norm": 4.507070541381836, "learning_rate": 9.158766677111257e-06, "loss": 0.6200597882270813, "step": 1511 }, { "epoch": 0.21201710720044872, "grad_norm": 3.485896348953247, "learning_rate": 9.157505739058881e-06, "loss": 0.5574387311935425, "step": 1512 }, { "epoch": 0.21215733015494637, "grad_norm": 3.7309489250183105, "learning_rate": 9.156243943630194e-06, "loss": 0.6425981521606445, "step": 1513 }, { "epoch": 0.212297553109444, "grad_norm": 3.341569185256958, "learning_rate": 9.154981291085408e-06, "loss": 0.4448619484901428, "step": 1514 }, { "epoch": 0.21243777606394168, "grad_norm": 3.1165125370025635, "learning_rate": 9.153717781684913e-06, "loss": 0.6111419200897217, "step": 1515 }, { "epoch": 0.21257799901843932, "grad_norm": 2.6528377532958984, "learning_rate": 9.152453415689272e-06, "loss": 0.6913496255874634, "step": 1516 }, { "epoch": 0.21271822197293697, "grad_norm": 4.26411247253418, "learning_rate": 9.151188193359228e-06, "loss": 0.5632835030555725, "step": 1517 }, { "epoch": 0.2128584449274346, "grad_norm": 4.456014633178711, "learning_rate": 9.149922114955704e-06, "loss": 0.5705761313438416, "step": 1518 }, { "epoch": 0.21299866788193228, "grad_norm": 5.542660713195801, "learning_rate": 9.14865518073979e-06, "loss": 0.5856070518493652, "step": 1519 }, { "epoch": 0.21313889083642992, "grad_norm": 4.442028045654297, "learning_rate": 9.14738739097276e-06, "loss": 0.4867997169494629, "step": 1520 }, { "epoch": 0.21327911379092757, "grad_norm": 4.265754222869873, "learning_rate": 9.146118745916065e-06, "loss": 0.6056424975395203, "step": 1521 }, { "epoch": 0.21341933674542524, "grad_norm": 9.314237594604492, "learning_rate": 9.144849245831323e-06, "loss": 0.5183282494544983, "step": 1522 }, { "epoch": 0.21355955969992288, "grad_norm": 3.7316019535064697, "learning_rate": 9.143578890980342e-06, "loss": 0.5344526767730713, "step": 1523 }, { "epoch": 0.21369978265442052, "grad_norm": 3.6513161659240723, "learning_rate": 9.142307681625095e-06, "loss": 0.64890056848526, "step": 1524 }, { "epoch": 0.2138400056089182, "grad_norm": 3.619161367416382, "learning_rate": 9.141035618027737e-06, "loss": 0.6189275979995728, "step": 1525 }, { "epoch": 0.21398022856341584, "grad_norm": 3.2916641235351562, "learning_rate": 9.139762700450599e-06, "loss": 0.6358059048652649, "step": 1526 }, { "epoch": 0.21412045151791348, "grad_norm": 3.8855140209198, "learning_rate": 9.138488929156184e-06, "loss": 0.6527522802352905, "step": 1527 }, { "epoch": 0.21426067447241112, "grad_norm": 3.617724895477295, "learning_rate": 9.137214304407176e-06, "loss": 0.5751814246177673, "step": 1528 }, { "epoch": 0.2144008974269088, "grad_norm": 8.078729629516602, "learning_rate": 9.135938826466432e-06, "loss": 0.6120302677154541, "step": 1529 }, { "epoch": 0.21454112038140644, "grad_norm": 4.029226779937744, "learning_rate": 9.134662495596987e-06, "loss": 0.5838061571121216, "step": 1530 }, { "epoch": 0.21468134333590408, "grad_norm": 4.922122478485107, "learning_rate": 9.133385312062047e-06, "loss": 0.6042060852050781, "step": 1531 }, { "epoch": 0.21482156629040175, "grad_norm": 3.6703109741210938, "learning_rate": 9.132107276125002e-06, "loss": 0.49395230412483215, "step": 1532 }, { "epoch": 0.2149617892448994, "grad_norm": 3.240971326828003, "learning_rate": 9.13082838804941e-06, "loss": 0.5114603638648987, "step": 1533 }, { "epoch": 0.21510201219939704, "grad_norm": 2.8677430152893066, "learning_rate": 9.129548648099012e-06, "loss": 0.6915218830108643, "step": 1534 }, { "epoch": 0.21524223515389468, "grad_norm": 4.470846176147461, "learning_rate": 9.128268056537717e-06, "loss": 0.6088858842849731, "step": 1535 }, { "epoch": 0.21538245810839235, "grad_norm": 3.976412057876587, "learning_rate": 9.126986613629616e-06, "loss": 0.5377830266952515, "step": 1536 }, { "epoch": 0.21552268106289, "grad_norm": 9.949728965759277, "learning_rate": 9.125704319638971e-06, "loss": 0.5886582136154175, "step": 1537 }, { "epoch": 0.21566290401738764, "grad_norm": 3.643277645111084, "learning_rate": 9.12442117483022e-06, "loss": 0.615954577922821, "step": 1538 }, { "epoch": 0.2158031269718853, "grad_norm": 3.1924185752868652, "learning_rate": 9.123137179467983e-06, "loss": 0.6137266755104065, "step": 1539 }, { "epoch": 0.21594334992638295, "grad_norm": 3.257405996322632, "learning_rate": 9.121852333817045e-06, "loss": 0.5911160707473755, "step": 1540 }, { "epoch": 0.2160835728808806, "grad_norm": 4.141968727111816, "learning_rate": 9.120566638142373e-06, "loss": 0.5390908718109131, "step": 1541 }, { "epoch": 0.21622379583537826, "grad_norm": 8.625919342041016, "learning_rate": 9.119280092709113e-06, "loss": 0.6080214977264404, "step": 1542 }, { "epoch": 0.2163640187898759, "grad_norm": 4.72654390335083, "learning_rate": 9.117992697782574e-06, "loss": 0.5911881327629089, "step": 1543 }, { "epoch": 0.21650424174437355, "grad_norm": 4.154613018035889, "learning_rate": 9.11670445362825e-06, "loss": 0.6106699705123901, "step": 1544 }, { "epoch": 0.2166444646988712, "grad_norm": 2.9632785320281982, "learning_rate": 9.11541536051181e-06, "loss": 0.4862573742866516, "step": 1545 }, { "epoch": 0.21678468765336886, "grad_norm": 3.9304823875427246, "learning_rate": 9.114125418699092e-06, "loss": 0.6306127309799194, "step": 1546 }, { "epoch": 0.2169249106078665, "grad_norm": 3.5792901515960693, "learning_rate": 9.112834628456114e-06, "loss": 0.512171745300293, "step": 1547 }, { "epoch": 0.21706513356236415, "grad_norm": 12.54033088684082, "learning_rate": 9.111542990049069e-06, "loss": 0.5071094036102295, "step": 1548 }, { "epoch": 0.21720535651686182, "grad_norm": 3.077291965484619, "learning_rate": 9.11025050374432e-06, "loss": 0.542259931564331, "step": 1549 }, { "epoch": 0.21734557947135946, "grad_norm": 3.6374857425689697, "learning_rate": 9.108957169808413e-06, "loss": 0.5846565961837769, "step": 1550 }, { "epoch": 0.2174858024258571, "grad_norm": 3.9634034633636475, "learning_rate": 9.10766298850806e-06, "loss": 0.5049611926078796, "step": 1551 }, { "epoch": 0.21762602538035478, "grad_norm": 6.820105075836182, "learning_rate": 9.106367960110155e-06, "loss": 0.5131992697715759, "step": 1552 }, { "epoch": 0.21776624833485242, "grad_norm": 3.8811092376708984, "learning_rate": 9.105072084881762e-06, "loss": 0.6475578546524048, "step": 1553 }, { "epoch": 0.21790647128935006, "grad_norm": 4.534228801727295, "learning_rate": 9.10377536309012e-06, "loss": 0.7012125253677368, "step": 1554 }, { "epoch": 0.2180466942438477, "grad_norm": 4.505533695220947, "learning_rate": 9.102477795002644e-06, "loss": 0.47027841210365295, "step": 1555 }, { "epoch": 0.21818691719834538, "grad_norm": 8.741999626159668, "learning_rate": 9.101179380886926e-06, "loss": 0.5355714559555054, "step": 1556 }, { "epoch": 0.21832714015284302, "grad_norm": 3.522260904312134, "learning_rate": 9.09988012101073e-06, "loss": 0.594054102897644, "step": 1557 }, { "epoch": 0.21846736310734066, "grad_norm": 2.692099094390869, "learning_rate": 9.09858001564199e-06, "loss": 0.5481730103492737, "step": 1558 }, { "epoch": 0.21860758606183833, "grad_norm": 4.258490085601807, "learning_rate": 9.097279065048821e-06, "loss": 0.5783334970474243, "step": 1559 }, { "epoch": 0.21874780901633598, "grad_norm": 8.782188415527344, "learning_rate": 9.09597726949951e-06, "loss": 0.5755483508110046, "step": 1560 }, { "epoch": 0.21888803197083362, "grad_norm": 3.4761035442352295, "learning_rate": 9.09467462926252e-06, "loss": 0.47370243072509766, "step": 1561 }, { "epoch": 0.2190282549253313, "grad_norm": 5.60128927230835, "learning_rate": 9.093371144606482e-06, "loss": 0.5572060942649841, "step": 1562 }, { "epoch": 0.21916847787982893, "grad_norm": 4.192512512207031, "learning_rate": 9.092066815800209e-06, "loss": 0.6038615107536316, "step": 1563 }, { "epoch": 0.21930870083432658, "grad_norm": 4.164246559143066, "learning_rate": 9.090761643112682e-06, "loss": 0.5714491605758667, "step": 1564 }, { "epoch": 0.21944892378882422, "grad_norm": 4.189786911010742, "learning_rate": 9.089455626813062e-06, "loss": 0.5777188539505005, "step": 1565 }, { "epoch": 0.2195891467433219, "grad_norm": 3.5664572715759277, "learning_rate": 9.088148767170676e-06, "loss": 0.5209677219390869, "step": 1566 }, { "epoch": 0.21972936969781953, "grad_norm": 5.210649013519287, "learning_rate": 9.086841064455034e-06, "loss": 0.5618607997894287, "step": 1567 }, { "epoch": 0.21986959265231718, "grad_norm": 4.042819023132324, "learning_rate": 9.085532518935813e-06, "loss": 0.520734429359436, "step": 1568 }, { "epoch": 0.22000981560681485, "grad_norm": 18.574573516845703, "learning_rate": 9.084223130882865e-06, "loss": 0.6262537837028503, "step": 1569 }, { "epoch": 0.2201500385613125, "grad_norm": 4.661703109741211, "learning_rate": 9.08291290056622e-06, "loss": 0.5948489904403687, "step": 1570 }, { "epoch": 0.22029026151581013, "grad_norm": 3.448601245880127, "learning_rate": 9.081601828256074e-06, "loss": 0.6151673793792725, "step": 1571 }, { "epoch": 0.2204304844703078, "grad_norm": 3.460286855697632, "learning_rate": 9.080289914222806e-06, "loss": 0.6575862765312195, "step": 1572 }, { "epoch": 0.22057070742480545, "grad_norm": 3.9258410930633545, "learning_rate": 9.078977158736964e-06, "loss": 0.4628080129623413, "step": 1573 }, { "epoch": 0.2207109303793031, "grad_norm": 3.8462393283843994, "learning_rate": 9.077663562069263e-06, "loss": 0.6475107669830322, "step": 1574 }, { "epoch": 0.22085115333380073, "grad_norm": 3.7221314907073975, "learning_rate": 9.076349124490605e-06, "loss": 0.4819812774658203, "step": 1575 }, { "epoch": 0.2209913762882984, "grad_norm": 5.49155855178833, "learning_rate": 9.075033846272053e-06, "loss": 0.5870974063873291, "step": 1576 }, { "epoch": 0.22113159924279605, "grad_norm": 7.453122615814209, "learning_rate": 9.073717727684852e-06, "loss": 0.6307589411735535, "step": 1577 }, { "epoch": 0.2212718221972937, "grad_norm": 14.039101600646973, "learning_rate": 9.072400769000415e-06, "loss": 0.5355660319328308, "step": 1578 }, { "epoch": 0.22141204515179136, "grad_norm": 4.553247928619385, "learning_rate": 9.07108297049033e-06, "loss": 0.638128936290741, "step": 1579 }, { "epoch": 0.221552268106289, "grad_norm": 3.297060251235962, "learning_rate": 9.069764332426361e-06, "loss": 0.591349184513092, "step": 1580 }, { "epoch": 0.22169249106078665, "grad_norm": 8.584835052490234, "learning_rate": 9.068444855080438e-06, "loss": 0.6551046371459961, "step": 1581 }, { "epoch": 0.22183271401528432, "grad_norm": 5.393617630004883, "learning_rate": 9.067124538724673e-06, "loss": 0.6068919897079468, "step": 1582 }, { "epoch": 0.22197293696978196, "grad_norm": 6.541913032531738, "learning_rate": 9.065803383631344e-06, "loss": 0.5654501914978027, "step": 1583 }, { "epoch": 0.2221131599242796, "grad_norm": 3.679685354232788, "learning_rate": 9.064481390072905e-06, "loss": 0.5891593098640442, "step": 1584 }, { "epoch": 0.22225338287877724, "grad_norm": 3.1264004707336426, "learning_rate": 9.063158558321982e-06, "loss": 0.5495917201042175, "step": 1585 }, { "epoch": 0.22239360583327492, "grad_norm": 3.2642202377319336, "learning_rate": 9.061834888651376e-06, "loss": 0.513137698173523, "step": 1586 }, { "epoch": 0.22253382878777256, "grad_norm": 2.9239659309387207, "learning_rate": 9.060510381334056e-06, "loss": 0.5928494334220886, "step": 1587 }, { "epoch": 0.2226740517422702, "grad_norm": 3.1424672603607178, "learning_rate": 9.05918503664317e-06, "loss": 0.5745271444320679, "step": 1588 }, { "epoch": 0.22281427469676787, "grad_norm": 5.6060943603515625, "learning_rate": 9.057858854852036e-06, "loss": 0.6425158977508545, "step": 1589 }, { "epoch": 0.22295449765126552, "grad_norm": 5.1078572273254395, "learning_rate": 9.05653183623414e-06, "loss": 0.5498658418655396, "step": 1590 }, { "epoch": 0.22309472060576316, "grad_norm": 2.680309534072876, "learning_rate": 9.055203981063147e-06, "loss": 0.5429998636245728, "step": 1591 }, { "epoch": 0.2232349435602608, "grad_norm": 4.024084091186523, "learning_rate": 9.053875289612892e-06, "loss": 0.5698997974395752, "step": 1592 }, { "epoch": 0.22337516651475847, "grad_norm": 4.5133466720581055, "learning_rate": 9.052545762157385e-06, "loss": 0.550398588180542, "step": 1593 }, { "epoch": 0.22351538946925611, "grad_norm": 5.887524127960205, "learning_rate": 9.051215398970802e-06, "loss": 0.6294881105422974, "step": 1594 }, { "epoch": 0.22365561242375376, "grad_norm": 3.066638708114624, "learning_rate": 9.0498842003275e-06, "loss": 0.49191153049468994, "step": 1595 }, { "epoch": 0.22379583537825143, "grad_norm": 3.734541177749634, "learning_rate": 9.048552166501999e-06, "loss": 0.5694756507873535, "step": 1596 }, { "epoch": 0.22393605833274907, "grad_norm": 4.046620845794678, "learning_rate": 9.047219297768999e-06, "loss": 0.6446696519851685, "step": 1597 }, { "epoch": 0.22407628128724671, "grad_norm": 4.031521797180176, "learning_rate": 9.04588559440337e-06, "loss": 0.5776305198669434, "step": 1598 }, { "epoch": 0.22421650424174439, "grad_norm": 3.4057252407073975, "learning_rate": 9.044551056680149e-06, "loss": 0.5740759968757629, "step": 1599 }, { "epoch": 0.22435672719624203, "grad_norm": 5.868136882781982, "learning_rate": 9.043215684874554e-06, "loss": 0.5888751745223999, "step": 1600 }, { "epoch": 0.22449695015073967, "grad_norm": 12.821599960327148, "learning_rate": 9.041879479261968e-06, "loss": 0.5961402058601379, "step": 1601 }, { "epoch": 0.22463717310523731, "grad_norm": 2.806835889816284, "learning_rate": 9.040542440117948e-06, "loss": 0.5528397560119629, "step": 1602 }, { "epoch": 0.22477739605973499, "grad_norm": 5.658702850341797, "learning_rate": 9.039204567718225e-06, "loss": 0.5214007496833801, "step": 1603 }, { "epoch": 0.22491761901423263, "grad_norm": 4.137579917907715, "learning_rate": 9.037865862338697e-06, "loss": 0.545019268989563, "step": 1604 }, { "epoch": 0.22505784196873027, "grad_norm": 8.997828483581543, "learning_rate": 9.03652632425544e-06, "loss": 0.4564507007598877, "step": 1605 }, { "epoch": 0.22519806492322794, "grad_norm": 5.056643962860107, "learning_rate": 9.0351859537447e-06, "loss": 0.6000811457633972, "step": 1606 }, { "epoch": 0.22533828787772558, "grad_norm": 6.666529655456543, "learning_rate": 9.033844751082886e-06, "loss": 0.6118102669715881, "step": 1607 }, { "epoch": 0.22547851083222323, "grad_norm": 3.4217758178710938, "learning_rate": 9.032502716546593e-06, "loss": 0.584175705909729, "step": 1608 }, { "epoch": 0.2256187337867209, "grad_norm": 5.676005840301514, "learning_rate": 9.031159850412577e-06, "loss": 0.6978840827941895, "step": 1609 }, { "epoch": 0.22575895674121854, "grad_norm": 6.610410213470459, "learning_rate": 9.029816152957769e-06, "loss": 0.5302653908729553, "step": 1610 }, { "epoch": 0.22589917969571618, "grad_norm": 3.26178240776062, "learning_rate": 9.028471624459271e-06, "loss": 0.5798341631889343, "step": 1611 }, { "epoch": 0.22603940265021383, "grad_norm": 7.720007419586182, "learning_rate": 9.027126265194359e-06, "loss": 0.5653817653656006, "step": 1612 }, { "epoch": 0.2261796256047115, "grad_norm": 3.713864326477051, "learning_rate": 9.025780075440476e-06, "loss": 0.6452080607414246, "step": 1613 }, { "epoch": 0.22631984855920914, "grad_norm": 3.76271390914917, "learning_rate": 9.024433055475239e-06, "loss": 0.5412168502807617, "step": 1614 }, { "epoch": 0.22646007151370678, "grad_norm": 3.415771245956421, "learning_rate": 9.023085205576434e-06, "loss": 0.6448614597320557, "step": 1615 }, { "epoch": 0.22660029446820446, "grad_norm": 3.4788360595703125, "learning_rate": 9.02173652602202e-06, "loss": 0.7079548835754395, "step": 1616 }, { "epoch": 0.2267405174227021, "grad_norm": 3.0522356033325195, "learning_rate": 9.02038701709013e-06, "loss": 0.555153489112854, "step": 1617 }, { "epoch": 0.22688074037719974, "grad_norm": 4.67995548248291, "learning_rate": 9.019036679059061e-06, "loss": 0.6046908497810364, "step": 1618 }, { "epoch": 0.2270209633316974, "grad_norm": 2.4945621490478516, "learning_rate": 9.017685512207287e-06, "loss": 0.5366849303245544, "step": 1619 }, { "epoch": 0.22716118628619505, "grad_norm": 3.719879388809204, "learning_rate": 9.016333516813447e-06, "loss": 0.5372419357299805, "step": 1620 }, { "epoch": 0.2273014092406927, "grad_norm": 3.5928070545196533, "learning_rate": 9.014980693156359e-06, "loss": 0.6001389026641846, "step": 1621 }, { "epoch": 0.22744163219519034, "grad_norm": 4.650298595428467, "learning_rate": 9.013627041515006e-06, "loss": 0.6264156103134155, "step": 1622 }, { "epoch": 0.227581855149688, "grad_norm": 3.374641180038452, "learning_rate": 9.012272562168542e-06, "loss": 0.6445906162261963, "step": 1623 }, { "epoch": 0.22772207810418565, "grad_norm": 3.545225143432617, "learning_rate": 9.010917255396294e-06, "loss": 0.5130384564399719, "step": 1624 }, { "epoch": 0.2278623010586833, "grad_norm": 3.362898111343384, "learning_rate": 9.009561121477756e-06, "loss": 0.532903790473938, "step": 1625 }, { "epoch": 0.22800252401318097, "grad_norm": 2.6048808097839355, "learning_rate": 9.0082041606926e-06, "loss": 0.5852770805358887, "step": 1626 }, { "epoch": 0.2281427469676786, "grad_norm": 3.7174108028411865, "learning_rate": 9.006846373320656e-06, "loss": 0.4730488061904907, "step": 1627 }, { "epoch": 0.22828296992217625, "grad_norm": 8.517419815063477, "learning_rate": 9.00548775964194e-06, "loss": 0.6002182960510254, "step": 1628 }, { "epoch": 0.22842319287667393, "grad_norm": 9.095056533813477, "learning_rate": 9.004128319936625e-06, "loss": 0.6195926070213318, "step": 1629 }, { "epoch": 0.22856341583117157, "grad_norm": 2.800435781478882, "learning_rate": 9.002768054485061e-06, "loss": 0.6079263687133789, "step": 1630 }, { "epoch": 0.2287036387856692, "grad_norm": 2.85184645652771, "learning_rate": 9.001406963567769e-06, "loss": 0.572331428527832, "step": 1631 }, { "epoch": 0.22884386174016685, "grad_norm": 5.721145153045654, "learning_rate": 9.000045047465434e-06, "loss": 0.6397566199302673, "step": 1632 }, { "epoch": 0.22898408469466452, "grad_norm": 4.709108352661133, "learning_rate": 8.998682306458919e-06, "loss": 0.6492569446563721, "step": 1633 }, { "epoch": 0.22912430764916217, "grad_norm": 5.879225730895996, "learning_rate": 8.997318740829253e-06, "loss": 0.39832812547683716, "step": 1634 }, { "epoch": 0.2292645306036598, "grad_norm": 4.3752055168151855, "learning_rate": 8.995954350857636e-06, "loss": 0.6171889305114746, "step": 1635 }, { "epoch": 0.22940475355815748, "grad_norm": 4.27247953414917, "learning_rate": 8.994589136825435e-06, "loss": 0.6916970014572144, "step": 1636 }, { "epoch": 0.22954497651265512, "grad_norm": 6.4716572761535645, "learning_rate": 8.993223099014191e-06, "loss": 0.6575666666030884, "step": 1637 }, { "epoch": 0.22968519946715277, "grad_norm": 7.070562839508057, "learning_rate": 8.991856237705615e-06, "loss": 0.6509618163108826, "step": 1638 }, { "epoch": 0.2298254224216504, "grad_norm": 4.736139297485352, "learning_rate": 8.990488553181584e-06, "loss": 0.6375766396522522, "step": 1639 }, { "epoch": 0.22996564537614808, "grad_norm": 5.003106117248535, "learning_rate": 8.989120045724146e-06, "loss": 0.6528133153915405, "step": 1640 }, { "epoch": 0.23010586833064572, "grad_norm": 2.7850987911224365, "learning_rate": 8.987750715615523e-06, "loss": 0.452060729265213, "step": 1641 }, { "epoch": 0.23024609128514337, "grad_norm": 4.0280866622924805, "learning_rate": 8.986380563138104e-06, "loss": 0.565694272518158, "step": 1642 }, { "epoch": 0.23038631423964104, "grad_norm": 3.583322525024414, "learning_rate": 8.985009588574442e-06, "loss": 0.555536150932312, "step": 1643 }, { "epoch": 0.23052653719413868, "grad_norm": 4.142464637756348, "learning_rate": 8.983637792207269e-06, "loss": 0.5231039524078369, "step": 1644 }, { "epoch": 0.23066676014863632, "grad_norm": 3.5039968490600586, "learning_rate": 8.982265174319478e-06, "loss": 0.551929771900177, "step": 1645 }, { "epoch": 0.230806983103134, "grad_norm": 5.0975022315979, "learning_rate": 8.98089173519414e-06, "loss": 0.6020686030387878, "step": 1646 }, { "epoch": 0.23094720605763164, "grad_norm": 3.9118661880493164, "learning_rate": 8.979517475114488e-06, "loss": 0.5998690724372864, "step": 1647 }, { "epoch": 0.23108742901212928, "grad_norm": 3.498650074005127, "learning_rate": 8.978142394363925e-06, "loss": 0.5506186485290527, "step": 1648 }, { "epoch": 0.23122765196662692, "grad_norm": 3.493351697921753, "learning_rate": 8.97676649322603e-06, "loss": 0.5754700899124146, "step": 1649 }, { "epoch": 0.2313678749211246, "grad_norm": 3.85316801071167, "learning_rate": 8.975389771984544e-06, "loss": 0.5876168012619019, "step": 1650 }, { "epoch": 0.23150809787562224, "grad_norm": 6.133416652679443, "learning_rate": 8.974012230923379e-06, "loss": 0.6182310581207275, "step": 1651 }, { "epoch": 0.23164832083011988, "grad_norm": 3.645988941192627, "learning_rate": 8.972633870326617e-06, "loss": 0.6150146722793579, "step": 1652 }, { "epoch": 0.23178854378461755, "grad_norm": 3.608891725540161, "learning_rate": 8.97125469047851e-06, "loss": 0.6064102649688721, "step": 1653 }, { "epoch": 0.2319287667391152, "grad_norm": 3.8874847888946533, "learning_rate": 8.969874691663477e-06, "loss": 0.44977867603302, "step": 1654 }, { "epoch": 0.23206898969361284, "grad_norm": 3.395632266998291, "learning_rate": 8.968493874166104e-06, "loss": 0.6001648902893066, "step": 1655 }, { "epoch": 0.2322092126481105, "grad_norm": 4.2455620765686035, "learning_rate": 8.967112238271151e-06, "loss": 0.66921067237854, "step": 1656 }, { "epoch": 0.23234943560260815, "grad_norm": 3.48742938041687, "learning_rate": 8.965729784263544e-06, "loss": 0.6494287252426147, "step": 1657 }, { "epoch": 0.2324896585571058, "grad_norm": 3.397998809814453, "learning_rate": 8.964346512428378e-06, "loss": 0.6825108528137207, "step": 1658 }, { "epoch": 0.23262988151160344, "grad_norm": 4.241802215576172, "learning_rate": 8.962962423050914e-06, "loss": 0.6113992929458618, "step": 1659 }, { "epoch": 0.2327701044661011, "grad_norm": 3.7450549602508545, "learning_rate": 8.961577516416587e-06, "loss": 0.5004172921180725, "step": 1660 }, { "epoch": 0.23291032742059875, "grad_norm": 4.950796127319336, "learning_rate": 8.960191792810995e-06, "loss": 0.6047247052192688, "step": 1661 }, { "epoch": 0.2330505503750964, "grad_norm": 2.942168951034546, "learning_rate": 8.95880525251991e-06, "loss": 0.6896801590919495, "step": 1662 }, { "epoch": 0.23319077332959406, "grad_norm": 4.564914226531982, "learning_rate": 8.957417895829268e-06, "loss": 0.5337393879890442, "step": 1663 }, { "epoch": 0.2333309962840917, "grad_norm": 3.196288824081421, "learning_rate": 8.956029723025175e-06, "loss": 0.6394835114479065, "step": 1664 }, { "epoch": 0.23347121923858935, "grad_norm": 3.0952413082122803, "learning_rate": 8.954640734393903e-06, "loss": 0.5915762186050415, "step": 1665 }, { "epoch": 0.23361144219308702, "grad_norm": 4.095795631408691, "learning_rate": 8.953250930221899e-06, "loss": 0.6437258720397949, "step": 1666 }, { "epoch": 0.23375166514758466, "grad_norm": 3.9386234283447266, "learning_rate": 8.95186031079577e-06, "loss": 0.6218746900558472, "step": 1667 }, { "epoch": 0.2338918881020823, "grad_norm": 5.0346879959106445, "learning_rate": 8.950468876402294e-06, "loss": 0.5417757630348206, "step": 1668 }, { "epoch": 0.23403211105657995, "grad_norm": 3.9649369716644287, "learning_rate": 8.949076627328423e-06, "loss": 0.5437141060829163, "step": 1669 }, { "epoch": 0.23417233401107762, "grad_norm": 3.8449482917785645, "learning_rate": 8.947683563861267e-06, "loss": 0.5986307263374329, "step": 1670 }, { "epoch": 0.23431255696557526, "grad_norm": 2.9612433910369873, "learning_rate": 8.94628968628811e-06, "loss": 0.5656077861785889, "step": 1671 }, { "epoch": 0.2344527799200729, "grad_norm": 5.214348793029785, "learning_rate": 8.9448949948964e-06, "loss": 0.5463271141052246, "step": 1672 }, { "epoch": 0.23459300287457058, "grad_norm": 2.8649723529815674, "learning_rate": 8.943499489973761e-06, "loss": 0.5250023603439331, "step": 1673 }, { "epoch": 0.23473322582906822, "grad_norm": 22.414493560791016, "learning_rate": 8.942103171807977e-06, "loss": 0.5707969665527344, "step": 1674 }, { "epoch": 0.23487344878356586, "grad_norm": 2.6721270084381104, "learning_rate": 8.940706040687e-06, "loss": 0.6142586469650269, "step": 1675 }, { "epoch": 0.23501367173806353, "grad_norm": 4.435406684875488, "learning_rate": 8.939308096898953e-06, "loss": 0.5892962217330933, "step": 1676 }, { "epoch": 0.23515389469256118, "grad_norm": 2.654740810394287, "learning_rate": 8.937909340732124e-06, "loss": 0.6414341926574707, "step": 1677 }, { "epoch": 0.23529411764705882, "grad_norm": 4.171870708465576, "learning_rate": 8.936509772474972e-06, "loss": 0.6482458114624023, "step": 1678 }, { "epoch": 0.23543434060155646, "grad_norm": 2.8794126510620117, "learning_rate": 8.935109392416119e-06, "loss": 0.5648084282875061, "step": 1679 }, { "epoch": 0.23557456355605413, "grad_norm": 3.8053808212280273, "learning_rate": 8.933708200844357e-06, "loss": 0.6416553854942322, "step": 1680 }, { "epoch": 0.23571478651055178, "grad_norm": 3.442657232284546, "learning_rate": 8.932306198048648e-06, "loss": 0.5199984312057495, "step": 1681 }, { "epoch": 0.23585500946504942, "grad_norm": 4.006880283355713, "learning_rate": 8.930903384318114e-06, "loss": 0.5425795316696167, "step": 1682 }, { "epoch": 0.2359952324195471, "grad_norm": 3.7693777084350586, "learning_rate": 8.92949975994205e-06, "loss": 0.5355290174484253, "step": 1683 }, { "epoch": 0.23613545537404473, "grad_norm": 3.3172154426574707, "learning_rate": 8.928095325209916e-06, "loss": 0.5093482136726379, "step": 1684 }, { "epoch": 0.23627567832854238, "grad_norm": 6.138156414031982, "learning_rate": 8.926690080411343e-06, "loss": 0.6282786726951599, "step": 1685 }, { "epoch": 0.23641590128304005, "grad_norm": 2.9836857318878174, "learning_rate": 8.925284025836121e-06, "loss": 0.686323344707489, "step": 1686 }, { "epoch": 0.2365561242375377, "grad_norm": 4.629907608032227, "learning_rate": 8.923877161774216e-06, "loss": 0.6005764007568359, "step": 1687 }, { "epoch": 0.23669634719203533, "grad_norm": 2.846644401550293, "learning_rate": 8.922469488515754e-06, "loss": 0.6118041276931763, "step": 1688 }, { "epoch": 0.23683657014653298, "grad_norm": 3.147317409515381, "learning_rate": 8.921061006351031e-06, "loss": 0.6221591830253601, "step": 1689 }, { "epoch": 0.23697679310103065, "grad_norm": 3.6038825511932373, "learning_rate": 8.919651715570511e-06, "loss": 0.5370442867279053, "step": 1690 }, { "epoch": 0.2371170160555283, "grad_norm": 3.0992257595062256, "learning_rate": 8.918241616464822e-06, "loss": 0.5393306016921997, "step": 1691 }, { "epoch": 0.23725723901002593, "grad_norm": 2.7825422286987305, "learning_rate": 8.91683070932476e-06, "loss": 0.4903857409954071, "step": 1692 }, { "epoch": 0.2373974619645236, "grad_norm": 3.882941961288452, "learning_rate": 8.915418994441287e-06, "loss": 0.5423718690872192, "step": 1693 }, { "epoch": 0.23753768491902125, "grad_norm": 5.4279632568359375, "learning_rate": 8.914006472105532e-06, "loss": 0.5581388473510742, "step": 1694 }, { "epoch": 0.2376779078735189, "grad_norm": 3.5252907276153564, "learning_rate": 8.912593142608792e-06, "loss": 0.5612087845802307, "step": 1695 }, { "epoch": 0.23781813082801653, "grad_norm": 3.2147767543792725, "learning_rate": 8.911179006242529e-06, "loss": 0.4995323419570923, "step": 1696 }, { "epoch": 0.2379583537825142, "grad_norm": 4.242537975311279, "learning_rate": 8.909764063298371e-06, "loss": 0.5436496734619141, "step": 1697 }, { "epoch": 0.23809857673701185, "grad_norm": 2.9969980716705322, "learning_rate": 8.908348314068111e-06, "loss": 0.5869162082672119, "step": 1698 }, { "epoch": 0.2382387996915095, "grad_norm": 4.747855186462402, "learning_rate": 8.906931758843713e-06, "loss": 0.5880348682403564, "step": 1699 }, { "epoch": 0.23837902264600716, "grad_norm": 10.174501419067383, "learning_rate": 8.905514397917303e-06, "loss": 0.5524253845214844, "step": 1700 }, { "epoch": 0.2385192456005048, "grad_norm": 3.635745048522949, "learning_rate": 8.904096231581173e-06, "loss": 0.6079657077789307, "step": 1701 }, { "epoch": 0.23865946855500245, "grad_norm": 5.296257019042969, "learning_rate": 8.902677260127786e-06, "loss": 0.5672435760498047, "step": 1702 }, { "epoch": 0.23879969150950012, "grad_norm": 3.2926995754241943, "learning_rate": 8.901257483849766e-06, "loss": 0.5312352180480957, "step": 1703 }, { "epoch": 0.23893991446399776, "grad_norm": 4.055819988250732, "learning_rate": 8.899836903039902e-06, "loss": 0.577424168586731, "step": 1704 }, { "epoch": 0.2390801374184954, "grad_norm": 2.7252566814422607, "learning_rate": 8.898415517991154e-06, "loss": 0.6560479402542114, "step": 1705 }, { "epoch": 0.23922036037299305, "grad_norm": 3.8119094371795654, "learning_rate": 8.896993328996645e-06, "loss": 0.6293927431106567, "step": 1706 }, { "epoch": 0.23936058332749072, "grad_norm": 3.7756688594818115, "learning_rate": 8.895570336349664e-06, "loss": 0.536406397819519, "step": 1707 }, { "epoch": 0.23950080628198836, "grad_norm": 3.1382532119750977, "learning_rate": 8.894146540343667e-06, "loss": 0.6694639921188354, "step": 1708 }, { "epoch": 0.239641029236486, "grad_norm": 3.174741268157959, "learning_rate": 8.892721941272272e-06, "loss": 0.43138355016708374, "step": 1709 }, { "epoch": 0.23978125219098367, "grad_norm": 6.763868808746338, "learning_rate": 8.891296539429266e-06, "loss": 0.5967525243759155, "step": 1710 }, { "epoch": 0.23992147514548132, "grad_norm": 3.618896722793579, "learning_rate": 8.889870335108603e-06, "loss": 0.5135518312454224, "step": 1711 }, { "epoch": 0.24006169809997896, "grad_norm": 2.868946075439453, "learning_rate": 8.888443328604398e-06, "loss": 0.5291064977645874, "step": 1712 }, { "epoch": 0.24020192105447663, "grad_norm": 3.677651882171631, "learning_rate": 8.887015520210932e-06, "loss": 0.5590741634368896, "step": 1713 }, { "epoch": 0.24034214400897427, "grad_norm": 2.866971254348755, "learning_rate": 8.885586910222657e-06, "loss": 0.5649508237838745, "step": 1714 }, { "epoch": 0.24048236696347192, "grad_norm": 4.027466773986816, "learning_rate": 8.884157498934183e-06, "loss": 0.6206886768341064, "step": 1715 }, { "epoch": 0.24062258991796956, "grad_norm": 3.9526255130767822, "learning_rate": 8.882727286640289e-06, "loss": 0.6554785966873169, "step": 1716 }, { "epoch": 0.24076281287246723, "grad_norm": 7.599788188934326, "learning_rate": 8.88129627363592e-06, "loss": 0.5874443650245667, "step": 1717 }, { "epoch": 0.24090303582696487, "grad_norm": 3.4353694915771484, "learning_rate": 8.879864460216186e-06, "loss": 0.4850062131881714, "step": 1718 }, { "epoch": 0.24104325878146252, "grad_norm": 3.8459203243255615, "learning_rate": 8.878431846676356e-06, "loss": 0.5828545093536377, "step": 1719 }, { "epoch": 0.2411834817359602, "grad_norm": 3.075338125228882, "learning_rate": 8.876998433311874e-06, "loss": 0.4470393657684326, "step": 1720 }, { "epoch": 0.24132370469045783, "grad_norm": 3.1820054054260254, "learning_rate": 8.87556422041834e-06, "loss": 0.48874431848526, "step": 1721 }, { "epoch": 0.24146392764495547, "grad_norm": 3.602665662765503, "learning_rate": 8.874129208291527e-06, "loss": 0.5676736235618591, "step": 1722 }, { "epoch": 0.24160415059945314, "grad_norm": 3.7263050079345703, "learning_rate": 8.872693397227364e-06, "loss": 0.5849317312240601, "step": 1723 }, { "epoch": 0.2417443735539508, "grad_norm": 6.58273983001709, "learning_rate": 8.871256787521953e-06, "loss": 0.5928614139556885, "step": 1724 }, { "epoch": 0.24188459650844843, "grad_norm": 2.9763898849487305, "learning_rate": 8.869819379471553e-06, "loss": 0.5915541052818298, "step": 1725 }, { "epoch": 0.24202481946294607, "grad_norm": 2.967402219772339, "learning_rate": 8.868381173372597e-06, "loss": 0.6149771809577942, "step": 1726 }, { "epoch": 0.24216504241744374, "grad_norm": 4.314509391784668, "learning_rate": 8.866942169521672e-06, "loss": 0.45522868633270264, "step": 1727 }, { "epoch": 0.2423052653719414, "grad_norm": 3.131345510482788, "learning_rate": 8.865502368215538e-06, "loss": 0.5884299874305725, "step": 1728 }, { "epoch": 0.24244548832643903, "grad_norm": 10.823710441589355, "learning_rate": 8.864061769751115e-06, "loss": 0.6472725868225098, "step": 1729 }, { "epoch": 0.2425857112809367, "grad_norm": 6.02665901184082, "learning_rate": 8.86262037442549e-06, "loss": 0.550506591796875, "step": 1730 }, { "epoch": 0.24272593423543434, "grad_norm": 4.775340557098389, "learning_rate": 8.86117818253591e-06, "loss": 0.6103633642196655, "step": 1731 }, { "epoch": 0.24286615718993199, "grad_norm": 3.324282169342041, "learning_rate": 8.85973519437979e-06, "loss": 0.5743398666381836, "step": 1732 }, { "epoch": 0.24300638014442966, "grad_norm": 3.066495418548584, "learning_rate": 8.85829141025471e-06, "loss": 0.5898178815841675, "step": 1733 }, { "epoch": 0.2431466030989273, "grad_norm": 5.030037879943848, "learning_rate": 8.856846830458414e-06, "loss": 0.5951356291770935, "step": 1734 }, { "epoch": 0.24328682605342494, "grad_norm": 4.69780158996582, "learning_rate": 8.855401455288804e-06, "loss": 0.514532208442688, "step": 1735 }, { "epoch": 0.24342704900792259, "grad_norm": 3.1109445095062256, "learning_rate": 8.853955285043953e-06, "loss": 0.6027734279632568, "step": 1736 }, { "epoch": 0.24356727196242026, "grad_norm": 4.819581985473633, "learning_rate": 8.852508320022097e-06, "loss": 0.648367166519165, "step": 1737 }, { "epoch": 0.2437074949169179, "grad_norm": 8.28742790222168, "learning_rate": 8.851060560521632e-06, "loss": 0.6185219287872314, "step": 1738 }, { "epoch": 0.24384771787141554, "grad_norm": 3.6274337768554688, "learning_rate": 8.849612006841121e-06, "loss": 0.7403665781021118, "step": 1739 }, { "epoch": 0.2439879408259132, "grad_norm": 3.6587536334991455, "learning_rate": 8.848162659279293e-06, "loss": 0.5387477874755859, "step": 1740 }, { "epoch": 0.24412816378041086, "grad_norm": 3.0212130546569824, "learning_rate": 8.846712518135033e-06, "loss": 0.51812744140625, "step": 1741 }, { "epoch": 0.2442683867349085, "grad_norm": 4.271726608276367, "learning_rate": 8.845261583707399e-06, "loss": 0.6767152547836304, "step": 1742 }, { "epoch": 0.24440860968940614, "grad_norm": 3.728705644607544, "learning_rate": 8.843809856295604e-06, "loss": 0.5090997219085693, "step": 1743 }, { "epoch": 0.2445488326439038, "grad_norm": 8.177384376525879, "learning_rate": 8.842357336199033e-06, "loss": 0.5420479774475098, "step": 1744 }, { "epoch": 0.24468905559840146, "grad_norm": 3.875396728515625, "learning_rate": 8.840904023717225e-06, "loss": 0.6828616857528687, "step": 1745 }, { "epoch": 0.2448292785528991, "grad_norm": 3.0584685802459717, "learning_rate": 8.839449919149893e-06, "loss": 0.499365895986557, "step": 1746 }, { "epoch": 0.24496950150739677, "grad_norm": 6.875380992889404, "learning_rate": 8.837995022796903e-06, "loss": 0.548239529132843, "step": 1747 }, { "epoch": 0.2451097244618944, "grad_norm": 3.357849597930908, "learning_rate": 8.836539334958294e-06, "loss": 0.5971091985702515, "step": 1748 }, { "epoch": 0.24524994741639206, "grad_norm": 3.964022636413574, "learning_rate": 8.835082855934258e-06, "loss": 0.43399548530578613, "step": 1749 }, { "epoch": 0.24539017037088973, "grad_norm": 5.138737201690674, "learning_rate": 8.83362558602516e-06, "loss": 0.6759029030799866, "step": 1750 }, { "epoch": 0.24553039332538737, "grad_norm": 3.768995523452759, "learning_rate": 8.83216752553152e-06, "loss": 0.602433443069458, "step": 1751 }, { "epoch": 0.245670616279885, "grad_norm": 5.219105243682861, "learning_rate": 8.830708674754029e-06, "loss": 0.6149768829345703, "step": 1752 }, { "epoch": 0.24581083923438266, "grad_norm": 2.491253137588501, "learning_rate": 8.829249033993532e-06, "loss": 0.5095318555831909, "step": 1753 }, { "epoch": 0.24595106218888033, "grad_norm": 3.49395751953125, "learning_rate": 8.827788603551046e-06, "loss": 0.6372556686401367, "step": 1754 }, { "epoch": 0.24609128514337797, "grad_norm": 2.475642681121826, "learning_rate": 8.826327383727742e-06, "loss": 0.5903401374816895, "step": 1755 }, { "epoch": 0.2462315080978756, "grad_norm": 6.388079643249512, "learning_rate": 8.824865374824961e-06, "loss": 0.5440061092376709, "step": 1756 }, { "epoch": 0.24637173105237328, "grad_norm": 4.5942254066467285, "learning_rate": 8.823402577144203e-06, "loss": 0.6292832493782043, "step": 1757 }, { "epoch": 0.24651195400687093, "grad_norm": 5.250320911407471, "learning_rate": 8.821938990987132e-06, "loss": 0.5394306182861328, "step": 1758 }, { "epoch": 0.24665217696136857, "grad_norm": 4.510232448577881, "learning_rate": 8.820474616655575e-06, "loss": 0.6843840479850769, "step": 1759 }, { "epoch": 0.24679239991586624, "grad_norm": 5.151352882385254, "learning_rate": 8.819009454451517e-06, "loss": 0.6058231592178345, "step": 1760 }, { "epoch": 0.24693262287036388, "grad_norm": 18.46104621887207, "learning_rate": 8.817543504677115e-06, "loss": 0.48356714844703674, "step": 1761 }, { "epoch": 0.24707284582486153, "grad_norm": 3.076375722885132, "learning_rate": 8.816076767634679e-06, "loss": 0.5914121866226196, "step": 1762 }, { "epoch": 0.24721306877935917, "grad_norm": 2.810962438583374, "learning_rate": 8.814609243626682e-06, "loss": 0.557772159576416, "step": 1763 }, { "epoch": 0.24735329173385684, "grad_norm": 3.2033145427703857, "learning_rate": 8.81314093295577e-06, "loss": 0.6829338073730469, "step": 1764 }, { "epoch": 0.24749351468835448, "grad_norm": 2.3781678676605225, "learning_rate": 8.811671835924737e-06, "loss": 0.5386377573013306, "step": 1765 }, { "epoch": 0.24763373764285213, "grad_norm": 3.157132148742676, "learning_rate": 8.810201952836548e-06, "loss": 0.606110692024231, "step": 1766 }, { "epoch": 0.2477739605973498, "grad_norm": 4.682838439941406, "learning_rate": 8.808731283994329e-06, "loss": 0.6025000810623169, "step": 1767 }, { "epoch": 0.24791418355184744, "grad_norm": 2.9795265197753906, "learning_rate": 8.807259829701365e-06, "loss": 0.5115381479263306, "step": 1768 }, { "epoch": 0.24805440650634508, "grad_norm": 4.657365798950195, "learning_rate": 8.805787590261105e-06, "loss": 0.5803285837173462, "step": 1769 }, { "epoch": 0.24819462946084275, "grad_norm": 4.221493721008301, "learning_rate": 8.804314565977161e-06, "loss": 0.608871579170227, "step": 1770 }, { "epoch": 0.2483348524153404, "grad_norm": 4.528402328491211, "learning_rate": 8.802840757153301e-06, "loss": 0.5920511484146118, "step": 1771 }, { "epoch": 0.24847507536983804, "grad_norm": 9.217483520507812, "learning_rate": 8.801366164093467e-06, "loss": 0.49439942836761475, "step": 1772 }, { "epoch": 0.24861529832433568, "grad_norm": 2.6044676303863525, "learning_rate": 8.799890787101747e-06, "loss": 0.5555398464202881, "step": 1773 }, { "epoch": 0.24875552127883335, "grad_norm": 3.7903075218200684, "learning_rate": 8.798414626482407e-06, "loss": 0.5734109878540039, "step": 1774 }, { "epoch": 0.248895744233331, "grad_norm": 3.1998748779296875, "learning_rate": 8.79693768253986e-06, "loss": 0.6451035141944885, "step": 1775 }, { "epoch": 0.24903596718782864, "grad_norm": 4.426762580871582, "learning_rate": 8.795459955578688e-06, "loss": 0.6547963619232178, "step": 1776 }, { "epoch": 0.2491761901423263, "grad_norm": 2.901259183883667, "learning_rate": 8.793981445903636e-06, "loss": 0.4864223599433899, "step": 1777 }, { "epoch": 0.24931641309682395, "grad_norm": 3.8567519187927246, "learning_rate": 8.792502153819606e-06, "loss": 0.6151624917984009, "step": 1778 }, { "epoch": 0.2494566360513216, "grad_norm": 3.4449262619018555, "learning_rate": 8.79102207963166e-06, "loss": 0.6518480181694031, "step": 1779 }, { "epoch": 0.24959685900581927, "grad_norm": 2.7196106910705566, "learning_rate": 8.789541223645031e-06, "loss": 0.5193225741386414, "step": 1780 }, { "epoch": 0.2497370819603169, "grad_norm": 4.5836896896362305, "learning_rate": 8.788059586165103e-06, "loss": 0.578071117401123, "step": 1781 }, { "epoch": 0.24987730491481455, "grad_norm": 4.120945453643799, "learning_rate": 8.786577167497423e-06, "loss": 0.5365176796913147, "step": 1782 }, { "epoch": 0.2500175278693122, "grad_norm": 3.3610892295837402, "learning_rate": 8.785093967947704e-06, "loss": 0.6328309774398804, "step": 1783 }, { "epoch": 0.25015775082380987, "grad_norm": 4.098238468170166, "learning_rate": 8.783609987821817e-06, "loss": 0.5625135898590088, "step": 1784 }, { "epoch": 0.25029797377830754, "grad_norm": 2.5969960689544678, "learning_rate": 8.78212522742579e-06, "loss": 0.5765585899353027, "step": 1785 }, { "epoch": 0.25043819673280515, "grad_norm": 3.6246612071990967, "learning_rate": 8.78063968706582e-06, "loss": 0.5946084260940552, "step": 1786 }, { "epoch": 0.2505784196873028, "grad_norm": 4.451273441314697, "learning_rate": 8.779153367048259e-06, "loss": 0.6791266798973083, "step": 1787 }, { "epoch": 0.25071864264180044, "grad_norm": 5.948458671569824, "learning_rate": 8.777666267679622e-06, "loss": 0.5708842277526855, "step": 1788 }, { "epoch": 0.2508588655962981, "grad_norm": 4.316166400909424, "learning_rate": 8.776178389266583e-06, "loss": 0.637507975101471, "step": 1789 }, { "epoch": 0.2509990885507958, "grad_norm": 3.161750078201294, "learning_rate": 8.77468973211598e-06, "loss": 0.5102627277374268, "step": 1790 }, { "epoch": 0.2511393115052934, "grad_norm": 3.3729372024536133, "learning_rate": 8.773200296534808e-06, "loss": 0.6271131038665771, "step": 1791 }, { "epoch": 0.25127953445979107, "grad_norm": 3.280827045440674, "learning_rate": 8.771710082830222e-06, "loss": 0.6298079490661621, "step": 1792 }, { "epoch": 0.25141975741428874, "grad_norm": 3.7394979000091553, "learning_rate": 8.770219091309543e-06, "loss": 0.6556540131568909, "step": 1793 }, { "epoch": 0.25155998036878635, "grad_norm": 4.809515476226807, "learning_rate": 8.768727322280246e-06, "loss": 0.5252683162689209, "step": 1794 }, { "epoch": 0.251700203323284, "grad_norm": 2.880408525466919, "learning_rate": 8.767234776049973e-06, "loss": 0.5313420295715332, "step": 1795 }, { "epoch": 0.2518404262777817, "grad_norm": 3.182553768157959, "learning_rate": 8.765741452926517e-06, "loss": 0.5354381799697876, "step": 1796 }, { "epoch": 0.2519806492322793, "grad_norm": 2.1635243892669678, "learning_rate": 8.76424735321784e-06, "loss": 0.5238628387451172, "step": 1797 }, { "epoch": 0.252120872186777, "grad_norm": 7.208446502685547, "learning_rate": 8.762752477232061e-06, "loss": 0.5995115637779236, "step": 1798 }, { "epoch": 0.25226109514127465, "grad_norm": 3.4190545082092285, "learning_rate": 8.761256825277458e-06, "loss": 0.5985393524169922, "step": 1799 }, { "epoch": 0.25240131809577226, "grad_norm": 3.706050157546997, "learning_rate": 8.759760397662471e-06, "loss": 0.5379060506820679, "step": 1800 }, { "epoch": 0.25254154105026994, "grad_norm": 2.979853868484497, "learning_rate": 8.758263194695698e-06, "loss": 0.5873063206672668, "step": 1801 }, { "epoch": 0.2526817640047676, "grad_norm": 3.389944314956665, "learning_rate": 8.756765216685897e-06, "loss": 0.6056170463562012, "step": 1802 }, { "epoch": 0.2528219869592652, "grad_norm": 3.3248891830444336, "learning_rate": 8.755266463941986e-06, "loss": 0.5757933259010315, "step": 1803 }, { "epoch": 0.2529622099137629, "grad_norm": 4.554576396942139, "learning_rate": 8.753766936773047e-06, "loss": 0.559252917766571, "step": 1804 }, { "epoch": 0.2531024328682605, "grad_norm": 4.100575923919678, "learning_rate": 8.752266635488313e-06, "loss": 0.5491762161254883, "step": 1805 }, { "epoch": 0.2532426558227582, "grad_norm": 5.442667484283447, "learning_rate": 8.750765560397188e-06, "loss": 0.5723036527633667, "step": 1806 }, { "epoch": 0.25338287877725585, "grad_norm": 2.913914680480957, "learning_rate": 8.749263711809224e-06, "loss": 0.6301402449607849, "step": 1807 }, { "epoch": 0.25352310173175346, "grad_norm": 3.347762107849121, "learning_rate": 8.747761090034138e-06, "loss": 0.6276699304580688, "step": 1808 }, { "epoch": 0.25366332468625113, "grad_norm": 4.446063041687012, "learning_rate": 8.74625769538181e-06, "loss": 0.5105441808700562, "step": 1809 }, { "epoch": 0.2538035476407488, "grad_norm": 4.2033185958862305, "learning_rate": 8.744753528162273e-06, "loss": 0.5407695770263672, "step": 1810 }, { "epoch": 0.2539437705952464, "grad_norm": 4.075489044189453, "learning_rate": 8.743248588685724e-06, "loss": 0.5234379172325134, "step": 1811 }, { "epoch": 0.2540839935497441, "grad_norm": 4.1656622886657715, "learning_rate": 8.741742877262514e-06, "loss": 0.5034075975418091, "step": 1812 }, { "epoch": 0.25422421650424176, "grad_norm": 4.701844692230225, "learning_rate": 8.740236394203159e-06, "loss": 0.5452364683151245, "step": 1813 }, { "epoch": 0.2543644394587394, "grad_norm": 3.2802228927612305, "learning_rate": 8.73872913981833e-06, "loss": 0.603797197341919, "step": 1814 }, { "epoch": 0.25450466241323705, "grad_norm": 3.5896685123443604, "learning_rate": 8.73722111441886e-06, "loss": 0.6276065111160278, "step": 1815 }, { "epoch": 0.2546448853677347, "grad_norm": 4.117814540863037, "learning_rate": 8.735712318315737e-06, "loss": 0.575721800327301, "step": 1816 }, { "epoch": 0.25478510832223233, "grad_norm": 3.6554038524627686, "learning_rate": 8.734202751820114e-06, "loss": 0.5934094190597534, "step": 1817 }, { "epoch": 0.25492533127673, "grad_norm": 4.747923374176025, "learning_rate": 8.732692415243296e-06, "loss": 0.5665898323059082, "step": 1818 }, { "epoch": 0.2550655542312277, "grad_norm": 3.1050570011138916, "learning_rate": 8.731181308896755e-06, "loss": 0.5124664306640625, "step": 1819 }, { "epoch": 0.2552057771857253, "grad_norm": 2.9599404335021973, "learning_rate": 8.729669433092112e-06, "loss": 0.5137664675712585, "step": 1820 }, { "epoch": 0.25534600014022296, "grad_norm": 6.951761722564697, "learning_rate": 8.728156788141154e-06, "loss": 0.6163932681083679, "step": 1821 }, { "epoch": 0.25548622309472063, "grad_norm": 6.815899848937988, "learning_rate": 8.726643374355825e-06, "loss": 0.6080081462860107, "step": 1822 }, { "epoch": 0.25562644604921825, "grad_norm": 6.428788661956787, "learning_rate": 8.725129192048226e-06, "loss": 0.5772079229354858, "step": 1823 }, { "epoch": 0.2557666690037159, "grad_norm": 5.115321636199951, "learning_rate": 8.723614241530615e-06, "loss": 0.6158089637756348, "step": 1824 }, { "epoch": 0.25590689195821353, "grad_norm": 3.9402732849121094, "learning_rate": 8.722098523115414e-06, "loss": 0.5702472925186157, "step": 1825 }, { "epoch": 0.2560471149127112, "grad_norm": 2.7962236404418945, "learning_rate": 8.7205820371152e-06, "loss": 0.5073167085647583, "step": 1826 }, { "epoch": 0.2561873378672089, "grad_norm": 2.6268811225891113, "learning_rate": 8.719064783842706e-06, "loss": 0.43188223242759705, "step": 1827 }, { "epoch": 0.2563275608217065, "grad_norm": 3.3596034049987793, "learning_rate": 8.717546763610827e-06, "loss": 0.5950806736946106, "step": 1828 }, { "epoch": 0.25646778377620416, "grad_norm": 4.391979694366455, "learning_rate": 8.716027976732616e-06, "loss": 0.5779260396957397, "step": 1829 }, { "epoch": 0.25660800673070183, "grad_norm": 6.3609209060668945, "learning_rate": 8.71450842352128e-06, "loss": 0.5925577878952026, "step": 1830 }, { "epoch": 0.25674822968519945, "grad_norm": 3.6536262035369873, "learning_rate": 8.712988104290188e-06, "loss": 0.5226534605026245, "step": 1831 }, { "epoch": 0.2568884526396971, "grad_norm": 3.1486518383026123, "learning_rate": 8.711467019352869e-06, "loss": 0.5512034296989441, "step": 1832 }, { "epoch": 0.2570286755941948, "grad_norm": 3.570466995239258, "learning_rate": 8.709945169023001e-06, "loss": 0.5920038223266602, "step": 1833 }, { "epoch": 0.2571688985486924, "grad_norm": 3.5993669033050537, "learning_rate": 8.708422553614432e-06, "loss": 0.6002395153045654, "step": 1834 }, { "epoch": 0.2573091215031901, "grad_norm": 3.5165963172912598, "learning_rate": 8.706899173441157e-06, "loss": 0.5713338255882263, "step": 1835 }, { "epoch": 0.25744934445768775, "grad_norm": 2.6596038341522217, "learning_rate": 8.705375028817336e-06, "loss": 0.6344123482704163, "step": 1836 }, { "epoch": 0.25758956741218536, "grad_norm": 2.607285261154175, "learning_rate": 8.70385012005728e-06, "loss": 0.5710083246231079, "step": 1837 }, { "epoch": 0.25772979036668303, "grad_norm": 3.3403899669647217, "learning_rate": 8.702324447475465e-06, "loss": 0.5693377256393433, "step": 1838 }, { "epoch": 0.2578700133211807, "grad_norm": 7.767582893371582, "learning_rate": 8.700798011386518e-06, "loss": 0.4793682396411896, "step": 1839 }, { "epoch": 0.2580102362756783, "grad_norm": 5.020839214324951, "learning_rate": 8.69927081210523e-06, "loss": 0.5600985884666443, "step": 1840 }, { "epoch": 0.258150459230176, "grad_norm": 3.0847678184509277, "learning_rate": 8.69774284994654e-06, "loss": 0.5168713927268982, "step": 1841 }, { "epoch": 0.2582906821846736, "grad_norm": 3.49896502494812, "learning_rate": 8.696214125225556e-06, "loss": 0.6075201034545898, "step": 1842 }, { "epoch": 0.2584309051391713, "grad_norm": 3.669513702392578, "learning_rate": 8.694684638257535e-06, "loss": 0.6130319833755493, "step": 1843 }, { "epoch": 0.25857112809366894, "grad_norm": 3.3648533821105957, "learning_rate": 8.693154389357892e-06, "loss": 0.5889811515808105, "step": 1844 }, { "epoch": 0.25871135104816656, "grad_norm": 3.319037437438965, "learning_rate": 8.691623378842204e-06, "loss": 0.5392980575561523, "step": 1845 }, { "epoch": 0.25885157400266423, "grad_norm": 3.0758755207061768, "learning_rate": 8.690091607026198e-06, "loss": 0.5213278532028198, "step": 1846 }, { "epoch": 0.2589917969571619, "grad_norm": 8.297051429748535, "learning_rate": 8.688559074225764e-06, "loss": 0.5381153225898743, "step": 1847 }, { "epoch": 0.2591320199116595, "grad_norm": 7.96444034576416, "learning_rate": 8.687025780756946e-06, "loss": 0.5464196801185608, "step": 1848 }, { "epoch": 0.2592722428661572, "grad_norm": 5.914955139160156, "learning_rate": 8.685491726935944e-06, "loss": 0.5538217425346375, "step": 1849 }, { "epoch": 0.25941246582065486, "grad_norm": 3.1814732551574707, "learning_rate": 8.68395691307912e-06, "loss": 0.48464471101760864, "step": 1850 }, { "epoch": 0.2595526887751525, "grad_norm": 5.079481601715088, "learning_rate": 8.682421339502985e-06, "loss": 0.6675615310668945, "step": 1851 }, { "epoch": 0.25969291172965014, "grad_norm": 7.236573696136475, "learning_rate": 8.680885006524213e-06, "loss": 0.543739378452301, "step": 1852 }, { "epoch": 0.2598331346841478, "grad_norm": 3.701139450073242, "learning_rate": 8.679347914459633e-06, "loss": 0.4628801941871643, "step": 1853 }, { "epoch": 0.25997335763864543, "grad_norm": 3.036630392074585, "learning_rate": 8.677810063626226e-06, "loss": 0.5055800676345825, "step": 1854 }, { "epoch": 0.2601135805931431, "grad_norm": 4.1041364669799805, "learning_rate": 8.676271454341139e-06, "loss": 0.5293359756469727, "step": 1855 }, { "epoch": 0.26025380354764077, "grad_norm": 3.1487245559692383, "learning_rate": 8.674732086921665e-06, "loss": 0.5214464664459229, "step": 1856 }, { "epoch": 0.2603940265021384, "grad_norm": 5.2374348640441895, "learning_rate": 8.67319196168526e-06, "loss": 0.5340123176574707, "step": 1857 }, { "epoch": 0.26053424945663606, "grad_norm": 4.725361347198486, "learning_rate": 8.671651078949535e-06, "loss": 0.553186297416687, "step": 1858 }, { "epoch": 0.26067447241113373, "grad_norm": 2.96407413482666, "learning_rate": 8.670109439032254e-06, "loss": 0.5037491917610168, "step": 1859 }, { "epoch": 0.26081469536563134, "grad_norm": 6.505245685577393, "learning_rate": 8.668567042251342e-06, "loss": 0.472609281539917, "step": 1860 }, { "epoch": 0.260954918320129, "grad_norm": 2.906219244003296, "learning_rate": 8.667023888924877e-06, "loss": 0.5321058034896851, "step": 1861 }, { "epoch": 0.26109514127462663, "grad_norm": 3.4425981044769287, "learning_rate": 8.665479979371094e-06, "loss": 0.5895671844482422, "step": 1862 }, { "epoch": 0.2612353642291243, "grad_norm": 5.562176704406738, "learning_rate": 8.663935313908385e-06, "loss": 0.473257839679718, "step": 1863 }, { "epoch": 0.26137558718362197, "grad_norm": 3.0691823959350586, "learning_rate": 8.662389892855294e-06, "loss": 0.6197575330734253, "step": 1864 }, { "epoch": 0.2615158101381196, "grad_norm": 3.393977642059326, "learning_rate": 8.660843716530526e-06, "loss": 0.6141848564147949, "step": 1865 }, { "epoch": 0.26165603309261726, "grad_norm": 4.068802833557129, "learning_rate": 8.659296785252938e-06, "loss": 0.644903302192688, "step": 1866 }, { "epoch": 0.26179625604711493, "grad_norm": 3.2136216163635254, "learning_rate": 8.657749099341544e-06, "loss": 0.6196070909500122, "step": 1867 }, { "epoch": 0.26193647900161254, "grad_norm": 3.4312803745269775, "learning_rate": 8.656200659115515e-06, "loss": 0.6281217336654663, "step": 1868 }, { "epoch": 0.2620767019561102, "grad_norm": 3.7340686321258545, "learning_rate": 8.654651464894173e-06, "loss": 0.5558048486709595, "step": 1869 }, { "epoch": 0.2622169249106079, "grad_norm": 3.6039950847625732, "learning_rate": 8.653101516997001e-06, "loss": 0.5089840888977051, "step": 1870 }, { "epoch": 0.2623571478651055, "grad_norm": 4.942955493927002, "learning_rate": 8.651550815743635e-06, "loss": 0.4771727919578552, "step": 1871 }, { "epoch": 0.26249737081960317, "grad_norm": 3.5902836322784424, "learning_rate": 8.649999361453864e-06, "loss": 0.600969672203064, "step": 1872 }, { "epoch": 0.26263759377410084, "grad_norm": 4.553799629211426, "learning_rate": 8.648447154447639e-06, "loss": 0.579310417175293, "step": 1873 }, { "epoch": 0.26277781672859846, "grad_norm": 7.795530319213867, "learning_rate": 8.646894195045057e-06, "loss": 0.5728267431259155, "step": 1874 }, { "epoch": 0.2629180396830961, "grad_norm": 3.7513391971588135, "learning_rate": 8.645340483566381e-06, "loss": 0.53194260597229, "step": 1875 }, { "epoch": 0.2630582626375938, "grad_norm": 3.409071445465088, "learning_rate": 8.643786020332015e-06, "loss": 0.49038293957710266, "step": 1876 }, { "epoch": 0.2631984855920914, "grad_norm": 2.9995906352996826, "learning_rate": 8.642230805662532e-06, "loss": 0.5835483074188232, "step": 1877 }, { "epoch": 0.2633387085465891, "grad_norm": 3.4828431606292725, "learning_rate": 8.640674839878655e-06, "loss": 0.5933776497840881, "step": 1878 }, { "epoch": 0.26347893150108675, "grad_norm": 3.9214227199554443, "learning_rate": 8.639118123301257e-06, "loss": 0.6796260476112366, "step": 1879 }, { "epoch": 0.26361915445558437, "grad_norm": 3.565967321395874, "learning_rate": 8.637560656251374e-06, "loss": 0.6499730348587036, "step": 1880 }, { "epoch": 0.26375937741008204, "grad_norm": 3.1962051391601562, "learning_rate": 8.636002439050191e-06, "loss": 0.4641020894050598, "step": 1881 }, { "epoch": 0.26389960036457966, "grad_norm": 3.50276780128479, "learning_rate": 8.634443472019046e-06, "loss": 0.5876539945602417, "step": 1882 }, { "epoch": 0.2640398233190773, "grad_norm": 3.1287167072296143, "learning_rate": 8.63288375547944e-06, "loss": 0.5639714002609253, "step": 1883 }, { "epoch": 0.264180046273575, "grad_norm": 3.5502448081970215, "learning_rate": 8.63132328975302e-06, "loss": 0.5687921047210693, "step": 1884 }, { "epoch": 0.2643202692280726, "grad_norm": 7.338390350341797, "learning_rate": 8.629762075161593e-06, "loss": 0.5227786302566528, "step": 1885 }, { "epoch": 0.2644604921825703, "grad_norm": 3.6727397441864014, "learning_rate": 8.628200112027119e-06, "loss": 0.6772019267082214, "step": 1886 }, { "epoch": 0.26460071513706795, "grad_norm": 4.361928462982178, "learning_rate": 8.62663740067171e-06, "loss": 0.5545731782913208, "step": 1887 }, { "epoch": 0.26474093809156557, "grad_norm": 4.4151201248168945, "learning_rate": 8.625073941417635e-06, "loss": 0.6204304695129395, "step": 1888 }, { "epoch": 0.26488116104606324, "grad_norm": 4.1626877784729, "learning_rate": 8.623509734587317e-06, "loss": 0.49584126472473145, "step": 1889 }, { "epoch": 0.2650213840005609, "grad_norm": 2.8731441497802734, "learning_rate": 8.621944780503332e-06, "loss": 0.5968765020370483, "step": 1890 }, { "epoch": 0.2651616069550585, "grad_norm": 4.2341227531433105, "learning_rate": 8.62037907948841e-06, "loss": 0.5383313894271851, "step": 1891 }, { "epoch": 0.2653018299095562, "grad_norm": 3.1529541015625, "learning_rate": 8.618812631865436e-06, "loss": 0.6157143115997314, "step": 1892 }, { "epoch": 0.26544205286405387, "grad_norm": 3.803420066833496, "learning_rate": 8.61724543795745e-06, "loss": 0.6888075470924377, "step": 1893 }, { "epoch": 0.2655822758185515, "grad_norm": 3.618497848510742, "learning_rate": 8.615677498087641e-06, "loss": 0.5587062835693359, "step": 1894 }, { "epoch": 0.26572249877304915, "grad_norm": 3.785771369934082, "learning_rate": 8.614108812579362e-06, "loss": 0.47015976905822754, "step": 1895 }, { "epoch": 0.2658627217275468, "grad_norm": 9.65227222442627, "learning_rate": 8.612539381756107e-06, "loss": 0.575263261795044, "step": 1896 }, { "epoch": 0.26600294468204444, "grad_norm": 4.750154495239258, "learning_rate": 8.61096920594153e-06, "loss": 0.5565943717956543, "step": 1897 }, { "epoch": 0.2661431676365421, "grad_norm": 22.59467124938965, "learning_rate": 8.609398285459443e-06, "loss": 0.5694027543067932, "step": 1898 }, { "epoch": 0.2662833905910397, "grad_norm": 5.892762184143066, "learning_rate": 8.607826620633806e-06, "loss": 0.490814208984375, "step": 1899 }, { "epoch": 0.2664236135455374, "grad_norm": 2.9613289833068848, "learning_rate": 8.60625421178873e-06, "loss": 0.5033987760543823, "step": 1900 }, { "epoch": 0.26656383650003507, "grad_norm": 6.477963447570801, "learning_rate": 8.604681059248483e-06, "loss": 0.5750914812088013, "step": 1901 }, { "epoch": 0.2667040594545327, "grad_norm": 3.3731532096862793, "learning_rate": 8.603107163337491e-06, "loss": 0.5807865262031555, "step": 1902 }, { "epoch": 0.26684428240903035, "grad_norm": 3.936922788619995, "learning_rate": 8.601532524380327e-06, "loss": 0.5417741537094116, "step": 1903 }, { "epoch": 0.266984505363528, "grad_norm": 2.7389514446258545, "learning_rate": 8.599957142701716e-06, "loss": 0.5517255067825317, "step": 1904 }, { "epoch": 0.26712472831802564, "grad_norm": 5.010937690734863, "learning_rate": 8.598381018626541e-06, "loss": 0.5399606823921204, "step": 1905 }, { "epoch": 0.2672649512725233, "grad_norm": 5.836872100830078, "learning_rate": 8.596804152479838e-06, "loss": 0.6224966049194336, "step": 1906 }, { "epoch": 0.267405174227021, "grad_norm": 4.607711315155029, "learning_rate": 8.595226544586792e-06, "loss": 0.6655696630477905, "step": 1907 }, { "epoch": 0.2675453971815186, "grad_norm": 2.4234373569488525, "learning_rate": 8.593648195272743e-06, "loss": 0.5029387474060059, "step": 1908 }, { "epoch": 0.26768562013601627, "grad_norm": 3.6918365955352783, "learning_rate": 8.592069104863186e-06, "loss": 0.5656893849372864, "step": 1909 }, { "epoch": 0.26782584309051394, "grad_norm": 2.723116636276245, "learning_rate": 8.590489273683764e-06, "loss": 0.5690483450889587, "step": 1910 }, { "epoch": 0.26796606604501155, "grad_norm": 3.399523973464966, "learning_rate": 8.588908702060279e-06, "loss": 0.5539677739143372, "step": 1911 }, { "epoch": 0.2681062889995092, "grad_norm": 4.68408727645874, "learning_rate": 8.58732739031868e-06, "loss": 0.5789996385574341, "step": 1912 }, { "epoch": 0.2682465119540069, "grad_norm": 5.299771785736084, "learning_rate": 8.58574533878507e-06, "loss": 0.6656997799873352, "step": 1913 }, { "epoch": 0.2683867349085045, "grad_norm": 3.1558310985565186, "learning_rate": 8.58416254778571e-06, "loss": 0.6290168166160583, "step": 1914 }, { "epoch": 0.2685269578630022, "grad_norm": 4.692863464355469, "learning_rate": 8.582579017647005e-06, "loss": 0.5925536751747131, "step": 1915 }, { "epoch": 0.26866718081749985, "grad_norm": 5.343796253204346, "learning_rate": 8.580994748695517e-06, "loss": 0.5139977931976318, "step": 1916 }, { "epoch": 0.26880740377199747, "grad_norm": 3.7751028537750244, "learning_rate": 8.579409741257962e-06, "loss": 0.5615399479866028, "step": 1917 }, { "epoch": 0.26894762672649514, "grad_norm": 5.073750019073486, "learning_rate": 8.577823995661204e-06, "loss": 0.5683436393737793, "step": 1918 }, { "epoch": 0.26908784968099275, "grad_norm": 4.361395835876465, "learning_rate": 8.576237512232262e-06, "loss": 0.5958201885223389, "step": 1919 }, { "epoch": 0.2692280726354904, "grad_norm": 2.8959784507751465, "learning_rate": 8.574650291298308e-06, "loss": 0.5695931911468506, "step": 1920 }, { "epoch": 0.2693682955899881, "grad_norm": 3.732055187225342, "learning_rate": 8.573062333186661e-06, "loss": 0.5401505827903748, "step": 1921 }, { "epoch": 0.2695085185444857, "grad_norm": 5.0171356201171875, "learning_rate": 8.5714736382248e-06, "loss": 0.5271964073181152, "step": 1922 }, { "epoch": 0.2696487414989834, "grad_norm": 3.9822781085968018, "learning_rate": 8.56988420674035e-06, "loss": 0.5722911953926086, "step": 1923 }, { "epoch": 0.26978896445348105, "grad_norm": 4.255314826965332, "learning_rate": 8.568294039061084e-06, "loss": 0.6954314112663269, "step": 1924 }, { "epoch": 0.26992918740797867, "grad_norm": 3.3930583000183105, "learning_rate": 8.566703135514942e-06, "loss": 0.5339263081550598, "step": 1925 }, { "epoch": 0.27006941036247634, "grad_norm": 4.673666000366211, "learning_rate": 8.56511149643e-06, "loss": 0.5142340064048767, "step": 1926 }, { "epoch": 0.270209633316974, "grad_norm": 3.4230778217315674, "learning_rate": 8.563519122134493e-06, "loss": 0.5865139961242676, "step": 1927 }, { "epoch": 0.2703498562714716, "grad_norm": 3.5062437057495117, "learning_rate": 8.561926012956807e-06, "loss": 0.6416163444519043, "step": 1928 }, { "epoch": 0.2704900792259693, "grad_norm": 3.136563777923584, "learning_rate": 8.560332169225478e-06, "loss": 0.5967477560043335, "step": 1929 }, { "epoch": 0.27063030218046696, "grad_norm": 4.140655040740967, "learning_rate": 8.558737591269193e-06, "loss": 0.5295991897583008, "step": 1930 }, { "epoch": 0.2707705251349646, "grad_norm": 21.241127014160156, "learning_rate": 8.557142279416794e-06, "loss": 0.5448144674301147, "step": 1931 }, { "epoch": 0.27091074808946225, "grad_norm": 5.332663059234619, "learning_rate": 8.555546233997274e-06, "loss": 0.5639660358428955, "step": 1932 }, { "epoch": 0.2710509710439599, "grad_norm": 4.832594871520996, "learning_rate": 8.553949455339771e-06, "loss": 0.5144200921058655, "step": 1933 }, { "epoch": 0.27119119399845754, "grad_norm": 4.05438756942749, "learning_rate": 8.552351943773582e-06, "loss": 0.6336546540260315, "step": 1934 }, { "epoch": 0.2713314169529552, "grad_norm": 6.20754337310791, "learning_rate": 8.55075369962815e-06, "loss": 0.6027551293373108, "step": 1935 }, { "epoch": 0.2714716399074529, "grad_norm": 2.927658796310425, "learning_rate": 8.54915472323307e-06, "loss": 0.5680960416793823, "step": 1936 }, { "epoch": 0.2716118628619505, "grad_norm": 7.431466579437256, "learning_rate": 8.547555014918091e-06, "loss": 0.6226484775543213, "step": 1937 }, { "epoch": 0.27175208581644816, "grad_norm": 3.614032745361328, "learning_rate": 8.54595457501311e-06, "loss": 0.5902671813964844, "step": 1938 }, { "epoch": 0.2718923087709458, "grad_norm": 2.9301114082336426, "learning_rate": 8.544353403848176e-06, "loss": 0.5367077589035034, "step": 1939 }, { "epoch": 0.27203253172544345, "grad_norm": 2.744837522506714, "learning_rate": 8.542751501753488e-06, "loss": 0.5798013210296631, "step": 1940 }, { "epoch": 0.2721727546799411, "grad_norm": 3.0827720165252686, "learning_rate": 8.541148869059397e-06, "loss": 0.5591835975646973, "step": 1941 }, { "epoch": 0.27231297763443874, "grad_norm": 3.858665704727173, "learning_rate": 8.539545506096402e-06, "loss": 0.6079289317131042, "step": 1942 }, { "epoch": 0.2724532005889364, "grad_norm": 4.302287578582764, "learning_rate": 8.537941413195156e-06, "loss": 0.5255364179611206, "step": 1943 }, { "epoch": 0.2725934235434341, "grad_norm": 4.014014720916748, "learning_rate": 8.536336590686462e-06, "loss": 0.674196183681488, "step": 1944 }, { "epoch": 0.2727336464979317, "grad_norm": 2.979726552963257, "learning_rate": 8.534731038901272e-06, "loss": 0.627183735370636, "step": 1945 }, { "epoch": 0.27287386945242936, "grad_norm": 8.38114070892334, "learning_rate": 8.533124758170686e-06, "loss": 0.6105585098266602, "step": 1946 }, { "epoch": 0.27301409240692703, "grad_norm": 3.764030933380127, "learning_rate": 8.53151774882596e-06, "loss": 0.5672309398651123, "step": 1947 }, { "epoch": 0.27315431536142465, "grad_norm": 2.5769572257995605, "learning_rate": 8.529910011198497e-06, "loss": 0.6195642352104187, "step": 1948 }, { "epoch": 0.2732945383159223, "grad_norm": 3.0631186962127686, "learning_rate": 8.528301545619848e-06, "loss": 0.5886156558990479, "step": 1949 }, { "epoch": 0.27343476127042, "grad_norm": 3.9521327018737793, "learning_rate": 8.526692352421721e-06, "loss": 0.47881239652633667, "step": 1950 }, { "epoch": 0.2735749842249176, "grad_norm": 5.575995922088623, "learning_rate": 8.525082431935969e-06, "loss": 0.5139523148536682, "step": 1951 }, { "epoch": 0.2737152071794153, "grad_norm": 5.1143317222595215, "learning_rate": 8.523471784494592e-06, "loss": 0.47785383462905884, "step": 1952 }, { "epoch": 0.27385543013391295, "grad_norm": 7.152234077453613, "learning_rate": 8.521860410429748e-06, "loss": 0.5313494205474854, "step": 1953 }, { "epoch": 0.27399565308841056, "grad_norm": 5.246188640594482, "learning_rate": 8.52024831007374e-06, "loss": 0.5147950649261475, "step": 1954 }, { "epoch": 0.27413587604290823, "grad_norm": 4.49190616607666, "learning_rate": 8.51863548375902e-06, "loss": 0.520752489566803, "step": 1955 }, { "epoch": 0.27427609899740585, "grad_norm": 4.458554744720459, "learning_rate": 8.51702193181819e-06, "loss": 0.6064139604568481, "step": 1956 }, { "epoch": 0.2744163219519035, "grad_norm": 5.477504253387451, "learning_rate": 8.515407654584004e-06, "loss": 0.46716123819351196, "step": 1957 }, { "epoch": 0.2745565449064012, "grad_norm": 7.994570255279541, "learning_rate": 8.513792652389366e-06, "loss": 0.5407637357711792, "step": 1958 }, { "epoch": 0.2746967678608988, "grad_norm": 7.650838375091553, "learning_rate": 8.512176925567325e-06, "loss": 0.6147035956382751, "step": 1959 }, { "epoch": 0.2748369908153965, "grad_norm": 7.696932315826416, "learning_rate": 8.510560474451084e-06, "loss": 0.5164457559585571, "step": 1960 }, { "epoch": 0.27497721376989415, "grad_norm": 2.805744171142578, "learning_rate": 8.508943299373993e-06, "loss": 0.5901681184768677, "step": 1961 }, { "epoch": 0.27511743672439176, "grad_norm": 4.018374443054199, "learning_rate": 8.507325400669551e-06, "loss": 0.5004661083221436, "step": 1962 }, { "epoch": 0.27525765967888943, "grad_norm": 4.649715900421143, "learning_rate": 8.505706778671407e-06, "loss": 0.6400988101959229, "step": 1963 }, { "epoch": 0.2753978826333871, "grad_norm": 15.100796699523926, "learning_rate": 8.504087433713361e-06, "loss": 0.6025710105895996, "step": 1964 }, { "epoch": 0.2755381055878847, "grad_norm": 3.7002387046813965, "learning_rate": 8.502467366129361e-06, "loss": 0.5604220032691956, "step": 1965 }, { "epoch": 0.2756783285423824, "grad_norm": 6.470468997955322, "learning_rate": 8.500846576253498e-06, "loss": 0.5130401849746704, "step": 1966 }, { "epoch": 0.27581855149688006, "grad_norm": 9.407022476196289, "learning_rate": 8.499225064420025e-06, "loss": 0.5299760103225708, "step": 1967 }, { "epoch": 0.2759587744513777, "grad_norm": 2.8164448738098145, "learning_rate": 8.497602830963331e-06, "loss": 0.5759710073471069, "step": 1968 }, { "epoch": 0.27609899740587535, "grad_norm": 3.6773905754089355, "learning_rate": 8.49597987621796e-06, "loss": 0.5801406502723694, "step": 1969 }, { "epoch": 0.276239220360373, "grad_norm": 2.948413848876953, "learning_rate": 8.494356200518603e-06, "loss": 0.5416200160980225, "step": 1970 }, { "epoch": 0.27637944331487063, "grad_norm": 3.323103666305542, "learning_rate": 8.492731804200103e-06, "loss": 0.5586788654327393, "step": 1971 }, { "epoch": 0.2765196662693683, "grad_norm": 5.573704242706299, "learning_rate": 8.491106687597447e-06, "loss": 0.4605604410171509, "step": 1972 }, { "epoch": 0.276659889223866, "grad_norm": 5.677545070648193, "learning_rate": 8.489480851045774e-06, "loss": 0.4006184935569763, "step": 1973 }, { "epoch": 0.2768001121783636, "grad_norm": 3.8256373405456543, "learning_rate": 8.487854294880368e-06, "loss": 0.5435730814933777, "step": 1974 }, { "epoch": 0.27694033513286126, "grad_norm": 3.0266482830047607, "learning_rate": 8.486227019436668e-06, "loss": 0.6451830267906189, "step": 1975 }, { "epoch": 0.2770805580873589, "grad_norm": 3.688778877258301, "learning_rate": 8.48459902505025e-06, "loss": 0.5677943229675293, "step": 1976 }, { "epoch": 0.27722078104185655, "grad_norm": 3.6287291049957275, "learning_rate": 8.48297031205685e-06, "loss": 0.5769397020339966, "step": 1977 }, { "epoch": 0.2773610039963542, "grad_norm": 11.177260398864746, "learning_rate": 8.481340880792346e-06, "loss": 0.6332710385322571, "step": 1978 }, { "epoch": 0.27750122695085183, "grad_norm": 2.9953465461730957, "learning_rate": 8.479710731592763e-06, "loss": 0.5825208425521851, "step": 1979 }, { "epoch": 0.2776414499053495, "grad_norm": 3.514650583267212, "learning_rate": 8.478079864794281e-06, "loss": 0.4898960590362549, "step": 1980 }, { "epoch": 0.2777816728598472, "grad_norm": 5.667956352233887, "learning_rate": 8.476448280733221e-06, "loss": 0.3771824836730957, "step": 1981 }, { "epoch": 0.2779218958143448, "grad_norm": 4.1006903648376465, "learning_rate": 8.474815979746054e-06, "loss": 0.47053292393684387, "step": 1982 }, { "epoch": 0.27806211876884246, "grad_norm": 3.9826507568359375, "learning_rate": 8.4731829621694e-06, "loss": 0.6474391222000122, "step": 1983 }, { "epoch": 0.27820234172334013, "grad_norm": 2.5359182357788086, "learning_rate": 8.471549228340026e-06, "loss": 0.5898668766021729, "step": 1984 }, { "epoch": 0.27834256467783774, "grad_norm": 2.4189488887786865, "learning_rate": 8.469914778594845e-06, "loss": 0.6257592439651489, "step": 1985 }, { "epoch": 0.2784827876323354, "grad_norm": 5.078105449676514, "learning_rate": 8.46827961327092e-06, "loss": 0.55628901720047, "step": 1986 }, { "epoch": 0.2786230105868331, "grad_norm": 4.079092025756836, "learning_rate": 8.466643732705463e-06, "loss": 0.5366882085800171, "step": 1987 }, { "epoch": 0.2787632335413307, "grad_norm": 5.6136088371276855, "learning_rate": 8.46500713723583e-06, "loss": 0.6292518973350525, "step": 1988 }, { "epoch": 0.2789034564958284, "grad_norm": 3.8444204330444336, "learning_rate": 8.463369827199525e-06, "loss": 0.6128564476966858, "step": 1989 }, { "epoch": 0.27904367945032604, "grad_norm": 10.845605850219727, "learning_rate": 8.461731802934202e-06, "loss": 0.5402828454971313, "step": 1990 }, { "epoch": 0.27918390240482366, "grad_norm": 3.809274196624756, "learning_rate": 8.460093064777657e-06, "loss": 0.53385329246521, "step": 1991 }, { "epoch": 0.27932412535932133, "grad_norm": 2.742027521133423, "learning_rate": 8.45845361306784e-06, "loss": 0.5746668577194214, "step": 1992 }, { "epoch": 0.279464348313819, "grad_norm": 3.1982908248901367, "learning_rate": 8.456813448142844e-06, "loss": 0.461914598941803, "step": 1993 }, { "epoch": 0.2796045712683166, "grad_norm": 6.372834205627441, "learning_rate": 8.45517257034091e-06, "loss": 0.6409652233123779, "step": 1994 }, { "epoch": 0.2797447942228143, "grad_norm": 3.143906593322754, "learning_rate": 8.453530980000423e-06, "loss": 0.6603090167045593, "step": 1995 }, { "epoch": 0.2798850171773119, "grad_norm": 3.389554738998413, "learning_rate": 8.451888677459924e-06, "loss": 0.4961227774620056, "step": 1996 }, { "epoch": 0.28002524013180957, "grad_norm": 4.879336357116699, "learning_rate": 8.450245663058091e-06, "loss": 0.5861974954605103, "step": 1997 }, { "epoch": 0.28016546308630724, "grad_norm": 2.8860442638397217, "learning_rate": 8.448601937133751e-06, "loss": 0.4901604652404785, "step": 1998 }, { "epoch": 0.28030568604080486, "grad_norm": 3.465757369995117, "learning_rate": 8.446957500025883e-06, "loss": 0.6037340760231018, "step": 1999 }, { "epoch": 0.28044590899530253, "grad_norm": 2.2276415824890137, "learning_rate": 8.445312352073607e-06, "loss": 0.5899030566215515, "step": 2000 }, { "epoch": 0.2805861319498002, "grad_norm": 3.299391984939575, "learning_rate": 8.443666493616189e-06, "loss": 0.5753309726715088, "step": 2001 }, { "epoch": 0.2807263549042978, "grad_norm": 4.061591148376465, "learning_rate": 8.442019924993048e-06, "loss": 0.5709566473960876, "step": 2002 }, { "epoch": 0.2808665778587955, "grad_norm": 5.50213623046875, "learning_rate": 8.440372646543745e-06, "loss": 0.5945056080818176, "step": 2003 }, { "epoch": 0.28100680081329316, "grad_norm": 3.1606476306915283, "learning_rate": 8.438724658607986e-06, "loss": 0.6493343710899353, "step": 2004 }, { "epoch": 0.28114702376779077, "grad_norm": 2.586306571960449, "learning_rate": 8.437075961525628e-06, "loss": 0.5201458930969238, "step": 2005 }, { "epoch": 0.28128724672228844, "grad_norm": 4.369040012359619, "learning_rate": 8.435426555636668e-06, "loss": 0.534527063369751, "step": 2006 }, { "epoch": 0.2814274696767861, "grad_norm": 2.8477747440338135, "learning_rate": 8.433776441281255e-06, "loss": 0.5865775346755981, "step": 2007 }, { "epoch": 0.28156769263128373, "grad_norm": 4.852731704711914, "learning_rate": 8.43212561879968e-06, "loss": 0.5867157578468323, "step": 2008 }, { "epoch": 0.2817079155857814, "grad_norm": 2.9200894832611084, "learning_rate": 8.430474088532384e-06, "loss": 0.6295478940010071, "step": 2009 }, { "epoch": 0.28184813854027907, "grad_norm": 3.250394582748413, "learning_rate": 8.428821850819949e-06, "loss": 0.6485199928283691, "step": 2010 }, { "epoch": 0.2819883614947767, "grad_norm": 5.584706783294678, "learning_rate": 8.427168906003107e-06, "loss": 0.521002471446991, "step": 2011 }, { "epoch": 0.28212858444927436, "grad_norm": 2.9008965492248535, "learning_rate": 8.425515254422736e-06, "loss": 0.6087394952774048, "step": 2012 }, { "epoch": 0.28226880740377197, "grad_norm": 3.236445188522339, "learning_rate": 8.423860896419857e-06, "loss": 0.6499676704406738, "step": 2013 }, { "epoch": 0.28240903035826964, "grad_norm": 3.943305015563965, "learning_rate": 8.422205832335637e-06, "loss": 0.6375818252563477, "step": 2014 }, { "epoch": 0.2825492533127673, "grad_norm": 3.9410483837127686, "learning_rate": 8.420550062511391e-06, "loss": 0.5897077322006226, "step": 2015 }, { "epoch": 0.2826894762672649, "grad_norm": 7.471409797668457, "learning_rate": 8.418893587288575e-06, "loss": 0.5565953254699707, "step": 2016 }, { "epoch": 0.2828296992217626, "grad_norm": 2.789966344833374, "learning_rate": 8.417236407008796e-06, "loss": 0.6172618269920349, "step": 2017 }, { "epoch": 0.28296992217626027, "grad_norm": 3.5060856342315674, "learning_rate": 8.415578522013806e-06, "loss": 0.5841090679168701, "step": 2018 }, { "epoch": 0.2831101451307579, "grad_norm": 3.2963240146636963, "learning_rate": 8.413919932645494e-06, "loss": 0.5467811822891235, "step": 2019 }, { "epoch": 0.28325036808525555, "grad_norm": 3.240886926651001, "learning_rate": 8.412260639245907e-06, "loss": 0.5062946081161499, "step": 2020 }, { "epoch": 0.2833905910397532, "grad_norm": 3.083270788192749, "learning_rate": 8.410600642157228e-06, "loss": 0.5273875594139099, "step": 2021 }, { "epoch": 0.28353081399425084, "grad_norm": 3.4509408473968506, "learning_rate": 8.408939941721785e-06, "loss": 0.5613828301429749, "step": 2022 }, { "epoch": 0.2836710369487485, "grad_norm": 9.343088150024414, "learning_rate": 8.407278538282058e-06, "loss": 0.5643124580383301, "step": 2023 }, { "epoch": 0.2838112599032462, "grad_norm": 2.835740327835083, "learning_rate": 8.405616432180667e-06, "loss": 0.5021304488182068, "step": 2024 }, { "epoch": 0.2839514828577438, "grad_norm": 5.0930047035217285, "learning_rate": 8.403953623760376e-06, "loss": 0.6344360113143921, "step": 2025 }, { "epoch": 0.28409170581224147, "grad_norm": 3.727936267852783, "learning_rate": 8.402290113364096e-06, "loss": 0.6049938201904297, "step": 2026 }, { "epoch": 0.28423192876673914, "grad_norm": 8.042560577392578, "learning_rate": 8.400625901334883e-06, "loss": 0.588661789894104, "step": 2027 }, { "epoch": 0.28437215172123675, "grad_norm": 3.0369162559509277, "learning_rate": 8.398960988015938e-06, "loss": 0.5081719160079956, "step": 2028 }, { "epoch": 0.2845123746757344, "grad_norm": 3.0481183528900146, "learning_rate": 8.397295373750604e-06, "loss": 0.5303040146827698, "step": 2029 }, { "epoch": 0.2846525976302321, "grad_norm": 2.505330801010132, "learning_rate": 8.39562905888237e-06, "loss": 0.5178381204605103, "step": 2030 }, { "epoch": 0.2847928205847297, "grad_norm": 7.918802261352539, "learning_rate": 8.393962043754872e-06, "loss": 0.6145185232162476, "step": 2031 }, { "epoch": 0.2849330435392274, "grad_norm": 3.5355188846588135, "learning_rate": 8.392294328711884e-06, "loss": 0.6058331727981567, "step": 2032 }, { "epoch": 0.285073266493725, "grad_norm": 8.504541397094727, "learning_rate": 8.39062591409733e-06, "loss": 0.6111521124839783, "step": 2033 }, { "epoch": 0.28521348944822267, "grad_norm": 3.562842845916748, "learning_rate": 8.388956800255278e-06, "loss": 0.6128937005996704, "step": 2034 }, { "epoch": 0.28535371240272034, "grad_norm": 4.056427478790283, "learning_rate": 8.387286987529942e-06, "loss": 0.47805508971214294, "step": 2035 }, { "epoch": 0.28549393535721795, "grad_norm": 3.8702359199523926, "learning_rate": 8.38561647626567e-06, "loss": 0.6074252128601074, "step": 2036 }, { "epoch": 0.2856341583117156, "grad_norm": 4.141784191131592, "learning_rate": 8.383945266806963e-06, "loss": 0.6131556630134583, "step": 2037 }, { "epoch": 0.2857743812662133, "grad_norm": 3.6815578937530518, "learning_rate": 8.382273359498468e-06, "loss": 0.5597299337387085, "step": 2038 }, { "epoch": 0.2859146042207109, "grad_norm": 3.2569761276245117, "learning_rate": 8.380600754684969e-06, "loss": 0.4902728199958801, "step": 2039 }, { "epoch": 0.2860548271752086, "grad_norm": 2.6827807426452637, "learning_rate": 8.378927452711396e-06, "loss": 0.5728330612182617, "step": 2040 }, { "epoch": 0.28619505012970625, "grad_norm": 3.075202226638794, "learning_rate": 8.377253453922825e-06, "loss": 0.5878757238388062, "step": 2041 }, { "epoch": 0.28633527308420387, "grad_norm": 5.804978847503662, "learning_rate": 8.375578758664473e-06, "loss": 0.589236855506897, "step": 2042 }, { "epoch": 0.28647549603870154, "grad_norm": 4.712141513824463, "learning_rate": 8.373903367281705e-06, "loss": 0.583387553691864, "step": 2043 }, { "epoch": 0.2866157189931992, "grad_norm": 3.693999767303467, "learning_rate": 8.372227280120023e-06, "loss": 0.6265102624893188, "step": 2044 }, { "epoch": 0.2867559419476968, "grad_norm": 72.52173614501953, "learning_rate": 8.370550497525077e-06, "loss": 0.4955158531665802, "step": 2045 }, { "epoch": 0.2868961649021945, "grad_norm": 5.902512073516846, "learning_rate": 8.36887301984266e-06, "loss": 0.5340797901153564, "step": 2046 }, { "epoch": 0.28703638785669217, "grad_norm": 2.919083833694458, "learning_rate": 8.367194847418707e-06, "loss": 0.5528596639633179, "step": 2047 }, { "epoch": 0.2871766108111898, "grad_norm": 3.1060264110565186, "learning_rate": 8.365515980599297e-06, "loss": 0.566946268081665, "step": 2048 }, { "epoch": 0.28731683376568745, "grad_norm": 3.0270485877990723, "learning_rate": 8.363836419730653e-06, "loss": 0.5972481369972229, "step": 2049 }, { "epoch": 0.28745705672018507, "grad_norm": 4.704928874969482, "learning_rate": 8.362156165159138e-06, "loss": 0.5664722919464111, "step": 2050 }, { "epoch": 0.28759727967468274, "grad_norm": 3.8412721157073975, "learning_rate": 8.360475217231265e-06, "loss": 0.5491865873336792, "step": 2051 }, { "epoch": 0.2877375026291804, "grad_norm": 5.134997367858887, "learning_rate": 8.35879357629368e-06, "loss": 0.5801665782928467, "step": 2052 }, { "epoch": 0.287877725583678, "grad_norm": 5.1077728271484375, "learning_rate": 8.35711124269318e-06, "loss": 0.5714231133460999, "step": 2053 }, { "epoch": 0.2880179485381757, "grad_norm": 3.4535627365112305, "learning_rate": 8.355428216776702e-06, "loss": 0.6119486093521118, "step": 2054 }, { "epoch": 0.28815817149267337, "grad_norm": 2.6473817825317383, "learning_rate": 8.353744498891325e-06, "loss": 0.5262473821640015, "step": 2055 }, { "epoch": 0.288298394447171, "grad_norm": 2.9027938842773438, "learning_rate": 8.352060089384273e-06, "loss": 0.4922884404659271, "step": 2056 }, { "epoch": 0.28843861740166865, "grad_norm": 3.14028000831604, "learning_rate": 8.35037498860291e-06, "loss": 0.6245633363723755, "step": 2057 }, { "epoch": 0.2885788403561663, "grad_norm": 3.144652843475342, "learning_rate": 8.348689196894743e-06, "loss": 0.6220868229866028, "step": 2058 }, { "epoch": 0.28871906331066394, "grad_norm": 8.679044723510742, "learning_rate": 8.347002714607424e-06, "loss": 0.5688492059707642, "step": 2059 }, { "epoch": 0.2888592862651616, "grad_norm": 3.044524669647217, "learning_rate": 8.345315542088746e-06, "loss": 0.5403327941894531, "step": 2060 }, { "epoch": 0.2889995092196593, "grad_norm": 2.4206202030181885, "learning_rate": 8.343627679686643e-06, "loss": 0.5362212657928467, "step": 2061 }, { "epoch": 0.2891397321741569, "grad_norm": 3.4509871006011963, "learning_rate": 8.34193912774919e-06, "loss": 0.5279580354690552, "step": 2062 }, { "epoch": 0.28927995512865456, "grad_norm": 3.0871379375457764, "learning_rate": 8.340249886624612e-06, "loss": 0.5516982078552246, "step": 2063 }, { "epoch": 0.28942017808315224, "grad_norm": 5.633816719055176, "learning_rate": 8.338559956661265e-06, "loss": 0.532084047794342, "step": 2064 }, { "epoch": 0.28956040103764985, "grad_norm": 8.468451499938965, "learning_rate": 8.336869338207655e-06, "loss": 0.6779213547706604, "step": 2065 }, { "epoch": 0.2897006239921475, "grad_norm": 4.3086347579956055, "learning_rate": 8.335178031612428e-06, "loss": 0.5576326847076416, "step": 2066 }, { "epoch": 0.2898408469466452, "grad_norm": 3.529494524002075, "learning_rate": 8.333486037224371e-06, "loss": 0.6068576574325562, "step": 2067 }, { "epoch": 0.2899810699011428, "grad_norm": 4.562119483947754, "learning_rate": 8.331793355392415e-06, "loss": 0.5553630590438843, "step": 2068 }, { "epoch": 0.2901212928556405, "grad_norm": 3.6713716983795166, "learning_rate": 8.330099986465627e-06, "loss": 0.626011848449707, "step": 2069 }, { "epoch": 0.2902615158101381, "grad_norm": 3.4313805103302, "learning_rate": 8.328405930793227e-06, "loss": 0.6027530431747437, "step": 2070 }, { "epoch": 0.29040173876463576, "grad_norm": 2.8345706462860107, "learning_rate": 8.326711188724561e-06, "loss": 0.5136862993240356, "step": 2071 }, { "epoch": 0.29054196171913343, "grad_norm": 3.276057243347168, "learning_rate": 8.32501576060913e-06, "loss": 0.6646316051483154, "step": 2072 }, { "epoch": 0.29068218467363105, "grad_norm": 3.436735153198242, "learning_rate": 8.32331964679657e-06, "loss": 0.4873068928718567, "step": 2073 }, { "epoch": 0.2908224076281287, "grad_norm": 3.769728660583496, "learning_rate": 8.321622847636662e-06, "loss": 0.5687506198883057, "step": 2074 }, { "epoch": 0.2909626305826264, "grad_norm": 3.966982841491699, "learning_rate": 8.319925363479322e-06, "loss": 0.5982519388198853, "step": 2075 }, { "epoch": 0.291102853537124, "grad_norm": 2.3651211261749268, "learning_rate": 8.318227194674616e-06, "loss": 0.5116792917251587, "step": 2076 }, { "epoch": 0.2912430764916217, "grad_norm": 3.9723944664001465, "learning_rate": 8.316528341572745e-06, "loss": 0.6187714338302612, "step": 2077 }, { "epoch": 0.29138329944611935, "grad_norm": 2.776116371154785, "learning_rate": 8.31482880452405e-06, "loss": 0.5862654447555542, "step": 2078 }, { "epoch": 0.29152352240061696, "grad_norm": 3.7586982250213623, "learning_rate": 8.313128583879023e-06, "loss": 0.6244102716445923, "step": 2079 }, { "epoch": 0.29166374535511463, "grad_norm": 6.254406452178955, "learning_rate": 8.311427679988282e-06, "loss": 0.49143582582473755, "step": 2080 }, { "epoch": 0.2918039683096123, "grad_norm": 3.671855926513672, "learning_rate": 8.309726093202598e-06, "loss": 0.5894014239311218, "step": 2081 }, { "epoch": 0.2919441912641099, "grad_norm": 3.4521803855895996, "learning_rate": 8.308023823872876e-06, "loss": 0.598542332649231, "step": 2082 }, { "epoch": 0.2920844142186076, "grad_norm": 2.779567003250122, "learning_rate": 8.30632087235017e-06, "loss": 0.5163477659225464, "step": 2083 }, { "epoch": 0.29222463717310526, "grad_norm": 121.57207489013672, "learning_rate": 8.304617238985662e-06, "loss": 0.4934823215007782, "step": 2084 }, { "epoch": 0.2923648601276029, "grad_norm": 2.271583080291748, "learning_rate": 8.302912924130685e-06, "loss": 0.5736873149871826, "step": 2085 }, { "epoch": 0.29250508308210055, "grad_norm": 2.8191192150115967, "learning_rate": 8.301207928136708e-06, "loss": 0.662481427192688, "step": 2086 }, { "epoch": 0.2926453060365982, "grad_norm": 10.318970680236816, "learning_rate": 8.299502251355344e-06, "loss": 0.6170225143432617, "step": 2087 }, { "epoch": 0.29278552899109583, "grad_norm": 3.9661409854888916, "learning_rate": 8.297795894138342e-06, "loss": 0.5548955202102661, "step": 2088 }, { "epoch": 0.2929257519455935, "grad_norm": 2.786928415298462, "learning_rate": 8.296088856837591e-06, "loss": 0.5672979354858398, "step": 2089 }, { "epoch": 0.2930659749000911, "grad_norm": 4.467149257659912, "learning_rate": 8.29438113980513e-06, "loss": 0.5463626384735107, "step": 2090 }, { "epoch": 0.2932061978545888, "grad_norm": 3.709786891937256, "learning_rate": 8.292672743393123e-06, "loss": 0.5403978824615479, "step": 2091 }, { "epoch": 0.29334642080908646, "grad_norm": 4.143531799316406, "learning_rate": 8.290963667953885e-06, "loss": 0.6241132020950317, "step": 2092 }, { "epoch": 0.2934866437635841, "grad_norm": 9.72048282623291, "learning_rate": 8.28925391383987e-06, "loss": 0.6193321943283081, "step": 2093 }, { "epoch": 0.29362686671808175, "grad_norm": 2.1803150177001953, "learning_rate": 8.287543481403665e-06, "loss": 0.5615444183349609, "step": 2094 }, { "epoch": 0.2937670896725794, "grad_norm": 3.409013032913208, "learning_rate": 8.285832370998005e-06, "loss": 0.5886234641075134, "step": 2095 }, { "epoch": 0.29390731262707703, "grad_norm": 3.934475898742676, "learning_rate": 8.284120582975763e-06, "loss": 0.5931459665298462, "step": 2096 }, { "epoch": 0.2940475355815747, "grad_norm": 4.870490074157715, "learning_rate": 8.282408117689945e-06, "loss": 0.4773617088794708, "step": 2097 }, { "epoch": 0.2941877585360724, "grad_norm": 2.8923583030700684, "learning_rate": 8.280694975493707e-06, "loss": 0.5851510763168335, "step": 2098 }, { "epoch": 0.29432798149057, "grad_norm": 3.009111166000366, "learning_rate": 8.278981156740338e-06, "loss": 0.5975564122200012, "step": 2099 }, { "epoch": 0.29446820444506766, "grad_norm": 3.187609910964966, "learning_rate": 8.277266661783267e-06, "loss": 0.5566803216934204, "step": 2100 }, { "epoch": 0.29460842739956533, "grad_norm": 2.8585026264190674, "learning_rate": 8.275551490976067e-06, "loss": 0.5744675397872925, "step": 2101 }, { "epoch": 0.29474865035406295, "grad_norm": 3.4302525520324707, "learning_rate": 8.27383564467244e-06, "loss": 0.45979392528533936, "step": 2102 }, { "epoch": 0.2948888733085606, "grad_norm": 4.536699295043945, "learning_rate": 8.272119123226242e-06, "loss": 0.63271564245224, "step": 2103 }, { "epoch": 0.2950290962630583, "grad_norm": 3.1966183185577393, "learning_rate": 8.270401926991455e-06, "loss": 0.6263521313667297, "step": 2104 }, { "epoch": 0.2951693192175559, "grad_norm": 3.3290271759033203, "learning_rate": 8.26868405632221e-06, "loss": 0.5283573269844055, "step": 2105 }, { "epoch": 0.2953095421720536, "grad_norm": 3.032201051712036, "learning_rate": 8.266965511572767e-06, "loss": 0.5595779418945312, "step": 2106 }, { "epoch": 0.2954497651265512, "grad_norm": 4.3709025382995605, "learning_rate": 8.265246293097536e-06, "loss": 0.553001880645752, "step": 2107 }, { "epoch": 0.29558998808104886, "grad_norm": 6.116060733795166, "learning_rate": 8.263526401251058e-06, "loss": 0.537335216999054, "step": 2108 }, { "epoch": 0.29573021103554653, "grad_norm": 3.694286823272705, "learning_rate": 8.261805836388018e-06, "loss": 0.6867038607597351, "step": 2109 }, { "epoch": 0.29587043399004415, "grad_norm": 3.1689815521240234, "learning_rate": 8.260084598863231e-06, "loss": 0.5765888690948486, "step": 2110 }, { "epoch": 0.2960106569445418, "grad_norm": 2.911440849304199, "learning_rate": 8.258362689031665e-06, "loss": 0.5813426375389099, "step": 2111 }, { "epoch": 0.2961508798990395, "grad_norm": 2.8587486743927, "learning_rate": 8.256640107248414e-06, "loss": 0.4945342242717743, "step": 2112 }, { "epoch": 0.2962911028535371, "grad_norm": 4.053394794464111, "learning_rate": 8.254916853868718e-06, "loss": 0.5285744071006775, "step": 2113 }, { "epoch": 0.2964313258080348, "grad_norm": 3.451340913772583, "learning_rate": 8.253192929247948e-06, "loss": 0.4450187087059021, "step": 2114 }, { "epoch": 0.29657154876253244, "grad_norm": 2.7291548252105713, "learning_rate": 8.251468333741623e-06, "loss": 0.5339919328689575, "step": 2115 }, { "epoch": 0.29671177171703006, "grad_norm": 3.2346065044403076, "learning_rate": 8.249743067705394e-06, "loss": 0.5212621092796326, "step": 2116 }, { "epoch": 0.29685199467152773, "grad_norm": 3.7162060737609863, "learning_rate": 8.24801713149505e-06, "loss": 0.5006344318389893, "step": 2117 }, { "epoch": 0.2969922176260254, "grad_norm": 3.906852960586548, "learning_rate": 8.246290525466523e-06, "loss": 0.5855118036270142, "step": 2118 }, { "epoch": 0.297132440580523, "grad_norm": 24.298480987548828, "learning_rate": 8.244563249975878e-06, "loss": 0.5458447337150574, "step": 2119 }, { "epoch": 0.2972726635350207, "grad_norm": 2.773667812347412, "learning_rate": 8.24283530537932e-06, "loss": 0.5582234859466553, "step": 2120 }, { "epoch": 0.29741288648951836, "grad_norm": 18.042587280273438, "learning_rate": 8.241106692033193e-06, "loss": 0.5287619829177856, "step": 2121 }, { "epoch": 0.297553109444016, "grad_norm": 2.656071186065674, "learning_rate": 8.239377410293979e-06, "loss": 0.5997747778892517, "step": 2122 }, { "epoch": 0.29769333239851364, "grad_norm": 3.879394054412842, "learning_rate": 8.237647460518294e-06, "loss": 0.5074975490570068, "step": 2123 }, { "epoch": 0.2978335553530113, "grad_norm": 2.512010097503662, "learning_rate": 8.2359168430629e-06, "loss": 0.5881210565567017, "step": 2124 }, { "epoch": 0.29797377830750893, "grad_norm": 2.9990875720977783, "learning_rate": 8.234185558284685e-06, "loss": 0.59576016664505, "step": 2125 }, { "epoch": 0.2981140012620066, "grad_norm": 6.971667766571045, "learning_rate": 8.232453606540684e-06, "loss": 0.5252351760864258, "step": 2126 }, { "epoch": 0.2982542242165042, "grad_norm": 4.268877983093262, "learning_rate": 8.230720988188068e-06, "loss": 0.5341453552246094, "step": 2127 }, { "epoch": 0.2983944471710019, "grad_norm": 2.7993035316467285, "learning_rate": 8.228987703584141e-06, "loss": 0.5957086086273193, "step": 2128 }, { "epoch": 0.29853467012549956, "grad_norm": 3.548642158508301, "learning_rate": 8.227253753086351e-06, "loss": 0.608173131942749, "step": 2129 }, { "epoch": 0.2986748930799972, "grad_norm": 3.0337636470794678, "learning_rate": 8.225519137052275e-06, "loss": 0.57508784532547, "step": 2130 }, { "epoch": 0.29881511603449484, "grad_norm": 3.323979139328003, "learning_rate": 8.223783855839636e-06, "loss": 0.5620020031929016, "step": 2131 }, { "epoch": 0.2989553389889925, "grad_norm": 3.711397886276245, "learning_rate": 8.22204790980629e-06, "loss": 0.5685936212539673, "step": 2132 }, { "epoch": 0.29909556194349013, "grad_norm": 4.196128845214844, "learning_rate": 8.220311299310227e-06, "loss": 0.577837347984314, "step": 2133 }, { "epoch": 0.2992357848979878, "grad_norm": 2.326042890548706, "learning_rate": 8.218574024709581e-06, "loss": 0.5707622766494751, "step": 2134 }, { "epoch": 0.29937600785248547, "grad_norm": 3.673360586166382, "learning_rate": 8.216836086362616e-06, "loss": 0.5442360639572144, "step": 2135 }, { "epoch": 0.2995162308069831, "grad_norm": 5.042708396911621, "learning_rate": 8.215097484627738e-06, "loss": 0.5976307392120361, "step": 2136 }, { "epoch": 0.29965645376148076, "grad_norm": 19.864614486694336, "learning_rate": 8.213358219863488e-06, "loss": 0.5897817611694336, "step": 2137 }, { "epoch": 0.2997966767159784, "grad_norm": 9.10710620880127, "learning_rate": 8.211618292428544e-06, "loss": 0.6205715537071228, "step": 2138 }, { "epoch": 0.29993689967047604, "grad_norm": 7.967144966125488, "learning_rate": 8.209877702681717e-06, "loss": 0.459354430437088, "step": 2139 }, { "epoch": 0.3000771226249737, "grad_norm": 7.057395935058594, "learning_rate": 8.208136450981963e-06, "loss": 0.5136217474937439, "step": 2140 }, { "epoch": 0.3002173455794714, "grad_norm": 2.854914665222168, "learning_rate": 8.206394537688367e-06, "loss": 0.6470853090286255, "step": 2141 }, { "epoch": 0.300357568533969, "grad_norm": 5.522398471832275, "learning_rate": 8.20465196316015e-06, "loss": 0.4876350462436676, "step": 2142 }, { "epoch": 0.30049779148846667, "grad_norm": 4.078836441040039, "learning_rate": 8.202908727756677e-06, "loss": 0.6128321290016174, "step": 2143 }, { "epoch": 0.30063801444296434, "grad_norm": 5.276961803436279, "learning_rate": 8.201164831837442e-06, "loss": 0.6822034120559692, "step": 2144 }, { "epoch": 0.30077823739746196, "grad_norm": 3.4469614028930664, "learning_rate": 8.199420275762077e-06, "loss": 0.6299372911453247, "step": 2145 }, { "epoch": 0.3009184603519596, "grad_norm": 3.9805185794830322, "learning_rate": 8.197675059890353e-06, "loss": 0.6468787789344788, "step": 2146 }, { "epoch": 0.30105868330645724, "grad_norm": 2.6333279609680176, "learning_rate": 8.195929184582174e-06, "loss": 0.5848275423049927, "step": 2147 }, { "epoch": 0.3011989062609549, "grad_norm": 2.355585813522339, "learning_rate": 8.194182650197582e-06, "loss": 0.5804656147956848, "step": 2148 }, { "epoch": 0.3013391292154526, "grad_norm": 4.670017719268799, "learning_rate": 8.19243545709675e-06, "loss": 0.5673704147338867, "step": 2149 }, { "epoch": 0.3014793521699502, "grad_norm": 6.485518932342529, "learning_rate": 8.190687605639994e-06, "loss": 0.5506183505058289, "step": 2150 }, { "epoch": 0.30161957512444787, "grad_norm": 4.534637451171875, "learning_rate": 8.188939096187763e-06, "loss": 0.5220195055007935, "step": 2151 }, { "epoch": 0.30175979807894554, "grad_norm": 3.083343982696533, "learning_rate": 8.187189929100638e-06, "loss": 0.5932941436767578, "step": 2152 }, { "epoch": 0.30190002103344316, "grad_norm": 3.273442506790161, "learning_rate": 8.185440104739341e-06, "loss": 0.48160624504089355, "step": 2153 }, { "epoch": 0.3020402439879408, "grad_norm": 3.572981834411621, "learning_rate": 8.183689623464729e-06, "loss": 0.4801420569419861, "step": 2154 }, { "epoch": 0.3021804669424385, "grad_norm": 17.632476806640625, "learning_rate": 8.181938485637788e-06, "loss": 0.4790080189704895, "step": 2155 }, { "epoch": 0.3023206898969361, "grad_norm": 3.7538905143737793, "learning_rate": 8.180186691619647e-06, "loss": 0.5738979578018188, "step": 2156 }, { "epoch": 0.3024609128514338, "grad_norm": 3.290659189224243, "learning_rate": 8.17843424177157e-06, "loss": 0.5477414131164551, "step": 2157 }, { "epoch": 0.30260113580593145, "grad_norm": 3.32537841796875, "learning_rate": 8.176681136454948e-06, "loss": 0.5034183263778687, "step": 2158 }, { "epoch": 0.30274135876042907, "grad_norm": 5.045884609222412, "learning_rate": 8.174927376031316e-06, "loss": 0.6287804841995239, "step": 2159 }, { "epoch": 0.30288158171492674, "grad_norm": 2.552283763885498, "learning_rate": 8.173172960862342e-06, "loss": 0.5234578847885132, "step": 2160 }, { "epoch": 0.3030218046694244, "grad_norm": 4.449857234954834, "learning_rate": 8.171417891309827e-06, "loss": 0.6455628275871277, "step": 2161 }, { "epoch": 0.303162027623922, "grad_norm": 4.0570220947265625, "learning_rate": 8.169662167735709e-06, "loss": 0.5644753575325012, "step": 2162 }, { "epoch": 0.3033022505784197, "grad_norm": 3.9317777156829834, "learning_rate": 8.167905790502057e-06, "loss": 0.47175800800323486, "step": 2163 }, { "epoch": 0.3034424735329173, "grad_norm": 6.335577011108398, "learning_rate": 8.16614875997108e-06, "loss": 0.5529195070266724, "step": 2164 }, { "epoch": 0.303582696487415, "grad_norm": 3.589775800704956, "learning_rate": 8.164391076505118e-06, "loss": 0.5548098087310791, "step": 2165 }, { "epoch": 0.30372291944191265, "grad_norm": 3.8662514686584473, "learning_rate": 8.16263274046665e-06, "loss": 0.5304652452468872, "step": 2166 }, { "epoch": 0.30386314239641027, "grad_norm": 3.8289363384246826, "learning_rate": 8.160873752218283e-06, "loss": 0.5099050998687744, "step": 2167 }, { "epoch": 0.30400336535090794, "grad_norm": 3.7372982501983643, "learning_rate": 8.159114112122762e-06, "loss": 0.4926493465900421, "step": 2168 }, { "epoch": 0.3041435883054056, "grad_norm": 4.723440170288086, "learning_rate": 8.15735382054297e-06, "loss": 0.6472961902618408, "step": 2169 }, { "epoch": 0.3042838112599032, "grad_norm": 3.3326308727264404, "learning_rate": 8.155592877841917e-06, "loss": 0.5198704600334167, "step": 2170 }, { "epoch": 0.3044240342144009, "grad_norm": 2.499117374420166, "learning_rate": 8.153831284382757e-06, "loss": 0.48427844047546387, "step": 2171 }, { "epoch": 0.30456425716889857, "grad_norm": 2.8347864151000977, "learning_rate": 8.152069040528764e-06, "loss": 0.5899984240531921, "step": 2172 }, { "epoch": 0.3047044801233962, "grad_norm": 3.9715540409088135, "learning_rate": 8.150306146643364e-06, "loss": 0.5905967950820923, "step": 2173 }, { "epoch": 0.30484470307789385, "grad_norm": 15.965147972106934, "learning_rate": 8.148542603090098e-06, "loss": 0.5120106935501099, "step": 2174 }, { "epoch": 0.3049849260323915, "grad_norm": 3.7862460613250732, "learning_rate": 8.146778410232657e-06, "loss": 0.5213093161582947, "step": 2175 }, { "epoch": 0.30512514898688914, "grad_norm": 3.936414957046509, "learning_rate": 8.145013568434856e-06, "loss": 0.5107119083404541, "step": 2176 }, { "epoch": 0.3052653719413868, "grad_norm": 4.534740924835205, "learning_rate": 8.14324807806065e-06, "loss": 0.5747854113578796, "step": 2177 }, { "epoch": 0.3054055948958845, "grad_norm": 5.425404071807861, "learning_rate": 8.141481939474123e-06, "loss": 0.6332833170890808, "step": 2178 }, { "epoch": 0.3055458178503821, "grad_norm": 6.535844802856445, "learning_rate": 8.139715153039496e-06, "loss": 0.6399537920951843, "step": 2179 }, { "epoch": 0.30568604080487977, "grad_norm": 14.819989204406738, "learning_rate": 8.137947719121122e-06, "loss": 0.5379883646965027, "step": 2180 }, { "epoch": 0.30582626375937744, "grad_norm": 3.2957613468170166, "learning_rate": 8.136179638083486e-06, "loss": 0.6135121583938599, "step": 2181 }, { "epoch": 0.30596648671387505, "grad_norm": 2.7880773544311523, "learning_rate": 8.134410910291211e-06, "loss": 0.5699074268341064, "step": 2182 }, { "epoch": 0.3061067096683727, "grad_norm": 3.161250352859497, "learning_rate": 8.132641536109048e-06, "loss": 0.5969048142433167, "step": 2183 }, { "epoch": 0.30624693262287034, "grad_norm": 3.7802491188049316, "learning_rate": 8.130871515901886e-06, "loss": 0.6422454118728638, "step": 2184 }, { "epoch": 0.306387155577368, "grad_norm": 2.891024112701416, "learning_rate": 8.129100850034744e-06, "loss": 0.5618453025817871, "step": 2185 }, { "epoch": 0.3065273785318657, "grad_norm": 3.465581178665161, "learning_rate": 8.127329538872776e-06, "loss": 0.5217976570129395, "step": 2186 }, { "epoch": 0.3066676014863633, "grad_norm": 11.718733787536621, "learning_rate": 8.12555758278127e-06, "loss": 0.5450794100761414, "step": 2187 }, { "epoch": 0.30680782444086097, "grad_norm": 5.576655864715576, "learning_rate": 8.12378498212564e-06, "loss": 0.6324917078018188, "step": 2188 }, { "epoch": 0.30694804739535864, "grad_norm": 3.2220492362976074, "learning_rate": 8.122011737271443e-06, "loss": 0.42468851804733276, "step": 2189 }, { "epoch": 0.30708827034985625, "grad_norm": 3.724271059036255, "learning_rate": 8.120237848584364e-06, "loss": 0.5450170040130615, "step": 2190 }, { "epoch": 0.3072284933043539, "grad_norm": 10.825295448303223, "learning_rate": 8.118463316430219e-06, "loss": 0.5682071447372437, "step": 2191 }, { "epoch": 0.3073687162588516, "grad_norm": 3.8638243675231934, "learning_rate": 8.11668814117496e-06, "loss": 0.5708438158035278, "step": 2192 }, { "epoch": 0.3075089392133492, "grad_norm": 2.3281514644622803, "learning_rate": 8.11491232318467e-06, "loss": 0.5989788770675659, "step": 2193 }, { "epoch": 0.3076491621678469, "grad_norm": 4.060519218444824, "learning_rate": 8.113135862825563e-06, "loss": 0.5674097537994385, "step": 2194 }, { "epoch": 0.30778938512234455, "grad_norm": 2.9561498165130615, "learning_rate": 8.11135876046399e-06, "loss": 0.6813790798187256, "step": 2195 }, { "epoch": 0.30792960807684217, "grad_norm": 3.0567421913146973, "learning_rate": 8.10958101646643e-06, "loss": 0.5560741424560547, "step": 2196 }, { "epoch": 0.30806983103133984, "grad_norm": 2.798882484436035, "learning_rate": 8.107802631199497e-06, "loss": 0.5776761770248413, "step": 2197 }, { "epoch": 0.3082100539858375, "grad_norm": 2.946798086166382, "learning_rate": 8.106023605029935e-06, "loss": 0.5643505454063416, "step": 2198 }, { "epoch": 0.3083502769403351, "grad_norm": 5.624211311340332, "learning_rate": 8.104243938324622e-06, "loss": 0.5811512470245361, "step": 2199 }, { "epoch": 0.3084904998948328, "grad_norm": 2.4348795413970947, "learning_rate": 8.10246363145057e-06, "loss": 0.6145886182785034, "step": 2200 }, { "epoch": 0.3086307228493304, "grad_norm": 7.032984733581543, "learning_rate": 8.100682684774914e-06, "loss": 0.5075137615203857, "step": 2201 }, { "epoch": 0.3087709458038281, "grad_norm": 5.0660295486450195, "learning_rate": 8.098901098664934e-06, "loss": 0.5788043141365051, "step": 2202 }, { "epoch": 0.30891116875832575, "grad_norm": 3.596782684326172, "learning_rate": 8.097118873488033e-06, "loss": 0.6246411204338074, "step": 2203 }, { "epoch": 0.30905139171282336, "grad_norm": 2.7058706283569336, "learning_rate": 8.095336009611747e-06, "loss": 0.5883827805519104, "step": 2204 }, { "epoch": 0.30919161466732104, "grad_norm": 4.603332042694092, "learning_rate": 8.093552507403746e-06, "loss": 0.5074445605278015, "step": 2205 }, { "epoch": 0.3093318376218187, "grad_norm": 4.6256327629089355, "learning_rate": 8.09176836723183e-06, "loss": 0.6304129362106323, "step": 2206 }, { "epoch": 0.3094720605763163, "grad_norm": 3.0135409832000732, "learning_rate": 8.089983589463932e-06, "loss": 0.42973318696022034, "step": 2207 }, { "epoch": 0.309612283530814, "grad_norm": 5.964238166809082, "learning_rate": 8.088198174468116e-06, "loss": 0.4997105598449707, "step": 2208 }, { "epoch": 0.30975250648531166, "grad_norm": 3.643909215927124, "learning_rate": 8.086412122612573e-06, "loss": 0.6028774976730347, "step": 2209 }, { "epoch": 0.3098927294398093, "grad_norm": 5.817127704620361, "learning_rate": 8.084625434265634e-06, "loss": 0.55243980884552, "step": 2210 }, { "epoch": 0.31003295239430695, "grad_norm": 2.476982831954956, "learning_rate": 8.082838109795754e-06, "loss": 0.5499448776245117, "step": 2211 }, { "epoch": 0.3101731753488046, "grad_norm": 3.9869372844696045, "learning_rate": 8.081050149571522e-06, "loss": 0.5774970054626465, "step": 2212 }, { "epoch": 0.31031339830330223, "grad_norm": 2.464378595352173, "learning_rate": 8.079261553961659e-06, "loss": 0.6642564535140991, "step": 2213 }, { "epoch": 0.3104536212577999, "grad_norm": 4.54076623916626, "learning_rate": 8.077472323335014e-06, "loss": 0.5110950469970703, "step": 2214 }, { "epoch": 0.3105938442122976, "grad_norm": 15.82554817199707, "learning_rate": 8.07568245806057e-06, "loss": 0.5235629081726074, "step": 2215 }, { "epoch": 0.3107340671667952, "grad_norm": 2.3677268028259277, "learning_rate": 8.073891958507438e-06, "loss": 0.5644407272338867, "step": 2216 }, { "epoch": 0.31087429012129286, "grad_norm": 3.2319116592407227, "learning_rate": 8.072100825044863e-06, "loss": 0.5714287757873535, "step": 2217 }, { "epoch": 0.31101451307579053, "grad_norm": 3.2806286811828613, "learning_rate": 8.07030905804222e-06, "loss": 0.5466384291648865, "step": 2218 }, { "epoch": 0.31115473603028815, "grad_norm": 2.970792055130005, "learning_rate": 8.068516657869014e-06, "loss": 0.5299725532531738, "step": 2219 }, { "epoch": 0.3112949589847858, "grad_norm": 2.9321913719177246, "learning_rate": 8.066723624894879e-06, "loss": 0.4864230453968048, "step": 2220 }, { "epoch": 0.31143518193928343, "grad_norm": 3.0303831100463867, "learning_rate": 8.06492995948958e-06, "loss": 0.5843759775161743, "step": 2221 }, { "epoch": 0.3115754048937811, "grad_norm": 2.098634719848633, "learning_rate": 8.063135662023015e-06, "loss": 0.6916384696960449, "step": 2222 }, { "epoch": 0.3117156278482788, "grad_norm": 3.74880051612854, "learning_rate": 8.061340732865211e-06, "loss": 0.47965186834335327, "step": 2223 }, { "epoch": 0.3118558508027764, "grad_norm": 3.3725056648254395, "learning_rate": 8.059545172386322e-06, "loss": 0.4723256826400757, "step": 2224 }, { "epoch": 0.31199607375727406, "grad_norm": 2.8579416275024414, "learning_rate": 8.057748980956641e-06, "loss": 0.5347490310668945, "step": 2225 }, { "epoch": 0.31213629671177173, "grad_norm": 2.864910840988159, "learning_rate": 8.05595215894658e-06, "loss": 0.5441568493843079, "step": 2226 }, { "epoch": 0.31227651966626935, "grad_norm": 4.96328067779541, "learning_rate": 8.054154706726689e-06, "loss": 0.5567055940628052, "step": 2227 }, { "epoch": 0.312416742620767, "grad_norm": 3.6420295238494873, "learning_rate": 8.052356624667643e-06, "loss": 0.5635954141616821, "step": 2228 }, { "epoch": 0.3125569655752647, "grad_norm": 4.76947546005249, "learning_rate": 8.050557913140251e-06, "loss": 0.6355783939361572, "step": 2229 }, { "epoch": 0.3126971885297623, "grad_norm": 2.5892372131347656, "learning_rate": 8.04875857251545e-06, "loss": 0.5167145729064941, "step": 2230 }, { "epoch": 0.31283741148426, "grad_norm": 3.3575446605682373, "learning_rate": 8.046958603164306e-06, "loss": 0.5925601124763489, "step": 2231 }, { "epoch": 0.31297763443875765, "grad_norm": 3.3010919094085693, "learning_rate": 8.045158005458017e-06, "loss": 0.44035375118255615, "step": 2232 }, { "epoch": 0.31311785739325526, "grad_norm": 3.6234350204467773, "learning_rate": 8.043356779767906e-06, "loss": 0.6873584985733032, "step": 2233 }, { "epoch": 0.31325808034775293, "grad_norm": 3.851177215576172, "learning_rate": 8.041554926465429e-06, "loss": 0.5803329944610596, "step": 2234 }, { "epoch": 0.3133983033022506, "grad_norm": 3.1614882946014404, "learning_rate": 8.039752445922173e-06, "loss": 0.5821001529693604, "step": 2235 }, { "epoch": 0.3135385262567482, "grad_norm": 4.629972457885742, "learning_rate": 8.037949338509852e-06, "loss": 0.5041799545288086, "step": 2236 }, { "epoch": 0.3136787492112459, "grad_norm": 3.7556991577148438, "learning_rate": 8.036145604600309e-06, "loss": 0.6293319463729858, "step": 2237 }, { "epoch": 0.31381897216574356, "grad_norm": 3.855743408203125, "learning_rate": 8.034341244565516e-06, "loss": 0.5699858665466309, "step": 2238 }, { "epoch": 0.3139591951202412, "grad_norm": 4.376176834106445, "learning_rate": 8.032536258777574e-06, "loss": 0.6502513885498047, "step": 2239 }, { "epoch": 0.31409941807473885, "grad_norm": 2.188239812850952, "learning_rate": 8.030730647608718e-06, "loss": 0.44494616985321045, "step": 2240 }, { "epoch": 0.31423964102923646, "grad_norm": 4.893584251403809, "learning_rate": 8.028924411431303e-06, "loss": 0.4793068468570709, "step": 2241 }, { "epoch": 0.31437986398373413, "grad_norm": 4.295144081115723, "learning_rate": 8.027117550617821e-06, "loss": 0.5391694903373718, "step": 2242 }, { "epoch": 0.3145200869382318, "grad_norm": 5.1774516105651855, "learning_rate": 8.025310065540885e-06, "loss": 0.5914425849914551, "step": 2243 }, { "epoch": 0.3146603098927294, "grad_norm": 4.388153076171875, "learning_rate": 8.023501956573248e-06, "loss": 0.6686402559280396, "step": 2244 }, { "epoch": 0.3148005328472271, "grad_norm": 4.756496906280518, "learning_rate": 8.021693224087781e-06, "loss": 0.5400972366333008, "step": 2245 }, { "epoch": 0.31494075580172476, "grad_norm": 6.289305686950684, "learning_rate": 8.019883868457488e-06, "loss": 0.5779873728752136, "step": 2246 }, { "epoch": 0.3150809787562224, "grad_norm": 2.2339749336242676, "learning_rate": 8.018073890055502e-06, "loss": 0.5161775946617126, "step": 2247 }, { "epoch": 0.31522120171072004, "grad_norm": 4.673166751861572, "learning_rate": 8.016263289255082e-06, "loss": 0.5049059391021729, "step": 2248 }, { "epoch": 0.3153614246652177, "grad_norm": 4.478818416595459, "learning_rate": 8.014452066429617e-06, "loss": 0.6106867790222168, "step": 2249 }, { "epoch": 0.31550164761971533, "grad_norm": 2.5795531272888184, "learning_rate": 8.012640221952625e-06, "loss": 0.5913435220718384, "step": 2250 }, { "epoch": 0.315641870574213, "grad_norm": 2.7512080669403076, "learning_rate": 8.010827756197752e-06, "loss": 0.47652822732925415, "step": 2251 }, { "epoch": 0.3157820935287107, "grad_norm": 3.4671647548675537, "learning_rate": 8.00901466953877e-06, "loss": 0.6665650606155396, "step": 2252 }, { "epoch": 0.3159223164832083, "grad_norm": 2.4819366931915283, "learning_rate": 8.00720096234958e-06, "loss": 0.5929287672042847, "step": 2253 }, { "epoch": 0.31606253943770596, "grad_norm": 4.075047492980957, "learning_rate": 8.005386635004214e-06, "loss": 0.5213125348091125, "step": 2254 }, { "epoch": 0.31620276239220363, "grad_norm": 2.9273157119750977, "learning_rate": 8.003571687876825e-06, "loss": 0.5184850096702576, "step": 2255 }, { "epoch": 0.31634298534670124, "grad_norm": 3.4006519317626953, "learning_rate": 8.001756121341705e-06, "loss": 0.557400107383728, "step": 2256 }, { "epoch": 0.3164832083011989, "grad_norm": 3.2463877201080322, "learning_rate": 7.999939935773258e-06, "loss": 0.5385991334915161, "step": 2257 }, { "epoch": 0.31662343125569653, "grad_norm": 2.920170545578003, "learning_rate": 7.998123131546031e-06, "loss": 0.6877744793891907, "step": 2258 }, { "epoch": 0.3167636542101942, "grad_norm": 2.591588258743286, "learning_rate": 7.996305709034692e-06, "loss": 0.5405896902084351, "step": 2259 }, { "epoch": 0.31690387716469187, "grad_norm": 2.655524253845215, "learning_rate": 7.994487668614035e-06, "loss": 0.5439181327819824, "step": 2260 }, { "epoch": 0.3170441001191895, "grad_norm": 6.052009105682373, "learning_rate": 7.99266901065898e-06, "loss": 0.5622970461845398, "step": 2261 }, { "epoch": 0.31718432307368716, "grad_norm": 2.902104616165161, "learning_rate": 7.990849735544584e-06, "loss": 0.6198037266731262, "step": 2262 }, { "epoch": 0.31732454602818483, "grad_norm": 2.9765071868896484, "learning_rate": 7.989029843646018e-06, "loss": 0.5737191438674927, "step": 2263 }, { "epoch": 0.31746476898268244, "grad_norm": 3.043830633163452, "learning_rate": 7.987209335338594e-06, "loss": 0.5898066759109497, "step": 2264 }, { "epoch": 0.3176049919371801, "grad_norm": 2.1970417499542236, "learning_rate": 7.985388210997737e-06, "loss": 0.4895292818546295, "step": 2265 }, { "epoch": 0.3177452148916778, "grad_norm": 4.164760112762451, "learning_rate": 7.98356647099901e-06, "loss": 0.5209819078445435, "step": 2266 }, { "epoch": 0.3178854378461754, "grad_norm": 4.846504211425781, "learning_rate": 7.9817441157181e-06, "loss": 0.6473113298416138, "step": 2267 }, { "epoch": 0.31802566080067307, "grad_norm": 3.796032190322876, "learning_rate": 7.979921145530816e-06, "loss": 0.514298677444458, "step": 2268 }, { "epoch": 0.31816588375517074, "grad_norm": 2.528608560562134, "learning_rate": 7.9780975608131e-06, "loss": 0.5461100339889526, "step": 2269 }, { "epoch": 0.31830610670966836, "grad_norm": 2.196441173553467, "learning_rate": 7.976273361941018e-06, "loss": 0.5108029246330261, "step": 2270 }, { "epoch": 0.31844632966416603, "grad_norm": 2.713953971862793, "learning_rate": 7.974448549290764e-06, "loss": 0.6109528541564941, "step": 2271 }, { "epoch": 0.3185865526186637, "grad_norm": 3.966510772705078, "learning_rate": 7.972623123238656e-06, "loss": 0.5156863331794739, "step": 2272 }, { "epoch": 0.3187267755731613, "grad_norm": 2.4103143215179443, "learning_rate": 7.970797084161141e-06, "loss": 0.5589687824249268, "step": 2273 }, { "epoch": 0.318866998527659, "grad_norm": 3.048203945159912, "learning_rate": 7.968970432434793e-06, "loss": 0.5798625349998474, "step": 2274 }, { "epoch": 0.31900722148215666, "grad_norm": 4.15736198425293, "learning_rate": 7.96714316843631e-06, "loss": 0.5966430902481079, "step": 2275 }, { "epoch": 0.31914744443665427, "grad_norm": 4.886391639709473, "learning_rate": 7.965315292542514e-06, "loss": 0.575983464717865, "step": 2276 }, { "epoch": 0.31928766739115194, "grad_norm": 2.8554234504699707, "learning_rate": 7.96348680513036e-06, "loss": 0.5545313358306885, "step": 2277 }, { "epoch": 0.31942789034564956, "grad_norm": 4.504300117492676, "learning_rate": 7.961657706576925e-06, "loss": 0.5302813053131104, "step": 2278 }, { "epoch": 0.3195681133001472, "grad_norm": 5.416291236877441, "learning_rate": 7.959827997259413e-06, "loss": 0.4278285503387451, "step": 2279 }, { "epoch": 0.3197083362546449, "grad_norm": 3.663593292236328, "learning_rate": 7.957997677555152e-06, "loss": 0.5141955614089966, "step": 2280 }, { "epoch": 0.3198485592091425, "grad_norm": 4.110256195068359, "learning_rate": 7.956166747841597e-06, "loss": 0.596908688545227, "step": 2281 }, { "epoch": 0.3199887821636402, "grad_norm": 2.581296682357788, "learning_rate": 7.954335208496332e-06, "loss": 0.42214563488960266, "step": 2282 }, { "epoch": 0.32012900511813785, "grad_norm": 3.004450559616089, "learning_rate": 7.95250305989706e-06, "loss": 0.5669061541557312, "step": 2283 }, { "epoch": 0.32026922807263547, "grad_norm": 5.356258869171143, "learning_rate": 7.950670302421616e-06, "loss": 0.543682336807251, "step": 2284 }, { "epoch": 0.32040945102713314, "grad_norm": 2.204339027404785, "learning_rate": 7.948836936447957e-06, "loss": 0.5119956135749817, "step": 2285 }, { "epoch": 0.3205496739816308, "grad_norm": 4.028160572052002, "learning_rate": 7.94700296235417e-06, "loss": 0.6052367687225342, "step": 2286 }, { "epoch": 0.3206898969361284, "grad_norm": 3.80177640914917, "learning_rate": 7.945168380518456e-06, "loss": 0.6453623175621033, "step": 2287 }, { "epoch": 0.3208301198906261, "grad_norm": 3.1106390953063965, "learning_rate": 7.943333191319158e-06, "loss": 0.6233867406845093, "step": 2288 }, { "epoch": 0.32097034284512377, "grad_norm": 4.1897759437561035, "learning_rate": 7.94149739513473e-06, "loss": 0.4443986117839813, "step": 2289 }, { "epoch": 0.3211105657996214, "grad_norm": 2.651139736175537, "learning_rate": 7.93966099234376e-06, "loss": 0.6020355224609375, "step": 2290 }, { "epoch": 0.32125078875411905, "grad_norm": 2.3138535022735596, "learning_rate": 7.937823983324955e-06, "loss": 0.5220639705657959, "step": 2291 }, { "epoch": 0.3213910117086167, "grad_norm": 2.7977371215820312, "learning_rate": 7.935986368457152e-06, "loss": 0.41020575165748596, "step": 2292 }, { "epoch": 0.32153123466311434, "grad_norm": 2.6675305366516113, "learning_rate": 7.934148148119312e-06, "loss": 0.5908077359199524, "step": 2293 }, { "epoch": 0.321671457617612, "grad_norm": 5.6248064041137695, "learning_rate": 7.932309322690515e-06, "loss": 0.5957591533660889, "step": 2294 }, { "epoch": 0.3218116805721097, "grad_norm": 3.316875457763672, "learning_rate": 7.930469892549974e-06, "loss": 0.47321006655693054, "step": 2295 }, { "epoch": 0.3219519035266073, "grad_norm": 3.906297445297241, "learning_rate": 7.928629858077022e-06, "loss": 0.5556584000587463, "step": 2296 }, { "epoch": 0.32209212648110497, "grad_norm": 2.776132822036743, "learning_rate": 7.926789219651117e-06, "loss": 0.4977542459964752, "step": 2297 }, { "epoch": 0.3222323494356026, "grad_norm": 2.7897849082946777, "learning_rate": 7.924947977651844e-06, "loss": 0.5178398489952087, "step": 2298 }, { "epoch": 0.32237257239010025, "grad_norm": 3.844736337661743, "learning_rate": 7.923106132458913e-06, "loss": 0.6672236919403076, "step": 2299 }, { "epoch": 0.3225127953445979, "grad_norm": 3.2657766342163086, "learning_rate": 7.92126368445215e-06, "loss": 0.5733163952827454, "step": 2300 }, { "epoch": 0.32265301829909554, "grad_norm": 3.6717395782470703, "learning_rate": 7.919420634011514e-06, "loss": 0.5692238807678223, "step": 2301 }, { "epoch": 0.3227932412535932, "grad_norm": 4.003605365753174, "learning_rate": 7.91757698151709e-06, "loss": 0.6183369159698486, "step": 2302 }, { "epoch": 0.3229334642080909, "grad_norm": 3.4344799518585205, "learning_rate": 7.915732727349076e-06, "loss": 0.5215020775794983, "step": 2303 }, { "epoch": 0.3230736871625885, "grad_norm": 3.3424603939056396, "learning_rate": 7.913887871887804e-06, "loss": 0.5489205121994019, "step": 2304 }, { "epoch": 0.32321391011708617, "grad_norm": 2.7607834339141846, "learning_rate": 7.91204241551373e-06, "loss": 0.5349889993667603, "step": 2305 }, { "epoch": 0.32335413307158384, "grad_norm": 2.7221221923828125, "learning_rate": 7.910196358607427e-06, "loss": 0.49681779742240906, "step": 2306 }, { "epoch": 0.32349435602608145, "grad_norm": 3.000440835952759, "learning_rate": 7.908349701549596e-06, "loss": 0.541546106338501, "step": 2307 }, { "epoch": 0.3236345789805791, "grad_norm": 4.309610366821289, "learning_rate": 7.906502444721063e-06, "loss": 0.6604136228561401, "step": 2308 }, { "epoch": 0.3237748019350768, "grad_norm": 2.762871026992798, "learning_rate": 7.904654588502776e-06, "loss": 0.6040648818016052, "step": 2309 }, { "epoch": 0.3239150248895744, "grad_norm": 11.069907188415527, "learning_rate": 7.902806133275806e-06, "loss": 0.5339494943618774, "step": 2310 }, { "epoch": 0.3240552478440721, "grad_norm": 9.153778076171875, "learning_rate": 7.900957079421348e-06, "loss": 0.4787086844444275, "step": 2311 }, { "epoch": 0.32419547079856975, "grad_norm": 2.658998966217041, "learning_rate": 7.899107427320722e-06, "loss": 0.6687880754470825, "step": 2312 }, { "epoch": 0.32433569375306737, "grad_norm": 3.0545480251312256, "learning_rate": 7.89725717735537e-06, "loss": 0.48464635014533997, "step": 2313 }, { "epoch": 0.32447591670756504, "grad_norm": 2.883126735687256, "learning_rate": 7.895406329906857e-06, "loss": 0.6029061675071716, "step": 2314 }, { "epoch": 0.32461613966206265, "grad_norm": 3.638902187347412, "learning_rate": 7.893554885356871e-06, "loss": 0.5761083960533142, "step": 2315 }, { "epoch": 0.3247563626165603, "grad_norm": 2.5567915439605713, "learning_rate": 7.891702844087226e-06, "loss": 0.5062841773033142, "step": 2316 }, { "epoch": 0.324896585571058, "grad_norm": 4.567927360534668, "learning_rate": 7.889850206479851e-06, "loss": 0.684603214263916, "step": 2317 }, { "epoch": 0.3250368085255556, "grad_norm": 4.4183878898620605, "learning_rate": 7.887996972916814e-06, "loss": 0.5407902002334595, "step": 2318 }, { "epoch": 0.3251770314800533, "grad_norm": 3.0666465759277344, "learning_rate": 7.886143143780287e-06, "loss": 0.4956935942173004, "step": 2319 }, { "epoch": 0.32531725443455095, "grad_norm": 5.526111602783203, "learning_rate": 7.884288719452576e-06, "loss": 0.6119959354400635, "step": 2320 }, { "epoch": 0.32545747738904857, "grad_norm": 2.30641770362854, "learning_rate": 7.882433700316108e-06, "loss": 0.683112382888794, "step": 2321 }, { "epoch": 0.32559770034354624, "grad_norm": 3.582557439804077, "learning_rate": 7.88057808675343e-06, "loss": 0.6543422341346741, "step": 2322 }, { "epoch": 0.3257379232980439, "grad_norm": 2.2036352157592773, "learning_rate": 7.878721879147218e-06, "loss": 0.43248966336250305, "step": 2323 }, { "epoch": 0.3258781462525415, "grad_norm": 7.942376136779785, "learning_rate": 7.87686507788026e-06, "loss": 0.4815264046192169, "step": 2324 }, { "epoch": 0.3260183692070392, "grad_norm": 2.0710370540618896, "learning_rate": 7.875007683335478e-06, "loss": 0.6316695213317871, "step": 2325 }, { "epoch": 0.32615859216153686, "grad_norm": 2.2782390117645264, "learning_rate": 7.873149695895908e-06, "loss": 0.48527035117149353, "step": 2326 }, { "epoch": 0.3262988151160345, "grad_norm": 3.0770249366760254, "learning_rate": 7.871291115944712e-06, "loss": 0.5536624789237976, "step": 2327 }, { "epoch": 0.32643903807053215, "grad_norm": 3.035381317138672, "learning_rate": 7.869431943865172e-06, "loss": 0.48053091764450073, "step": 2328 }, { "epoch": 0.3265792610250298, "grad_norm": 3.171915054321289, "learning_rate": 7.867572180040694e-06, "loss": 0.6193178296089172, "step": 2329 }, { "epoch": 0.32671948397952744, "grad_norm": 2.772735357284546, "learning_rate": 7.865711824854807e-06, "loss": 0.5867417454719543, "step": 2330 }, { "epoch": 0.3268597069340251, "grad_norm": 2.805678367614746, "learning_rate": 7.863850878691159e-06, "loss": 0.5541773438453674, "step": 2331 }, { "epoch": 0.3269999298885228, "grad_norm": 3.815122127532959, "learning_rate": 7.86198934193352e-06, "loss": 0.5036294460296631, "step": 2332 }, { "epoch": 0.3271401528430204, "grad_norm": 3.602031707763672, "learning_rate": 7.860127214965785e-06, "loss": 0.5745514035224915, "step": 2333 }, { "epoch": 0.32728037579751806, "grad_norm": 2.6565725803375244, "learning_rate": 7.858264498171968e-06, "loss": 0.5346673727035522, "step": 2334 }, { "epoch": 0.3274205987520157, "grad_norm": 3.1632063388824463, "learning_rate": 7.856401191936205e-06, "loss": 0.5041893720626831, "step": 2335 }, { "epoch": 0.32756082170651335, "grad_norm": 14.67224407196045, "learning_rate": 7.854537296642755e-06, "loss": 0.5015082359313965, "step": 2336 }, { "epoch": 0.327701044661011, "grad_norm": 3.819786548614502, "learning_rate": 7.852672812675997e-06, "loss": 0.5269519090652466, "step": 2337 }, { "epoch": 0.32784126761550864, "grad_norm": 2.3392152786254883, "learning_rate": 7.85080774042043e-06, "loss": 0.6114739179611206, "step": 2338 }, { "epoch": 0.3279814905700063, "grad_norm": 4.343796730041504, "learning_rate": 7.84894208026068e-06, "loss": 0.46769002079963684, "step": 2339 }, { "epoch": 0.328121713524504, "grad_norm": 2.912611961364746, "learning_rate": 7.847075832581486e-06, "loss": 0.5931965708732605, "step": 2340 }, { "epoch": 0.3282619364790016, "grad_norm": 3.52059268951416, "learning_rate": 7.845208997767718e-06, "loss": 0.5646465420722961, "step": 2341 }, { "epoch": 0.32840215943349926, "grad_norm": 3.266845941543579, "learning_rate": 7.843341576204356e-06, "loss": 0.45403093099594116, "step": 2342 }, { "epoch": 0.32854238238799693, "grad_norm": 3.831204891204834, "learning_rate": 7.841473568276507e-06, "loss": 0.5524711608886719, "step": 2343 }, { "epoch": 0.32868260534249455, "grad_norm": 4.2714948654174805, "learning_rate": 7.839604974369405e-06, "loss": 0.5097349882125854, "step": 2344 }, { "epoch": 0.3288228282969922, "grad_norm": 2.679309368133545, "learning_rate": 7.837735794868391e-06, "loss": 0.548575758934021, "step": 2345 }, { "epoch": 0.3289630512514899, "grad_norm": 2.746748924255371, "learning_rate": 7.835866030158938e-06, "loss": 0.5400283932685852, "step": 2346 }, { "epoch": 0.3291032742059875, "grad_norm": 3.1294963359832764, "learning_rate": 7.833995680626634e-06, "loss": 0.6096116304397583, "step": 2347 }, { "epoch": 0.3292434971604852, "grad_norm": 2.516831159591675, "learning_rate": 7.832124746657193e-06, "loss": 0.5443049669265747, "step": 2348 }, { "epoch": 0.32938372011498285, "grad_norm": 3.5029234886169434, "learning_rate": 7.830253228636439e-06, "loss": 0.6673579216003418, "step": 2349 }, { "epoch": 0.32952394306948046, "grad_norm": 3.036249876022339, "learning_rate": 7.828381126950331e-06, "loss": 0.605463981628418, "step": 2350 }, { "epoch": 0.32966416602397813, "grad_norm": 3.7449541091918945, "learning_rate": 7.826508441984937e-06, "loss": 0.5501062870025635, "step": 2351 }, { "epoch": 0.32980438897847575, "grad_norm": 3.2308785915374756, "learning_rate": 7.824635174126449e-06, "loss": 0.6175344586372375, "step": 2352 }, { "epoch": 0.3299446119329734, "grad_norm": 2.4630749225616455, "learning_rate": 7.82276132376118e-06, "loss": 0.5225976705551147, "step": 2353 }, { "epoch": 0.3300848348874711, "grad_norm": 2.6184966564178467, "learning_rate": 7.820886891275563e-06, "loss": 0.5410408973693848, "step": 2354 }, { "epoch": 0.3302250578419687, "grad_norm": 2.6928484439849854, "learning_rate": 7.819011877056148e-06, "loss": 0.5278075337409973, "step": 2355 }, { "epoch": 0.3303652807964664, "grad_norm": 3.5487186908721924, "learning_rate": 7.81713628148961e-06, "loss": 0.5710477828979492, "step": 2356 }, { "epoch": 0.33050550375096405, "grad_norm": 2.921820640563965, "learning_rate": 7.815260104962742e-06, "loss": 0.4903869032859802, "step": 2357 }, { "epoch": 0.33064572670546166, "grad_norm": 3.3986380100250244, "learning_rate": 7.813383347862453e-06, "loss": 0.5758223533630371, "step": 2358 }, { "epoch": 0.33078594965995933, "grad_norm": 2.9733879566192627, "learning_rate": 7.811506010575775e-06, "loss": 0.5771765112876892, "step": 2359 }, { "epoch": 0.330926172614457, "grad_norm": 3.568833827972412, "learning_rate": 7.809628093489864e-06, "loss": 0.505890965461731, "step": 2360 }, { "epoch": 0.3310663955689546, "grad_norm": 4.423267364501953, "learning_rate": 7.807749596991986e-06, "loss": 0.6040964126586914, "step": 2361 }, { "epoch": 0.3312066185234523, "grad_norm": 5.112001419067383, "learning_rate": 7.805870521469533e-06, "loss": 0.5783190131187439, "step": 2362 }, { "epoch": 0.33134684147794996, "grad_norm": 2.7548398971557617, "learning_rate": 7.803990867310016e-06, "loss": 0.5901175737380981, "step": 2363 }, { "epoch": 0.3314870644324476, "grad_norm": 3.198796272277832, "learning_rate": 7.802110634901064e-06, "loss": 0.6281852722167969, "step": 2364 }, { "epoch": 0.33162728738694525, "grad_norm": 4.870669841766357, "learning_rate": 7.800229824630425e-06, "loss": 0.5475687384605408, "step": 2365 }, { "epoch": 0.3317675103414429, "grad_norm": 2.6183648109436035, "learning_rate": 7.798348436885966e-06, "loss": 0.6085065007209778, "step": 2366 }, { "epoch": 0.33190773329594053, "grad_norm": 6.583910942077637, "learning_rate": 7.796466472055677e-06, "loss": 0.4893101751804352, "step": 2367 }, { "epoch": 0.3320479562504382, "grad_norm": 3.1880617141723633, "learning_rate": 7.79458393052766e-06, "loss": 0.6448537707328796, "step": 2368 }, { "epoch": 0.3321881792049359, "grad_norm": 3.016252279281616, "learning_rate": 7.79270081269014e-06, "loss": 0.4870188236236572, "step": 2369 }, { "epoch": 0.3323284021594335, "grad_norm": 2.428945302963257, "learning_rate": 7.790817118931462e-06, "loss": 0.5101495981216431, "step": 2370 }, { "epoch": 0.33246862511393116, "grad_norm": 5.410871505737305, "learning_rate": 7.78893284964009e-06, "loss": 0.5708364248275757, "step": 2371 }, { "epoch": 0.3326088480684288, "grad_norm": 2.8676483631134033, "learning_rate": 7.787048005204602e-06, "loss": 0.5185609459877014, "step": 2372 }, { "epoch": 0.33274907102292645, "grad_norm": 2.188857316970825, "learning_rate": 7.785162586013699e-06, "loss": 0.5590569972991943, "step": 2373 }, { "epoch": 0.3328892939774241, "grad_norm": 2.861841917037964, "learning_rate": 7.783276592456199e-06, "loss": 0.4347993731498718, "step": 2374 }, { "epoch": 0.33302951693192173, "grad_norm": 2.835735321044922, "learning_rate": 7.781390024921036e-06, "loss": 0.5518051385879517, "step": 2375 }, { "epoch": 0.3331697398864194, "grad_norm": 2.3841397762298584, "learning_rate": 7.779502883797272e-06, "loss": 0.492902547121048, "step": 2376 }, { "epoch": 0.3333099628409171, "grad_norm": 13.047176361083984, "learning_rate": 7.777615169474073e-06, "loss": 0.5964192152023315, "step": 2377 }, { "epoch": 0.3334501857954147, "grad_norm": 2.842985153198242, "learning_rate": 7.775726882340733e-06, "loss": 0.5165205001831055, "step": 2378 }, { "epoch": 0.33359040874991236, "grad_norm": 4.59237003326416, "learning_rate": 7.773838022786664e-06, "loss": 0.5217845439910889, "step": 2379 }, { "epoch": 0.33373063170441003, "grad_norm": 2.690727710723877, "learning_rate": 7.77194859120139e-06, "loss": 0.5302376747131348, "step": 2380 }, { "epoch": 0.33387085465890765, "grad_norm": 5.643634796142578, "learning_rate": 7.770058587974558e-06, "loss": 0.49021926522254944, "step": 2381 }, { "epoch": 0.3340110776134053, "grad_norm": 3.7637321949005127, "learning_rate": 7.768168013495932e-06, "loss": 0.5129427909851074, "step": 2382 }, { "epoch": 0.334151300567903, "grad_norm": 3.353116989135742, "learning_rate": 7.766276868155394e-06, "loss": 0.6197059750556946, "step": 2383 }, { "epoch": 0.3342915235224006, "grad_norm": 3.695136070251465, "learning_rate": 7.76438515234294e-06, "loss": 0.4957049489021301, "step": 2384 }, { "epoch": 0.3344317464768983, "grad_norm": 2.9855356216430664, "learning_rate": 7.76249286644869e-06, "loss": 0.48926714062690735, "step": 2385 }, { "epoch": 0.33457196943139594, "grad_norm": 3.231041431427002, "learning_rate": 7.760600010862876e-06, "loss": 0.574254035949707, "step": 2386 }, { "epoch": 0.33471219238589356, "grad_norm": 2.886385917663574, "learning_rate": 7.75870658597585e-06, "loss": 0.6699687242507935, "step": 2387 }, { "epoch": 0.33485241534039123, "grad_norm": 2.4623706340789795, "learning_rate": 7.756812592178082e-06, "loss": 0.5787898302078247, "step": 2388 }, { "epoch": 0.3349926382948889, "grad_norm": 2.547089099884033, "learning_rate": 7.754918029860161e-06, "loss": 0.5255324840545654, "step": 2389 }, { "epoch": 0.3351328612493865, "grad_norm": 3.0519659519195557, "learning_rate": 7.753022899412786e-06, "loss": 0.4710099399089813, "step": 2390 }, { "epoch": 0.3352730842038842, "grad_norm": 2.6342616081237793, "learning_rate": 7.751127201226778e-06, "loss": 0.5131794214248657, "step": 2391 }, { "epoch": 0.3354133071583818, "grad_norm": 4.885062217712402, "learning_rate": 7.749230935693079e-06, "loss": 0.4825659692287445, "step": 2392 }, { "epoch": 0.3355535301128795, "grad_norm": 3.949002981185913, "learning_rate": 7.74733410320274e-06, "loss": 0.5732847452163696, "step": 2393 }, { "epoch": 0.33569375306737714, "grad_norm": 3.3220643997192383, "learning_rate": 7.745436704146936e-06, "loss": 0.49830102920532227, "step": 2394 }, { "epoch": 0.33583397602187476, "grad_norm": 3.021754741668701, "learning_rate": 7.743538738916954e-06, "loss": 0.597534716129303, "step": 2395 }, { "epoch": 0.33597419897637243, "grad_norm": 3.1461782455444336, "learning_rate": 7.7416402079042e-06, "loss": 0.6921151280403137, "step": 2396 }, { "epoch": 0.3361144219308701, "grad_norm": 3.2304623126983643, "learning_rate": 7.739741111500194e-06, "loss": 0.5997061133384705, "step": 2397 }, { "epoch": 0.3362546448853677, "grad_norm": 3.306940793991089, "learning_rate": 7.737841450096577e-06, "loss": 0.5841017365455627, "step": 2398 }, { "epoch": 0.3363948678398654, "grad_norm": 3.164700508117676, "learning_rate": 7.735941224085104e-06, "loss": 0.5484368205070496, "step": 2399 }, { "epoch": 0.33653509079436306, "grad_norm": 5.293096542358398, "learning_rate": 7.734040433857647e-06, "loss": 0.5575101971626282, "step": 2400 }, { "epoch": 0.33667531374886067, "grad_norm": 2.6084678173065186, "learning_rate": 7.732139079806194e-06, "loss": 0.6345292925834656, "step": 2401 }, { "epoch": 0.33681553670335834, "grad_norm": 2.4411535263061523, "learning_rate": 7.730237162322847e-06, "loss": 0.4736451208591461, "step": 2402 }, { "epoch": 0.336955759657856, "grad_norm": 3.612551689147949, "learning_rate": 7.72833468179983e-06, "loss": 0.5824601650238037, "step": 2403 }, { "epoch": 0.33709598261235363, "grad_norm": 2.6646013259887695, "learning_rate": 7.726431638629475e-06, "loss": 0.5723640322685242, "step": 2404 }, { "epoch": 0.3372362055668513, "grad_norm": 2.7098965644836426, "learning_rate": 7.72452803320424e-06, "loss": 0.4366219937801361, "step": 2405 }, { "epoch": 0.33737642852134897, "grad_norm": 3.162867784500122, "learning_rate": 7.722623865916692e-06, "loss": 0.5139424800872803, "step": 2406 }, { "epoch": 0.3375166514758466, "grad_norm": 3.342780351638794, "learning_rate": 7.72071913715951e-06, "loss": 0.6082315444946289, "step": 2407 }, { "epoch": 0.33765687443034426, "grad_norm": 3.740190029144287, "learning_rate": 7.718813847325504e-06, "loss": 0.5711667537689209, "step": 2408 }, { "epoch": 0.33779709738484187, "grad_norm": 4.315685272216797, "learning_rate": 7.716907996807583e-06, "loss": 0.5197920799255371, "step": 2409 }, { "epoch": 0.33793732033933954, "grad_norm": 3.520291328430176, "learning_rate": 7.71500158599878e-06, "loss": 0.5082988739013672, "step": 2410 }, { "epoch": 0.3380775432938372, "grad_norm": 2.219677209854126, "learning_rate": 7.713094615292242e-06, "loss": 0.5477904081344604, "step": 2411 }, { "epoch": 0.33821776624833483, "grad_norm": 3.008125066757202, "learning_rate": 7.711187085081233e-06, "loss": 0.6647560000419617, "step": 2412 }, { "epoch": 0.3383579892028325, "grad_norm": 4.0486602783203125, "learning_rate": 7.709278995759131e-06, "loss": 0.553533673286438, "step": 2413 }, { "epoch": 0.33849821215733017, "grad_norm": 5.887312412261963, "learning_rate": 7.707370347719427e-06, "loss": 0.5620407462120056, "step": 2414 }, { "epoch": 0.3386384351118278, "grad_norm": 5.584287643432617, "learning_rate": 7.705461141355732e-06, "loss": 0.6495324373245239, "step": 2415 }, { "epoch": 0.33877865806632546, "grad_norm": 2.7278101444244385, "learning_rate": 7.70355137706177e-06, "loss": 0.6508896946907043, "step": 2416 }, { "epoch": 0.3389188810208231, "grad_norm": 2.9870693683624268, "learning_rate": 7.701641055231374e-06, "loss": 0.49623802304267883, "step": 2417 }, { "epoch": 0.33905910397532074, "grad_norm": 5.318787574768066, "learning_rate": 7.699730176258505e-06, "loss": 0.6882403492927551, "step": 2418 }, { "epoch": 0.3391993269298184, "grad_norm": 2.8542721271514893, "learning_rate": 7.697818740537228e-06, "loss": 0.531656801700592, "step": 2419 }, { "epoch": 0.3393395498843161, "grad_norm": 27.302701950073242, "learning_rate": 7.695906748461726e-06, "loss": 0.5709990859031677, "step": 2420 }, { "epoch": 0.3394797728388137, "grad_norm": 4.012824535369873, "learning_rate": 7.6939942004263e-06, "loss": 0.5185689926147461, "step": 2421 }, { "epoch": 0.33961999579331137, "grad_norm": 3.7843995094299316, "learning_rate": 7.69208109682536e-06, "loss": 0.5464290380477905, "step": 2422 }, { "epoch": 0.33976021874780904, "grad_norm": 3.8211801052093506, "learning_rate": 7.69016743805343e-06, "loss": 0.5268909931182861, "step": 2423 }, { "epoch": 0.33990044170230665, "grad_norm": 2.2847180366516113, "learning_rate": 7.688253224505161e-06, "loss": 0.47434207797050476, "step": 2424 }, { "epoch": 0.3400406646568043, "grad_norm": 2.5068352222442627, "learning_rate": 7.686338456575302e-06, "loss": 0.604967474937439, "step": 2425 }, { "epoch": 0.340180887611302, "grad_norm": 3.0141992568969727, "learning_rate": 7.684423134658726e-06, "loss": 0.500288724899292, "step": 2426 }, { "epoch": 0.3403211105657996, "grad_norm": 2.8481922149658203, "learning_rate": 7.68250725915042e-06, "loss": 0.4502432346343994, "step": 2427 }, { "epoch": 0.3404613335202973, "grad_norm": 6.573915958404541, "learning_rate": 7.680590830445479e-06, "loss": 0.5534717440605164, "step": 2428 }, { "epoch": 0.3406015564747949, "grad_norm": 3.1751461029052734, "learning_rate": 7.678673848939118e-06, "loss": 0.6118881702423096, "step": 2429 }, { "epoch": 0.34074177942929257, "grad_norm": 3.049874782562256, "learning_rate": 7.676756315026661e-06, "loss": 0.5332691669464111, "step": 2430 }, { "epoch": 0.34088200238379024, "grad_norm": 3.195528745651245, "learning_rate": 7.674838229103556e-06, "loss": 0.45717957615852356, "step": 2431 }, { "epoch": 0.34102222533828785, "grad_norm": 5.053633689880371, "learning_rate": 7.672919591565352e-06, "loss": 0.6515671014785767, "step": 2432 }, { "epoch": 0.3411624482927855, "grad_norm": 2.4914815425872803, "learning_rate": 7.671000402807717e-06, "loss": 0.5956069231033325, "step": 2433 }, { "epoch": 0.3413026712472832, "grad_norm": 4.065962314605713, "learning_rate": 7.669080663226436e-06, "loss": 0.6544599533081055, "step": 2434 }, { "epoch": 0.3414428942017808, "grad_norm": 4.058374404907227, "learning_rate": 7.667160373217406e-06, "loss": 0.5087280869483948, "step": 2435 }, { "epoch": 0.3415831171562785, "grad_norm": 4.158768653869629, "learning_rate": 7.665239533176634e-06, "loss": 0.5430381298065186, "step": 2436 }, { "epoch": 0.34172334011077615, "grad_norm": 2.9971506595611572, "learning_rate": 7.663318143500242e-06, "loss": 0.5811315178871155, "step": 2437 }, { "epoch": 0.34186356306527377, "grad_norm": 4.096982002258301, "learning_rate": 7.661396204584467e-06, "loss": 0.5947309136390686, "step": 2438 }, { "epoch": 0.34200378601977144, "grad_norm": 7.704379081726074, "learning_rate": 7.659473716825662e-06, "loss": 0.4898233413696289, "step": 2439 }, { "epoch": 0.3421440089742691, "grad_norm": 2.5530753135681152, "learning_rate": 7.657550680620285e-06, "loss": 0.567366361618042, "step": 2440 }, { "epoch": 0.3422842319287667, "grad_norm": 3.750880002975464, "learning_rate": 7.655627096364913e-06, "loss": 0.509141206741333, "step": 2441 }, { "epoch": 0.3424244548832644, "grad_norm": 2.4298644065856934, "learning_rate": 7.653702964456233e-06, "loss": 0.5573975443840027, "step": 2442 }, { "epoch": 0.34256467783776207, "grad_norm": 3.9450197219848633, "learning_rate": 7.65177828529105e-06, "loss": 0.4751589596271515, "step": 2443 }, { "epoch": 0.3427049007922597, "grad_norm": 21.22579002380371, "learning_rate": 7.64985305926628e-06, "loss": 0.6266179084777832, "step": 2444 }, { "epoch": 0.34284512374675735, "grad_norm": 2.9484264850616455, "learning_rate": 7.647927286778943e-06, "loss": 0.492931991815567, "step": 2445 }, { "epoch": 0.342985346701255, "grad_norm": 3.314103364944458, "learning_rate": 7.646000968226183e-06, "loss": 0.5084889531135559, "step": 2446 }, { "epoch": 0.34312556965575264, "grad_norm": 2.919975519180298, "learning_rate": 7.644074104005255e-06, "loss": 0.5472883582115173, "step": 2447 }, { "epoch": 0.3432657926102503, "grad_norm": 2.2222793102264404, "learning_rate": 7.642146694513522e-06, "loss": 0.4403734803199768, "step": 2448 }, { "epoch": 0.3434060155647479, "grad_norm": 3.8038623332977295, "learning_rate": 7.640218740148461e-06, "loss": 0.6066837906837463, "step": 2449 }, { "epoch": 0.3435462385192456, "grad_norm": 2.975545644760132, "learning_rate": 7.638290241307663e-06, "loss": 0.5437015295028687, "step": 2450 }, { "epoch": 0.34368646147374327, "grad_norm": 4.331453800201416, "learning_rate": 7.636361198388828e-06, "loss": 0.4504557251930237, "step": 2451 }, { "epoch": 0.3438266844282409, "grad_norm": 2.8976447582244873, "learning_rate": 7.634431611789772e-06, "loss": 0.560580849647522, "step": 2452 }, { "epoch": 0.34396690738273855, "grad_norm": 2.3464443683624268, "learning_rate": 7.632501481908422e-06, "loss": 0.5271725654602051, "step": 2453 }, { "epoch": 0.3441071303372362, "grad_norm": 2.9227185249328613, "learning_rate": 7.630570809142818e-06, "loss": 0.48085612058639526, "step": 2454 }, { "epoch": 0.34424735329173384, "grad_norm": 3.1802656650543213, "learning_rate": 7.6286395938911075e-06, "loss": 0.5665066838264465, "step": 2455 }, { "epoch": 0.3443875762462315, "grad_norm": 4.924591541290283, "learning_rate": 7.6267078365515525e-06, "loss": 0.5152552127838135, "step": 2456 }, { "epoch": 0.3445277992007292, "grad_norm": 3.926070213317871, "learning_rate": 7.624775537522531e-06, "loss": 0.5366985201835632, "step": 2457 }, { "epoch": 0.3446680221552268, "grad_norm": 3.5671420097351074, "learning_rate": 7.622842697202526e-06, "loss": 0.38452309370040894, "step": 2458 }, { "epoch": 0.34480824510972446, "grad_norm": 3.289519786834717, "learning_rate": 7.620909315990135e-06, "loss": 0.5649698972702026, "step": 2459 }, { "epoch": 0.34494846806422214, "grad_norm": 3.066338539123535, "learning_rate": 7.618975394284068e-06, "loss": 0.6039626002311707, "step": 2460 }, { "epoch": 0.34508869101871975, "grad_norm": 3.4554171562194824, "learning_rate": 7.617040932483147e-06, "loss": 0.5794641375541687, "step": 2461 }, { "epoch": 0.3452289139732174, "grad_norm": 8.588191986083984, "learning_rate": 7.6151059309863e-06, "loss": 0.6290590167045593, "step": 2462 }, { "epoch": 0.3453691369277151, "grad_norm": 7.906505107879639, "learning_rate": 7.613170390192573e-06, "loss": 0.4651084542274475, "step": 2463 }, { "epoch": 0.3455093598822127, "grad_norm": 4.2564616203308105, "learning_rate": 7.6112343105011185e-06, "loss": 0.5413463711738586, "step": 2464 }, { "epoch": 0.3456495828367104, "grad_norm": 4.096136569976807, "learning_rate": 7.609297692311205e-06, "loss": 0.5536941289901733, "step": 2465 }, { "epoch": 0.345789805791208, "grad_norm": 2.6098692417144775, "learning_rate": 7.607360536022208e-06, "loss": 0.5749646425247192, "step": 2466 }, { "epoch": 0.34593002874570566, "grad_norm": 5.529772758483887, "learning_rate": 7.605422842033614e-06, "loss": 0.5073989629745483, "step": 2467 }, { "epoch": 0.34607025170020334, "grad_norm": 14.288260459899902, "learning_rate": 7.603484610745022e-06, "loss": 0.5671781301498413, "step": 2468 }, { "epoch": 0.34621047465470095, "grad_norm": 4.182156085968018, "learning_rate": 7.6015458425561415e-06, "loss": 0.5415068864822388, "step": 2469 }, { "epoch": 0.3463506976091986, "grad_norm": 2.787158489227295, "learning_rate": 7.599606537866791e-06, "loss": 0.556888222694397, "step": 2470 }, { "epoch": 0.3464909205636963, "grad_norm": 4.00185489654541, "learning_rate": 7.5976666970769046e-06, "loss": 0.6216747760772705, "step": 2471 }, { "epoch": 0.3466311435181939, "grad_norm": 3.5330069065093994, "learning_rate": 7.595726320586519e-06, "loss": 0.6538475751876831, "step": 2472 }, { "epoch": 0.3467713664726916, "grad_norm": 3.1688430309295654, "learning_rate": 7.5937854087957905e-06, "loss": 0.46179071068763733, "step": 2473 }, { "epoch": 0.34691158942718925, "grad_norm": 2.9797239303588867, "learning_rate": 7.591843962104978e-06, "loss": 0.5878452658653259, "step": 2474 }, { "epoch": 0.34705181238168686, "grad_norm": 4.551401615142822, "learning_rate": 7.589901980914453e-06, "loss": 0.5837163925170898, "step": 2475 }, { "epoch": 0.34719203533618453, "grad_norm": 16.448246002197266, "learning_rate": 7.587959465624704e-06, "loss": 0.5616468191146851, "step": 2476 }, { "epoch": 0.3473322582906822, "grad_norm": 3.197148084640503, "learning_rate": 7.586016416636316e-06, "loss": 0.7229385375976562, "step": 2477 }, { "epoch": 0.3474724812451798, "grad_norm": 2.7905361652374268, "learning_rate": 7.584072834349996e-06, "loss": 0.5896183252334595, "step": 2478 }, { "epoch": 0.3476127041996775, "grad_norm": 2.526482343673706, "learning_rate": 7.5821287191665575e-06, "loss": 0.5473780035972595, "step": 2479 }, { "epoch": 0.34775292715417516, "grad_norm": 4.4127278327941895, "learning_rate": 7.5801840714869205e-06, "loss": 0.5815931558609009, "step": 2480 }, { "epoch": 0.3478931501086728, "grad_norm": 2.569608688354492, "learning_rate": 7.578238891712119e-06, "loss": 0.5048328638076782, "step": 2481 }, { "epoch": 0.34803337306317045, "grad_norm": 8.942928314208984, "learning_rate": 7.576293180243295e-06, "loss": 0.5719466805458069, "step": 2482 }, { "epoch": 0.3481735960176681, "grad_norm": 7.151158332824707, "learning_rate": 7.5743469374817e-06, "loss": 0.5154567360877991, "step": 2483 }, { "epoch": 0.34831381897216573, "grad_norm": 3.9260716438293457, "learning_rate": 7.572400163828696e-06, "loss": 0.5218507051467896, "step": 2484 }, { "epoch": 0.3484540419266634, "grad_norm": 5.597561836242676, "learning_rate": 7.570452859685753e-06, "loss": 0.5599175095558167, "step": 2485 }, { "epoch": 0.348594264881161, "grad_norm": 3.765105724334717, "learning_rate": 7.568505025454455e-06, "loss": 0.5818772912025452, "step": 2486 }, { "epoch": 0.3487344878356587, "grad_norm": 3.5488340854644775, "learning_rate": 7.566556661536486e-06, "loss": 0.5713181495666504, "step": 2487 }, { "epoch": 0.34887471079015636, "grad_norm": 7.027508735656738, "learning_rate": 7.564607768333647e-06, "loss": 0.5752421617507935, "step": 2488 }, { "epoch": 0.349014933744654, "grad_norm": 3.3914682865142822, "learning_rate": 7.5626583462478485e-06, "loss": 0.6019995212554932, "step": 2489 }, { "epoch": 0.34915515669915165, "grad_norm": 4.341788291931152, "learning_rate": 7.560708395681105e-06, "loss": 0.6867859363555908, "step": 2490 }, { "epoch": 0.3492953796536493, "grad_norm": 3.9217381477355957, "learning_rate": 7.558757917035542e-06, "loss": 0.5300400853157043, "step": 2491 }, { "epoch": 0.34943560260814693, "grad_norm": 4.388482093811035, "learning_rate": 7.556806910713397e-06, "loss": 0.5311352014541626, "step": 2492 }, { "epoch": 0.3495758255626446, "grad_norm": 2.421048402786255, "learning_rate": 7.554855377117012e-06, "loss": 0.5438886284828186, "step": 2493 }, { "epoch": 0.3497160485171423, "grad_norm": 4.2215352058410645, "learning_rate": 7.552903316648839e-06, "loss": 0.574459433555603, "step": 2494 }, { "epoch": 0.3498562714716399, "grad_norm": 3.145684242248535, "learning_rate": 7.550950729711441e-06, "loss": 0.5656812787055969, "step": 2495 }, { "epoch": 0.34999649442613756, "grad_norm": 5.732184886932373, "learning_rate": 7.5489976167074875e-06, "loss": 0.615142822265625, "step": 2496 }, { "epoch": 0.35013671738063523, "grad_norm": 2.743675947189331, "learning_rate": 7.547043978039754e-06, "loss": 0.5639115571975708, "step": 2497 }, { "epoch": 0.35027694033513285, "grad_norm": 3.428764581680298, "learning_rate": 7.545089814111132e-06, "loss": 0.6071669459342957, "step": 2498 }, { "epoch": 0.3504171632896305, "grad_norm": 3.5912322998046875, "learning_rate": 7.543135125324612e-06, "loss": 0.5864271521568298, "step": 2499 }, { "epoch": 0.3505573862441282, "grad_norm": 3.0845789909362793, "learning_rate": 7.541179912083299e-06, "loss": 0.5556640625, "step": 2500 }, { "epoch": 0.3506976091986258, "grad_norm": 4.689542770385742, "learning_rate": 7.5392241747904024e-06, "loss": 0.3893759846687317, "step": 2501 }, { "epoch": 0.3508378321531235, "grad_norm": 29.420164108276367, "learning_rate": 7.537267913849247e-06, "loss": 0.618225634098053, "step": 2502 }, { "epoch": 0.35097805510762115, "grad_norm": 2.919597625732422, "learning_rate": 7.5353111296632544e-06, "loss": 0.5890786647796631, "step": 2503 }, { "epoch": 0.35111827806211876, "grad_norm": 3.812291383743286, "learning_rate": 7.533353822635963e-06, "loss": 0.5375776290893555, "step": 2504 }, { "epoch": 0.35125850101661643, "grad_norm": 2.8616561889648438, "learning_rate": 7.531395993171016e-06, "loss": 0.509125292301178, "step": 2505 }, { "epoch": 0.35139872397111405, "grad_norm": 4.575392246246338, "learning_rate": 7.529437641672161e-06, "loss": 0.628395676612854, "step": 2506 }, { "epoch": 0.3515389469256117, "grad_norm": 3.551041841506958, "learning_rate": 7.527478768543262e-06, "loss": 0.5926687121391296, "step": 2507 }, { "epoch": 0.3516791698801094, "grad_norm": 4.029367923736572, "learning_rate": 7.5255193741882806e-06, "loss": 0.6741359829902649, "step": 2508 }, { "epoch": 0.351819392834607, "grad_norm": 3.0900440216064453, "learning_rate": 7.523559459011292e-06, "loss": 0.6048343181610107, "step": 2509 }, { "epoch": 0.3519596157891047, "grad_norm": 4.350034236907959, "learning_rate": 7.521599023416475e-06, "loss": 0.5638354420661926, "step": 2510 }, { "epoch": 0.35209983874360234, "grad_norm": 13.791830062866211, "learning_rate": 7.519638067808124e-06, "loss": 0.5536468625068665, "step": 2511 }, { "epoch": 0.35224006169809996, "grad_norm": 4.431426048278809, "learning_rate": 7.517676592590627e-06, "loss": 0.45258376002311707, "step": 2512 }, { "epoch": 0.35238028465259763, "grad_norm": 7.891136169433594, "learning_rate": 7.515714598168491e-06, "loss": 0.5021843910217285, "step": 2513 }, { "epoch": 0.3525205076070953, "grad_norm": 4.429927349090576, "learning_rate": 7.513752084946327e-06, "loss": 0.4986613392829895, "step": 2514 }, { "epoch": 0.3526607305615929, "grad_norm": 2.5784213542938232, "learning_rate": 7.5117890533288485e-06, "loss": 0.5227686166763306, "step": 2515 }, { "epoch": 0.3528009535160906, "grad_norm": 4.158939838409424, "learning_rate": 7.50982550372088e-06, "loss": 0.6016337871551514, "step": 2516 }, { "epoch": 0.35294117647058826, "grad_norm": 4.997903347015381, "learning_rate": 7.5078614365273526e-06, "loss": 0.5475668907165527, "step": 2517 }, { "epoch": 0.3530813994250859, "grad_norm": 5.619833469390869, "learning_rate": 7.505896852153305e-06, "loss": 0.605424165725708, "step": 2518 }, { "epoch": 0.35322162237958354, "grad_norm": 5.607386589050293, "learning_rate": 7.503931751003879e-06, "loss": 0.5750837326049805, "step": 2519 }, { "epoch": 0.3533618453340812, "grad_norm": 3.8038437366485596, "learning_rate": 7.501966133484324e-06, "loss": 0.6224671602249146, "step": 2520 }, { "epoch": 0.35350206828857883, "grad_norm": 4.768709182739258, "learning_rate": 7.500000000000001e-06, "loss": 0.5890734195709229, "step": 2521 }, { "epoch": 0.3536422912430765, "grad_norm": 3.925603151321411, "learning_rate": 7.49803335095637e-06, "loss": 0.4980763792991638, "step": 2522 }, { "epoch": 0.3537825141975741, "grad_norm": 3.446335792541504, "learning_rate": 7.496066186759001e-06, "loss": 0.49247056245803833, "step": 2523 }, { "epoch": 0.3539227371520718, "grad_norm": 2.9048733711242676, "learning_rate": 7.494098507813572e-06, "loss": 0.5872885584831238, "step": 2524 }, { "epoch": 0.35406296010656946, "grad_norm": 3.2615978717803955, "learning_rate": 7.492130314525863e-06, "loss": 0.5548452138900757, "step": 2525 }, { "epoch": 0.3542031830610671, "grad_norm": 2.7183313369750977, "learning_rate": 7.490161607301762e-06, "loss": 0.5603764057159424, "step": 2526 }, { "epoch": 0.35434340601556474, "grad_norm": 3.067681312561035, "learning_rate": 7.488192386547266e-06, "loss": 0.44837555289268494, "step": 2527 }, { "epoch": 0.3544836289700624, "grad_norm": 4.009026527404785, "learning_rate": 7.4862226526684725e-06, "loss": 0.5701431035995483, "step": 2528 }, { "epoch": 0.35462385192456003, "grad_norm": 2.9782028198242188, "learning_rate": 7.484252406071586e-06, "loss": 0.6239343285560608, "step": 2529 }, { "epoch": 0.3547640748790577, "grad_norm": 3.9296791553497314, "learning_rate": 7.482281647162921e-06, "loss": 0.6308462619781494, "step": 2530 }, { "epoch": 0.35490429783355537, "grad_norm": 3.441431999206543, "learning_rate": 7.480310376348895e-06, "loss": 0.47301268577575684, "step": 2531 }, { "epoch": 0.355044520788053, "grad_norm": 4.022948741912842, "learning_rate": 7.478338594036028e-06, "loss": 0.5952893495559692, "step": 2532 }, { "epoch": 0.35518474374255066, "grad_norm": 7.379421234130859, "learning_rate": 7.476366300630951e-06, "loss": 0.6208801865577698, "step": 2533 }, { "epoch": 0.35532496669704833, "grad_norm": 3.6234066486358643, "learning_rate": 7.474393496540395e-06, "loss": 0.5310239791870117, "step": 2534 }, { "epoch": 0.35546518965154594, "grad_norm": 5.791629314422607, "learning_rate": 7.472420182171202e-06, "loss": 0.5198620557785034, "step": 2535 }, { "epoch": 0.3556054126060436, "grad_norm": 5.947381973266602, "learning_rate": 7.470446357930313e-06, "loss": 0.6459347009658813, "step": 2536 }, { "epoch": 0.3557456355605413, "grad_norm": 3.4675168991088867, "learning_rate": 7.468472024224781e-06, "loss": 0.6043793559074402, "step": 2537 }, { "epoch": 0.3558858585150389, "grad_norm": 4.9536967277526855, "learning_rate": 7.466497181461757e-06, "loss": 0.4974563717842102, "step": 2538 }, { "epoch": 0.35602608146953657, "grad_norm": 4.135379314422607, "learning_rate": 7.464521830048502e-06, "loss": 0.49454551935195923, "step": 2539 }, { "epoch": 0.35616630442403424, "grad_norm": 7.490772247314453, "learning_rate": 7.462545970392382e-06, "loss": 0.5131189227104187, "step": 2540 }, { "epoch": 0.35630652737853186, "grad_norm": 17.193294525146484, "learning_rate": 7.4605696029008626e-06, "loss": 0.5371299386024475, "step": 2541 }, { "epoch": 0.3564467503330295, "grad_norm": 3.6397275924682617, "learning_rate": 7.458592727981519e-06, "loss": 0.6359347105026245, "step": 2542 }, { "epoch": 0.35658697328752714, "grad_norm": 7.6662702560424805, "learning_rate": 7.4566153460420335e-06, "loss": 0.5363744497299194, "step": 2543 }, { "epoch": 0.3567271962420248, "grad_norm": 2.991119861602783, "learning_rate": 7.4546374574901835e-06, "loss": 0.6209262609481812, "step": 2544 }, { "epoch": 0.3568674191965225, "grad_norm": 5.913171768188477, "learning_rate": 7.452659062733858e-06, "loss": 0.4783961772918701, "step": 2545 }, { "epoch": 0.3570076421510201, "grad_norm": 2.8080499172210693, "learning_rate": 7.450680162181051e-06, "loss": 0.47509610652923584, "step": 2546 }, { "epoch": 0.35714786510551777, "grad_norm": 5.586554527282715, "learning_rate": 7.448700756239859e-06, "loss": 0.5586015582084656, "step": 2547 }, { "epoch": 0.35728808806001544, "grad_norm": 3.944331645965576, "learning_rate": 7.446720845318479e-06, "loss": 0.5885287523269653, "step": 2548 }, { "epoch": 0.35742831101451306, "grad_norm": 3.123171806335449, "learning_rate": 7.444740429825218e-06, "loss": 0.6651862859725952, "step": 2549 }, { "epoch": 0.3575685339690107, "grad_norm": 3.325713872909546, "learning_rate": 7.442759510168485e-06, "loss": 0.5152818560600281, "step": 2550 }, { "epoch": 0.3577087569235084, "grad_norm": 5.759105205535889, "learning_rate": 7.440778086756791e-06, "loss": 0.4948490858078003, "step": 2551 }, { "epoch": 0.357848979878006, "grad_norm": 2.1992595195770264, "learning_rate": 7.4387961599987535e-06, "loss": 0.5023289322853088, "step": 2552 }, { "epoch": 0.3579892028325037, "grad_norm": 3.515712022781372, "learning_rate": 7.436813730303094e-06, "loss": 0.5176868438720703, "step": 2553 }, { "epoch": 0.35812942578700135, "grad_norm": 3.9834299087524414, "learning_rate": 7.434830798078634e-06, "loss": 0.5593926906585693, "step": 2554 }, { "epoch": 0.35826964874149897, "grad_norm": 4.400489807128906, "learning_rate": 7.432847363734302e-06, "loss": 0.6116652488708496, "step": 2555 }, { "epoch": 0.35840987169599664, "grad_norm": 2.9622385501861572, "learning_rate": 7.430863427679131e-06, "loss": 0.5136082172393799, "step": 2556 }, { "epoch": 0.3585500946504943, "grad_norm": 4.525762557983398, "learning_rate": 7.428878990322255e-06, "loss": 0.5098742842674255, "step": 2557 }, { "epoch": 0.3586903176049919, "grad_norm": 4.461646556854248, "learning_rate": 7.426894052072909e-06, "loss": 0.5232002139091492, "step": 2558 }, { "epoch": 0.3588305405594896, "grad_norm": 4.641399383544922, "learning_rate": 7.424908613340438e-06, "loss": 0.5408085584640503, "step": 2559 }, { "epoch": 0.3589707635139872, "grad_norm": 3.113966226577759, "learning_rate": 7.422922674534287e-06, "loss": 0.5788297057151794, "step": 2560 }, { "epoch": 0.3591109864684849, "grad_norm": 3.483207941055298, "learning_rate": 7.420936236063999e-06, "loss": 0.5718480348587036, "step": 2561 }, { "epoch": 0.35925120942298255, "grad_norm": 2.7049853801727295, "learning_rate": 7.418949298339228e-06, "loss": 0.5009992718696594, "step": 2562 }, { "epoch": 0.35939143237748017, "grad_norm": 6.389861106872559, "learning_rate": 7.41696186176973e-06, "loss": 0.4689650535583496, "step": 2563 }, { "epoch": 0.35953165533197784, "grad_norm": 3.542215347290039, "learning_rate": 7.414973926765358e-06, "loss": 0.4500986635684967, "step": 2564 }, { "epoch": 0.3596718782864755, "grad_norm": 10.200981140136719, "learning_rate": 7.4129854937360714e-06, "loss": 0.5895773768424988, "step": 2565 }, { "epoch": 0.3598121012409731, "grad_norm": 4.104851245880127, "learning_rate": 7.410996563091935e-06, "loss": 0.5723235607147217, "step": 2566 }, { "epoch": 0.3599523241954708, "grad_norm": 5.184566497802734, "learning_rate": 7.409007135243109e-06, "loss": 0.5504167079925537, "step": 2567 }, { "epoch": 0.36009254714996847, "grad_norm": 3.225914239883423, "learning_rate": 7.407017210599865e-06, "loss": 0.5296061038970947, "step": 2568 }, { "epoch": 0.3602327701044661, "grad_norm": 44.629493713378906, "learning_rate": 7.405026789572571e-06, "loss": 0.6155612468719482, "step": 2569 }, { "epoch": 0.36037299305896375, "grad_norm": 4.325238227844238, "learning_rate": 7.403035872571699e-06, "loss": 0.5246367454528809, "step": 2570 }, { "epoch": 0.3605132160134614, "grad_norm": 3.0162084102630615, "learning_rate": 7.401044460007822e-06, "loss": 0.6453099250793457, "step": 2571 }, { "epoch": 0.36065343896795904, "grad_norm": 3.639073133468628, "learning_rate": 7.3990525522916214e-06, "loss": 0.5458926558494568, "step": 2572 }, { "epoch": 0.3607936619224567, "grad_norm": 4.613197326660156, "learning_rate": 7.397060149833869e-06, "loss": 0.5644938945770264, "step": 2573 }, { "epoch": 0.3609338848769544, "grad_norm": 3.889310359954834, "learning_rate": 7.3950672530454495e-06, "loss": 0.5825586318969727, "step": 2574 }, { "epoch": 0.361074107831452, "grad_norm": 3.264474868774414, "learning_rate": 7.393073862337344e-06, "loss": 0.498008131980896, "step": 2575 }, { "epoch": 0.36121433078594967, "grad_norm": 3.3211543560028076, "learning_rate": 7.39107997812064e-06, "loss": 0.5718727111816406, "step": 2576 }, { "epoch": 0.36135455374044734, "grad_norm": 3.2098445892333984, "learning_rate": 7.389085600806519e-06, "loss": 0.5388379096984863, "step": 2577 }, { "epoch": 0.36149477669494495, "grad_norm": 2.5280518531799316, "learning_rate": 7.387090730806272e-06, "loss": 0.4985138773918152, "step": 2578 }, { "epoch": 0.3616349996494426, "grad_norm": 3.6341264247894287, "learning_rate": 7.3850953685312895e-06, "loss": 0.6122509241104126, "step": 2579 }, { "epoch": 0.36177522260394024, "grad_norm": 2.6919748783111572, "learning_rate": 7.383099514393059e-06, "loss": 0.5867822766304016, "step": 2580 }, { "epoch": 0.3619154455584379, "grad_norm": 3.703918695449829, "learning_rate": 7.381103168803175e-06, "loss": 0.5848097205162048, "step": 2581 }, { "epoch": 0.3620556685129356, "grad_norm": 7.245774745941162, "learning_rate": 7.3791063321733325e-06, "loss": 0.5801123380661011, "step": 2582 }, { "epoch": 0.3621958914674332, "grad_norm": 2.6165008544921875, "learning_rate": 7.377109004915323e-06, "loss": 0.6094182729721069, "step": 2583 }, { "epoch": 0.36233611442193087, "grad_norm": 3.2559266090393066, "learning_rate": 7.3751111874410475e-06, "loss": 0.5994807481765747, "step": 2584 }, { "epoch": 0.36247633737642854, "grad_norm": 4.823209762573242, "learning_rate": 7.373112880162501e-06, "loss": 0.520054042339325, "step": 2585 }, { "epoch": 0.36261656033092615, "grad_norm": 3.3824918270111084, "learning_rate": 7.37111408349178e-06, "loss": 0.458967924118042, "step": 2586 }, { "epoch": 0.3627567832854238, "grad_norm": 7.2163166999816895, "learning_rate": 7.369114797841085e-06, "loss": 0.5694996118545532, "step": 2587 }, { "epoch": 0.3628970062399215, "grad_norm": 2.8072669506073, "learning_rate": 7.3671150236227176e-06, "loss": 0.5628564953804016, "step": 2588 }, { "epoch": 0.3630372291944191, "grad_norm": 3.2482545375823975, "learning_rate": 7.365114761249078e-06, "loss": 0.5760043859481812, "step": 2589 }, { "epoch": 0.3631774521489168, "grad_norm": 4.517473220825195, "learning_rate": 7.363114011132667e-06, "loss": 0.4697515666484833, "step": 2590 }, { "epoch": 0.36331767510341445, "grad_norm": 4.667855262756348, "learning_rate": 7.3611127736860876e-06, "loss": 0.5233460068702698, "step": 2591 }, { "epoch": 0.36345789805791207, "grad_norm": 4.0417962074279785, "learning_rate": 7.359111049322043e-06, "loss": 0.5928722023963928, "step": 2592 }, { "epoch": 0.36359812101240974, "grad_norm": 3.405653476715088, "learning_rate": 7.357108838453334e-06, "loss": 0.5485878586769104, "step": 2593 }, { "epoch": 0.3637383439669074, "grad_norm": 3.4676387310028076, "learning_rate": 7.355106141492865e-06, "loss": 0.550739049911499, "step": 2594 }, { "epoch": 0.363878566921405, "grad_norm": 3.8193979263305664, "learning_rate": 7.353102958853641e-06, "loss": 0.626860499382019, "step": 2595 }, { "epoch": 0.3640187898759027, "grad_norm": 4.523795127868652, "learning_rate": 7.3510992909487645e-06, "loss": 0.531939685344696, "step": 2596 }, { "epoch": 0.36415901283040036, "grad_norm": 5.485779762268066, "learning_rate": 7.349095138191439e-06, "loss": 0.5511167049407959, "step": 2597 }, { "epoch": 0.364299235784898, "grad_norm": 4.263613224029541, "learning_rate": 7.34709050099497e-06, "loss": 0.5410046577453613, "step": 2598 }, { "epoch": 0.36443945873939565, "grad_norm": 3.0277059078216553, "learning_rate": 7.345085379772758e-06, "loss": 0.5851380825042725, "step": 2599 }, { "epoch": 0.36457968169389326, "grad_norm": 4.101871967315674, "learning_rate": 7.343079774938311e-06, "loss": 0.617367148399353, "step": 2600 }, { "epoch": 0.36471990464839094, "grad_norm": 2.6941823959350586, "learning_rate": 7.341073686905229e-06, "loss": 0.5630991458892822, "step": 2601 }, { "epoch": 0.3648601276028886, "grad_norm": 2.4543263912200928, "learning_rate": 7.339067116087216e-06, "loss": 0.5744104385375977, "step": 2602 }, { "epoch": 0.3650003505573862, "grad_norm": 3.053452968597412, "learning_rate": 7.337060062898075e-06, "loss": 0.587148129940033, "step": 2603 }, { "epoch": 0.3651405735118839, "grad_norm": 3.415165424346924, "learning_rate": 7.335052527751706e-06, "loss": 0.44047820568084717, "step": 2604 }, { "epoch": 0.36528079646638156, "grad_norm": 2.8523647785186768, "learning_rate": 7.333044511062114e-06, "loss": 0.5757187604904175, "step": 2605 }, { "epoch": 0.3654210194208792, "grad_norm": 4.53439998626709, "learning_rate": 7.331036013243396e-06, "loss": 0.5750495791435242, "step": 2606 }, { "epoch": 0.36556124237537685, "grad_norm": 2.7470247745513916, "learning_rate": 7.329027034709753e-06, "loss": 0.581373393535614, "step": 2607 }, { "epoch": 0.3657014653298745, "grad_norm": 3.02313494682312, "learning_rate": 7.327017575875486e-06, "loss": 0.49521929025650024, "step": 2608 }, { "epoch": 0.36584168828437214, "grad_norm": 4.136106491088867, "learning_rate": 7.325007637154991e-06, "loss": 0.6890761852264404, "step": 2609 }, { "epoch": 0.3659819112388698, "grad_norm": 2.057492256164551, "learning_rate": 7.322997218962764e-06, "loss": 0.5008811354637146, "step": 2610 }, { "epoch": 0.3661221341933675, "grad_norm": 2.571397542953491, "learning_rate": 7.320986321713404e-06, "loss": 0.5382242202758789, "step": 2611 }, { "epoch": 0.3662623571478651, "grad_norm": 2.248438596725464, "learning_rate": 7.318974945821603e-06, "loss": 0.5951203107833862, "step": 2612 }, { "epoch": 0.36640258010236276, "grad_norm": 2.938514471054077, "learning_rate": 7.316963091702156e-06, "loss": 0.6388818025588989, "step": 2613 }, { "epoch": 0.36654280305686043, "grad_norm": 4.4235920906066895, "learning_rate": 7.314950759769956e-06, "loss": 0.5737965106964111, "step": 2614 }, { "epoch": 0.36668302601135805, "grad_norm": 4.703866481781006, "learning_rate": 7.312937950439991e-06, "loss": 0.5047283172607422, "step": 2615 }, { "epoch": 0.3668232489658557, "grad_norm": 2.888282299041748, "learning_rate": 7.310924664127351e-06, "loss": 0.3811272978782654, "step": 2616 }, { "epoch": 0.36696347192035333, "grad_norm": 2.8554701805114746, "learning_rate": 7.3089109012472244e-06, "loss": 0.526153564453125, "step": 2617 }, { "epoch": 0.367103694874851, "grad_norm": 2.933891773223877, "learning_rate": 7.306896662214896e-06, "loss": 0.6461998820304871, "step": 2618 }, { "epoch": 0.3672439178293487, "grad_norm": 7.111593723297119, "learning_rate": 7.30488194744575e-06, "loss": 0.5921328663825989, "step": 2619 }, { "epoch": 0.3673841407838463, "grad_norm": 3.453033924102783, "learning_rate": 7.302866757355267e-06, "loss": 0.6204977035522461, "step": 2620 }, { "epoch": 0.36752436373834396, "grad_norm": 6.6860032081604, "learning_rate": 7.300851092359029e-06, "loss": 0.5457391738891602, "step": 2621 }, { "epoch": 0.36766458669284163, "grad_norm": 2.712719440460205, "learning_rate": 7.298834952872713e-06, "loss": 0.4748745858669281, "step": 2622 }, { "epoch": 0.36780480964733925, "grad_norm": 3.8288497924804688, "learning_rate": 7.296818339312095e-06, "loss": 0.5312740802764893, "step": 2623 }, { "epoch": 0.3679450326018369, "grad_norm": 4.472662448883057, "learning_rate": 7.29480125209305e-06, "loss": 0.6476055383682251, "step": 2624 }, { "epoch": 0.3680852555563346, "grad_norm": 2.545921564102173, "learning_rate": 7.292783691631546e-06, "loss": 0.5572400093078613, "step": 2625 }, { "epoch": 0.3682254785108322, "grad_norm": 4.453869819641113, "learning_rate": 7.290765658343653e-06, "loss": 0.5146587491035461, "step": 2626 }, { "epoch": 0.3683657014653299, "grad_norm": 3.4033429622650146, "learning_rate": 7.28874715264554e-06, "loss": 0.4841079115867615, "step": 2627 }, { "epoch": 0.36850592441982755, "grad_norm": 2.5619192123413086, "learning_rate": 7.286728174953468e-06, "loss": 0.4863523542881012, "step": 2628 }, { "epoch": 0.36864614737432516, "grad_norm": 2.6373305320739746, "learning_rate": 7.284708725683798e-06, "loss": 0.5625406503677368, "step": 2629 }, { "epoch": 0.36878637032882283, "grad_norm": 3.461693048477173, "learning_rate": 7.282688805252989e-06, "loss": 0.47361046075820923, "step": 2630 }, { "epoch": 0.3689265932833205, "grad_norm": 2.92870831489563, "learning_rate": 7.280668414077596e-06, "loss": 0.576372504234314, "step": 2631 }, { "epoch": 0.3690668162378181, "grad_norm": 2.8968796730041504, "learning_rate": 7.278647552574274e-06, "loss": 0.5637578964233398, "step": 2632 }, { "epoch": 0.3692070391923158, "grad_norm": 3.6795101165771484, "learning_rate": 7.276626221159769e-06, "loss": 0.4879677891731262, "step": 2633 }, { "epoch": 0.36934726214681346, "grad_norm": 5.5529279708862305, "learning_rate": 7.27460442025093e-06, "loss": 0.5657122135162354, "step": 2634 }, { "epoch": 0.3694874851013111, "grad_norm": 3.230989933013916, "learning_rate": 7.2725821502647e-06, "loss": 0.5055123567581177, "step": 2635 }, { "epoch": 0.36962770805580875, "grad_norm": 2.427253007888794, "learning_rate": 7.270559411618119e-06, "loss": 0.4861781895160675, "step": 2636 }, { "epoch": 0.36976793101030636, "grad_norm": 2.868823528289795, "learning_rate": 7.2685362047283225e-06, "loss": 0.5545622110366821, "step": 2637 }, { "epoch": 0.36990815396480403, "grad_norm": 2.3569891452789307, "learning_rate": 7.266512530012544e-06, "loss": 0.5828183889389038, "step": 2638 }, { "epoch": 0.3700483769193017, "grad_norm": 2.958850860595703, "learning_rate": 7.264488387888115e-06, "loss": 0.5981156229972839, "step": 2639 }, { "epoch": 0.3701885998737993, "grad_norm": 3.8442273139953613, "learning_rate": 7.26246377877246e-06, "loss": 0.539557695388794, "step": 2640 }, { "epoch": 0.370328822828297, "grad_norm": 3.358748197555542, "learning_rate": 7.260438703083101e-06, "loss": 0.4875113070011139, "step": 2641 }, { "epoch": 0.37046904578279466, "grad_norm": 4.839015960693359, "learning_rate": 7.258413161237658e-06, "loss": 0.6245366930961609, "step": 2642 }, { "epoch": 0.3706092687372923, "grad_norm": 3.396328926086426, "learning_rate": 7.256387153653847e-06, "loss": 0.5548284649848938, "step": 2643 }, { "epoch": 0.37074949169178995, "grad_norm": 4.828509330749512, "learning_rate": 7.254360680749475e-06, "loss": 0.6629898548126221, "step": 2644 }, { "epoch": 0.3708897146462876, "grad_norm": 4.3024773597717285, "learning_rate": 7.252333742942451e-06, "loss": 0.5845503807067871, "step": 2645 }, { "epoch": 0.37102993760078523, "grad_norm": 2.9007890224456787, "learning_rate": 7.250306340650779e-06, "loss": 0.5049178600311279, "step": 2646 }, { "epoch": 0.3711701605552829, "grad_norm": 3.052959680557251, "learning_rate": 7.248278474292555e-06, "loss": 0.5302278399467468, "step": 2647 }, { "epoch": 0.3713103835097806, "grad_norm": 2.60308575630188, "learning_rate": 7.2462501442859735e-06, "loss": 0.4921254813671112, "step": 2648 }, { "epoch": 0.3714506064642782, "grad_norm": 3.467858076095581, "learning_rate": 7.244221351049325e-06, "loss": 0.5880788564682007, "step": 2649 }, { "epoch": 0.37159082941877586, "grad_norm": 2.8011021614074707, "learning_rate": 7.2421920950009975e-06, "loss": 0.5639222264289856, "step": 2650 }, { "epoch": 0.37173105237327353, "grad_norm": 5.439321994781494, "learning_rate": 7.240162376559465e-06, "loss": 0.5100705623626709, "step": 2651 }, { "epoch": 0.37187127532777114, "grad_norm": 4.049920558929443, "learning_rate": 7.23813219614331e-06, "loss": 0.45562121272087097, "step": 2652 }, { "epoch": 0.3720114982822688, "grad_norm": 2.363694667816162, "learning_rate": 7.236101554171201e-06, "loss": 0.5560779571533203, "step": 2653 }, { "epoch": 0.3721517212367665, "grad_norm": 6.362305164337158, "learning_rate": 7.234070451061905e-06, "loss": 0.5475766658782959, "step": 2654 }, { "epoch": 0.3722919441912641, "grad_norm": 4.540317058563232, "learning_rate": 7.232038887234283e-06, "loss": 0.524884819984436, "step": 2655 }, { "epoch": 0.37243216714576177, "grad_norm": 3.0473415851593018, "learning_rate": 7.230006863107293e-06, "loss": 0.5001640319824219, "step": 2656 }, { "epoch": 0.3725723901002594, "grad_norm": 5.166039943695068, "learning_rate": 7.227974379099984e-06, "loss": 0.4785042703151703, "step": 2657 }, { "epoch": 0.37271261305475706, "grad_norm": 6.851475238800049, "learning_rate": 7.2259414356315065e-06, "loss": 0.5570017695426941, "step": 2658 }, { "epoch": 0.37285283600925473, "grad_norm": 3.1064016819000244, "learning_rate": 7.223908033121099e-06, "loss": 0.5924043655395508, "step": 2659 }, { "epoch": 0.37299305896375234, "grad_norm": 5.615164756774902, "learning_rate": 7.221874171988097e-06, "loss": 0.5416467785835266, "step": 2660 }, { "epoch": 0.37313328191825, "grad_norm": 2.8580069541931152, "learning_rate": 7.219839852651932e-06, "loss": 0.5105133056640625, "step": 2661 }, { "epoch": 0.3732735048727477, "grad_norm": 5.408809185028076, "learning_rate": 7.217805075532129e-06, "loss": 0.5568222999572754, "step": 2662 }, { "epoch": 0.3734137278272453, "grad_norm": 5.301233768463135, "learning_rate": 7.215769841048306e-06, "loss": 0.5542960166931152, "step": 2663 }, { "epoch": 0.37355395078174297, "grad_norm": 2.979843854904175, "learning_rate": 7.213734149620177e-06, "loss": 0.6589598655700684, "step": 2664 }, { "epoch": 0.37369417373624064, "grad_norm": 4.406835079193115, "learning_rate": 7.211698001667552e-06, "loss": 0.5825188159942627, "step": 2665 }, { "epoch": 0.37383439669073826, "grad_norm": 5.021378993988037, "learning_rate": 7.2096613976103315e-06, "loss": 0.6614723205566406, "step": 2666 }, { "epoch": 0.37397461964523593, "grad_norm": 4.309240818023682, "learning_rate": 7.207624337868511e-06, "loss": 0.591760516166687, "step": 2667 }, { "epoch": 0.3741148425997336, "grad_norm": 2.1651430130004883, "learning_rate": 7.20558682286218e-06, "loss": 0.5831841230392456, "step": 2668 }, { "epoch": 0.3742550655542312, "grad_norm": 2.838190793991089, "learning_rate": 7.2035488530115245e-06, "loss": 0.4965406060218811, "step": 2669 }, { "epoch": 0.3743952885087289, "grad_norm": 3.2694950103759766, "learning_rate": 7.201510428736821e-06, "loss": 0.494247704744339, "step": 2670 }, { "epoch": 0.37453551146322656, "grad_norm": 3.4074127674102783, "learning_rate": 7.199471550458441e-06, "loss": 0.5263098478317261, "step": 2671 }, { "epoch": 0.37467573441772417, "grad_norm": 4.279339790344238, "learning_rate": 7.19743221859685e-06, "loss": 0.5260679125785828, "step": 2672 }, { "epoch": 0.37481595737222184, "grad_norm": 2.7486824989318848, "learning_rate": 7.195392433572606e-06, "loss": 0.5517528653144836, "step": 2673 }, { "epoch": 0.37495618032671946, "grad_norm": 3.956756114959717, "learning_rate": 7.19335219580636e-06, "loss": 0.5140856504440308, "step": 2674 }, { "epoch": 0.37509640328121713, "grad_norm": 2.811375617980957, "learning_rate": 7.1913115057188605e-06, "loss": 0.6388821601867676, "step": 2675 }, { "epoch": 0.3752366262357148, "grad_norm": 3.195452928543091, "learning_rate": 7.189270363730945e-06, "loss": 0.5827488303184509, "step": 2676 }, { "epoch": 0.3753768491902124, "grad_norm": 3.547579288482666, "learning_rate": 7.187228770263544e-06, "loss": 0.5361647009849548, "step": 2677 }, { "epoch": 0.3755170721447101, "grad_norm": 2.8803014755249023, "learning_rate": 7.185186725737683e-06, "loss": 0.5496463775634766, "step": 2678 }, { "epoch": 0.37565729509920776, "grad_norm": 3.6880714893341064, "learning_rate": 7.183144230574481e-06, "loss": 0.5788984894752502, "step": 2679 }, { "epoch": 0.37579751805370537, "grad_norm": 2.9820854663848877, "learning_rate": 7.181101285195148e-06, "loss": 0.5553658604621887, "step": 2680 }, { "epoch": 0.37593774100820304, "grad_norm": 3.3152599334716797, "learning_rate": 7.1790578900209886e-06, "loss": 0.5669684410095215, "step": 2681 }, { "epoch": 0.3760779639627007, "grad_norm": 3.445117473602295, "learning_rate": 7.177014045473398e-06, "loss": 0.5244474411010742, "step": 2682 }, { "epoch": 0.3762181869171983, "grad_norm": 4.2244062423706055, "learning_rate": 7.174969751973867e-06, "loss": 0.4945679306983948, "step": 2683 }, { "epoch": 0.376358409871696, "grad_norm": 5.398369312286377, "learning_rate": 7.172925009943976e-06, "loss": 0.550175130367279, "step": 2684 }, { "epoch": 0.37649863282619367, "grad_norm": 4.371063709259033, "learning_rate": 7.1708798198054e-06, "loss": 0.43814146518707275, "step": 2685 }, { "epoch": 0.3766388557806913, "grad_norm": 2.81233549118042, "learning_rate": 7.168834181979909e-06, "loss": 0.5250528454780579, "step": 2686 }, { "epoch": 0.37677907873518895, "grad_norm": 3.4868781566619873, "learning_rate": 7.166788096889356e-06, "loss": 0.5524141788482666, "step": 2687 }, { "epoch": 0.3769193016896866, "grad_norm": 2.5034046173095703, "learning_rate": 7.164741564955695e-06, "loss": 0.5017008781433105, "step": 2688 }, { "epoch": 0.37705952464418424, "grad_norm": 3.5118656158447266, "learning_rate": 7.162694586600971e-06, "loss": 0.6288073658943176, "step": 2689 }, { "epoch": 0.3771997475986819, "grad_norm": 5.234574317932129, "learning_rate": 7.160647162247319e-06, "loss": 0.5297010540962219, "step": 2690 }, { "epoch": 0.3773399705531796, "grad_norm": 2.928804636001587, "learning_rate": 7.158599292316962e-06, "loss": 0.531234860420227, "step": 2691 }, { "epoch": 0.3774801935076772, "grad_norm": 7.088360786437988, "learning_rate": 7.1565509772322265e-06, "loss": 0.6123095154762268, "step": 2692 }, { "epoch": 0.37762041646217487, "grad_norm": 4.122281551361084, "learning_rate": 7.154502217415518e-06, "loss": 0.6270065903663635, "step": 2693 }, { "epoch": 0.3777606394166725, "grad_norm": 5.279295921325684, "learning_rate": 7.152453013289341e-06, "loss": 0.5692806243896484, "step": 2694 }, { "epoch": 0.37790086237117015, "grad_norm": 3.0304813385009766, "learning_rate": 7.1504033652762916e-06, "loss": 0.5994712114334106, "step": 2695 }, { "epoch": 0.3780410853256678, "grad_norm": 5.480512619018555, "learning_rate": 7.148353273799055e-06, "loss": 0.5836108922958374, "step": 2696 }, { "epoch": 0.37818130828016544, "grad_norm": 4.830137252807617, "learning_rate": 7.146302739280407e-06, "loss": 0.5638278722763062, "step": 2697 }, { "epoch": 0.3783215312346631, "grad_norm": 3.252549171447754, "learning_rate": 7.144251762143219e-06, "loss": 0.521188497543335, "step": 2698 }, { "epoch": 0.3784617541891608, "grad_norm": 3.2760531902313232, "learning_rate": 7.14220034281045e-06, "loss": 0.588296115398407, "step": 2699 }, { "epoch": 0.3786019771436584, "grad_norm": 6.323062896728516, "learning_rate": 7.140148481705151e-06, "loss": 0.5057153701782227, "step": 2700 }, { "epoch": 0.37874220009815607, "grad_norm": 5.3006110191345215, "learning_rate": 7.138096179250464e-06, "loss": 0.6350283026695251, "step": 2701 }, { "epoch": 0.37888242305265374, "grad_norm": 2.9369165897369385, "learning_rate": 7.136043435869626e-06, "loss": 0.5259522199630737, "step": 2702 }, { "epoch": 0.37902264600715135, "grad_norm": 3.3327465057373047, "learning_rate": 7.133990251985956e-06, "loss": 0.4748128652572632, "step": 2703 }, { "epoch": 0.379162868961649, "grad_norm": 2.9020910263061523, "learning_rate": 7.131936628022872e-06, "loss": 0.5349149703979492, "step": 2704 }, { "epoch": 0.3793030919161467, "grad_norm": 2.7619457244873047, "learning_rate": 7.1298825644038805e-06, "loss": 0.6155295968055725, "step": 2705 }, { "epoch": 0.3794433148706443, "grad_norm": 9.297718048095703, "learning_rate": 7.127828061552578e-06, "loss": 0.612877607345581, "step": 2706 }, { "epoch": 0.379583537825142, "grad_norm": 6.860739231109619, "learning_rate": 7.125773119892649e-06, "loss": 0.6243138313293457, "step": 2707 }, { "epoch": 0.37972376077963965, "grad_norm": 3.9078359603881836, "learning_rate": 7.123717739847875e-06, "loss": 0.6134937405586243, "step": 2708 }, { "epoch": 0.37986398373413727, "grad_norm": 3.9652206897735596, "learning_rate": 7.121661921842124e-06, "loss": 0.48574674129486084, "step": 2709 }, { "epoch": 0.38000420668863494, "grad_norm": 3.3184609413146973, "learning_rate": 7.11960566629935e-06, "loss": 0.5911341309547424, "step": 2710 }, { "epoch": 0.38014442964313255, "grad_norm": 2.7492544651031494, "learning_rate": 7.117548973643607e-06, "loss": 0.6092895269393921, "step": 2711 }, { "epoch": 0.3802846525976302, "grad_norm": 3.2832868099212646, "learning_rate": 7.115491844299031e-06, "loss": 0.5294088125228882, "step": 2712 }, { "epoch": 0.3804248755521279, "grad_norm": 2.6627633571624756, "learning_rate": 7.11343427868985e-06, "loss": 0.6035583019256592, "step": 2713 }, { "epoch": 0.3805650985066255, "grad_norm": 4.956230640411377, "learning_rate": 7.111376277240385e-06, "loss": 0.5704773664474487, "step": 2714 }, { "epoch": 0.3807053214611232, "grad_norm": 4.281803607940674, "learning_rate": 7.109317840375043e-06, "loss": 0.5855672359466553, "step": 2715 }, { "epoch": 0.38084554441562085, "grad_norm": 5.378177165985107, "learning_rate": 7.107258968518325e-06, "loss": 0.5425554513931274, "step": 2716 }, { "epoch": 0.38098576737011847, "grad_norm": 2.8179872035980225, "learning_rate": 7.105199662094816e-06, "loss": 0.5188352465629578, "step": 2717 }, { "epoch": 0.38112599032461614, "grad_norm": 4.053977012634277, "learning_rate": 7.103139921529197e-06, "loss": 0.47509074211120605, "step": 2718 }, { "epoch": 0.3812662132791138, "grad_norm": 2.6218323707580566, "learning_rate": 7.101079747246233e-06, "loss": 0.6517366170883179, "step": 2719 }, { "epoch": 0.3814064362336114, "grad_norm": 6.88167667388916, "learning_rate": 7.099019139670782e-06, "loss": 0.5375661849975586, "step": 2720 }, { "epoch": 0.3815466591881091, "grad_norm": 2.449647903442383, "learning_rate": 7.096958099227789e-06, "loss": 0.6245862245559692, "step": 2721 }, { "epoch": 0.38168688214260676, "grad_norm": 3.111607789993286, "learning_rate": 7.094896626342291e-06, "loss": 0.5861050486564636, "step": 2722 }, { "epoch": 0.3818271050971044, "grad_norm": 3.373983383178711, "learning_rate": 7.092834721439412e-06, "loss": 0.5792412161827087, "step": 2723 }, { "epoch": 0.38196732805160205, "grad_norm": 6.541496753692627, "learning_rate": 7.090772384944364e-06, "loss": 0.6290234327316284, "step": 2724 }, { "epoch": 0.3821075510060997, "grad_norm": 2.1125569343566895, "learning_rate": 7.0887096172824525e-06, "loss": 0.36100271344184875, "step": 2725 }, { "epoch": 0.38224777396059734, "grad_norm": 2.629290819168091, "learning_rate": 7.086646418879068e-06, "loss": 0.5403457880020142, "step": 2726 }, { "epoch": 0.382387996915095, "grad_norm": 4.091013431549072, "learning_rate": 7.084582790159691e-06, "loss": 0.5914885997772217, "step": 2727 }, { "epoch": 0.3825282198695927, "grad_norm": 3.48187255859375, "learning_rate": 7.08251873154989e-06, "loss": 0.5796616077423096, "step": 2728 }, { "epoch": 0.3826684428240903, "grad_norm": 2.5477802753448486, "learning_rate": 7.080454243475324e-06, "loss": 0.6122130751609802, "step": 2729 }, { "epoch": 0.38280866577858796, "grad_norm": 2.7628049850463867, "learning_rate": 7.0783893263617384e-06, "loss": 0.5643129348754883, "step": 2730 }, { "epoch": 0.3829488887330856, "grad_norm": 3.511197328567505, "learning_rate": 7.076323980634969e-06, "loss": 0.5726970434188843, "step": 2731 }, { "epoch": 0.38308911168758325, "grad_norm": 4.450284004211426, "learning_rate": 7.074258206720939e-06, "loss": 0.5429693460464478, "step": 2732 }, { "epoch": 0.3832293346420809, "grad_norm": 2.9762747287750244, "learning_rate": 7.072192005045657e-06, "loss": 0.486909419298172, "step": 2733 }, { "epoch": 0.38336955759657854, "grad_norm": 3.1097235679626465, "learning_rate": 7.070125376035227e-06, "loss": 0.6229084730148315, "step": 2734 }, { "epoch": 0.3835097805510762, "grad_norm": 5.808561325073242, "learning_rate": 7.068058320115835e-06, "loss": 0.4942983090877533, "step": 2735 }, { "epoch": 0.3836500035055739, "grad_norm": 3.2028470039367676, "learning_rate": 7.0659908377137586e-06, "loss": 0.629708468914032, "step": 2736 }, { "epoch": 0.3837902264600715, "grad_norm": 2.9366676807403564, "learning_rate": 7.063922929255359e-06, "loss": 0.5821851491928101, "step": 2737 }, { "epoch": 0.38393044941456916, "grad_norm": 5.337916851043701, "learning_rate": 7.061854595167089e-06, "loss": 0.6065834760665894, "step": 2738 }, { "epoch": 0.38407067236906683, "grad_norm": 4.054759502410889, "learning_rate": 7.05978583587549e-06, "loss": 0.5925698280334473, "step": 2739 }, { "epoch": 0.38421089532356445, "grad_norm": 3.999990701675415, "learning_rate": 7.057716651807187e-06, "loss": 0.5167020559310913, "step": 2740 }, { "epoch": 0.3843511182780621, "grad_norm": 3.5280447006225586, "learning_rate": 7.055647043388896e-06, "loss": 0.5885681509971619, "step": 2741 }, { "epoch": 0.3844913412325598, "grad_norm": 6.325968265533447, "learning_rate": 7.053577011047419e-06, "loss": 0.43151143193244934, "step": 2742 }, { "epoch": 0.3846315641870574, "grad_norm": 2.2643539905548096, "learning_rate": 7.051506555209645e-06, "loss": 0.43360552191734314, "step": 2743 }, { "epoch": 0.3847717871415551, "grad_norm": 2.3303236961364746, "learning_rate": 7.049435676302552e-06, "loss": 0.5008305311203003, "step": 2744 }, { "epoch": 0.38491201009605275, "grad_norm": 3.862123489379883, "learning_rate": 7.047364374753204e-06, "loss": 0.5766575336456299, "step": 2745 }, { "epoch": 0.38505223305055036, "grad_norm": 2.417891025543213, "learning_rate": 7.045292650988755e-06, "loss": 0.5265214443206787, "step": 2746 }, { "epoch": 0.38519245600504803, "grad_norm": 3.140953779220581, "learning_rate": 7.043220505436438e-06, "loss": 0.5514111518859863, "step": 2747 }, { "epoch": 0.3853326789595457, "grad_norm": 2.6220929622650146, "learning_rate": 7.041147938523583e-06, "loss": 0.589996337890625, "step": 2748 }, { "epoch": 0.3854729019140433, "grad_norm": 4.007809162139893, "learning_rate": 7.039074950677603e-06, "loss": 0.5503170490264893, "step": 2749 }, { "epoch": 0.385613124868541, "grad_norm": 4.491278648376465, "learning_rate": 7.037001542325994e-06, "loss": 0.5358104705810547, "step": 2750 }, { "epoch": 0.3857533478230386, "grad_norm": 4.321889400482178, "learning_rate": 7.034927713896342e-06, "loss": 0.5378881692886353, "step": 2751 }, { "epoch": 0.3858935707775363, "grad_norm": 12.508682250976562, "learning_rate": 7.032853465816324e-06, "loss": 0.6661581993103027, "step": 2752 }, { "epoch": 0.38603379373203395, "grad_norm": 4.358321666717529, "learning_rate": 7.030778798513696e-06, "loss": 0.5257261991500854, "step": 2753 }, { "epoch": 0.38617401668653156, "grad_norm": 3.608809471130371, "learning_rate": 7.028703712416302e-06, "loss": 0.4510846734046936, "step": 2754 }, { "epoch": 0.38631423964102923, "grad_norm": 1.9946565628051758, "learning_rate": 7.026628207952079e-06, "loss": 0.5372186303138733, "step": 2755 }, { "epoch": 0.3864544625955269, "grad_norm": 2.7326242923736572, "learning_rate": 7.024552285549041e-06, "loss": 0.48774048686027527, "step": 2756 }, { "epoch": 0.3865946855500245, "grad_norm": 4.722197532653809, "learning_rate": 7.022475945635293e-06, "loss": 0.5426286458969116, "step": 2757 }, { "epoch": 0.3867349085045222, "grad_norm": 3.5568649768829346, "learning_rate": 7.020399188639027e-06, "loss": 0.5085214376449585, "step": 2758 }, { "epoch": 0.38687513145901986, "grad_norm": 2.6439871788024902, "learning_rate": 7.018322014988519e-06, "loss": 0.5449065566062927, "step": 2759 }, { "epoch": 0.3870153544135175, "grad_norm": 3.9952399730682373, "learning_rate": 7.01624442511213e-06, "loss": 0.47727662324905396, "step": 2760 }, { "epoch": 0.38715557736801515, "grad_norm": 2.6451423168182373, "learning_rate": 7.01416641943831e-06, "loss": 0.514960765838623, "step": 2761 }, { "epoch": 0.3872958003225128, "grad_norm": 3.1821577548980713, "learning_rate": 7.012087998395593e-06, "loss": 0.5170938968658447, "step": 2762 }, { "epoch": 0.38743602327701043, "grad_norm": 5.792007923126221, "learning_rate": 7.010009162412599e-06, "loss": 0.627521276473999, "step": 2763 }, { "epoch": 0.3875762462315081, "grad_norm": 5.6320719718933105, "learning_rate": 7.007929911918031e-06, "loss": 0.6604599356651306, "step": 2764 }, { "epoch": 0.3877164691860058, "grad_norm": 3.187654972076416, "learning_rate": 7.005850247340682e-06, "loss": 0.5824849605560303, "step": 2765 }, { "epoch": 0.3878566921405034, "grad_norm": 4.980924606323242, "learning_rate": 7.0037701691094285e-06, "loss": 0.5139914751052856, "step": 2766 }, { "epoch": 0.38799691509500106, "grad_norm": 3.8302364349365234, "learning_rate": 7.001689677653231e-06, "loss": 0.5131248831748962, "step": 2767 }, { "epoch": 0.3881371380494987, "grad_norm": 4.310015678405762, "learning_rate": 6.9996087734011356e-06, "loss": 0.6330168843269348, "step": 2768 }, { "epoch": 0.38827736100399635, "grad_norm": 4.152894973754883, "learning_rate": 6.9975274567822756e-06, "loss": 0.47951948642730713, "step": 2769 }, { "epoch": 0.388417583958494, "grad_norm": 3.3712410926818848, "learning_rate": 6.995445728225867e-06, "loss": 0.5357280373573303, "step": 2770 }, { "epoch": 0.38855780691299163, "grad_norm": 2.462869644165039, "learning_rate": 6.99336358816121e-06, "loss": 0.47518593072891235, "step": 2771 }, { "epoch": 0.3886980298674893, "grad_norm": 3.370450735092163, "learning_rate": 6.991281037017695e-06, "loss": 0.4930460453033447, "step": 2772 }, { "epoch": 0.388838252821987, "grad_norm": 15.143145561218262, "learning_rate": 6.9891980752247905e-06, "loss": 0.4691206216812134, "step": 2773 }, { "epoch": 0.3889784757764846, "grad_norm": 3.2507882118225098, "learning_rate": 6.987114703212053e-06, "loss": 0.46143120527267456, "step": 2774 }, { "epoch": 0.38911869873098226, "grad_norm": 2.5540504455566406, "learning_rate": 6.985030921409126e-06, "loss": 0.53498774766922, "step": 2775 }, { "epoch": 0.38925892168547993, "grad_norm": 5.923192977905273, "learning_rate": 6.982946730245731e-06, "loss": 0.6962440013885498, "step": 2776 }, { "epoch": 0.38939914463997755, "grad_norm": 2.5520565509796143, "learning_rate": 6.980862130151679e-06, "loss": 0.5108926296234131, "step": 2777 }, { "epoch": 0.3895393675944752, "grad_norm": 4.0337443351745605, "learning_rate": 6.978777121556865e-06, "loss": 0.593769371509552, "step": 2778 }, { "epoch": 0.3896795905489729, "grad_norm": 5.342620372772217, "learning_rate": 6.976691704891265e-06, "loss": 0.616807758808136, "step": 2779 }, { "epoch": 0.3898198135034705, "grad_norm": 2.7827377319335938, "learning_rate": 6.9746058805849434e-06, "loss": 0.5240565538406372, "step": 2780 }, { "epoch": 0.3899600364579682, "grad_norm": 3.315609931945801, "learning_rate": 6.972519649068046e-06, "loss": 0.6248493194580078, "step": 2781 }, { "epoch": 0.39010025941246584, "grad_norm": 11.865484237670898, "learning_rate": 6.970433010770805e-06, "loss": 0.5759644508361816, "step": 2782 }, { "epoch": 0.39024048236696346, "grad_norm": 2.49499249458313, "learning_rate": 6.968345966123531e-06, "loss": 0.5394729971885681, "step": 2783 }, { "epoch": 0.39038070532146113, "grad_norm": 16.12752914428711, "learning_rate": 6.966258515556624e-06, "loss": 0.5075886249542236, "step": 2784 }, { "epoch": 0.3905209282759588, "grad_norm": 3.4559123516082764, "learning_rate": 6.964170659500567e-06, "loss": 0.5766557455062866, "step": 2785 }, { "epoch": 0.3906611512304564, "grad_norm": 2.722315788269043, "learning_rate": 6.962082398385924e-06, "loss": 0.6276406049728394, "step": 2786 }, { "epoch": 0.3908013741849541, "grad_norm": 3.151541233062744, "learning_rate": 6.959993732643344e-06, "loss": 0.5366272926330566, "step": 2787 }, { "epoch": 0.3909415971394517, "grad_norm": 2.7024691104888916, "learning_rate": 6.957904662703562e-06, "loss": 0.5346789360046387, "step": 2788 }, { "epoch": 0.3910818200939494, "grad_norm": 2.9601657390594482, "learning_rate": 6.955815188997389e-06, "loss": 0.5698539018630981, "step": 2789 }, { "epoch": 0.39122204304844704, "grad_norm": 4.251521110534668, "learning_rate": 6.953725311955727e-06, "loss": 0.6196953654289246, "step": 2790 }, { "epoch": 0.39136226600294466, "grad_norm": 3.1492903232574463, "learning_rate": 6.951635032009559e-06, "loss": 0.5554091930389404, "step": 2791 }, { "epoch": 0.39150248895744233, "grad_norm": 4.62584114074707, "learning_rate": 6.949544349589948e-06, "loss": 0.49678969383239746, "step": 2792 }, { "epoch": 0.39164271191194, "grad_norm": 2.4349775314331055, "learning_rate": 6.947453265128044e-06, "loss": 0.5435152649879456, "step": 2793 }, { "epoch": 0.3917829348664376, "grad_norm": 4.9154229164123535, "learning_rate": 6.945361779055078e-06, "loss": 0.5938752889633179, "step": 2794 }, { "epoch": 0.3919231578209353, "grad_norm": 2.69909405708313, "learning_rate": 6.943269891802363e-06, "loss": 0.5651270151138306, "step": 2795 }, { "epoch": 0.39206338077543296, "grad_norm": 3.9182984828948975, "learning_rate": 6.9411776038012964e-06, "loss": 0.5829855799674988, "step": 2796 }, { "epoch": 0.39220360372993057, "grad_norm": 4.3333353996276855, "learning_rate": 6.939084915483358e-06, "loss": 0.6093493103981018, "step": 2797 }, { "epoch": 0.39234382668442824, "grad_norm": 4.733331680297852, "learning_rate": 6.93699182728011e-06, "loss": 0.5450236797332764, "step": 2798 }, { "epoch": 0.3924840496389259, "grad_norm": 2.4359524250030518, "learning_rate": 6.934898339623197e-06, "loss": 0.6315159797668457, "step": 2799 }, { "epoch": 0.39262427259342353, "grad_norm": 2.468517541885376, "learning_rate": 6.932804452944344e-06, "loss": 0.5780280828475952, "step": 2800 }, { "epoch": 0.3927644955479212, "grad_norm": 4.009905815124512, "learning_rate": 6.930710167675362e-06, "loss": 0.5582623481750488, "step": 2801 }, { "epoch": 0.39290471850241887, "grad_norm": 3.5063364505767822, "learning_rate": 6.92861548424814e-06, "loss": 0.5284621119499207, "step": 2802 }, { "epoch": 0.3930449414569165, "grad_norm": 5.9936909675598145, "learning_rate": 6.926520403094654e-06, "loss": 0.5738998651504517, "step": 2803 }, { "epoch": 0.39318516441141416, "grad_norm": 4.885098457336426, "learning_rate": 6.92442492464696e-06, "loss": 0.4540421962738037, "step": 2804 }, { "epoch": 0.3933253873659118, "grad_norm": 2.8202109336853027, "learning_rate": 6.9223290493371915e-06, "loss": 0.5673445463180542, "step": 2805 }, { "epoch": 0.39346561032040944, "grad_norm": 3.1715893745422363, "learning_rate": 6.920232777597571e-06, "loss": 0.527015745639801, "step": 2806 }, { "epoch": 0.3936058332749071, "grad_norm": 5.18222188949585, "learning_rate": 6.918136109860399e-06, "loss": 0.6486899852752686, "step": 2807 }, { "epoch": 0.39374605622940473, "grad_norm": 3.5058372020721436, "learning_rate": 6.9160390465580566e-06, "loss": 0.4401315450668335, "step": 2808 }, { "epoch": 0.3938862791839024, "grad_norm": 3.531642436981201, "learning_rate": 6.913941588123009e-06, "loss": 0.5978766083717346, "step": 2809 }, { "epoch": 0.39402650213840007, "grad_norm": 5.013066291809082, "learning_rate": 6.911843734987802e-06, "loss": 0.6267775893211365, "step": 2810 }, { "epoch": 0.3941667250928977, "grad_norm": 3.7456648349761963, "learning_rate": 6.909745487585063e-06, "loss": 0.6053950786590576, "step": 2811 }, { "epoch": 0.39430694804739536, "grad_norm": 2.0706543922424316, "learning_rate": 6.9076468463475e-06, "loss": 0.5429559946060181, "step": 2812 }, { "epoch": 0.394447171001893, "grad_norm": 2.543008804321289, "learning_rate": 6.905547811707902e-06, "loss": 0.5518031120300293, "step": 2813 }, { "epoch": 0.39458739395639064, "grad_norm": 2.5277247428894043, "learning_rate": 6.903448384099141e-06, "loss": 0.6229455471038818, "step": 2814 }, { "epoch": 0.3947276169108883, "grad_norm": 2.739635467529297, "learning_rate": 6.901348563954168e-06, "loss": 0.5820136666297913, "step": 2815 }, { "epoch": 0.394867839865386, "grad_norm": 4.5380449295043945, "learning_rate": 6.899248351706015e-06, "loss": 0.5053831934928894, "step": 2816 }, { "epoch": 0.3950080628198836, "grad_norm": 2.731640100479126, "learning_rate": 6.897147747787798e-06, "loss": 0.43891382217407227, "step": 2817 }, { "epoch": 0.39514828577438127, "grad_norm": 3.512575387954712, "learning_rate": 6.8950467526327084e-06, "loss": 0.6058375835418701, "step": 2818 }, { "epoch": 0.39528850872887894, "grad_norm": 3.69270658493042, "learning_rate": 6.892945366674022e-06, "loss": 0.5826478600502014, "step": 2819 }, { "epoch": 0.39542873168337656, "grad_norm": 4.251041412353516, "learning_rate": 6.8908435903450966e-06, "loss": 0.5449074506759644, "step": 2820 }, { "epoch": 0.3955689546378742, "grad_norm": 8.549251556396484, "learning_rate": 6.888741424079366e-06, "loss": 0.4025343358516693, "step": 2821 }, { "epoch": 0.3957091775923719, "grad_norm": 3.730011463165283, "learning_rate": 6.886638868310347e-06, "loss": 0.5159472823143005, "step": 2822 }, { "epoch": 0.3958494005468695, "grad_norm": 2.686997890472412, "learning_rate": 6.884535923471638e-06, "loss": 0.6145998239517212, "step": 2823 }, { "epoch": 0.3959896235013672, "grad_norm": 6.5968828201293945, "learning_rate": 6.8824325899969145e-06, "loss": 0.5848932266235352, "step": 2824 }, { "epoch": 0.3961298464558648, "grad_norm": 3.0943782329559326, "learning_rate": 6.880328868319935e-06, "loss": 0.5484011173248291, "step": 2825 }, { "epoch": 0.39627006941036247, "grad_norm": 4.547174453735352, "learning_rate": 6.878224758874535e-06, "loss": 0.40560948848724365, "step": 2826 }, { "epoch": 0.39641029236486014, "grad_norm": 2.3638253211975098, "learning_rate": 6.876120262094634e-06, "loss": 0.5749796628952026, "step": 2827 }, { "epoch": 0.39655051531935775, "grad_norm": 3.85772442817688, "learning_rate": 6.874015378414228e-06, "loss": 0.5558016300201416, "step": 2828 }, { "epoch": 0.3966907382738554, "grad_norm": 3.3119561672210693, "learning_rate": 6.871910108267395e-06, "loss": 0.5595346093177795, "step": 2829 }, { "epoch": 0.3968309612283531, "grad_norm": 3.6301889419555664, "learning_rate": 6.86980445208829e-06, "loss": 0.5948004722595215, "step": 2830 }, { "epoch": 0.3969711841828507, "grad_norm": 4.258559703826904, "learning_rate": 6.86769841031115e-06, "loss": 0.5099815130233765, "step": 2831 }, { "epoch": 0.3971114071373484, "grad_norm": 3.167351007461548, "learning_rate": 6.86559198337029e-06, "loss": 0.517810583114624, "step": 2832 }, { "epoch": 0.39725163009184605, "grad_norm": 2.7882893085479736, "learning_rate": 6.8634851717001076e-06, "loss": 0.5345836281776428, "step": 2833 }, { "epoch": 0.39739185304634367, "grad_norm": 4.40838623046875, "learning_rate": 6.861377975735073e-06, "loss": 0.6260024309158325, "step": 2834 }, { "epoch": 0.39753207600084134, "grad_norm": 2.7116870880126953, "learning_rate": 6.859270395909745e-06, "loss": 0.521468997001648, "step": 2835 }, { "epoch": 0.397672298955339, "grad_norm": 2.853919506072998, "learning_rate": 6.857162432658754e-06, "loss": 0.4707780182361603, "step": 2836 }, { "epoch": 0.3978125219098366, "grad_norm": 2.4396936893463135, "learning_rate": 6.855054086416812e-06, "loss": 0.6701788902282715, "step": 2837 }, { "epoch": 0.3979527448643343, "grad_norm": 3.670741081237793, "learning_rate": 6.85294535761871e-06, "loss": 0.6114829182624817, "step": 2838 }, { "epoch": 0.39809296781883197, "grad_norm": 4.242297649383545, "learning_rate": 6.850836246699317e-06, "loss": 0.4974394142627716, "step": 2839 }, { "epoch": 0.3982331907733296, "grad_norm": 2.9440557956695557, "learning_rate": 6.848726754093586e-06, "loss": 0.5069859027862549, "step": 2840 }, { "epoch": 0.39837341372782725, "grad_norm": 4.692869186401367, "learning_rate": 6.846616880236538e-06, "loss": 0.55597984790802, "step": 2841 }, { "epoch": 0.3985136366823249, "grad_norm": 2.821444034576416, "learning_rate": 6.8445066255632854e-06, "loss": 0.5421751737594604, "step": 2842 }, { "epoch": 0.39865385963682254, "grad_norm": 3.2517330646514893, "learning_rate": 6.842395990509008e-06, "loss": 0.5581924915313721, "step": 2843 }, { "epoch": 0.3987940825913202, "grad_norm": 2.7076497077941895, "learning_rate": 6.840284975508972e-06, "loss": 0.5580491423606873, "step": 2844 }, { "epoch": 0.3989343055458178, "grad_norm": 8.756707191467285, "learning_rate": 6.838173580998515e-06, "loss": 0.4757256805896759, "step": 2845 }, { "epoch": 0.3990745285003155, "grad_norm": 2.9215807914733887, "learning_rate": 6.836061807413061e-06, "loss": 0.5992851853370667, "step": 2846 }, { "epoch": 0.39921475145481317, "grad_norm": 2.8322389125823975, "learning_rate": 6.833949655188106e-06, "loss": 0.6343979239463806, "step": 2847 }, { "epoch": 0.3993549744093108, "grad_norm": 4.059620380401611, "learning_rate": 6.831837124759224e-06, "loss": 0.5500391125679016, "step": 2848 }, { "epoch": 0.39949519736380845, "grad_norm": 3.678837537765503, "learning_rate": 6.829724216562072e-06, "loss": 0.4746473729610443, "step": 2849 }, { "epoch": 0.3996354203183061, "grad_norm": 4.3251729011535645, "learning_rate": 6.82761093103238e-06, "loss": 0.5671735405921936, "step": 2850 }, { "epoch": 0.39977564327280374, "grad_norm": 3.490314483642578, "learning_rate": 6.825497268605957e-06, "loss": 0.6210050582885742, "step": 2851 }, { "epoch": 0.3999158662273014, "grad_norm": 3.493370532989502, "learning_rate": 6.823383229718693e-06, "loss": 0.6022001504898071, "step": 2852 }, { "epoch": 0.4000560891817991, "grad_norm": 3.292618751525879, "learning_rate": 6.82126881480655e-06, "loss": 0.6213454008102417, "step": 2853 }, { "epoch": 0.4001963121362967, "grad_norm": 4.147826194763184, "learning_rate": 6.819154024305572e-06, "loss": 0.606031596660614, "step": 2854 }, { "epoch": 0.40033653509079437, "grad_norm": 4.174203872680664, "learning_rate": 6.8170388586518785e-06, "loss": 0.6824429035186768, "step": 2855 }, { "epoch": 0.40047675804529204, "grad_norm": 3.3516011238098145, "learning_rate": 6.814923318281669e-06, "loss": 0.5925411581993103, "step": 2856 }, { "epoch": 0.40061698099978965, "grad_norm": 3.4049696922302246, "learning_rate": 6.812807403631214e-06, "loss": 0.6061564683914185, "step": 2857 }, { "epoch": 0.4007572039542873, "grad_norm": 4.854274272918701, "learning_rate": 6.810691115136869e-06, "loss": 0.5214067101478577, "step": 2858 }, { "epoch": 0.400897426908785, "grad_norm": 5.070200443267822, "learning_rate": 6.808574453235061e-06, "loss": 0.5642020106315613, "step": 2859 }, { "epoch": 0.4010376498632826, "grad_norm": 3.3792786598205566, "learning_rate": 6.806457418362296e-06, "loss": 0.5488349199295044, "step": 2860 }, { "epoch": 0.4011778728177803, "grad_norm": 3.9550836086273193, "learning_rate": 6.804340010955156e-06, "loss": 0.5634347200393677, "step": 2861 }, { "epoch": 0.40131809577227795, "grad_norm": 4.929121017456055, "learning_rate": 6.802222231450304e-06, "loss": 0.5964206457138062, "step": 2862 }, { "epoch": 0.40145831872677556, "grad_norm": 5.438243389129639, "learning_rate": 6.800104080284472e-06, "loss": 0.5903942584991455, "step": 2863 }, { "epoch": 0.40159854168127324, "grad_norm": 2.814389705657959, "learning_rate": 6.797985557894475e-06, "loss": 0.529875636100769, "step": 2864 }, { "epoch": 0.40173876463577085, "grad_norm": 4.94564962387085, "learning_rate": 6.7958666647172055e-06, "loss": 0.6204919815063477, "step": 2865 }, { "epoch": 0.4018789875902685, "grad_norm": 5.754042625427246, "learning_rate": 6.7937474011896254e-06, "loss": 0.4994085729122162, "step": 2866 }, { "epoch": 0.4020192105447662, "grad_norm": 12.399232864379883, "learning_rate": 6.791627767748777e-06, "loss": 0.5403823852539062, "step": 2867 }, { "epoch": 0.4021594334992638, "grad_norm": 4.538434982299805, "learning_rate": 6.789507764831783e-06, "loss": 0.5353509783744812, "step": 2868 }, { "epoch": 0.4022996564537615, "grad_norm": 3.4420244693756104, "learning_rate": 6.787387392875834e-06, "loss": 0.48069676756858826, "step": 2869 }, { "epoch": 0.40243987940825915, "grad_norm": 2.962651491165161, "learning_rate": 6.785266652318203e-06, "loss": 0.593031108379364, "step": 2870 }, { "epoch": 0.40258010236275676, "grad_norm": 11.379496574401855, "learning_rate": 6.783145543596237e-06, "loss": 0.5079144835472107, "step": 2871 }, { "epoch": 0.40272032531725444, "grad_norm": 4.950178146362305, "learning_rate": 6.781024067147359e-06, "loss": 0.5729032754898071, "step": 2872 }, { "epoch": 0.4028605482717521, "grad_norm": 4.287334442138672, "learning_rate": 6.7789022234090675e-06, "loss": 0.6157537698745728, "step": 2873 }, { "epoch": 0.4030007712262497, "grad_norm": 3.4915554523468018, "learning_rate": 6.776780012818935e-06, "loss": 0.5040416717529297, "step": 2874 }, { "epoch": 0.4031409941807474, "grad_norm": 3.175227403640747, "learning_rate": 6.7746574358146166e-06, "loss": 0.589905321598053, "step": 2875 }, { "epoch": 0.40328121713524506, "grad_norm": 2.5800273418426514, "learning_rate": 6.772534492833833e-06, "loss": 0.5222885608673096, "step": 2876 }, { "epoch": 0.4034214400897427, "grad_norm": 2.460817813873291, "learning_rate": 6.770411184314389e-06, "loss": 0.5829553008079529, "step": 2877 }, { "epoch": 0.40356166304424035, "grad_norm": 2.6068739891052246, "learning_rate": 6.7682875106941595e-06, "loss": 0.5773661136627197, "step": 2878 }, { "epoch": 0.403701885998738, "grad_norm": 4.564123630523682, "learning_rate": 6.766163472411096e-06, "loss": 0.6675111055374146, "step": 2879 }, { "epoch": 0.40384210895323563, "grad_norm": 5.739872932434082, "learning_rate": 6.764039069903225e-06, "loss": 0.6161857843399048, "step": 2880 }, { "epoch": 0.4039823319077333, "grad_norm": 2.821869373321533, "learning_rate": 6.761914303608652e-06, "loss": 0.5303544402122498, "step": 2881 }, { "epoch": 0.4041225548622309, "grad_norm": 3.1295948028564453, "learning_rate": 6.759789173965552e-06, "loss": 0.60529625415802, "step": 2882 }, { "epoch": 0.4042627778167286, "grad_norm": 11.225285530090332, "learning_rate": 6.757663681412175e-06, "loss": 0.500097393989563, "step": 2883 }, { "epoch": 0.40440300077122626, "grad_norm": 2.525709867477417, "learning_rate": 6.755537826386852e-06, "loss": 0.5777824521064758, "step": 2884 }, { "epoch": 0.4045432237257239, "grad_norm": 2.4093258380889893, "learning_rate": 6.7534116093279835e-06, "loss": 0.5655114650726318, "step": 2885 }, { "epoch": 0.40468344668022155, "grad_norm": 4.023854732513428, "learning_rate": 6.7512850306740444e-06, "loss": 0.586644172668457, "step": 2886 }, { "epoch": 0.4048236696347192, "grad_norm": 3.7626614570617676, "learning_rate": 6.749158090863586e-06, "loss": 0.5683059692382812, "step": 2887 }, { "epoch": 0.40496389258921683, "grad_norm": 5.021844863891602, "learning_rate": 6.747030790335236e-06, "loss": 0.6055147647857666, "step": 2888 }, { "epoch": 0.4051041155437145, "grad_norm": 4.691761493682861, "learning_rate": 6.744903129527692e-06, "loss": 0.5758024454116821, "step": 2889 }, { "epoch": 0.4052443384982122, "grad_norm": 2.8423237800598145, "learning_rate": 6.742775108879727e-06, "loss": 0.4144725203514099, "step": 2890 }, { "epoch": 0.4053845614527098, "grad_norm": 3.1646251678466797, "learning_rate": 6.740646728830193e-06, "loss": 0.555609941482544, "step": 2891 }, { "epoch": 0.40552478440720746, "grad_norm": 3.582998037338257, "learning_rate": 6.738517989818008e-06, "loss": 0.6841434836387634, "step": 2892 }, { "epoch": 0.40566500736170513, "grad_norm": 7.184382438659668, "learning_rate": 6.736388892282173e-06, "loss": 0.618426501750946, "step": 2893 }, { "epoch": 0.40580523031620275, "grad_norm": 3.605189800262451, "learning_rate": 6.734259436661758e-06, "loss": 0.6179988980293274, "step": 2894 }, { "epoch": 0.4059454532707004, "grad_norm": 2.1169331073760986, "learning_rate": 6.732129623395903e-06, "loss": 0.48497915267944336, "step": 2895 }, { "epoch": 0.4060856762251981, "grad_norm": 3.6169276237487793, "learning_rate": 6.729999452923829e-06, "loss": 0.5590653419494629, "step": 2896 }, { "epoch": 0.4062258991796957, "grad_norm": 2.823190450668335, "learning_rate": 6.727868925684828e-06, "loss": 0.5835716128349304, "step": 2897 }, { "epoch": 0.4063661221341934, "grad_norm": 3.9794762134552, "learning_rate": 6.725738042118265e-06, "loss": 0.5964475274085999, "step": 2898 }, { "epoch": 0.40650634508869105, "grad_norm": 6.1481218338012695, "learning_rate": 6.7236068026635785e-06, "loss": 0.573830246925354, "step": 2899 }, { "epoch": 0.40664656804318866, "grad_norm": 3.0638198852539062, "learning_rate": 6.721475207760279e-06, "loss": 0.5914226770401001, "step": 2900 }, { "epoch": 0.40678679099768633, "grad_norm": 2.160987138748169, "learning_rate": 6.719343257847955e-06, "loss": 0.5585342645645142, "step": 2901 }, { "epoch": 0.40692701395218395, "grad_norm": 2.8184356689453125, "learning_rate": 6.717210953366263e-06, "loss": 0.4903959035873413, "step": 2902 }, { "epoch": 0.4070672369066816, "grad_norm": 3.441175937652588, "learning_rate": 6.715078294754936e-06, "loss": 0.5698332786560059, "step": 2903 }, { "epoch": 0.4072074598611793, "grad_norm": 2.9882090091705322, "learning_rate": 6.712945282453778e-06, "loss": 0.58268141746521, "step": 2904 }, { "epoch": 0.4073476828156769, "grad_norm": 3.0625710487365723, "learning_rate": 6.710811916902667e-06, "loss": 0.43635475635528564, "step": 2905 }, { "epoch": 0.4074879057701746, "grad_norm": 2.5375897884368896, "learning_rate": 6.708678198541552e-06, "loss": 0.567082405090332, "step": 2906 }, { "epoch": 0.40762812872467225, "grad_norm": 6.114831924438477, "learning_rate": 6.7065441278104595e-06, "loss": 0.6278536915779114, "step": 2907 }, { "epoch": 0.40776835167916986, "grad_norm": 2.204444408416748, "learning_rate": 6.704409705149482e-06, "loss": 0.4012308120727539, "step": 2908 }, { "epoch": 0.40790857463366753, "grad_norm": 3.0078959465026855, "learning_rate": 6.702274930998791e-06, "loss": 0.5626140236854553, "step": 2909 }, { "epoch": 0.4080487975881652, "grad_norm": 4.839203357696533, "learning_rate": 6.7001398057986274e-06, "loss": 0.5048048496246338, "step": 2910 }, { "epoch": 0.4081890205426628, "grad_norm": 2.444279432296753, "learning_rate": 6.698004329989303e-06, "loss": 0.5960503220558167, "step": 2911 }, { "epoch": 0.4083292434971605, "grad_norm": 3.7295875549316406, "learning_rate": 6.6958685040112035e-06, "loss": 0.5948667526245117, "step": 2912 }, { "epoch": 0.40846946645165816, "grad_norm": 7.4636664390563965, "learning_rate": 6.693732328304789e-06, "loss": 0.6057467460632324, "step": 2913 }, { "epoch": 0.4086096894061558, "grad_norm": 2.231550455093384, "learning_rate": 6.691595803310589e-06, "loss": 0.5782713890075684, "step": 2914 }, { "epoch": 0.40874991236065344, "grad_norm": 3.9896962642669678, "learning_rate": 6.689458929469203e-06, "loss": 0.5129111409187317, "step": 2915 }, { "epoch": 0.4088901353151511, "grad_norm": 3.213771104812622, "learning_rate": 6.687321707221308e-06, "loss": 0.46917593479156494, "step": 2916 }, { "epoch": 0.40903035826964873, "grad_norm": 3.210516929626465, "learning_rate": 6.68518413700765e-06, "loss": 0.6359631419181824, "step": 2917 }, { "epoch": 0.4091705812241464, "grad_norm": 3.040449619293213, "learning_rate": 6.683046219269043e-06, "loss": 0.5855483412742615, "step": 2918 }, { "epoch": 0.409310804178644, "grad_norm": 3.24430513381958, "learning_rate": 6.680907954446381e-06, "loss": 0.49730706214904785, "step": 2919 }, { "epoch": 0.4094510271331417, "grad_norm": 3.2110283374786377, "learning_rate": 6.678769342980623e-06, "loss": 0.48663055896759033, "step": 2920 }, { "epoch": 0.40959125008763936, "grad_norm": 2.4440348148345947, "learning_rate": 6.676630385312801e-06, "loss": 0.628200113773346, "step": 2921 }, { "epoch": 0.409731473042137, "grad_norm": 2.4438908100128174, "learning_rate": 6.674491081884019e-06, "loss": 0.6031495332717896, "step": 2922 }, { "epoch": 0.40987169599663464, "grad_norm": 4.49253511428833, "learning_rate": 6.6723514331354534e-06, "loss": 0.5462010502815247, "step": 2923 }, { "epoch": 0.4100119189511323, "grad_norm": 5.685369491577148, "learning_rate": 6.670211439508348e-06, "loss": 0.5575579404830933, "step": 2924 }, { "epoch": 0.41015214190562993, "grad_norm": 3.1367831230163574, "learning_rate": 6.668071101444022e-06, "loss": 0.5762616991996765, "step": 2925 }, { "epoch": 0.4102923648601276, "grad_norm": 6.829540729522705, "learning_rate": 6.665930419383865e-06, "loss": 0.6411690711975098, "step": 2926 }, { "epoch": 0.41043258781462527, "grad_norm": 4.755783557891846, "learning_rate": 6.663789393769333e-06, "loss": 0.5475298166275024, "step": 2927 }, { "epoch": 0.4105728107691229, "grad_norm": 4.57452917098999, "learning_rate": 6.661648025041959e-06, "loss": 0.5368885397911072, "step": 2928 }, { "epoch": 0.41071303372362056, "grad_norm": 3.334627151489258, "learning_rate": 6.6595063136433426e-06, "loss": 0.5969216823577881, "step": 2929 }, { "epoch": 0.41085325667811823, "grad_norm": 2.9649384021759033, "learning_rate": 6.657364260015158e-06, "loss": 0.5574969053268433, "step": 2930 }, { "epoch": 0.41099347963261584, "grad_norm": 2.5859591960906982, "learning_rate": 6.655221864599144e-06, "loss": 0.5526454448699951, "step": 2931 }, { "epoch": 0.4111337025871135, "grad_norm": 2.460343837738037, "learning_rate": 6.653079127837117e-06, "loss": 0.5980675220489502, "step": 2932 }, { "epoch": 0.4112739255416112, "grad_norm": 2.6538853645324707, "learning_rate": 6.650936050170956e-06, "loss": 0.5297117233276367, "step": 2933 }, { "epoch": 0.4114141484961088, "grad_norm": 2.665776491165161, "learning_rate": 6.648792632042618e-06, "loss": 0.5409371852874756, "step": 2934 }, { "epoch": 0.41155437145060647, "grad_norm": 5.76003885269165, "learning_rate": 6.6466488738941235e-06, "loss": 0.603469967842102, "step": 2935 }, { "epoch": 0.41169459440510414, "grad_norm": 2.7073493003845215, "learning_rate": 6.644504776167571e-06, "loss": 0.5765537023544312, "step": 2936 }, { "epoch": 0.41183481735960176, "grad_norm": 2.9418156147003174, "learning_rate": 6.642360339305119e-06, "loss": 0.5146385431289673, "step": 2937 }, { "epoch": 0.4119750403140994, "grad_norm": 3.460721969604492, "learning_rate": 6.640215563749004e-06, "loss": 0.49036723375320435, "step": 2938 }, { "epoch": 0.41211526326859704, "grad_norm": 3.7410717010498047, "learning_rate": 6.63807044994153e-06, "loss": 0.5666778087615967, "step": 2939 }, { "epoch": 0.4122554862230947, "grad_norm": 2.8876149654388428, "learning_rate": 6.63592499832507e-06, "loss": 0.5514495968818665, "step": 2940 }, { "epoch": 0.4123957091775924, "grad_norm": 4.262160778045654, "learning_rate": 6.633779209342066e-06, "loss": 0.5320500731468201, "step": 2941 }, { "epoch": 0.41253593213209, "grad_norm": 2.1684091091156006, "learning_rate": 6.631633083435032e-06, "loss": 0.5297889709472656, "step": 2942 }, { "epoch": 0.41267615508658767, "grad_norm": 2.8167529106140137, "learning_rate": 6.629486621046548e-06, "loss": 0.5032055377960205, "step": 2943 }, { "epoch": 0.41281637804108534, "grad_norm": 4.599859237670898, "learning_rate": 6.6273398226192665e-06, "loss": 0.4692973792552948, "step": 2944 }, { "epoch": 0.41295660099558296, "grad_norm": 3.900319814682007, "learning_rate": 6.625192688595909e-06, "loss": 0.5212363600730896, "step": 2945 }, { "epoch": 0.4130968239500806, "grad_norm": 2.6738853454589844, "learning_rate": 6.623045219419267e-06, "loss": 0.5058574676513672, "step": 2946 }, { "epoch": 0.4132370469045783, "grad_norm": 3.867443323135376, "learning_rate": 6.620897415532195e-06, "loss": 0.5547022819519043, "step": 2947 }, { "epoch": 0.4133772698590759, "grad_norm": 3.3765244483947754, "learning_rate": 6.618749277377624e-06, "loss": 0.558746874332428, "step": 2948 }, { "epoch": 0.4135174928135736, "grad_norm": 3.0083231925964355, "learning_rate": 6.616600805398552e-06, "loss": 0.486386775970459, "step": 2949 }, { "epoch": 0.41365771576807125, "grad_norm": 3.421485185623169, "learning_rate": 6.614452000038043e-06, "loss": 0.4950096905231476, "step": 2950 }, { "epoch": 0.41379793872256887, "grad_norm": 2.9345266819000244, "learning_rate": 6.612302861739231e-06, "loss": 0.5093281269073486, "step": 2951 }, { "epoch": 0.41393816167706654, "grad_norm": 2.5606472492218018, "learning_rate": 6.610153390945323e-06, "loss": 0.5401517748832703, "step": 2952 }, { "epoch": 0.4140783846315642, "grad_norm": 3.541163921356201, "learning_rate": 6.608003588099587e-06, "loss": 0.602784276008606, "step": 2953 }, { "epoch": 0.4142186075860618, "grad_norm": 3.3752644062042236, "learning_rate": 6.605853453645365e-06, "loss": 0.4788694977760315, "step": 2954 }, { "epoch": 0.4143588305405595, "grad_norm": 4.233368873596191, "learning_rate": 6.603702988026066e-06, "loss": 0.5165000557899475, "step": 2955 }, { "epoch": 0.41449905349505717, "grad_norm": 2.620112895965576, "learning_rate": 6.601552191685165e-06, "loss": 0.5487060546875, "step": 2956 }, { "epoch": 0.4146392764495548, "grad_norm": 3.200606346130371, "learning_rate": 6.599401065066211e-06, "loss": 0.5285886526107788, "step": 2957 }, { "epoch": 0.41477949940405245, "grad_norm": 2.525393486022949, "learning_rate": 6.597249608612814e-06, "loss": 0.527208149433136, "step": 2958 }, { "epoch": 0.41491972235855007, "grad_norm": 2.6354691982269287, "learning_rate": 6.595097822768657e-06, "loss": 0.5417706966400146, "step": 2959 }, { "epoch": 0.41505994531304774, "grad_norm": 4.09453010559082, "learning_rate": 6.592945707977487e-06, "loss": 0.49350568652153015, "step": 2960 }, { "epoch": 0.4152001682675454, "grad_norm": 2.8881311416625977, "learning_rate": 6.590793264683124e-06, "loss": 0.6086088418960571, "step": 2961 }, { "epoch": 0.415340391222043, "grad_norm": 3.1892356872558594, "learning_rate": 6.588640493329454e-06, "loss": 0.4822695255279541, "step": 2962 }, { "epoch": 0.4154806141765407, "grad_norm": 4.378210544586182, "learning_rate": 6.586487394360424e-06, "loss": 0.5381317138671875, "step": 2963 }, { "epoch": 0.41562083713103837, "grad_norm": 5.1354169845581055, "learning_rate": 6.584333968220058e-06, "loss": 0.5328291058540344, "step": 2964 }, { "epoch": 0.415761060085536, "grad_norm": 2.4189906120300293, "learning_rate": 6.582180215352445e-06, "loss": 0.6378926038742065, "step": 2965 }, { "epoch": 0.41590128304003365, "grad_norm": 3.193371057510376, "learning_rate": 6.580026136201736e-06, "loss": 0.4518583416938782, "step": 2966 }, { "epoch": 0.4160415059945313, "grad_norm": 4.9935688972473145, "learning_rate": 6.577871731212154e-06, "loss": 0.6361703872680664, "step": 2967 }, { "epoch": 0.41618172894902894, "grad_norm": 3.6353206634521484, "learning_rate": 6.575717000827993e-06, "loss": 0.557397723197937, "step": 2968 }, { "epoch": 0.4163219519035266, "grad_norm": 2.955531358718872, "learning_rate": 6.573561945493603e-06, "loss": 0.4873065948486328, "step": 2969 }, { "epoch": 0.4164621748580243, "grad_norm": 2.92248272895813, "learning_rate": 6.571406565653411e-06, "loss": 0.5659637451171875, "step": 2970 }, { "epoch": 0.4166023978125219, "grad_norm": 3.293086528778076, "learning_rate": 6.569250861751908e-06, "loss": 0.5798248052597046, "step": 2971 }, { "epoch": 0.41674262076701957, "grad_norm": 2.7903308868408203, "learning_rate": 6.56709483423365e-06, "loss": 0.448436975479126, "step": 2972 }, { "epoch": 0.41688284372151724, "grad_norm": 2.554190158843994, "learning_rate": 6.56493848354326e-06, "loss": 0.43174779415130615, "step": 2973 }, { "epoch": 0.41702306667601485, "grad_norm": 3.0043108463287354, "learning_rate": 6.562781810125431e-06, "loss": 0.5522119998931885, "step": 2974 }, { "epoch": 0.4171632896305125, "grad_norm": 2.914550304412842, "learning_rate": 6.560624814424921e-06, "loss": 0.6408329010009766, "step": 2975 }, { "epoch": 0.41730351258501014, "grad_norm": 2.9318268299102783, "learning_rate": 6.558467496886549e-06, "loss": 0.6211261749267578, "step": 2976 }, { "epoch": 0.4174437355395078, "grad_norm": 2.2406888008117676, "learning_rate": 6.55630985795521e-06, "loss": 0.540339469909668, "step": 2977 }, { "epoch": 0.4175839584940055, "grad_norm": 2.687718152999878, "learning_rate": 6.554151898075858e-06, "loss": 0.5404150485992432, "step": 2978 }, { "epoch": 0.4177241814485031, "grad_norm": 2.5551271438598633, "learning_rate": 6.551993617693514e-06, "loss": 0.5079708099365234, "step": 2979 }, { "epoch": 0.41786440440300077, "grad_norm": 2.760573387145996, "learning_rate": 6.5498350172532694e-06, "loss": 0.583961009979248, "step": 2980 }, { "epoch": 0.41800462735749844, "grad_norm": 3.2119362354278564, "learning_rate": 6.547676097200279e-06, "loss": 0.5630414485931396, "step": 2981 }, { "epoch": 0.41814485031199605, "grad_norm": 5.5828166007995605, "learning_rate": 6.545516857979761e-06, "loss": 0.5245143175125122, "step": 2982 }, { "epoch": 0.4182850732664937, "grad_norm": 2.6152431964874268, "learning_rate": 6.543357300037003e-06, "loss": 0.5364072918891907, "step": 2983 }, { "epoch": 0.4184252962209914, "grad_norm": 3.2627854347229004, "learning_rate": 6.541197423817358e-06, "loss": 0.5023473501205444, "step": 2984 }, { "epoch": 0.418565519175489, "grad_norm": 12.013358116149902, "learning_rate": 6.539037229766241e-06, "loss": 0.5323479771614075, "step": 2985 }, { "epoch": 0.4187057421299867, "grad_norm": 5.334545612335205, "learning_rate": 6.536876718329137e-06, "loss": 0.4652128219604492, "step": 2986 }, { "epoch": 0.41884596508448435, "grad_norm": 2.1622650623321533, "learning_rate": 6.534715889951595e-06, "loss": 0.5915572643280029, "step": 2987 }, { "epoch": 0.41898618803898197, "grad_norm": 15.129109382629395, "learning_rate": 6.53255474507923e-06, "loss": 0.6133859157562256, "step": 2988 }, { "epoch": 0.41912641099347964, "grad_norm": 2.605111837387085, "learning_rate": 6.530393284157719e-06, "loss": 0.5128726363182068, "step": 2989 }, { "epoch": 0.4192666339479773, "grad_norm": 2.7164690494537354, "learning_rate": 6.528231507632807e-06, "loss": 0.603718638420105, "step": 2990 }, { "epoch": 0.4194068569024749, "grad_norm": 3.527388334274292, "learning_rate": 6.526069415950307e-06, "loss": 0.5852565765380859, "step": 2991 }, { "epoch": 0.4195470798569726, "grad_norm": 2.990438222885132, "learning_rate": 6.523907009556087e-06, "loss": 0.5099117159843445, "step": 2992 }, { "epoch": 0.41968730281147026, "grad_norm": 2.8319573402404785, "learning_rate": 6.5217442888960926e-06, "loss": 0.507806122303009, "step": 2993 }, { "epoch": 0.4198275257659679, "grad_norm": 4.739870071411133, "learning_rate": 6.519581254416326e-06, "loss": 0.4437580108642578, "step": 2994 }, { "epoch": 0.41996774872046555, "grad_norm": 3.5522875785827637, "learning_rate": 6.517417906562855e-06, "loss": 0.5926772356033325, "step": 2995 }, { "epoch": 0.42010797167496317, "grad_norm": 3.7380974292755127, "learning_rate": 6.515254245781815e-06, "loss": 0.5402560234069824, "step": 2996 }, { "epoch": 0.42024819462946084, "grad_norm": 4.693148136138916, "learning_rate": 6.513090272519404e-06, "loss": 0.5149369835853577, "step": 2997 }, { "epoch": 0.4203884175839585, "grad_norm": 4.320194244384766, "learning_rate": 6.510925987221882e-06, "loss": 0.4779636561870575, "step": 2998 }, { "epoch": 0.4205286405384561, "grad_norm": 3.783601760864258, "learning_rate": 6.508761390335579e-06, "loss": 0.518242359161377, "step": 2999 }, { "epoch": 0.4206688634929538, "grad_norm": 4.612386226654053, "learning_rate": 6.506596482306886e-06, "loss": 0.6049606204032898, "step": 3000 }, { "epoch": 0.42080908644745146, "grad_norm": 2.9488210678100586, "learning_rate": 6.504431263582257e-06, "loss": 0.6095640063285828, "step": 3001 }, { "epoch": 0.4209493094019491, "grad_norm": 2.9454641342163086, "learning_rate": 6.502265734608212e-06, "loss": 0.48642659187316895, "step": 3002 }, { "epoch": 0.42108953235644675, "grad_norm": 3.317122220993042, "learning_rate": 6.500099895831334e-06, "loss": 0.5966173410415649, "step": 3003 }, { "epoch": 0.4212297553109444, "grad_norm": 2.701441526412964, "learning_rate": 6.4979337476982726e-06, "loss": 0.5599963665008545, "step": 3004 }, { "epoch": 0.42136997826544204, "grad_norm": 2.5438904762268066, "learning_rate": 6.495767290655737e-06, "loss": 0.3922332227230072, "step": 3005 }, { "epoch": 0.4215102012199397, "grad_norm": 3.967503786087036, "learning_rate": 6.493600525150501e-06, "loss": 0.4520047903060913, "step": 3006 }, { "epoch": 0.4216504241744374, "grad_norm": 4.734541893005371, "learning_rate": 6.491433451629405e-06, "loss": 0.5415528416633606, "step": 3007 }, { "epoch": 0.421790647128935, "grad_norm": 3.1779234409332275, "learning_rate": 6.4892660705393506e-06, "loss": 0.574235200881958, "step": 3008 }, { "epoch": 0.42193087008343266, "grad_norm": 3.0372531414031982, "learning_rate": 6.487098382327302e-06, "loss": 0.46032750606536865, "step": 3009 }, { "epoch": 0.42207109303793033, "grad_norm": 4.980142116546631, "learning_rate": 6.484930387440292e-06, "loss": 0.5100509524345398, "step": 3010 }, { "epoch": 0.42221131599242795, "grad_norm": 2.6684176921844482, "learning_rate": 6.482762086325406e-06, "loss": 0.6100683212280273, "step": 3011 }, { "epoch": 0.4223515389469256, "grad_norm": 3.229675054550171, "learning_rate": 6.480593479429803e-06, "loss": 0.5753735303878784, "step": 3012 }, { "epoch": 0.4224917619014233, "grad_norm": 2.9390735626220703, "learning_rate": 6.4784245672007014e-06, "loss": 0.5535095930099487, "step": 3013 }, { "epoch": 0.4226319848559209, "grad_norm": 5.065556049346924, "learning_rate": 6.476255350085381e-06, "loss": 0.5915001630783081, "step": 3014 }, { "epoch": 0.4227722078104186, "grad_norm": 10.318857192993164, "learning_rate": 6.474085828531187e-06, "loss": 0.5761550664901733, "step": 3015 }, { "epoch": 0.4229124307649162, "grad_norm": 5.287416934967041, "learning_rate": 6.471916002985526e-06, "loss": 0.47702038288116455, "step": 3016 }, { "epoch": 0.42305265371941386, "grad_norm": 2.5956709384918213, "learning_rate": 6.469745873895868e-06, "loss": 0.5530630350112915, "step": 3017 }, { "epoch": 0.42319287667391153, "grad_norm": 3.1858112812042236, "learning_rate": 6.4675754417097415e-06, "loss": 0.541657030582428, "step": 3018 }, { "epoch": 0.42333309962840915, "grad_norm": 2.6016554832458496, "learning_rate": 6.465404706874746e-06, "loss": 0.5677878856658936, "step": 3019 }, { "epoch": 0.4234733225829068, "grad_norm": 5.253712177276611, "learning_rate": 6.463233669838537e-06, "loss": 0.5361571907997131, "step": 3020 }, { "epoch": 0.4236135455374045, "grad_norm": 3.0431807041168213, "learning_rate": 6.461062331048832e-06, "loss": 0.520602822303772, "step": 3021 }, { "epoch": 0.4237537684919021, "grad_norm": 3.339723825454712, "learning_rate": 6.4588906909534135e-06, "loss": 0.5262004137039185, "step": 3022 }, { "epoch": 0.4238939914463998, "grad_norm": 3.1411285400390625, "learning_rate": 6.456718750000127e-06, "loss": 0.5036299824714661, "step": 3023 }, { "epoch": 0.42403421440089745, "grad_norm": 3.1242127418518066, "learning_rate": 6.454546508636876e-06, "loss": 0.6922075748443604, "step": 3024 }, { "epoch": 0.42417443735539506, "grad_norm": 2.432297468185425, "learning_rate": 6.452373967311629e-06, "loss": 0.5123195648193359, "step": 3025 }, { "epoch": 0.42431466030989273, "grad_norm": 2.683924674987793, "learning_rate": 6.450201126472416e-06, "loss": 0.47931063175201416, "step": 3026 }, { "epoch": 0.4244548832643904, "grad_norm": 3.430370807647705, "learning_rate": 6.448027986567328e-06, "loss": 0.4971325993537903, "step": 3027 }, { "epoch": 0.424595106218888, "grad_norm": 3.4775915145874023, "learning_rate": 6.445854548044517e-06, "loss": 0.5505298972129822, "step": 3028 }, { "epoch": 0.4247353291733857, "grad_norm": 2.911349296569824, "learning_rate": 6.4436808113521995e-06, "loss": 0.4840797483921051, "step": 3029 }, { "epoch": 0.42487555212788336, "grad_norm": 3.316739559173584, "learning_rate": 6.44150677693865e-06, "loss": 0.6247694492340088, "step": 3030 }, { "epoch": 0.425015775082381, "grad_norm": 4.877209186553955, "learning_rate": 6.439332445252207e-06, "loss": 0.5631203651428223, "step": 3031 }, { "epoch": 0.42515599803687865, "grad_norm": 3.934781551361084, "learning_rate": 6.437157816741268e-06, "loss": 0.5259253978729248, "step": 3032 }, { "epoch": 0.42529622099137626, "grad_norm": 2.7177774906158447, "learning_rate": 6.434982891854293e-06, "loss": 0.5279162526130676, "step": 3033 }, { "epoch": 0.42543644394587393, "grad_norm": 4.097611427307129, "learning_rate": 6.4328076710398055e-06, "loss": 0.46906083822250366, "step": 3034 }, { "epoch": 0.4255766669003716, "grad_norm": 3.260756731033325, "learning_rate": 6.430632154746385e-06, "loss": 0.5079835057258606, "step": 3035 }, { "epoch": 0.4257168898548692, "grad_norm": 12.652124404907227, "learning_rate": 6.428456343422678e-06, "loss": 0.5853298306465149, "step": 3036 }, { "epoch": 0.4258571128093669, "grad_norm": 2.5522687435150146, "learning_rate": 6.426280237517384e-06, "loss": 0.5682039260864258, "step": 3037 }, { "epoch": 0.42599733576386456, "grad_norm": 3.5538623332977295, "learning_rate": 6.4241038374792685e-06, "loss": 0.5829483866691589, "step": 3038 }, { "epoch": 0.4261375587183622, "grad_norm": 3.0394861698150635, "learning_rate": 6.42192714375716e-06, "loss": 0.6540553569793701, "step": 3039 }, { "epoch": 0.42627778167285985, "grad_norm": 4.1502203941345215, "learning_rate": 6.419750156799942e-06, "loss": 0.4993276298046112, "step": 3040 }, { "epoch": 0.4264180046273575, "grad_norm": 2.507580280303955, "learning_rate": 6.4175728770565606e-06, "loss": 0.5721807479858398, "step": 3041 }, { "epoch": 0.42655822758185513, "grad_norm": 4.659326076507568, "learning_rate": 6.4153953049760246e-06, "loss": 0.6736037731170654, "step": 3042 }, { "epoch": 0.4266984505363528, "grad_norm": 2.4670817852020264, "learning_rate": 6.413217441007398e-06, "loss": 0.5278868675231934, "step": 3043 }, { "epoch": 0.4268386734908505, "grad_norm": 2.6453635692596436, "learning_rate": 6.41103928559981e-06, "loss": 0.5932217836380005, "step": 3044 }, { "epoch": 0.4269788964453481, "grad_norm": 4.685027599334717, "learning_rate": 6.408860839202447e-06, "loss": 0.5353671908378601, "step": 3045 }, { "epoch": 0.42711911939984576, "grad_norm": 3.0825865268707275, "learning_rate": 6.406682102264558e-06, "loss": 0.5240294933319092, "step": 3046 }, { "epoch": 0.42725934235434343, "grad_norm": 2.9350674152374268, "learning_rate": 6.4045030752354486e-06, "loss": 0.5198484063148499, "step": 3047 }, { "epoch": 0.42739956530884105, "grad_norm": 3.010380983352661, "learning_rate": 6.402323758564486e-06, "loss": 0.5998263955116272, "step": 3048 }, { "epoch": 0.4275397882633387, "grad_norm": 3.0761237144470215, "learning_rate": 6.400144152701098e-06, "loss": 0.4853784441947937, "step": 3049 }, { "epoch": 0.4276800112178364, "grad_norm": 3.829164981842041, "learning_rate": 6.3979642580947696e-06, "loss": 0.6078180074691772, "step": 3050 }, { "epoch": 0.427820234172334, "grad_norm": 3.191385269165039, "learning_rate": 6.395784075195047e-06, "loss": 0.5531386137008667, "step": 3051 }, { "epoch": 0.4279604571268317, "grad_norm": 2.345235824584961, "learning_rate": 6.393603604451538e-06, "loss": 0.4716494679450989, "step": 3052 }, { "epoch": 0.4281006800813293, "grad_norm": 4.079148292541504, "learning_rate": 6.391422846313905e-06, "loss": 0.48843419551849365, "step": 3053 }, { "epoch": 0.42824090303582696, "grad_norm": 11.470765113830566, "learning_rate": 6.389241801231873e-06, "loss": 0.5877289772033691, "step": 3054 }, { "epoch": 0.42838112599032463, "grad_norm": 3.0912187099456787, "learning_rate": 6.387060469655224e-06, "loss": 0.5891883373260498, "step": 3055 }, { "epoch": 0.42852134894482224, "grad_norm": 3.400000810623169, "learning_rate": 6.384878852033801e-06, "loss": 0.4639756977558136, "step": 3056 }, { "epoch": 0.4286615718993199, "grad_norm": 4.409453392028809, "learning_rate": 6.3826969488175065e-06, "loss": 0.6076583862304688, "step": 3057 }, { "epoch": 0.4288017948538176, "grad_norm": 2.512209892272949, "learning_rate": 6.3805147604563e-06, "loss": 0.5472984910011292, "step": 3058 }, { "epoch": 0.4289420178083152, "grad_norm": 4.017592906951904, "learning_rate": 6.378332287400199e-06, "loss": 0.5617058277130127, "step": 3059 }, { "epoch": 0.42908224076281287, "grad_norm": 4.473353385925293, "learning_rate": 6.376149530099283e-06, "loss": 0.5415884256362915, "step": 3060 }, { "epoch": 0.42922246371731054, "grad_norm": 3.2518489360809326, "learning_rate": 6.3739664890036865e-06, "loss": 0.5954722762107849, "step": 3061 }, { "epoch": 0.42936268667180816, "grad_norm": 2.5472123622894287, "learning_rate": 6.371783164563607e-06, "loss": 0.4422147572040558, "step": 3062 }, { "epoch": 0.42950290962630583, "grad_norm": 2.8681225776672363, "learning_rate": 6.369599557229297e-06, "loss": 0.5184190273284912, "step": 3063 }, { "epoch": 0.4296431325808035, "grad_norm": 3.67384934425354, "learning_rate": 6.367415667451067e-06, "loss": 0.5080884099006653, "step": 3064 }, { "epoch": 0.4297833555353011, "grad_norm": 3.151414155960083, "learning_rate": 6.3652314956792875e-06, "loss": 0.5725361704826355, "step": 3065 }, { "epoch": 0.4299235784897988, "grad_norm": 4.518579483032227, "learning_rate": 6.363047042364385e-06, "loss": 0.46753814816474915, "step": 3066 }, { "epoch": 0.43006380144429646, "grad_norm": 3.0499470233917236, "learning_rate": 6.360862307956849e-06, "loss": 0.5366334319114685, "step": 3067 }, { "epoch": 0.43020402439879407, "grad_norm": 12.193689346313477, "learning_rate": 6.358677292907221e-06, "loss": 0.5150176286697388, "step": 3068 }, { "epoch": 0.43034424735329174, "grad_norm": 3.4368863105773926, "learning_rate": 6.356491997666103e-06, "loss": 0.6229866743087769, "step": 3069 }, { "epoch": 0.43048447030778936, "grad_norm": 2.266042709350586, "learning_rate": 6.354306422684155e-06, "loss": 0.4600118398666382, "step": 3070 }, { "epoch": 0.43062469326228703, "grad_norm": 3.970156669616699, "learning_rate": 6.3521205684120966e-06, "loss": 0.4813685417175293, "step": 3071 }, { "epoch": 0.4307649162167847, "grad_norm": 3.172652244567871, "learning_rate": 6.3499344353007e-06, "loss": 0.5552278757095337, "step": 3072 }, { "epoch": 0.4309051391712823, "grad_norm": 4.50263786315918, "learning_rate": 6.347748023800798e-06, "loss": 0.5554709434509277, "step": 3073 }, { "epoch": 0.43104536212578, "grad_norm": 4.511133193969727, "learning_rate": 6.345561334363282e-06, "loss": 0.4816519320011139, "step": 3074 }, { "epoch": 0.43118558508027766, "grad_norm": 1.952729344367981, "learning_rate": 6.343374367439099e-06, "loss": 0.5353766083717346, "step": 3075 }, { "epoch": 0.43132580803477527, "grad_norm": 2.945089340209961, "learning_rate": 6.341187123479251e-06, "loss": 0.47044283151626587, "step": 3076 }, { "epoch": 0.43146603098927294, "grad_norm": 2.7613775730133057, "learning_rate": 6.338999602934802e-06, "loss": 0.5705439448356628, "step": 3077 }, { "epoch": 0.4316062539437706, "grad_norm": 3.457911491394043, "learning_rate": 6.336811806256872e-06, "loss": 0.5761417150497437, "step": 3078 }, { "epoch": 0.4317464768982682, "grad_norm": 3.2768657207489014, "learning_rate": 6.334623733896632e-06, "loss": 0.5344340801239014, "step": 3079 }, { "epoch": 0.4318866998527659, "grad_norm": 2.1343233585357666, "learning_rate": 6.332435386305318e-06, "loss": 0.5871196389198303, "step": 3080 }, { "epoch": 0.43202692280726357, "grad_norm": 2.473027467727661, "learning_rate": 6.330246763934218e-06, "loss": 0.44351065158843994, "step": 3081 }, { "epoch": 0.4321671457617612, "grad_norm": 3.439678192138672, "learning_rate": 6.328057867234679e-06, "loss": 0.5215136408805847, "step": 3082 }, { "epoch": 0.43230736871625886, "grad_norm": 5.248805999755859, "learning_rate": 6.325868696658102e-06, "loss": 0.6098520159721375, "step": 3083 }, { "epoch": 0.4324475916707565, "grad_norm": 3.615084648132324, "learning_rate": 6.3236792526559455e-06, "loss": 0.6277151107788086, "step": 3084 }, { "epoch": 0.43258781462525414, "grad_norm": 3.3487510681152344, "learning_rate": 6.321489535679728e-06, "loss": 0.4978111982345581, "step": 3085 }, { "epoch": 0.4327280375797518, "grad_norm": 2.4142730236053467, "learning_rate": 6.319299546181017e-06, "loss": 0.5324485301971436, "step": 3086 }, { "epoch": 0.4328682605342495, "grad_norm": 4.576684474945068, "learning_rate": 6.317109284611442e-06, "loss": 0.47713473439216614, "step": 3087 }, { "epoch": 0.4330084834887471, "grad_norm": 2.5493226051330566, "learning_rate": 6.3149187514226875e-06, "loss": 0.4770386815071106, "step": 3088 }, { "epoch": 0.43314870644324477, "grad_norm": 2.407884359359741, "learning_rate": 6.312727947066493e-06, "loss": 0.4538210928440094, "step": 3089 }, { "epoch": 0.4332889293977424, "grad_norm": 2.8483188152313232, "learning_rate": 6.310536871994655e-06, "loss": 0.5431556701660156, "step": 3090 }, { "epoch": 0.43342915235224005, "grad_norm": 3.6580731868743896, "learning_rate": 6.308345526659023e-06, "loss": 0.5323259830474854, "step": 3091 }, { "epoch": 0.4335693753067377, "grad_norm": 6.033937454223633, "learning_rate": 6.306153911511506e-06, "loss": 0.530764639377594, "step": 3092 }, { "epoch": 0.43370959826123534, "grad_norm": 10.01916790008545, "learning_rate": 6.303962027004068e-06, "loss": 0.4965749979019165, "step": 3093 }, { "epoch": 0.433849821215733, "grad_norm": 2.615673780441284, "learning_rate": 6.301769873588726e-06, "loss": 0.5110131502151489, "step": 3094 }, { "epoch": 0.4339900441702307, "grad_norm": 6.81607723236084, "learning_rate": 6.299577451717553e-06, "loss": 0.5721416473388672, "step": 3095 }, { "epoch": 0.4341302671247283, "grad_norm": 2.0005311965942383, "learning_rate": 6.297384761842682e-06, "loss": 0.5256560444831848, "step": 3096 }, { "epoch": 0.43427049007922597, "grad_norm": 3.41371488571167, "learning_rate": 6.2951918044162945e-06, "loss": 0.4786742329597473, "step": 3097 }, { "epoch": 0.43441071303372364, "grad_norm": 1.9762840270996094, "learning_rate": 6.29299857989063e-06, "loss": 0.5061745047569275, "step": 3098 }, { "epoch": 0.43455093598822125, "grad_norm": 2.7213003635406494, "learning_rate": 6.290805088717987e-06, "loss": 0.4466902017593384, "step": 3099 }, { "epoch": 0.4346911589427189, "grad_norm": 3.455843925476074, "learning_rate": 6.288611331350711e-06, "loss": 0.5797800421714783, "step": 3100 }, { "epoch": 0.4348313818972166, "grad_norm": 5.5425825119018555, "learning_rate": 6.286417308241211e-06, "loss": 0.48868507146835327, "step": 3101 }, { "epoch": 0.4349716048517142, "grad_norm": 3.1795296669006348, "learning_rate": 6.284223019841944e-06, "loss": 0.5569186210632324, "step": 3102 }, { "epoch": 0.4351118278062119, "grad_norm": 3.157090425491333, "learning_rate": 6.282028466605425e-06, "loss": 0.6086174249649048, "step": 3103 }, { "epoch": 0.43525205076070955, "grad_norm": 3.7597157955169678, "learning_rate": 6.279833648984222e-06, "loss": 0.4714728891849518, "step": 3104 }, { "epoch": 0.43539227371520717, "grad_norm": 2.4990296363830566, "learning_rate": 6.2776385674309615e-06, "loss": 0.5610348582267761, "step": 3105 }, { "epoch": 0.43553249666970484, "grad_norm": 2.795062303543091, "learning_rate": 6.275443222398318e-06, "loss": 0.5746327638626099, "step": 3106 }, { "epoch": 0.4356727196242025, "grad_norm": 3.363431453704834, "learning_rate": 6.2732476143390246e-06, "loss": 0.604994535446167, "step": 3107 }, { "epoch": 0.4358129425787001, "grad_norm": 3.3460733890533447, "learning_rate": 6.271051743705867e-06, "loss": 0.5355621576309204, "step": 3108 }, { "epoch": 0.4359531655331978, "grad_norm": 2.6590874195098877, "learning_rate": 6.26885561095169e-06, "loss": 0.48835891485214233, "step": 3109 }, { "epoch": 0.4360933884876954, "grad_norm": 3.3593225479125977, "learning_rate": 6.266659216529383e-06, "loss": 0.46198150515556335, "step": 3110 }, { "epoch": 0.4362336114421931, "grad_norm": 3.516526460647583, "learning_rate": 6.264462560891897e-06, "loss": 0.642803966999054, "step": 3111 }, { "epoch": 0.43637383439669075, "grad_norm": 5.70535945892334, "learning_rate": 6.262265644492236e-06, "loss": 0.402346670627594, "step": 3112 }, { "epoch": 0.43651405735118837, "grad_norm": 3.1108407974243164, "learning_rate": 6.260068467783453e-06, "loss": 0.6508403420448303, "step": 3113 }, { "epoch": 0.43665428030568604, "grad_norm": 3.915493965148926, "learning_rate": 6.2578710312186585e-06, "loss": 0.49198371171951294, "step": 3114 }, { "epoch": 0.4367945032601837, "grad_norm": 3.5291812419891357, "learning_rate": 6.25567333525102e-06, "loss": 0.5555867552757263, "step": 3115 }, { "epoch": 0.4369347262146813, "grad_norm": 10.958402633666992, "learning_rate": 6.25347538033375e-06, "loss": 0.610549807548523, "step": 3116 }, { "epoch": 0.437074949169179, "grad_norm": 2.1331722736358643, "learning_rate": 6.25127716692012e-06, "loss": 0.5364953279495239, "step": 3117 }, { "epoch": 0.43721517212367667, "grad_norm": 4.000982761383057, "learning_rate": 6.249078695463455e-06, "loss": 0.5155065059661865, "step": 3118 }, { "epoch": 0.4373553950781743, "grad_norm": 3.1536061763763428, "learning_rate": 6.246879966417133e-06, "loss": 0.5542914867401123, "step": 3119 }, { "epoch": 0.43749561803267195, "grad_norm": 4.1559271812438965, "learning_rate": 6.244680980234581e-06, "loss": 0.5542060136795044, "step": 3120 }, { "epoch": 0.4376358409871696, "grad_norm": 2.418334484100342, "learning_rate": 6.242481737369284e-06, "loss": 0.6005222797393799, "step": 3121 }, { "epoch": 0.43777606394166724, "grad_norm": 2.709815502166748, "learning_rate": 6.240282238274777e-06, "loss": 0.5106134414672852, "step": 3122 }, { "epoch": 0.4379162868961649, "grad_norm": 3.865645170211792, "learning_rate": 6.238082483404649e-06, "loss": 0.5744975805282593, "step": 3123 }, { "epoch": 0.4380565098506626, "grad_norm": 2.3404200077056885, "learning_rate": 6.235882473212544e-06, "loss": 0.5249297618865967, "step": 3124 }, { "epoch": 0.4381967328051602, "grad_norm": 3.6349732875823975, "learning_rate": 6.233682208152153e-06, "loss": 0.5972858667373657, "step": 3125 }, { "epoch": 0.43833695575965786, "grad_norm": 2.765540599822998, "learning_rate": 6.231481688677224e-06, "loss": 0.5710580945014954, "step": 3126 }, { "epoch": 0.4384771787141555, "grad_norm": 2.3186166286468506, "learning_rate": 6.229280915241558e-06, "loss": 0.4667682647705078, "step": 3127 }, { "epoch": 0.43861740166865315, "grad_norm": 2.276292085647583, "learning_rate": 6.227079888299004e-06, "loss": 0.46176546812057495, "step": 3128 }, { "epoch": 0.4387576246231508, "grad_norm": 2.1640617847442627, "learning_rate": 6.224878608303469e-06, "loss": 0.6663590669631958, "step": 3129 }, { "epoch": 0.43889784757764844, "grad_norm": 2.6382253170013428, "learning_rate": 6.222677075708906e-06, "loss": 0.5283374786376953, "step": 3130 }, { "epoch": 0.4390380705321461, "grad_norm": 3.251523494720459, "learning_rate": 6.220475290969324e-06, "loss": 0.6536221504211426, "step": 3131 }, { "epoch": 0.4391782934866438, "grad_norm": 2.9909517765045166, "learning_rate": 6.218273254538786e-06, "loss": 0.5222045183181763, "step": 3132 }, { "epoch": 0.4393185164411414, "grad_norm": 2.2301580905914307, "learning_rate": 6.2160709668714e-06, "loss": 0.5061837434768677, "step": 3133 }, { "epoch": 0.43945873939563906, "grad_norm": 3.2228405475616455, "learning_rate": 6.213868428421334e-06, "loss": 0.5819216370582581, "step": 3134 }, { "epoch": 0.43959896235013673, "grad_norm": 4.228912830352783, "learning_rate": 6.211665639642801e-06, "loss": 0.5204465389251709, "step": 3135 }, { "epoch": 0.43973918530463435, "grad_norm": 3.1627285480499268, "learning_rate": 6.209462600990068e-06, "loss": 0.505693256855011, "step": 3136 }, { "epoch": 0.439879408259132, "grad_norm": 2.560248851776123, "learning_rate": 6.207259312917455e-06, "loss": 0.5240621566772461, "step": 3137 }, { "epoch": 0.4400196312136297, "grad_norm": 2.5891075134277344, "learning_rate": 6.205055775879333e-06, "loss": 0.5039082169532776, "step": 3138 }, { "epoch": 0.4401598541681273, "grad_norm": 23.34946632385254, "learning_rate": 6.2028519903301235e-06, "loss": 0.549186110496521, "step": 3139 }, { "epoch": 0.440300077122625, "grad_norm": 2.5585439205169678, "learning_rate": 6.200647956724297e-06, "loss": 0.5160700082778931, "step": 3140 }, { "epoch": 0.44044030007712265, "grad_norm": 6.377148151397705, "learning_rate": 6.198443675516379e-06, "loss": 0.5514101982116699, "step": 3141 }, { "epoch": 0.44058052303162026, "grad_norm": 3.4177286624908447, "learning_rate": 6.196239147160946e-06, "loss": 0.6260017156600952, "step": 3142 }, { "epoch": 0.44072074598611793, "grad_norm": 2.7019708156585693, "learning_rate": 6.1940343721126216e-06, "loss": 0.48120203614234924, "step": 3143 }, { "epoch": 0.4408609689406156, "grad_norm": 2.2839019298553467, "learning_rate": 6.191829350826084e-06, "loss": 0.49997061491012573, "step": 3144 }, { "epoch": 0.4410011918951132, "grad_norm": 2.640110492706299, "learning_rate": 6.189624083756062e-06, "loss": 0.5922353267669678, "step": 3145 }, { "epoch": 0.4411414148496109, "grad_norm": 3.248922109603882, "learning_rate": 6.187418571357331e-06, "loss": 0.5010636448860168, "step": 3146 }, { "epoch": 0.4412816378041085, "grad_norm": 2.847742795944214, "learning_rate": 6.1852128140847226e-06, "loss": 0.5024563074111938, "step": 3147 }, { "epoch": 0.4414218607586062, "grad_norm": 2.5063254833221436, "learning_rate": 6.183006812393115e-06, "loss": 0.4677649140357971, "step": 3148 }, { "epoch": 0.44156208371310385, "grad_norm": 2.856213092803955, "learning_rate": 6.180800566737438e-06, "loss": 0.47205835580825806, "step": 3149 }, { "epoch": 0.44170230666760146, "grad_norm": 4.773336410522461, "learning_rate": 6.178594077572673e-06, "loss": 0.661718487739563, "step": 3150 }, { "epoch": 0.44184252962209913, "grad_norm": 2.640218496322632, "learning_rate": 6.176387345353849e-06, "loss": 0.5485032200813293, "step": 3151 }, { "epoch": 0.4419827525765968, "grad_norm": 2.761054515838623, "learning_rate": 6.174180370536048e-06, "loss": 0.5185350179672241, "step": 3152 }, { "epoch": 0.4421229755310944, "grad_norm": 3.8165371417999268, "learning_rate": 6.1719731535744e-06, "loss": 0.5416277050971985, "step": 3153 }, { "epoch": 0.4422631984855921, "grad_norm": 1.806652307510376, "learning_rate": 6.169765694924083e-06, "loss": 0.45839646458625793, "step": 3154 }, { "epoch": 0.44240342144008976, "grad_norm": 8.566816329956055, "learning_rate": 6.167557995040333e-06, "loss": 0.5734703540802002, "step": 3155 }, { "epoch": 0.4425436443945874, "grad_norm": 2.72556471824646, "learning_rate": 6.165350054378425e-06, "loss": 0.4399505853652954, "step": 3156 }, { "epoch": 0.44268386734908505, "grad_norm": 2.6976377964019775, "learning_rate": 6.16314187339369e-06, "loss": 0.5548809766769409, "step": 3157 }, { "epoch": 0.4428240903035827, "grad_norm": 3.055497884750366, "learning_rate": 6.1609334525415086e-06, "loss": 0.6219429969787598, "step": 3158 }, { "epoch": 0.44296431325808033, "grad_norm": 2.633026123046875, "learning_rate": 6.1587247922773086e-06, "loss": 0.6415003538131714, "step": 3159 }, { "epoch": 0.443104536212578, "grad_norm": 2.4040699005126953, "learning_rate": 6.156515893056567e-06, "loss": 0.5673556327819824, "step": 3160 }, { "epoch": 0.4432447591670757, "grad_norm": 3.333998441696167, "learning_rate": 6.154306755334813e-06, "loss": 0.5842278599739075, "step": 3161 }, { "epoch": 0.4433849821215733, "grad_norm": 3.9485247135162354, "learning_rate": 6.152097379567625e-06, "loss": 0.5139188766479492, "step": 3162 }, { "epoch": 0.44352520507607096, "grad_norm": 2.0818116664886475, "learning_rate": 6.1498877662106224e-06, "loss": 0.5053907036781311, "step": 3163 }, { "epoch": 0.44366542803056863, "grad_norm": 5.412153720855713, "learning_rate": 6.147677915719487e-06, "loss": 0.5382409691810608, "step": 3164 }, { "epoch": 0.44380565098506625, "grad_norm": 6.376851558685303, "learning_rate": 6.145467828549938e-06, "loss": 0.7018424868583679, "step": 3165 }, { "epoch": 0.4439458739395639, "grad_norm": 2.442905902862549, "learning_rate": 6.1432575051577485e-06, "loss": 0.5371605753898621, "step": 3166 }, { "epoch": 0.44408609689406153, "grad_norm": 3.530527114868164, "learning_rate": 6.141046945998741e-06, "loss": 0.5013558268547058, "step": 3167 }, { "epoch": 0.4442263198485592, "grad_norm": 3.4166808128356934, "learning_rate": 6.138836151528784e-06, "loss": 0.540520191192627, "step": 3168 }, { "epoch": 0.4443665428030569, "grad_norm": 8.453721046447754, "learning_rate": 6.136625122203796e-06, "loss": 0.602716326713562, "step": 3169 }, { "epoch": 0.4445067657575545, "grad_norm": 2.2198221683502197, "learning_rate": 6.134413858479744e-06, "loss": 0.5267218351364136, "step": 3170 }, { "epoch": 0.44464698871205216, "grad_norm": 2.442199230194092, "learning_rate": 6.132202360812645e-06, "loss": 0.6055750846862793, "step": 3171 }, { "epoch": 0.44478721166654983, "grad_norm": 5.521307468414307, "learning_rate": 6.1299906296585575e-06, "loss": 0.611344575881958, "step": 3172 }, { "epoch": 0.44492743462104745, "grad_norm": 3.0432286262512207, "learning_rate": 6.127778665473596e-06, "loss": 0.5537256002426147, "step": 3173 }, { "epoch": 0.4450676575755451, "grad_norm": 7.6042914390563965, "learning_rate": 6.125566468713922e-06, "loss": 0.49848759174346924, "step": 3174 }, { "epoch": 0.4452078805300428, "grad_norm": 21.04638671875, "learning_rate": 6.123354039835737e-06, "loss": 0.4952602982521057, "step": 3175 }, { "epoch": 0.4453481034845404, "grad_norm": 3.1710731983184814, "learning_rate": 6.121141379295302e-06, "loss": 0.5444431304931641, "step": 3176 }, { "epoch": 0.4454883264390381, "grad_norm": 5.78292179107666, "learning_rate": 6.1189284875489185e-06, "loss": 0.46739715337753296, "step": 3177 }, { "epoch": 0.44562854939353574, "grad_norm": 5.213823318481445, "learning_rate": 6.116715365052935e-06, "loss": 0.5293245315551758, "step": 3178 }, { "epoch": 0.44576877234803336, "grad_norm": 6.715625286102295, "learning_rate": 6.114502012263752e-06, "loss": 0.5428980588912964, "step": 3179 }, { "epoch": 0.44590899530253103, "grad_norm": 2.6921937465667725, "learning_rate": 6.112288429637816e-06, "loss": 0.5362856984138489, "step": 3180 }, { "epoch": 0.4460492182570287, "grad_norm": 3.9724643230438232, "learning_rate": 6.110074617631618e-06, "loss": 0.5110139846801758, "step": 3181 }, { "epoch": 0.4461894412115263, "grad_norm": 4.718648910522461, "learning_rate": 6.1078605767017004e-06, "loss": 0.4578869342803955, "step": 3182 }, { "epoch": 0.446329664166024, "grad_norm": 7.523965358734131, "learning_rate": 6.10564630730465e-06, "loss": 0.650135338306427, "step": 3183 }, { "epoch": 0.4464698871205216, "grad_norm": 3.3834378719329834, "learning_rate": 6.103431809897103e-06, "loss": 0.49892884492874146, "step": 3184 }, { "epoch": 0.4466101100750193, "grad_norm": 2.721045970916748, "learning_rate": 6.10121708493574e-06, "loss": 0.5231506824493408, "step": 3185 }, { "epoch": 0.44675033302951694, "grad_norm": 3.001028299331665, "learning_rate": 6.09900213287729e-06, "loss": 0.6051909327507019, "step": 3186 }, { "epoch": 0.44689055598401456, "grad_norm": 2.2802083492279053, "learning_rate": 6.096786954178529e-06, "loss": 0.5191020965576172, "step": 3187 }, { "epoch": 0.44703077893851223, "grad_norm": 4.319792747497559, "learning_rate": 6.094571549296279e-06, "loss": 0.5775173902511597, "step": 3188 }, { "epoch": 0.4471710018930099, "grad_norm": 3.978872060775757, "learning_rate": 6.092355918687408e-06, "loss": 0.5631883144378662, "step": 3189 }, { "epoch": 0.4473112248475075, "grad_norm": 4.22425651550293, "learning_rate": 6.0901400628088345e-06, "loss": 0.5440964698791504, "step": 3190 }, { "epoch": 0.4474514478020052, "grad_norm": 3.176853656768799, "learning_rate": 6.087923982117519e-06, "loss": 0.574501633644104, "step": 3191 }, { "epoch": 0.44759167075650286, "grad_norm": 3.9130403995513916, "learning_rate": 6.085707677070468e-06, "loss": 0.6231876611709595, "step": 3192 }, { "epoch": 0.4477318937110005, "grad_norm": 2.4050209522247314, "learning_rate": 6.083491148124739e-06, "loss": 0.6525572538375854, "step": 3193 }, { "epoch": 0.44787211666549814, "grad_norm": 4.504016876220703, "learning_rate": 6.081274395737432e-06, "loss": 0.49963438510894775, "step": 3194 }, { "epoch": 0.4480123396199958, "grad_norm": 3.0089292526245117, "learning_rate": 6.079057420365694e-06, "loss": 0.5135188698768616, "step": 3195 }, { "epoch": 0.44815256257449343, "grad_norm": 2.8857784271240234, "learning_rate": 6.076840222466716e-06, "loss": 0.5445793867111206, "step": 3196 }, { "epoch": 0.4482927855289911, "grad_norm": 3.9494540691375732, "learning_rate": 6.074622802497741e-06, "loss": 0.5964459180831909, "step": 3197 }, { "epoch": 0.44843300848348877, "grad_norm": 3.678957462310791, "learning_rate": 6.07240516091605e-06, "loss": 0.5556503534317017, "step": 3198 }, { "epoch": 0.4485732314379864, "grad_norm": 2.6376535892486572, "learning_rate": 6.070187298178973e-06, "loss": 0.5342772603034973, "step": 3199 }, { "epoch": 0.44871345439248406, "grad_norm": 3.1630845069885254, "learning_rate": 6.067969214743889e-06, "loss": 0.559389054775238, "step": 3200 }, { "epoch": 0.4488536773469817, "grad_norm": 2.6736109256744385, "learning_rate": 6.0657509110682166e-06, "loss": 0.5007051229476929, "step": 3201 }, { "epoch": 0.44899390030147934, "grad_norm": 3.581965923309326, "learning_rate": 6.0635323876094244e-06, "loss": 0.5439141988754272, "step": 3202 }, { "epoch": 0.449134123255977, "grad_norm": 5.273268222808838, "learning_rate": 6.061313644825024e-06, "loss": 0.6835896968841553, "step": 3203 }, { "epoch": 0.44927434621047463, "grad_norm": 4.895318508148193, "learning_rate": 6.059094683172572e-06, "loss": 0.5543469786643982, "step": 3204 }, { "epoch": 0.4494145691649723, "grad_norm": 2.267256021499634, "learning_rate": 6.056875503109672e-06, "loss": 0.549558162689209, "step": 3205 }, { "epoch": 0.44955479211946997, "grad_norm": 3.133073091506958, "learning_rate": 6.0546561050939725e-06, "loss": 0.5576919913291931, "step": 3206 }, { "epoch": 0.4496950150739676, "grad_norm": 2.1393203735351562, "learning_rate": 6.052436489583163e-06, "loss": 0.6180708408355713, "step": 3207 }, { "epoch": 0.44983523802846526, "grad_norm": 2.7774198055267334, "learning_rate": 6.050216657034984e-06, "loss": 0.5839280486106873, "step": 3208 }, { "epoch": 0.4499754609829629, "grad_norm": 2.3542792797088623, "learning_rate": 6.047996607907215e-06, "loss": 0.4678767919540405, "step": 3209 }, { "epoch": 0.45011568393746054, "grad_norm": 5.374728679656982, "learning_rate": 6.045776342657685e-06, "loss": 0.5693557262420654, "step": 3210 }, { "epoch": 0.4502559068919582, "grad_norm": 3.2923786640167236, "learning_rate": 6.043555861744263e-06, "loss": 0.5266254544258118, "step": 3211 }, { "epoch": 0.4503961298464559, "grad_norm": 3.270347833633423, "learning_rate": 6.041335165624868e-06, "loss": 0.5749059915542603, "step": 3212 }, { "epoch": 0.4505363528009535, "grad_norm": 4.719015598297119, "learning_rate": 6.039114254757458e-06, "loss": 0.5149205923080444, "step": 3213 }, { "epoch": 0.45067657575545117, "grad_norm": 2.938798427581787, "learning_rate": 6.036893129600037e-06, "loss": 0.5708791613578796, "step": 3214 }, { "epoch": 0.45081679870994884, "grad_norm": 2.418846368789673, "learning_rate": 6.034671790610655e-06, "loss": 0.4902109205722809, "step": 3215 }, { "epoch": 0.45095702166444646, "grad_norm": 2.0798985958099365, "learning_rate": 6.032450238247406e-06, "loss": 0.44446367025375366, "step": 3216 }, { "epoch": 0.4510972446189441, "grad_norm": 2.5136160850524902, "learning_rate": 6.030228472968423e-06, "loss": 0.5775825381278992, "step": 3217 }, { "epoch": 0.4512374675734418, "grad_norm": 2.4500844478607178, "learning_rate": 6.028006495231891e-06, "loss": 0.5199552774429321, "step": 3218 }, { "epoch": 0.4513776905279394, "grad_norm": 2.5589711666107178, "learning_rate": 6.025784305496032e-06, "loss": 0.5827277898788452, "step": 3219 }, { "epoch": 0.4515179134824371, "grad_norm": 3.276841402053833, "learning_rate": 6.023561904219113e-06, "loss": 0.562839150428772, "step": 3220 }, { "epoch": 0.4516581364369347, "grad_norm": 2.4071974754333496, "learning_rate": 6.021339291859449e-06, "loss": 0.6360418796539307, "step": 3221 }, { "epoch": 0.45179835939143237, "grad_norm": 2.329314947128296, "learning_rate": 6.019116468875395e-06, "loss": 0.4489296078681946, "step": 3222 }, { "epoch": 0.45193858234593004, "grad_norm": 5.069872856140137, "learning_rate": 6.0168934357253464e-06, "loss": 0.4836265444755554, "step": 3223 }, { "epoch": 0.45207880530042766, "grad_norm": 4.880649566650391, "learning_rate": 6.0146701928677485e-06, "loss": 0.6064504981040955, "step": 3224 }, { "epoch": 0.4522190282549253, "grad_norm": 4.466292858123779, "learning_rate": 6.012446740761086e-06, "loss": 0.6056503057479858, "step": 3225 }, { "epoch": 0.452359251209423, "grad_norm": 3.7864139080047607, "learning_rate": 6.01022307986389e-06, "loss": 0.5111831426620483, "step": 3226 }, { "epoch": 0.4524994741639206, "grad_norm": 3.0580685138702393, "learning_rate": 6.007999210634728e-06, "loss": 0.39241456985473633, "step": 3227 }, { "epoch": 0.4526396971184183, "grad_norm": 4.331368923187256, "learning_rate": 6.005775133532214e-06, "loss": 0.5531491041183472, "step": 3228 }, { "epoch": 0.45277992007291595, "grad_norm": 9.19948673248291, "learning_rate": 6.003550849015011e-06, "loss": 0.5327402949333191, "step": 3229 }, { "epoch": 0.45292014302741357, "grad_norm": 2.694077968597412, "learning_rate": 6.001326357541814e-06, "loss": 0.6208152770996094, "step": 3230 }, { "epoch": 0.45306036598191124, "grad_norm": 3.6638612747192383, "learning_rate": 5.999101659571368e-06, "loss": 0.5713013410568237, "step": 3231 }, { "epoch": 0.4532005889364089, "grad_norm": 2.402935028076172, "learning_rate": 5.996876755562459e-06, "loss": 0.5625872015953064, "step": 3232 }, { "epoch": 0.4533408118909065, "grad_norm": 3.9023866653442383, "learning_rate": 5.994651645973914e-06, "loss": 0.49684229493141174, "step": 3233 }, { "epoch": 0.4534810348454042, "grad_norm": 3.33251953125, "learning_rate": 5.992426331264603e-06, "loss": 0.5879784822463989, "step": 3234 }, { "epoch": 0.45362125779990187, "grad_norm": 2.4924094676971436, "learning_rate": 5.9902008118934405e-06, "loss": 0.48558369278907776, "step": 3235 }, { "epoch": 0.4537614807543995, "grad_norm": 2.7096426486968994, "learning_rate": 5.98797508831938e-06, "loss": 0.5280001759529114, "step": 3236 }, { "epoch": 0.45390170370889715, "grad_norm": 2.2007172107696533, "learning_rate": 5.985749161001417e-06, "loss": 0.5655363202095032, "step": 3237 }, { "epoch": 0.4540419266633948, "grad_norm": 3.8284902572631836, "learning_rate": 5.9835230303985945e-06, "loss": 0.5863395929336548, "step": 3238 }, { "epoch": 0.45418214961789244, "grad_norm": 2.4951915740966797, "learning_rate": 5.981296696969991e-06, "loss": 0.5166152715682983, "step": 3239 }, { "epoch": 0.4543223725723901, "grad_norm": 2.5380311012268066, "learning_rate": 5.979070161174728e-06, "loss": 0.5406090021133423, "step": 3240 }, { "epoch": 0.4544625955268877, "grad_norm": 3.9778788089752197, "learning_rate": 5.976843423471973e-06, "loss": 0.6111580729484558, "step": 3241 }, { "epoch": 0.4546028184813854, "grad_norm": 3.6244287490844727, "learning_rate": 5.974616484320931e-06, "loss": 0.6106550693511963, "step": 3242 }, { "epoch": 0.45474304143588307, "grad_norm": 3.836477518081665, "learning_rate": 5.9723893441808475e-06, "loss": 0.5108296871185303, "step": 3243 }, { "epoch": 0.4548832643903807, "grad_norm": 3.5777223110198975, "learning_rate": 5.9701620035110145e-06, "loss": 0.541338324546814, "step": 3244 }, { "epoch": 0.45502348734487835, "grad_norm": 3.2470483779907227, "learning_rate": 5.967934462770762e-06, "loss": 0.6081109046936035, "step": 3245 }, { "epoch": 0.455163710299376, "grad_norm": 4.355741500854492, "learning_rate": 5.96570672241946e-06, "loss": 0.49816229939460754, "step": 3246 }, { "epoch": 0.45530393325387364, "grad_norm": 2.8925511837005615, "learning_rate": 5.963478782916522e-06, "loss": 0.5719441175460815, "step": 3247 }, { "epoch": 0.4554441562083713, "grad_norm": 2.6693778038024902, "learning_rate": 5.9612506447214045e-06, "loss": 0.5389782190322876, "step": 3248 }, { "epoch": 0.455584379162869, "grad_norm": 4.122330665588379, "learning_rate": 5.9590223082935995e-06, "loss": 0.5782985687255859, "step": 3249 }, { "epoch": 0.4557246021173666, "grad_norm": 3.715858221054077, "learning_rate": 5.956793774092643e-06, "loss": 0.5389354825019836, "step": 3250 }, { "epoch": 0.45586482507186427, "grad_norm": 4.517100811004639, "learning_rate": 5.954565042578114e-06, "loss": 0.5749396085739136, "step": 3251 }, { "epoch": 0.45600504802636194, "grad_norm": 4.7094221115112305, "learning_rate": 5.952336114209627e-06, "loss": 0.5107090473175049, "step": 3252 }, { "epoch": 0.45614527098085955, "grad_norm": 2.6916773319244385, "learning_rate": 5.950106989446842e-06, "loss": 0.46939897537231445, "step": 3253 }, { "epoch": 0.4562854939353572, "grad_norm": 3.5178334712982178, "learning_rate": 5.947877668749456e-06, "loss": 0.4478462040424347, "step": 3254 }, { "epoch": 0.4564257168898549, "grad_norm": 4.641184329986572, "learning_rate": 5.945648152577209e-06, "loss": 0.6363019347190857, "step": 3255 }, { "epoch": 0.4565659398443525, "grad_norm": 2.282252788543701, "learning_rate": 5.94341844138988e-06, "loss": 0.5565695762634277, "step": 3256 }, { "epoch": 0.4567061627988502, "grad_norm": 3.6083669662475586, "learning_rate": 5.941188535647287e-06, "loss": 0.4399542212486267, "step": 3257 }, { "epoch": 0.45684638575334785, "grad_norm": 2.7216782569885254, "learning_rate": 5.93895843580929e-06, "loss": 0.565839946269989, "step": 3258 }, { "epoch": 0.45698660870784547, "grad_norm": 3.4886887073516846, "learning_rate": 5.936728142335789e-06, "loss": 0.6162490844726562, "step": 3259 }, { "epoch": 0.45712683166234314, "grad_norm": 3.4294891357421875, "learning_rate": 5.934497655686724e-06, "loss": 0.6252291798591614, "step": 3260 }, { "epoch": 0.45726705461684075, "grad_norm": 3.1309008598327637, "learning_rate": 5.932266976322073e-06, "loss": 0.6218156814575195, "step": 3261 }, { "epoch": 0.4574072775713384, "grad_norm": 3.430245876312256, "learning_rate": 5.930036104701855e-06, "loss": 0.6221972107887268, "step": 3262 }, { "epoch": 0.4575475005258361, "grad_norm": 2.762223243713379, "learning_rate": 5.92780504128613e-06, "loss": 0.5945027470588684, "step": 3263 }, { "epoch": 0.4576877234803337, "grad_norm": 3.3822338581085205, "learning_rate": 5.925573786534996e-06, "loss": 0.3680908679962158, "step": 3264 }, { "epoch": 0.4578279464348314, "grad_norm": 2.5722908973693848, "learning_rate": 5.923342340908589e-06, "loss": 0.5238354802131653, "step": 3265 }, { "epoch": 0.45796816938932905, "grad_norm": 4.536324977874756, "learning_rate": 5.921110704867085e-06, "loss": 0.5425119400024414, "step": 3266 }, { "epoch": 0.45810839234382666, "grad_norm": 2.906916379928589, "learning_rate": 5.918878878870707e-06, "loss": 0.5290977358818054, "step": 3267 }, { "epoch": 0.45824861529832434, "grad_norm": 2.9577858448028564, "learning_rate": 5.9166468633797025e-06, "loss": 0.5815696120262146, "step": 3268 }, { "epoch": 0.458388838252822, "grad_norm": 4.366405010223389, "learning_rate": 5.914414658854369e-06, "loss": 0.5475561022758484, "step": 3269 }, { "epoch": 0.4585290612073196, "grad_norm": 2.611055612564087, "learning_rate": 5.912182265755042e-06, "loss": 0.6233324408531189, "step": 3270 }, { "epoch": 0.4586692841618173, "grad_norm": 2.8038506507873535, "learning_rate": 5.909949684542092e-06, "loss": 0.46988198161125183, "step": 3271 }, { "epoch": 0.45880950711631496, "grad_norm": 4.18865442276001, "learning_rate": 5.9077169156759304e-06, "loss": 0.49762415885925293, "step": 3272 }, { "epoch": 0.4589497300708126, "grad_norm": 2.1545674800872803, "learning_rate": 5.905483959617006e-06, "loss": 0.5555561780929565, "step": 3273 }, { "epoch": 0.45908995302531025, "grad_norm": 2.4779322147369385, "learning_rate": 5.903250816825811e-06, "loss": 0.4936385154724121, "step": 3274 }, { "epoch": 0.4592301759798079, "grad_norm": 3.609941244125366, "learning_rate": 5.901017487762868e-06, "loss": 0.6670963168144226, "step": 3275 }, { "epoch": 0.45937039893430553, "grad_norm": 2.7171695232391357, "learning_rate": 5.898783972888744e-06, "loss": 0.5137805938720703, "step": 3276 }, { "epoch": 0.4595106218888032, "grad_norm": 3.6361138820648193, "learning_rate": 5.8965502726640455e-06, "loss": 0.5687103271484375, "step": 3277 }, { "epoch": 0.4596508448433008, "grad_norm": 5.665175914764404, "learning_rate": 5.89431638754941e-06, "loss": 0.5752459764480591, "step": 3278 }, { "epoch": 0.4597910677977985, "grad_norm": 2.376190423965454, "learning_rate": 5.89208231800552e-06, "loss": 0.48316672444343567, "step": 3279 }, { "epoch": 0.45993129075229616, "grad_norm": 3.7779860496520996, "learning_rate": 5.889848064493094e-06, "loss": 0.5554748773574829, "step": 3280 }, { "epoch": 0.4600715137067938, "grad_norm": 3.629744052886963, "learning_rate": 5.887613627472886e-06, "loss": 0.562379002571106, "step": 3281 }, { "epoch": 0.46021173666129145, "grad_norm": 2.508866786956787, "learning_rate": 5.885379007405693e-06, "loss": 0.5235974788665771, "step": 3282 }, { "epoch": 0.4603519596157891, "grad_norm": 11.989851951599121, "learning_rate": 5.883144204752344e-06, "loss": 0.6081257462501526, "step": 3283 }, { "epoch": 0.46049218257028673, "grad_norm": 2.949868679046631, "learning_rate": 5.8809092199737105e-06, "loss": 0.5014057755470276, "step": 3284 }, { "epoch": 0.4606324055247844, "grad_norm": 2.323267698287964, "learning_rate": 5.878674053530697e-06, "loss": 0.5593101382255554, "step": 3285 }, { "epoch": 0.4607726284792821, "grad_norm": 3.613053321838379, "learning_rate": 5.87643870588425e-06, "loss": 0.5912981629371643, "step": 3286 }, { "epoch": 0.4609128514337797, "grad_norm": 5.219596862792969, "learning_rate": 5.87420317749535e-06, "loss": 0.5288310647010803, "step": 3287 }, { "epoch": 0.46105307438827736, "grad_norm": 2.794538974761963, "learning_rate": 5.871967468825016e-06, "loss": 0.6186224222183228, "step": 3288 }, { "epoch": 0.46119329734277503, "grad_norm": 3.8493573665618896, "learning_rate": 5.869731580334303e-06, "loss": 0.4903933107852936, "step": 3289 }, { "epoch": 0.46133352029727265, "grad_norm": 3.4640495777130127, "learning_rate": 5.867495512484309e-06, "loss": 0.5872013568878174, "step": 3290 }, { "epoch": 0.4614737432517703, "grad_norm": 5.558577060699463, "learning_rate": 5.865259265736158e-06, "loss": 0.5549343824386597, "step": 3291 }, { "epoch": 0.461613966206268, "grad_norm": 2.9214584827423096, "learning_rate": 5.8630228405510215e-06, "loss": 0.6150728464126587, "step": 3292 }, { "epoch": 0.4617541891607656, "grad_norm": 5.4169697761535645, "learning_rate": 5.8607862373901025e-06, "loss": 0.5285992622375488, "step": 3293 }, { "epoch": 0.4618944121152633, "grad_norm": 4.520823955535889, "learning_rate": 5.85854945671464e-06, "loss": 0.5359360575675964, "step": 3294 }, { "epoch": 0.46203463506976095, "grad_norm": 2.807910442352295, "learning_rate": 5.856312498985912e-06, "loss": 0.492079496383667, "step": 3295 }, { "epoch": 0.46217485802425856, "grad_norm": 2.469170331954956, "learning_rate": 5.854075364665234e-06, "loss": 0.5961180925369263, "step": 3296 }, { "epoch": 0.46231508097875623, "grad_norm": 18.775976181030273, "learning_rate": 5.851838054213953e-06, "loss": 0.5003658533096313, "step": 3297 }, { "epoch": 0.46245530393325385, "grad_norm": 6.028514385223389, "learning_rate": 5.849600568093458e-06, "loss": 0.5040505528450012, "step": 3298 }, { "epoch": 0.4625955268877515, "grad_norm": 4.4540863037109375, "learning_rate": 5.847362906765171e-06, "loss": 0.5243048667907715, "step": 3299 }, { "epoch": 0.4627357498422492, "grad_norm": 3.548171043395996, "learning_rate": 5.845125070690552e-06, "loss": 0.5496752262115479, "step": 3300 }, { "epoch": 0.4628759727967468, "grad_norm": 3.744140386581421, "learning_rate": 5.842887060331093e-06, "loss": 0.6685785055160522, "step": 3301 }, { "epoch": 0.4630161957512445, "grad_norm": 5.480810165405273, "learning_rate": 5.840648876148326e-06, "loss": 0.6053890585899353, "step": 3302 }, { "epoch": 0.46315641870574215, "grad_norm": 3.2081098556518555, "learning_rate": 5.838410518603819e-06, "loss": 0.5577733516693115, "step": 3303 }, { "epoch": 0.46329664166023976, "grad_norm": 2.6754043102264404, "learning_rate": 5.836171988159174e-06, "loss": 0.4769775867462158, "step": 3304 }, { "epoch": 0.46343686461473743, "grad_norm": 2.392444610595703, "learning_rate": 5.833933285276029e-06, "loss": 0.532470703125, "step": 3305 }, { "epoch": 0.4635770875692351, "grad_norm": 2.624103307723999, "learning_rate": 5.831694410416058e-06, "loss": 0.47921863198280334, "step": 3306 }, { "epoch": 0.4637173105237327, "grad_norm": 2.0591979026794434, "learning_rate": 5.829455364040968e-06, "loss": 0.48133584856987, "step": 3307 }, { "epoch": 0.4638575334782304, "grad_norm": 2.2164559364318848, "learning_rate": 5.8272161466125046e-06, "loss": 0.46849969029426575, "step": 3308 }, { "epoch": 0.46399775643272806, "grad_norm": 3.089398145675659, "learning_rate": 5.824976758592449e-06, "loss": 0.40475475788116455, "step": 3309 }, { "epoch": 0.4641379793872257, "grad_norm": 2.5754575729370117, "learning_rate": 5.822737200442614e-06, "loss": 0.43435823917388916, "step": 3310 }, { "epoch": 0.46427820234172335, "grad_norm": 2.7565300464630127, "learning_rate": 5.820497472624851e-06, "loss": 0.5895066857337952, "step": 3311 }, { "epoch": 0.464418425296221, "grad_norm": 2.498823881149292, "learning_rate": 5.818257575601045e-06, "loss": 0.6280571222305298, "step": 3312 }, { "epoch": 0.46455864825071863, "grad_norm": 2.7819039821624756, "learning_rate": 5.816017509833116e-06, "loss": 0.5097383260726929, "step": 3313 }, { "epoch": 0.4646988712052163, "grad_norm": 7.301587104797363, "learning_rate": 5.813777275783018e-06, "loss": 0.615916907787323, "step": 3314 }, { "epoch": 0.464839094159714, "grad_norm": 2.118053674697876, "learning_rate": 5.811536873912739e-06, "loss": 0.5410547256469727, "step": 3315 }, { "epoch": 0.4649793171142116, "grad_norm": 3.179215908050537, "learning_rate": 5.8092963046843075e-06, "loss": 0.5038465261459351, "step": 3316 }, { "epoch": 0.46511954006870926, "grad_norm": 2.392676830291748, "learning_rate": 5.8070555685597774e-06, "loss": 0.5729691982269287, "step": 3317 }, { "epoch": 0.4652597630232069, "grad_norm": 2.485208511352539, "learning_rate": 5.804814666001244e-06, "loss": 0.4778088927268982, "step": 3318 }, { "epoch": 0.46539998597770454, "grad_norm": 3.9833929538726807, "learning_rate": 5.802573597470834e-06, "loss": 0.5487377047538757, "step": 3319 }, { "epoch": 0.4655402089322022, "grad_norm": 2.428396701812744, "learning_rate": 5.800332363430709e-06, "loss": 0.5871164798736572, "step": 3320 }, { "epoch": 0.46568043188669983, "grad_norm": 2.7988197803497314, "learning_rate": 5.798090964343064e-06, "loss": 0.5255099534988403, "step": 3321 }, { "epoch": 0.4658206548411975, "grad_norm": 6.909344673156738, "learning_rate": 5.795849400670129e-06, "loss": 0.5582417249679565, "step": 3322 }, { "epoch": 0.46596087779569517, "grad_norm": 2.2095327377319336, "learning_rate": 5.793607672874168e-06, "loss": 0.5336617231369019, "step": 3323 }, { "epoch": 0.4661011007501928, "grad_norm": 2.795055389404297, "learning_rate": 5.791365781417478e-06, "loss": 0.585142195224762, "step": 3324 }, { "epoch": 0.46624132370469046, "grad_norm": 3.524763345718384, "learning_rate": 5.789123726762392e-06, "loss": 0.5887982845306396, "step": 3325 }, { "epoch": 0.46638154665918813, "grad_norm": 2.3727641105651855, "learning_rate": 5.7868815093712725e-06, "loss": 0.5501434803009033, "step": 3326 }, { "epoch": 0.46652176961368574, "grad_norm": 2.9106853008270264, "learning_rate": 5.784639129706518e-06, "loss": 0.6197828054428101, "step": 3327 }, { "epoch": 0.4666619925681834, "grad_norm": 5.802350997924805, "learning_rate": 5.782396588230562e-06, "loss": 0.5141925811767578, "step": 3328 }, { "epoch": 0.4668022155226811, "grad_norm": 5.9573235511779785, "learning_rate": 5.780153885405869e-06, "loss": 0.42281830310821533, "step": 3329 }, { "epoch": 0.4669424384771787, "grad_norm": 2.307579755783081, "learning_rate": 5.777911021694937e-06, "loss": 0.5370204448699951, "step": 3330 }, { "epoch": 0.46708266143167637, "grad_norm": 2.7001171112060547, "learning_rate": 5.775667997560298e-06, "loss": 0.48709553480148315, "step": 3331 }, { "epoch": 0.46722288438617404, "grad_norm": 3.112992286682129, "learning_rate": 5.773424813464518e-06, "loss": 0.5203812718391418, "step": 3332 }, { "epoch": 0.46736310734067166, "grad_norm": 7.367093563079834, "learning_rate": 5.771181469870192e-06, "loss": 0.6159328818321228, "step": 3333 }, { "epoch": 0.46750333029516933, "grad_norm": 4.334322452545166, "learning_rate": 5.768937967239953e-06, "loss": 0.5644435882568359, "step": 3334 }, { "epoch": 0.46764355324966694, "grad_norm": 2.655088424682617, "learning_rate": 5.7666943060364644e-06, "loss": 0.5543255805969238, "step": 3335 }, { "epoch": 0.4677837762041646, "grad_norm": 2.690063953399658, "learning_rate": 5.764450486722421e-06, "loss": 0.5729469060897827, "step": 3336 }, { "epoch": 0.4679239991586623, "grad_norm": 3.40226149559021, "learning_rate": 5.762206509760552e-06, "loss": 0.5215251445770264, "step": 3337 }, { "epoch": 0.4680642221131599, "grad_norm": 3.0585989952087402, "learning_rate": 5.759962375613619e-06, "loss": 0.5103635787963867, "step": 3338 }, { "epoch": 0.46820444506765757, "grad_norm": 2.1079490184783936, "learning_rate": 5.757718084744417e-06, "loss": 0.5542342662811279, "step": 3339 }, { "epoch": 0.46834466802215524, "grad_norm": 2.1433844566345215, "learning_rate": 5.755473637615769e-06, "loss": 0.47481995820999146, "step": 3340 }, { "epoch": 0.46848489097665286, "grad_norm": 4.791419982910156, "learning_rate": 5.753229034690537e-06, "loss": 0.5044695138931274, "step": 3341 }, { "epoch": 0.4686251139311505, "grad_norm": 3.1920809745788574, "learning_rate": 5.750984276431608e-06, "loss": 0.6395910978317261, "step": 3342 }, { "epoch": 0.4687653368856482, "grad_norm": 3.109342575073242, "learning_rate": 5.748739363301905e-06, "loss": 0.5466104745864868, "step": 3343 }, { "epoch": 0.4689055598401458, "grad_norm": 1.9489587545394897, "learning_rate": 5.746494295764385e-06, "loss": 0.518990159034729, "step": 3344 }, { "epoch": 0.4690457827946435, "grad_norm": 2.3944122791290283, "learning_rate": 5.744249074282031e-06, "loss": 0.47134822607040405, "step": 3345 }, { "epoch": 0.46918600574914116, "grad_norm": 2.421592950820923, "learning_rate": 5.742003699317863e-06, "loss": 0.47900956869125366, "step": 3346 }, { "epoch": 0.46932622870363877, "grad_norm": 2.1838059425354004, "learning_rate": 5.739758171334928e-06, "loss": 0.4509202241897583, "step": 3347 }, { "epoch": 0.46946645165813644, "grad_norm": 2.89101505279541, "learning_rate": 5.737512490796312e-06, "loss": 0.5272670388221741, "step": 3348 }, { "epoch": 0.4696066746126341, "grad_norm": 2.349440574645996, "learning_rate": 5.735266658165123e-06, "loss": 0.5360713005065918, "step": 3349 }, { "epoch": 0.4697468975671317, "grad_norm": 2.2262818813323975, "learning_rate": 5.733020673904506e-06, "loss": 0.5680201053619385, "step": 3350 }, { "epoch": 0.4698871205216294, "grad_norm": 3.0024287700653076, "learning_rate": 5.730774538477637e-06, "loss": 0.5264306664466858, "step": 3351 }, { "epoch": 0.47002734347612707, "grad_norm": 2.5534093379974365, "learning_rate": 5.728528252347723e-06, "loss": 0.5445711612701416, "step": 3352 }, { "epoch": 0.4701675664306247, "grad_norm": 3.190485954284668, "learning_rate": 5.726281815977999e-06, "loss": 0.542786717414856, "step": 3353 }, { "epoch": 0.47030778938512235, "grad_norm": 8.61196517944336, "learning_rate": 5.724035229831737e-06, "loss": 0.5371220707893372, "step": 3354 }, { "epoch": 0.47044801233961997, "grad_norm": 5.006650924682617, "learning_rate": 5.721788494372234e-06, "loss": 0.547096848487854, "step": 3355 }, { "epoch": 0.47058823529411764, "grad_norm": 3.7249178886413574, "learning_rate": 5.7195416100628185e-06, "loss": 0.5648584365844727, "step": 3356 }, { "epoch": 0.4707284582486153, "grad_norm": 5.748043060302734, "learning_rate": 5.7172945773668555e-06, "loss": 0.46079277992248535, "step": 3357 }, { "epoch": 0.4708686812031129, "grad_norm": 3.6314315795898438, "learning_rate": 5.715047396747735e-06, "loss": 0.5796060562133789, "step": 3358 }, { "epoch": 0.4710089041576106, "grad_norm": 3.4285099506378174, "learning_rate": 5.712800068668877e-06, "loss": 0.47150444984436035, "step": 3359 }, { "epoch": 0.47114912711210827, "grad_norm": 3.19883394241333, "learning_rate": 5.710552593593735e-06, "loss": 0.5733311176300049, "step": 3360 }, { "epoch": 0.4712893500666059, "grad_norm": 2.378915309906006, "learning_rate": 5.7083049719857934e-06, "loss": 0.5544995069503784, "step": 3361 }, { "epoch": 0.47142957302110355, "grad_norm": 2.330996036529541, "learning_rate": 5.706057204308562e-06, "loss": 0.6044537425041199, "step": 3362 }, { "epoch": 0.4715697959756012, "grad_norm": 2.5460755825042725, "learning_rate": 5.703809291025586e-06, "loss": 0.5040851831436157, "step": 3363 }, { "epoch": 0.47171001893009884, "grad_norm": 3.0764827728271484, "learning_rate": 5.7015612326004385e-06, "loss": 0.523004412651062, "step": 3364 }, { "epoch": 0.4718502418845965, "grad_norm": 8.529685020446777, "learning_rate": 5.699313029496722e-06, "loss": 0.5914118885993958, "step": 3365 }, { "epoch": 0.4719904648390942, "grad_norm": 4.129830837249756, "learning_rate": 5.697064682178067e-06, "loss": 0.5002925395965576, "step": 3366 }, { "epoch": 0.4721306877935918, "grad_norm": 2.616586685180664, "learning_rate": 5.694816191108142e-06, "loss": 0.542635440826416, "step": 3367 }, { "epoch": 0.47227091074808947, "grad_norm": 2.185126304626465, "learning_rate": 5.692567556750632e-06, "loss": 0.5489650964736938, "step": 3368 }, { "epoch": 0.47241113370258714, "grad_norm": 3.5960960388183594, "learning_rate": 5.690318779569263e-06, "loss": 0.6412572264671326, "step": 3369 }, { "epoch": 0.47255135665708475, "grad_norm": 2.4584977626800537, "learning_rate": 5.688069860027786e-06, "loss": 0.6073319315910339, "step": 3370 }, { "epoch": 0.4726915796115824, "grad_norm": 3.689854383468628, "learning_rate": 5.685820798589981e-06, "loss": 0.6465556621551514, "step": 3371 }, { "epoch": 0.4728318025660801, "grad_norm": 2.59491229057312, "learning_rate": 5.683571595719657e-06, "loss": 0.5452029705047607, "step": 3372 }, { "epoch": 0.4729720255205777, "grad_norm": 3.8160667419433594, "learning_rate": 5.681322251880653e-06, "loss": 0.5866860151290894, "step": 3373 }, { "epoch": 0.4731122484750754, "grad_norm": 2.5085885524749756, "learning_rate": 5.67907276753684e-06, "loss": 0.5443798303604126, "step": 3374 }, { "epoch": 0.473252471429573, "grad_norm": 2.7578325271606445, "learning_rate": 5.676823143152111e-06, "loss": 0.521045446395874, "step": 3375 }, { "epoch": 0.47339269438407067, "grad_norm": 3.0415709018707275, "learning_rate": 5.674573379190394e-06, "loss": 0.5216878056526184, "step": 3376 }, { "epoch": 0.47353291733856834, "grad_norm": 3.081460475921631, "learning_rate": 5.672323476115645e-06, "loss": 0.33870434761047363, "step": 3377 }, { "epoch": 0.47367314029306595, "grad_norm": 3.030794382095337, "learning_rate": 5.670073434391844e-06, "loss": 0.4534602165222168, "step": 3378 }, { "epoch": 0.4738133632475636, "grad_norm": 3.1818926334381104, "learning_rate": 5.667823254483006e-06, "loss": 0.5513501167297363, "step": 3379 }, { "epoch": 0.4739535862020613, "grad_norm": 3.8675801753997803, "learning_rate": 5.665572936853169e-06, "loss": 0.615808367729187, "step": 3380 }, { "epoch": 0.4740938091565589, "grad_norm": 4.171962261199951, "learning_rate": 5.663322481966405e-06, "loss": 0.5116972923278809, "step": 3381 }, { "epoch": 0.4742340321110566, "grad_norm": 3.8097193241119385, "learning_rate": 5.661071890286808e-06, "loss": 0.5786520838737488, "step": 3382 }, { "epoch": 0.47437425506555425, "grad_norm": 7.372814655303955, "learning_rate": 5.658821162278506e-06, "loss": 0.5042989253997803, "step": 3383 }, { "epoch": 0.47451447802005187, "grad_norm": 3.7181506156921387, "learning_rate": 5.656570298405651e-06, "loss": 0.6455236673355103, "step": 3384 }, { "epoch": 0.47465470097454954, "grad_norm": 4.8849358558654785, "learning_rate": 5.654319299132423e-06, "loss": 0.501336932182312, "step": 3385 }, { "epoch": 0.4747949239290472, "grad_norm": 3.9714901447296143, "learning_rate": 5.652068164923034e-06, "loss": 0.47968003153800964, "step": 3386 }, { "epoch": 0.4749351468835448, "grad_norm": 3.272336959838867, "learning_rate": 5.649816896241721e-06, "loss": 0.5955873727798462, "step": 3387 }, { "epoch": 0.4750753698380425, "grad_norm": 4.835391044616699, "learning_rate": 5.647565493552748e-06, "loss": 0.6499359011650085, "step": 3388 }, { "epoch": 0.47521559279254016, "grad_norm": 3.721977949142456, "learning_rate": 5.6453139573204085e-06, "loss": 0.5487741827964783, "step": 3389 }, { "epoch": 0.4753558157470378, "grad_norm": 4.103385925292969, "learning_rate": 5.643062288009023e-06, "loss": 0.5478547811508179, "step": 3390 }, { "epoch": 0.47549603870153545, "grad_norm": 2.8256375789642334, "learning_rate": 5.6408104860829385e-06, "loss": 0.5374158024787903, "step": 3391 }, { "epoch": 0.47563626165603307, "grad_norm": 2.450876474380493, "learning_rate": 5.638558552006529e-06, "loss": 0.5015771389007568, "step": 3392 }, { "epoch": 0.47577648461053074, "grad_norm": 2.8116865158081055, "learning_rate": 5.6363064862441985e-06, "loss": 0.514927327632904, "step": 3393 }, { "epoch": 0.4759167075650284, "grad_norm": 3.782074451446533, "learning_rate": 5.634054289260374e-06, "loss": 0.5984890460968018, "step": 3394 }, { "epoch": 0.476056930519526, "grad_norm": 4.066357135772705, "learning_rate": 5.631801961519515e-06, "loss": 0.6658791899681091, "step": 3395 }, { "epoch": 0.4761971534740237, "grad_norm": 2.5208849906921387, "learning_rate": 5.6295495034861035e-06, "loss": 0.5255621671676636, "step": 3396 }, { "epoch": 0.47633737642852136, "grad_norm": 2.996450901031494, "learning_rate": 5.627296915624649e-06, "loss": 0.6348835229873657, "step": 3397 }, { "epoch": 0.476477599383019, "grad_norm": 2.6891582012176514, "learning_rate": 5.625044198399689e-06, "loss": 0.6432143449783325, "step": 3398 }, { "epoch": 0.47661782233751665, "grad_norm": 3.2843048572540283, "learning_rate": 5.6227913522757894e-06, "loss": 0.5340894460678101, "step": 3399 }, { "epoch": 0.4767580452920143, "grad_norm": 2.700248956680298, "learning_rate": 5.620538377717537e-06, "loss": 0.5927181243896484, "step": 3400 }, { "epoch": 0.47689826824651194, "grad_norm": 5.183452129364014, "learning_rate": 5.61828527518955e-06, "loss": 0.4757925271987915, "step": 3401 }, { "epoch": 0.4770384912010096, "grad_norm": 5.6226372718811035, "learning_rate": 5.616032045156472e-06, "loss": 0.5089014768600464, "step": 3402 }, { "epoch": 0.4771787141555073, "grad_norm": 2.886286497116089, "learning_rate": 5.613778688082973e-06, "loss": 0.5977315902709961, "step": 3403 }, { "epoch": 0.4773189371100049, "grad_norm": 3.292715311050415, "learning_rate": 5.611525204433748e-06, "loss": 0.5745714902877808, "step": 3404 }, { "epoch": 0.47745916006450256, "grad_norm": 3.538360834121704, "learning_rate": 5.609271594673517e-06, "loss": 0.5728336572647095, "step": 3405 }, { "epoch": 0.47759938301900023, "grad_norm": 3.3445799350738525, "learning_rate": 5.607017859267032e-06, "loss": 0.5935364961624146, "step": 3406 }, { "epoch": 0.47773960597349785, "grad_norm": 3.6490724086761475, "learning_rate": 5.604763998679062e-06, "loss": 0.4263288676738739, "step": 3407 }, { "epoch": 0.4778798289279955, "grad_norm": 2.9299874305725098, "learning_rate": 5.6025100133744105e-06, "loss": 0.5311236381530762, "step": 3408 }, { "epoch": 0.4780200518824932, "grad_norm": 2.769580602645874, "learning_rate": 5.6002559038179e-06, "loss": 0.5578575730323792, "step": 3409 }, { "epoch": 0.4781602748369908, "grad_norm": 3.0141894817352295, "learning_rate": 5.598001670474383e-06, "loss": 0.5728801488876343, "step": 3410 }, { "epoch": 0.4783004977914885, "grad_norm": 7.068459987640381, "learning_rate": 5.595747313808735e-06, "loss": 0.6072370409965515, "step": 3411 }, { "epoch": 0.4784407207459861, "grad_norm": 2.4444539546966553, "learning_rate": 5.593492834285858e-06, "loss": 0.5369824171066284, "step": 3412 }, { "epoch": 0.47858094370048376, "grad_norm": 3.084153652191162, "learning_rate": 5.591238232370679e-06, "loss": 0.46962934732437134, "step": 3413 }, { "epoch": 0.47872116665498143, "grad_norm": 5.146599769592285, "learning_rate": 5.588983508528152e-06, "loss": 0.4822525680065155, "step": 3414 }, { "epoch": 0.47886138960947905, "grad_norm": 3.113142490386963, "learning_rate": 5.586728663223253e-06, "loss": 0.5375912189483643, "step": 3415 }, { "epoch": 0.4790016125639767, "grad_norm": 3.514064073562622, "learning_rate": 5.584473696920983e-06, "loss": 0.5832316279411316, "step": 3416 }, { "epoch": 0.4791418355184744, "grad_norm": 2.187908887863159, "learning_rate": 5.582218610086373e-06, "loss": 0.5531537532806396, "step": 3417 }, { "epoch": 0.479282058472972, "grad_norm": 2.2000319957733154, "learning_rate": 5.579963403184472e-06, "loss": 0.6333833932876587, "step": 3418 }, { "epoch": 0.4794222814274697, "grad_norm": 2.88374662399292, "learning_rate": 5.5777080766803615e-06, "loss": 0.5105412602424622, "step": 3419 }, { "epoch": 0.47956250438196735, "grad_norm": 3.0420749187469482, "learning_rate": 5.575452631039139e-06, "loss": 0.48815104365348816, "step": 3420 }, { "epoch": 0.47970272733646496, "grad_norm": 3.3619298934936523, "learning_rate": 5.573197066725933e-06, "loss": 0.5291683077812195, "step": 3421 }, { "epoch": 0.47984295029096263, "grad_norm": 3.231994152069092, "learning_rate": 5.570941384205894e-06, "loss": 0.5772398114204407, "step": 3422 }, { "epoch": 0.4799831732454603, "grad_norm": 2.914417266845703, "learning_rate": 5.5686855839441966e-06, "loss": 0.5686842799186707, "step": 3423 }, { "epoch": 0.4801233961999579, "grad_norm": 2.5631487369537354, "learning_rate": 5.566429666406041e-06, "loss": 0.4281037747859955, "step": 3424 }, { "epoch": 0.4802636191544556, "grad_norm": 3.161311626434326, "learning_rate": 5.564173632056653e-06, "loss": 0.5252358317375183, "step": 3425 }, { "epoch": 0.48040384210895326, "grad_norm": 3.613978624343872, "learning_rate": 5.561917481361277e-06, "loss": 0.4971843361854553, "step": 3426 }, { "epoch": 0.4805440650634509, "grad_norm": 2.6804826259613037, "learning_rate": 5.559661214785185e-06, "loss": 0.5346362590789795, "step": 3427 }, { "epoch": 0.48068428801794855, "grad_norm": 3.538666248321533, "learning_rate": 5.557404832793675e-06, "loss": 0.6308689713478088, "step": 3428 }, { "epoch": 0.48082451097244616, "grad_norm": 2.88169002532959, "learning_rate": 5.555148335852065e-06, "loss": 0.5936612486839294, "step": 3429 }, { "epoch": 0.48096473392694383, "grad_norm": 3.5566725730895996, "learning_rate": 5.5528917244256974e-06, "loss": 0.5185191631317139, "step": 3430 }, { "epoch": 0.4811049568814415, "grad_norm": 8.094470024108887, "learning_rate": 5.550634998979942e-06, "loss": 0.5248467922210693, "step": 3431 }, { "epoch": 0.4812451798359391, "grad_norm": 2.6650454998016357, "learning_rate": 5.548378159980187e-06, "loss": 0.5114506483078003, "step": 3432 }, { "epoch": 0.4813854027904368, "grad_norm": 2.4280622005462646, "learning_rate": 5.546121207891845e-06, "loss": 0.6401200890541077, "step": 3433 }, { "epoch": 0.48152562574493446, "grad_norm": 2.9095799922943115, "learning_rate": 5.543864143180354e-06, "loss": 0.49254027009010315, "step": 3434 }, { "epoch": 0.4816658486994321, "grad_norm": 4.355474472045898, "learning_rate": 5.541606966311177e-06, "loss": 0.4708317518234253, "step": 3435 }, { "epoch": 0.48180607165392975, "grad_norm": 3.9075214862823486, "learning_rate": 5.539349677749794e-06, "loss": 0.5223392844200134, "step": 3436 }, { "epoch": 0.4819462946084274, "grad_norm": 2.1646535396575928, "learning_rate": 5.537092277961711e-06, "loss": 0.4866310656070709, "step": 3437 }, { "epoch": 0.48208651756292503, "grad_norm": 1.9226429462432861, "learning_rate": 5.534834767412461e-06, "loss": 0.5658246278762817, "step": 3438 }, { "epoch": 0.4822267405174227, "grad_norm": 2.804408311843872, "learning_rate": 5.5325771465675935e-06, "loss": 0.5530281066894531, "step": 3439 }, { "epoch": 0.4823669634719204, "grad_norm": 2.462477445602417, "learning_rate": 5.530319415892685e-06, "loss": 0.48126232624053955, "step": 3440 }, { "epoch": 0.482507186426418, "grad_norm": 3.565438747406006, "learning_rate": 5.528061575853332e-06, "loss": 0.49888044595718384, "step": 3441 }, { "epoch": 0.48264740938091566, "grad_norm": 2.7775306701660156, "learning_rate": 5.525803626915154e-06, "loss": 0.5930436849594116, "step": 3442 }, { "epoch": 0.48278763233541333, "grad_norm": 5.453760623931885, "learning_rate": 5.5235455695437945e-06, "loss": 0.629270613193512, "step": 3443 }, { "epoch": 0.48292785528991095, "grad_norm": 4.609071254730225, "learning_rate": 5.521287404204919e-06, "loss": 0.4849281311035156, "step": 3444 }, { "epoch": 0.4830680782444086, "grad_norm": 4.515076637268066, "learning_rate": 5.519029131364216e-06, "loss": 0.5986279249191284, "step": 3445 }, { "epoch": 0.4832083011989063, "grad_norm": 2.149118185043335, "learning_rate": 5.51677075148739e-06, "loss": 0.5851472616195679, "step": 3446 }, { "epoch": 0.4833485241534039, "grad_norm": 4.536550045013428, "learning_rate": 5.514512265040178e-06, "loss": 0.6338785290718079, "step": 3447 }, { "epoch": 0.4834887471079016, "grad_norm": 5.740521430969238, "learning_rate": 5.512253672488332e-06, "loss": 0.6623026728630066, "step": 3448 }, { "epoch": 0.4836289700623992, "grad_norm": 62.298255920410156, "learning_rate": 5.509994974297624e-06, "loss": 0.6296586990356445, "step": 3449 }, { "epoch": 0.48376919301689686, "grad_norm": 3.5955138206481934, "learning_rate": 5.507736170933856e-06, "loss": 0.5934607982635498, "step": 3450 }, { "epoch": 0.48390941597139453, "grad_norm": 3.999295473098755, "learning_rate": 5.505477262862845e-06, "loss": 0.5646607279777527, "step": 3451 }, { "epoch": 0.48404963892589215, "grad_norm": 4.607468605041504, "learning_rate": 5.503218250550429e-06, "loss": 0.53510981798172, "step": 3452 }, { "epoch": 0.4841898618803898, "grad_norm": 3.3198838233947754, "learning_rate": 5.500959134462474e-06, "loss": 0.5457161664962769, "step": 3453 }, { "epoch": 0.4843300848348875, "grad_norm": 4.2242350578308105, "learning_rate": 5.498699915064859e-06, "loss": 0.6268332004547119, "step": 3454 }, { "epoch": 0.4844703077893851, "grad_norm": 3.6489338874816895, "learning_rate": 5.496440592823493e-06, "loss": 0.5808915495872498, "step": 3455 }, { "epoch": 0.4846105307438828, "grad_norm": 3.512115955352783, "learning_rate": 5.4941811682042986e-06, "loss": 0.4815046489238739, "step": 3456 }, { "epoch": 0.48475075369838044, "grad_norm": 3.0997726917266846, "learning_rate": 5.491921641673224e-06, "loss": 0.5919495224952698, "step": 3457 }, { "epoch": 0.48489097665287806, "grad_norm": 3.1493563652038574, "learning_rate": 5.4896620136962385e-06, "loss": 0.6084730625152588, "step": 3458 }, { "epoch": 0.48503119960737573, "grad_norm": 2.741182565689087, "learning_rate": 5.487402284739328e-06, "loss": 0.4845924377441406, "step": 3459 }, { "epoch": 0.4851714225618734, "grad_norm": 2.96803879737854, "learning_rate": 5.485142455268505e-06, "loss": 0.6155170202255249, "step": 3460 }, { "epoch": 0.485311645516371, "grad_norm": 3.1537537574768066, "learning_rate": 5.482882525749798e-06, "loss": 0.5747175216674805, "step": 3461 }, { "epoch": 0.4854518684708687, "grad_norm": 2.4072930812835693, "learning_rate": 5.480622496649261e-06, "loss": 0.555142879486084, "step": 3462 }, { "epoch": 0.48559209142536636, "grad_norm": 3.2408409118652344, "learning_rate": 5.47836236843296e-06, "loss": 0.61576247215271, "step": 3463 }, { "epoch": 0.48573231437986397, "grad_norm": 4.2219438552856445, "learning_rate": 5.476102141566992e-06, "loss": 0.5073624849319458, "step": 3464 }, { "epoch": 0.48587253733436164, "grad_norm": 5.221927642822266, "learning_rate": 5.473841816517469e-06, "loss": 0.49984151124954224, "step": 3465 }, { "epoch": 0.4860127602888593, "grad_norm": 2.386718988418579, "learning_rate": 5.471581393750521e-06, "loss": 0.4226810932159424, "step": 3466 }, { "epoch": 0.48615298324335693, "grad_norm": 2.329554319381714, "learning_rate": 5.469320873732303e-06, "loss": 0.5503454208374023, "step": 3467 }, { "epoch": 0.4862932061978546, "grad_norm": 5.016707897186279, "learning_rate": 5.467060256928989e-06, "loss": 0.4914860725402832, "step": 3468 }, { "epoch": 0.4864334291523522, "grad_norm": 2.3401572704315186, "learning_rate": 5.464799543806768e-06, "loss": 0.5403796434402466, "step": 3469 }, { "epoch": 0.4865736521068499, "grad_norm": 2.98590087890625, "learning_rate": 5.462538734831855e-06, "loss": 0.4735472500324249, "step": 3470 }, { "epoch": 0.48671387506134756, "grad_norm": 3.219735860824585, "learning_rate": 5.460277830470483e-06, "loss": 0.42735347151756287, "step": 3471 }, { "epoch": 0.48685409801584517, "grad_norm": 3.721874237060547, "learning_rate": 5.458016831188902e-06, "loss": 0.5758829712867737, "step": 3472 }, { "epoch": 0.48699432097034284, "grad_norm": 2.7455670833587646, "learning_rate": 5.455755737453386e-06, "loss": 0.6286144256591797, "step": 3473 }, { "epoch": 0.4871345439248405, "grad_norm": 2.5463316440582275, "learning_rate": 5.453494549730224e-06, "loss": 0.6094178557395935, "step": 3474 }, { "epoch": 0.48727476687933813, "grad_norm": 4.569071292877197, "learning_rate": 5.451233268485728e-06, "loss": 0.5742272138595581, "step": 3475 }, { "epoch": 0.4874149898338358, "grad_norm": 3.0636439323425293, "learning_rate": 5.4489718941862276e-06, "loss": 0.5116424560546875, "step": 3476 }, { "epoch": 0.48755521278833347, "grad_norm": 3.762016534805298, "learning_rate": 5.446710427298072e-06, "loss": 0.4608096778392792, "step": 3477 }, { "epoch": 0.4876954357428311, "grad_norm": 5.170289516448975, "learning_rate": 5.444448868287631e-06, "loss": 0.5270265340805054, "step": 3478 }, { "epoch": 0.48783565869732876, "grad_norm": 4.160218238830566, "learning_rate": 5.442187217621287e-06, "loss": 0.5740556716918945, "step": 3479 }, { "epoch": 0.4879758816518264, "grad_norm": 3.7230629920959473, "learning_rate": 5.43992547576545e-06, "loss": 0.5388238430023193, "step": 3480 }, { "epoch": 0.48811610460632404, "grad_norm": 3.107820749282837, "learning_rate": 5.437663643186544e-06, "loss": 0.6365622878074646, "step": 3481 }, { "epoch": 0.4882563275608217, "grad_norm": 2.5714519023895264, "learning_rate": 5.435401720351011e-06, "loss": 0.6630539894104004, "step": 3482 }, { "epoch": 0.4883965505153194, "grad_norm": 3.234511613845825, "learning_rate": 5.433139707725314e-06, "loss": 0.590181827545166, "step": 3483 }, { "epoch": 0.488536773469817, "grad_norm": 3.523256540298462, "learning_rate": 5.430877605775935e-06, "loss": 0.6370213031768799, "step": 3484 }, { "epoch": 0.48867699642431467, "grad_norm": 3.393094778060913, "learning_rate": 5.428615414969373e-06, "loss": 0.5637320876121521, "step": 3485 }, { "epoch": 0.4888172193788123, "grad_norm": 3.1190598011016846, "learning_rate": 5.426353135772142e-06, "loss": 0.46810850501060486, "step": 3486 }, { "epoch": 0.48895744233330996, "grad_norm": 3.60630464553833, "learning_rate": 5.424090768650781e-06, "loss": 0.49503952264785767, "step": 3487 }, { "epoch": 0.4890976652878076, "grad_norm": 3.7076966762542725, "learning_rate": 5.421828314071846e-06, "loss": 0.4668772220611572, "step": 3488 }, { "epoch": 0.48923788824230524, "grad_norm": 3.6603918075561523, "learning_rate": 5.4195657725019014e-06, "loss": 0.5848541259765625, "step": 3489 }, { "epoch": 0.4893781111968029, "grad_norm": 2.1661927700042725, "learning_rate": 5.417303144407543e-06, "loss": 0.5404214859008789, "step": 3490 }, { "epoch": 0.4895183341513006, "grad_norm": 7.561669826507568, "learning_rate": 5.415040430255377e-06, "loss": 0.6168785095214844, "step": 3491 }, { "epoch": 0.4896585571057982, "grad_norm": 4.8452653884887695, "learning_rate": 5.412777630512027e-06, "loss": 0.588129997253418, "step": 3492 }, { "epoch": 0.48979878006029587, "grad_norm": 7.27083158493042, "learning_rate": 5.410514745644139e-06, "loss": 0.6019154787063599, "step": 3493 }, { "epoch": 0.48993900301479354, "grad_norm": 3.679589033126831, "learning_rate": 5.40825177611837e-06, "loss": 0.5630179643630981, "step": 3494 }, { "epoch": 0.49007922596929115, "grad_norm": 2.930161237716675, "learning_rate": 5.405988722401402e-06, "loss": 0.6172170639038086, "step": 3495 }, { "epoch": 0.4902194489237888, "grad_norm": 2.714735984802246, "learning_rate": 5.4037255849599264e-06, "loss": 0.5561268329620361, "step": 3496 }, { "epoch": 0.4903596718782865, "grad_norm": 3.8611204624176025, "learning_rate": 5.401462364260659e-06, "loss": 0.5766425728797913, "step": 3497 }, { "epoch": 0.4904998948327841, "grad_norm": 2.6170430183410645, "learning_rate": 5.399199060770329e-06, "loss": 0.5176615715026855, "step": 3498 }, { "epoch": 0.4906401177872818, "grad_norm": 3.873494863510132, "learning_rate": 5.396935674955681e-06, "loss": 0.47409194707870483, "step": 3499 }, { "epoch": 0.49078034074177945, "grad_norm": 3.968672513961792, "learning_rate": 5.39467220728348e-06, "loss": 0.4691679775714874, "step": 3500 }, { "epoch": 0.49092056369627707, "grad_norm": 2.5851926803588867, "learning_rate": 5.392408658220509e-06, "loss": 0.5671929717063904, "step": 3501 }, { "epoch": 0.49106078665077474, "grad_norm": 2.52774715423584, "learning_rate": 5.390145028233562e-06, "loss": 0.5464626550674438, "step": 3502 }, { "epoch": 0.4912010096052724, "grad_norm": 3.073594093322754, "learning_rate": 5.3878813177894555e-06, "loss": 0.5555014610290527, "step": 3503 }, { "epoch": 0.49134123255977, "grad_norm": 3.225252866744995, "learning_rate": 5.385617527355019e-06, "loss": 0.5710293650627136, "step": 3504 }, { "epoch": 0.4914814555142677, "grad_norm": 2.981015205383301, "learning_rate": 5.3833536573971025e-06, "loss": 0.5261827111244202, "step": 3505 }, { "epoch": 0.4916216784687653, "grad_norm": 4.002236843109131, "learning_rate": 5.381089708382565e-06, "loss": 0.48769474029541016, "step": 3506 }, { "epoch": 0.491761901423263, "grad_norm": 4.706636905670166, "learning_rate": 5.37882568077829e-06, "loss": 0.4325321614742279, "step": 3507 }, { "epoch": 0.49190212437776065, "grad_norm": 2.957744836807251, "learning_rate": 5.376561575051174e-06, "loss": 0.46771347522735596, "step": 3508 }, { "epoch": 0.49204234733225827, "grad_norm": 3.5743231773376465, "learning_rate": 5.374297391668128e-06, "loss": 0.5182493329048157, "step": 3509 }, { "epoch": 0.49218257028675594, "grad_norm": 2.636183738708496, "learning_rate": 5.3720331310960785e-06, "loss": 0.6368813514709473, "step": 3510 }, { "epoch": 0.4923227932412536, "grad_norm": 2.4213104248046875, "learning_rate": 5.369768793801973e-06, "loss": 0.5550711154937744, "step": 3511 }, { "epoch": 0.4924630161957512, "grad_norm": 3.5292303562164307, "learning_rate": 5.367504380252771e-06, "loss": 0.4383684992790222, "step": 3512 }, { "epoch": 0.4926032391502489, "grad_norm": 3.2394676208496094, "learning_rate": 5.365239890915446e-06, "loss": 0.3847264051437378, "step": 3513 }, { "epoch": 0.49274346210474657, "grad_norm": 3.1068522930145264, "learning_rate": 5.3629753262569904e-06, "loss": 0.5526134967803955, "step": 3514 }, { "epoch": 0.4928836850592442, "grad_norm": 9.698113441467285, "learning_rate": 5.360710686744415e-06, "loss": 0.5382425785064697, "step": 3515 }, { "epoch": 0.49302390801374185, "grad_norm": 3.056515693664551, "learning_rate": 5.3584459728447355e-06, "loss": 0.5467870831489563, "step": 3516 }, { "epoch": 0.4931641309682395, "grad_norm": 4.0215349197387695, "learning_rate": 5.3561811850249946e-06, "loss": 0.43974190950393677, "step": 3517 }, { "epoch": 0.49330435392273714, "grad_norm": 2.428812265396118, "learning_rate": 5.353916323752244e-06, "loss": 0.517941415309906, "step": 3518 }, { "epoch": 0.4934445768772348, "grad_norm": 3.171321392059326, "learning_rate": 5.351651389493551e-06, "loss": 0.5384202003479004, "step": 3519 }, { "epoch": 0.4935847998317325, "grad_norm": 3.246717929840088, "learning_rate": 5.349386382715999e-06, "loss": 0.47524046897888184, "step": 3520 }, { "epoch": 0.4937250227862301, "grad_norm": 4.685812473297119, "learning_rate": 5.3471213038866875e-06, "loss": 0.5543175935745239, "step": 3521 }, { "epoch": 0.49386524574072777, "grad_norm": 4.676193714141846, "learning_rate": 5.344856153472728e-06, "loss": 0.5303888320922852, "step": 3522 }, { "epoch": 0.49400546869522544, "grad_norm": 3.3659605979919434, "learning_rate": 5.342590931941248e-06, "loss": 0.4718972444534302, "step": 3523 }, { "epoch": 0.49414569164972305, "grad_norm": 3.1633198261260986, "learning_rate": 5.340325639759392e-06, "loss": 0.5650017857551575, "step": 3524 }, { "epoch": 0.4942859146042207, "grad_norm": 2.7735161781311035, "learning_rate": 5.338060277394315e-06, "loss": 0.4801527261734009, "step": 3525 }, { "epoch": 0.49442613755871834, "grad_norm": 2.767176866531372, "learning_rate": 5.335794845313189e-06, "loss": 0.47618597745895386, "step": 3526 }, { "epoch": 0.494566360513216, "grad_norm": 9.182343482971191, "learning_rate": 5.3335293439831995e-06, "loss": 0.4596446752548218, "step": 3527 }, { "epoch": 0.4947065834677137, "grad_norm": 5.319775104522705, "learning_rate": 5.331263773871548e-06, "loss": 0.6042392253875732, "step": 3528 }, { "epoch": 0.4948468064222113, "grad_norm": 3.1970789432525635, "learning_rate": 5.328998135445447e-06, "loss": 0.5992150902748108, "step": 3529 }, { "epoch": 0.49498702937670896, "grad_norm": 3.6407504081726074, "learning_rate": 5.3267324291721255e-06, "loss": 0.5390957593917847, "step": 3530 }, { "epoch": 0.49512725233120664, "grad_norm": 2.9542887210845947, "learning_rate": 5.3244666555188274e-06, "loss": 0.5035862922668457, "step": 3531 }, { "epoch": 0.49526747528570425, "grad_norm": 2.837972402572632, "learning_rate": 5.322200814952806e-06, "loss": 0.49909618496894836, "step": 3532 }, { "epoch": 0.4954076982402019, "grad_norm": 5.26007604598999, "learning_rate": 5.319934907941334e-06, "loss": 0.5694602727890015, "step": 3533 }, { "epoch": 0.4955479211946996, "grad_norm": 2.1661620140075684, "learning_rate": 5.317668934951693e-06, "loss": 0.481794536113739, "step": 3534 }, { "epoch": 0.4956881441491972, "grad_norm": 2.9458653926849365, "learning_rate": 5.315402896451184e-06, "loss": 0.525997519493103, "step": 3535 }, { "epoch": 0.4958283671036949, "grad_norm": 2.3085508346557617, "learning_rate": 5.313136792907114e-06, "loss": 0.547813355922699, "step": 3536 }, { "epoch": 0.49596859005819255, "grad_norm": 3.389497995376587, "learning_rate": 5.310870624786808e-06, "loss": 0.5620183944702148, "step": 3537 }, { "epoch": 0.49610881301269016, "grad_norm": 4.837990760803223, "learning_rate": 5.308604392557607e-06, "loss": 0.5687397122383118, "step": 3538 }, { "epoch": 0.49624903596718783, "grad_norm": 4.794081687927246, "learning_rate": 5.306338096686857e-06, "loss": 0.4844859540462494, "step": 3539 }, { "epoch": 0.4963892589216855, "grad_norm": 3.591200590133667, "learning_rate": 5.304071737641925e-06, "loss": 0.5106865763664246, "step": 3540 }, { "epoch": 0.4965294818761831, "grad_norm": 7.232281684875488, "learning_rate": 5.301805315890188e-06, "loss": 0.5991016626358032, "step": 3541 }, { "epoch": 0.4966697048306808, "grad_norm": 5.405261039733887, "learning_rate": 5.299538831899034e-06, "loss": 0.5870119333267212, "step": 3542 }, { "epoch": 0.4968099277851784, "grad_norm": 2.2735989093780518, "learning_rate": 5.297272286135867e-06, "loss": 0.5186420679092407, "step": 3543 }, { "epoch": 0.4969501507396761, "grad_norm": 2.3885715007781982, "learning_rate": 5.295005679068104e-06, "loss": 0.518174946308136, "step": 3544 }, { "epoch": 0.49709037369417375, "grad_norm": 5.1536383628845215, "learning_rate": 5.29273901116317e-06, "loss": 0.49973708391189575, "step": 3545 }, { "epoch": 0.49723059664867136, "grad_norm": 3.4379591941833496, "learning_rate": 5.290472282888508e-06, "loss": 0.4535330533981323, "step": 3546 }, { "epoch": 0.49737081960316903, "grad_norm": 4.588001251220703, "learning_rate": 5.2882054947115715e-06, "loss": 0.6421265602111816, "step": 3547 }, { "epoch": 0.4975110425576667, "grad_norm": 2.61749005317688, "learning_rate": 5.2859386470998234e-06, "loss": 0.6085027456283569, "step": 3548 }, { "epoch": 0.4976512655121643, "grad_norm": 2.757476329803467, "learning_rate": 5.283671740520743e-06, "loss": 0.4647136628627777, "step": 3549 }, { "epoch": 0.497791488466662, "grad_norm": 2.8271608352661133, "learning_rate": 5.28140477544182e-06, "loss": 0.6293727159500122, "step": 3550 }, { "epoch": 0.49793171142115966, "grad_norm": 5.576119899749756, "learning_rate": 5.279137752330558e-06, "loss": 0.5071172714233398, "step": 3551 }, { "epoch": 0.4980719343756573, "grad_norm": 2.742280960083008, "learning_rate": 5.276870671654468e-06, "loss": 0.4798717498779297, "step": 3552 }, { "epoch": 0.49821215733015495, "grad_norm": 3.3777260780334473, "learning_rate": 5.274603533881077e-06, "loss": 0.5615049600601196, "step": 3553 }, { "epoch": 0.4983523802846526, "grad_norm": 3.1075096130371094, "learning_rate": 5.272336339477926e-06, "loss": 0.4245270788669586, "step": 3554 }, { "epoch": 0.49849260323915023, "grad_norm": 2.9011929035186768, "learning_rate": 5.270069088912558e-06, "loss": 0.6365458965301514, "step": 3555 }, { "epoch": 0.4986328261936479, "grad_norm": 4.260005474090576, "learning_rate": 5.267801782652539e-06, "loss": 0.5128562450408936, "step": 3556 }, { "epoch": 0.4987730491481456, "grad_norm": 3.3416428565979004, "learning_rate": 5.265534421165439e-06, "loss": 0.5206050276756287, "step": 3557 }, { "epoch": 0.4989132721026432, "grad_norm": 3.301579475402832, "learning_rate": 5.263267004918842e-06, "loss": 0.47926098108291626, "step": 3558 }, { "epoch": 0.49905349505714086, "grad_norm": 4.022603988647461, "learning_rate": 5.260999534380342e-06, "loss": 0.5495815873146057, "step": 3559 }, { "epoch": 0.49919371801163853, "grad_norm": 2.3686702251434326, "learning_rate": 5.258732010017549e-06, "loss": 0.6317217350006104, "step": 3560 }, { "epoch": 0.49933394096613615, "grad_norm": 3.8692407608032227, "learning_rate": 5.256464432298075e-06, "loss": 0.5120224356651306, "step": 3561 }, { "epoch": 0.4994741639206338, "grad_norm": 4.242550849914551, "learning_rate": 5.254196801689552e-06, "loss": 0.4812697172164917, "step": 3562 }, { "epoch": 0.49961438687513143, "grad_norm": 3.4382381439208984, "learning_rate": 5.251929118659619e-06, "loss": 0.47671371698379517, "step": 3563 }, { "epoch": 0.4997546098296291, "grad_norm": 3.919851541519165, "learning_rate": 5.249661383675925e-06, "loss": 0.5947443246841431, "step": 3564 }, { "epoch": 0.4998948327841268, "grad_norm": 3.4946963787078857, "learning_rate": 5.24739359720613e-06, "loss": 0.5271642208099365, "step": 3565 }, { "epoch": 0.5000350557386244, "grad_norm": 4.9032487869262695, "learning_rate": 5.245125759717906e-06, "loss": 0.5218577980995178, "step": 3566 }, { "epoch": 0.5001752786931221, "grad_norm": 3.8659305572509766, "learning_rate": 5.242857871678937e-06, "loss": 0.625085175037384, "step": 3567 }, { "epoch": 0.5003155016476197, "grad_norm": 2.241881847381592, "learning_rate": 5.240589933556913e-06, "loss": 0.5918024778366089, "step": 3568 }, { "epoch": 0.5004557246021174, "grad_norm": 3.0291566848754883, "learning_rate": 5.238321945819536e-06, "loss": 0.5543572306632996, "step": 3569 }, { "epoch": 0.5005959475566151, "grad_norm": 5.211453437805176, "learning_rate": 5.236053908934523e-06, "loss": 0.5661112666130066, "step": 3570 }, { "epoch": 0.5007361705111126, "grad_norm": 30.626300811767578, "learning_rate": 5.2337858233695915e-06, "loss": 0.4580410122871399, "step": 3571 }, { "epoch": 0.5008763934656103, "grad_norm": 3.182311773300171, "learning_rate": 5.231517689592478e-06, "loss": 0.5171205401420593, "step": 3572 }, { "epoch": 0.501016616420108, "grad_norm": 3.3426146507263184, "learning_rate": 5.229249508070925e-06, "loss": 0.4504472017288208, "step": 3573 }, { "epoch": 0.5011568393746056, "grad_norm": 2.710838556289673, "learning_rate": 5.226981279272685e-06, "loss": 0.5679863691329956, "step": 3574 }, { "epoch": 0.5012970623291033, "grad_norm": 2.5973198413848877, "learning_rate": 5.224713003665519e-06, "loss": 0.5489882230758667, "step": 3575 }, { "epoch": 0.5014372852836009, "grad_norm": 3.458306312561035, "learning_rate": 5.222444681717204e-06, "loss": 0.5251597166061401, "step": 3576 }, { "epoch": 0.5015775082380985, "grad_norm": 2.7475428581237793, "learning_rate": 5.220176313895515e-06, "loss": 0.44737035036087036, "step": 3577 }, { "epoch": 0.5017177311925962, "grad_norm": 3.4619860649108887, "learning_rate": 5.217907900668249e-06, "loss": 0.39001336693763733, "step": 3578 }, { "epoch": 0.5018579541470939, "grad_norm": 3.4407174587249756, "learning_rate": 5.215639442503204e-06, "loss": 0.49299055337905884, "step": 3579 }, { "epoch": 0.5019981771015916, "grad_norm": 7.4412384033203125, "learning_rate": 5.213370939868191e-06, "loss": 0.5976066589355469, "step": 3580 }, { "epoch": 0.5021384000560892, "grad_norm": 3.073831796646118, "learning_rate": 5.211102393231028e-06, "loss": 0.5315659046173096, "step": 3581 }, { "epoch": 0.5022786230105868, "grad_norm": 3.4106266498565674, "learning_rate": 5.208833803059543e-06, "loss": 0.5173953771591187, "step": 3582 }, { "epoch": 0.5024188459650845, "grad_norm": 4.101779460906982, "learning_rate": 5.206565169821575e-06, "loss": 0.3911561965942383, "step": 3583 }, { "epoch": 0.5025590689195821, "grad_norm": 3.98795485496521, "learning_rate": 5.204296493984967e-06, "loss": 0.5372927188873291, "step": 3584 }, { "epoch": 0.5026992918740798, "grad_norm": 5.501819610595703, "learning_rate": 5.202027776017576e-06, "loss": 0.5001295804977417, "step": 3585 }, { "epoch": 0.5028395148285775, "grad_norm": 2.7329306602478027, "learning_rate": 5.199759016387266e-06, "loss": 0.6431818008422852, "step": 3586 }, { "epoch": 0.5029797377830751, "grad_norm": 4.89323616027832, "learning_rate": 5.197490215561907e-06, "loss": 0.48675966262817383, "step": 3587 }, { "epoch": 0.5031199607375727, "grad_norm": 3.431684970855713, "learning_rate": 5.1952213740093805e-06, "loss": 0.5824066400527954, "step": 3588 }, { "epoch": 0.5032601836920704, "grad_norm": 2.6844139099121094, "learning_rate": 5.192952492197576e-06, "loss": 0.48458921909332275, "step": 3589 }, { "epoch": 0.503400406646568, "grad_norm": 2.797541379928589, "learning_rate": 5.190683570594391e-06, "loss": 0.6116284132003784, "step": 3590 }, { "epoch": 0.5035406296010657, "grad_norm": 3.1882541179656982, "learning_rate": 5.188414609667728e-06, "loss": 0.4336688220500946, "step": 3591 }, { "epoch": 0.5036808525555634, "grad_norm": 3.6767516136169434, "learning_rate": 5.186145609885504e-06, "loss": 0.5456889271736145, "step": 3592 }, { "epoch": 0.503821075510061, "grad_norm": 3.424447536468506, "learning_rate": 5.183876571715639e-06, "loss": 0.5944780111312866, "step": 3593 }, { "epoch": 0.5039612984645586, "grad_norm": 11.03213119506836, "learning_rate": 5.1816074956260635e-06, "loss": 0.498481422662735, "step": 3594 }, { "epoch": 0.5041015214190563, "grad_norm": 3.6725351810455322, "learning_rate": 5.179338382084713e-06, "loss": 0.5511093139648438, "step": 3595 }, { "epoch": 0.504241744373554, "grad_norm": 6.824275493621826, "learning_rate": 5.177069231559535e-06, "loss": 0.47483503818511963, "step": 3596 }, { "epoch": 0.5043819673280516, "grad_norm": 2.9235141277313232, "learning_rate": 5.174800044518481e-06, "loss": 0.5823057889938354, "step": 3597 }, { "epoch": 0.5045221902825493, "grad_norm": 7.19901180267334, "learning_rate": 5.17253082142951e-06, "loss": 0.5207857489585876, "step": 3598 }, { "epoch": 0.5046624132370469, "grad_norm": 3.2509818077087402, "learning_rate": 5.170261562760591e-06, "loss": 0.4908679127693176, "step": 3599 }, { "epoch": 0.5048026361915445, "grad_norm": 7.610043048858643, "learning_rate": 5.167992268979699e-06, "loss": 0.4810851812362671, "step": 3600 }, { "epoch": 0.5049428591460422, "grad_norm": 2.8051114082336426, "learning_rate": 5.165722940554816e-06, "loss": 0.5214753150939941, "step": 3601 }, { "epoch": 0.5050830821005399, "grad_norm": 3.928828716278076, "learning_rate": 5.1634535779539305e-06, "loss": 0.5902148485183716, "step": 3602 }, { "epoch": 0.5052233050550375, "grad_norm": 4.114367485046387, "learning_rate": 5.16118418164504e-06, "loss": 0.4589209258556366, "step": 3603 }, { "epoch": 0.5053635280095352, "grad_norm": 3.027512550354004, "learning_rate": 5.158914752096148e-06, "loss": 0.4590907394886017, "step": 3604 }, { "epoch": 0.5055037509640328, "grad_norm": 3.2813045978546143, "learning_rate": 5.156645289775264e-06, "loss": 0.5394842028617859, "step": 3605 }, { "epoch": 0.5056439739185304, "grad_norm": 3.4215383529663086, "learning_rate": 5.154375795150405e-06, "loss": 0.5612068176269531, "step": 3606 }, { "epoch": 0.5057841968730281, "grad_norm": 3.0526814460754395, "learning_rate": 5.152106268689594e-06, "loss": 0.5290998220443726, "step": 3607 }, { "epoch": 0.5059244198275258, "grad_norm": 4.814601898193359, "learning_rate": 5.149836710860863e-06, "loss": 0.4909627139568329, "step": 3608 }, { "epoch": 0.5060646427820235, "grad_norm": 3.249068260192871, "learning_rate": 5.1475671221322485e-06, "loss": 0.5244923830032349, "step": 3609 }, { "epoch": 0.506204865736521, "grad_norm": 3.618401527404785, "learning_rate": 5.145297502971791e-06, "loss": 0.6248087286949158, "step": 3610 }, { "epoch": 0.5063450886910187, "grad_norm": 4.817678451538086, "learning_rate": 5.143027853847542e-06, "loss": 0.5531713962554932, "step": 3611 }, { "epoch": 0.5064853116455164, "grad_norm": 4.092517375946045, "learning_rate": 5.140758175227558e-06, "loss": 0.5762373208999634, "step": 3612 }, { "epoch": 0.506625534600014, "grad_norm": 3.8135476112365723, "learning_rate": 5.138488467579897e-06, "loss": 0.6525311470031738, "step": 3613 }, { "epoch": 0.5067657575545117, "grad_norm": 3.9004745483398438, "learning_rate": 5.13621873137263e-06, "loss": 0.5762865543365479, "step": 3614 }, { "epoch": 0.5069059805090094, "grad_norm": 4.127754211425781, "learning_rate": 5.133948967073829e-06, "loss": 0.5600019097328186, "step": 3615 }, { "epoch": 0.5070462034635069, "grad_norm": 3.6435420513153076, "learning_rate": 5.131679175151573e-06, "loss": 0.599605917930603, "step": 3616 }, { "epoch": 0.5071864264180046, "grad_norm": 3.5917177200317383, "learning_rate": 5.129409356073947e-06, "loss": 0.48172956705093384, "step": 3617 }, { "epoch": 0.5073266493725023, "grad_norm": 2.283062696456909, "learning_rate": 5.127139510309042e-06, "loss": 0.5925426483154297, "step": 3618 }, { "epoch": 0.5074668723269999, "grad_norm": 3.2242751121520996, "learning_rate": 5.124869638324954e-06, "loss": 0.6101581454277039, "step": 3619 }, { "epoch": 0.5076070952814976, "grad_norm": 2.8007335662841797, "learning_rate": 5.122599740589783e-06, "loss": 0.5667365789413452, "step": 3620 }, { "epoch": 0.5077473182359953, "grad_norm": 2.8464884757995605, "learning_rate": 5.12032981757164e-06, "loss": 0.5155741572380066, "step": 3621 }, { "epoch": 0.5078875411904928, "grad_norm": 5.485379219055176, "learning_rate": 5.1180598697386315e-06, "loss": 0.513578474521637, "step": 3622 }, { "epoch": 0.5080277641449905, "grad_norm": 3.3815994262695312, "learning_rate": 5.1157898975588786e-06, "loss": 0.5715720653533936, "step": 3623 }, { "epoch": 0.5081679870994882, "grad_norm": 3.3948934078216553, "learning_rate": 5.1135199015005e-06, "loss": 0.46590742468833923, "step": 3624 }, { "epoch": 0.5083082100539859, "grad_norm": 2.2028095722198486, "learning_rate": 5.111249882031627e-06, "loss": 0.5261805057525635, "step": 3625 }, { "epoch": 0.5084484330084835, "grad_norm": 3.0671603679656982, "learning_rate": 5.108979839620388e-06, "loss": 0.5266134738922119, "step": 3626 }, { "epoch": 0.5085886559629812, "grad_norm": 3.3493387699127197, "learning_rate": 5.106709774734921e-06, "loss": 0.5355098843574524, "step": 3627 }, { "epoch": 0.5087288789174788, "grad_norm": 2.7904815673828125, "learning_rate": 5.104439687843368e-06, "loss": 0.5026538372039795, "step": 3628 }, { "epoch": 0.5088691018719764, "grad_norm": 2.7796523571014404, "learning_rate": 5.102169579413873e-06, "loss": 0.5306061506271362, "step": 3629 }, { "epoch": 0.5090093248264741, "grad_norm": 3.0106890201568604, "learning_rate": 5.099899449914586e-06, "loss": 0.5490090847015381, "step": 3630 }, { "epoch": 0.5091495477809718, "grad_norm": 3.410308837890625, "learning_rate": 5.097629299813663e-06, "loss": 0.5646502375602722, "step": 3631 }, { "epoch": 0.5092897707354694, "grad_norm": 3.7699391841888428, "learning_rate": 5.095359129579263e-06, "loss": 0.44364309310913086, "step": 3632 }, { "epoch": 0.509429993689967, "grad_norm": 2.782224178314209, "learning_rate": 5.093088939679548e-06, "loss": 0.5700054168701172, "step": 3633 }, { "epoch": 0.5095702166444647, "grad_norm": 2.7138028144836426, "learning_rate": 5.090818730582686e-06, "loss": 0.47525590658187866, "step": 3634 }, { "epoch": 0.5097104395989623, "grad_norm": 3.4326694011688232, "learning_rate": 5.088548502756846e-06, "loss": 0.5413838624954224, "step": 3635 }, { "epoch": 0.50985066255346, "grad_norm": 4.374396800994873, "learning_rate": 5.086278256670204e-06, "loss": 0.529313862323761, "step": 3636 }, { "epoch": 0.5099908855079577, "grad_norm": 2.896062135696411, "learning_rate": 5.08400799279094e-06, "loss": 0.5827524662017822, "step": 3637 }, { "epoch": 0.5101311084624554, "grad_norm": 4.960326671600342, "learning_rate": 5.0817377115872345e-06, "loss": 0.4953402876853943, "step": 3638 }, { "epoch": 0.5102713314169529, "grad_norm": 4.070826053619385, "learning_rate": 5.0794674135272734e-06, "loss": 0.6510671377182007, "step": 3639 }, { "epoch": 0.5104115543714506, "grad_norm": 4.427222728729248, "learning_rate": 5.077197099079246e-06, "loss": 0.554277777671814, "step": 3640 }, { "epoch": 0.5105517773259483, "grad_norm": 5.478466987609863, "learning_rate": 5.074926768711347e-06, "loss": 0.47871649265289307, "step": 3641 }, { "epoch": 0.5106920002804459, "grad_norm": 2.5954155921936035, "learning_rate": 5.072656422891769e-06, "loss": 0.4512476921081543, "step": 3642 }, { "epoch": 0.5108322232349436, "grad_norm": 5.161808013916016, "learning_rate": 5.070386062088714e-06, "loss": 0.5364387631416321, "step": 3643 }, { "epoch": 0.5109724461894413, "grad_norm": 4.838057994842529, "learning_rate": 5.068115686770384e-06, "loss": 0.5504040718078613, "step": 3644 }, { "epoch": 0.5111126691439388, "grad_norm": 2.7925732135772705, "learning_rate": 5.0658452974049835e-06, "loss": 0.5161373019218445, "step": 3645 }, { "epoch": 0.5112528920984365, "grad_norm": 2.333653688430786, "learning_rate": 5.063574894460719e-06, "loss": 0.48655492067337036, "step": 3646 }, { "epoch": 0.5113931150529342, "grad_norm": 3.401637554168701, "learning_rate": 5.061304478405804e-06, "loss": 0.4362040162086487, "step": 3647 }, { "epoch": 0.5115333380074318, "grad_norm": 3.450078248977661, "learning_rate": 5.059034049708451e-06, "loss": 0.5301693677902222, "step": 3648 }, { "epoch": 0.5116735609619295, "grad_norm": 2.4034159183502197, "learning_rate": 5.056763608836877e-06, "loss": 0.5430083274841309, "step": 3649 }, { "epoch": 0.5118137839164271, "grad_norm": 2.230395793914795, "learning_rate": 5.0544931562593e-06, "loss": 0.5095150470733643, "step": 3650 }, { "epoch": 0.5119540068709247, "grad_norm": 3.229804754257202, "learning_rate": 5.052222692443941e-06, "loss": 0.49374571442604065, "step": 3651 }, { "epoch": 0.5120942298254224, "grad_norm": 3.5733864307403564, "learning_rate": 5.049952217859024e-06, "loss": 0.619402289390564, "step": 3652 }, { "epoch": 0.5122344527799201, "grad_norm": 4.120468616485596, "learning_rate": 5.047681732972774e-06, "loss": 0.5172606110572815, "step": 3653 }, { "epoch": 0.5123746757344178, "grad_norm": 2.927668571472168, "learning_rate": 5.045411238253422e-06, "loss": 0.5712525844573975, "step": 3654 }, { "epoch": 0.5125148986889154, "grad_norm": 3.062466621398926, "learning_rate": 5.043140734169194e-06, "loss": 0.5741167068481445, "step": 3655 }, { "epoch": 0.512655121643413, "grad_norm": 2.569329261779785, "learning_rate": 5.040870221188323e-06, "loss": 0.5774243474006653, "step": 3656 }, { "epoch": 0.5127953445979107, "grad_norm": 3.733078956604004, "learning_rate": 5.0385996997790435e-06, "loss": 0.5901269912719727, "step": 3657 }, { "epoch": 0.5129355675524083, "grad_norm": 3.064697742462158, "learning_rate": 5.03632917040959e-06, "loss": 0.49194449186325073, "step": 3658 }, { "epoch": 0.513075790506906, "grad_norm": 2.799912214279175, "learning_rate": 5.034058633548198e-06, "loss": 0.4686097502708435, "step": 3659 }, { "epoch": 0.5132160134614037, "grad_norm": 3.3083133697509766, "learning_rate": 5.03178808966311e-06, "loss": 0.5866503119468689, "step": 3660 }, { "epoch": 0.5133562364159013, "grad_norm": 2.926999807357788, "learning_rate": 5.029517539222562e-06, "loss": 0.5583392381668091, "step": 3661 }, { "epoch": 0.5134964593703989, "grad_norm": 2.378089666366577, "learning_rate": 5.0272469826947986e-06, "loss": 0.5560970306396484, "step": 3662 }, { "epoch": 0.5136366823248966, "grad_norm": 7.126736164093018, "learning_rate": 5.024976420548061e-06, "loss": 0.4686872065067291, "step": 3663 }, { "epoch": 0.5137769052793942, "grad_norm": 3.8764302730560303, "learning_rate": 5.022705853250592e-06, "loss": 0.5811277031898499, "step": 3664 }, { "epoch": 0.5139171282338919, "grad_norm": 2.2807469367980957, "learning_rate": 5.020435281270638e-06, "loss": 0.5670709609985352, "step": 3665 }, { "epoch": 0.5140573511883896, "grad_norm": 2.1090452671051025, "learning_rate": 5.0181647050764446e-06, "loss": 0.5286571979522705, "step": 3666 }, { "epoch": 0.5141975741428871, "grad_norm": 4.062343120574951, "learning_rate": 5.015894125136258e-06, "loss": 0.5233446359634399, "step": 3667 }, { "epoch": 0.5143377970973848, "grad_norm": 2.8124523162841797, "learning_rate": 5.013623541918325e-06, "loss": 0.5274826288223267, "step": 3668 }, { "epoch": 0.5144780200518825, "grad_norm": 3.14092755317688, "learning_rate": 5.0113529558908946e-06, "loss": 0.5771321654319763, "step": 3669 }, { "epoch": 0.5146182430063801, "grad_norm": 3.6116085052490234, "learning_rate": 5.009082367522216e-06, "loss": 0.6047936677932739, "step": 3670 }, { "epoch": 0.5147584659608778, "grad_norm": 2.4901351928710938, "learning_rate": 5.006811777280537e-06, "loss": 0.6044322848320007, "step": 3671 }, { "epoch": 0.5148986889153755, "grad_norm": 3.3511271476745605, "learning_rate": 5.004541185634108e-06, "loss": 0.5708152055740356, "step": 3672 }, { "epoch": 0.515038911869873, "grad_norm": 4.444284439086914, "learning_rate": 5.00227059305118e-06, "loss": 0.608834981918335, "step": 3673 }, { "epoch": 0.5151791348243707, "grad_norm": 4.03598165512085, "learning_rate": 5e-06, "loss": 0.5092960596084595, "step": 3674 }, { "epoch": 0.5153193577788684, "grad_norm": 2.6851987838745117, "learning_rate": 4.997729406948822e-06, "loss": 0.5336843729019165, "step": 3675 }, { "epoch": 0.5154595807333661, "grad_norm": 2.883883476257324, "learning_rate": 4.9954588143658926e-06, "loss": 0.5217018127441406, "step": 3676 }, { "epoch": 0.5155998036878637, "grad_norm": 3.3342702388763428, "learning_rate": 4.9931882227194644e-06, "loss": 0.5015572905540466, "step": 3677 }, { "epoch": 0.5157400266423614, "grad_norm": 2.476184129714966, "learning_rate": 4.990917632477786e-06, "loss": 0.5056915283203125, "step": 3678 }, { "epoch": 0.515880249596859, "grad_norm": 2.007620334625244, "learning_rate": 4.988647044109106e-06, "loss": 0.44529232382774353, "step": 3679 }, { "epoch": 0.5160204725513566, "grad_norm": 3.061600923538208, "learning_rate": 4.986376458081676e-06, "loss": 0.505064070224762, "step": 3680 }, { "epoch": 0.5161606955058543, "grad_norm": 3.934471845626831, "learning_rate": 4.984105874863745e-06, "loss": 0.6375214457511902, "step": 3681 }, { "epoch": 0.516300918460352, "grad_norm": 3.1423261165618896, "learning_rate": 4.981835294923556e-06, "loss": 0.5851379632949829, "step": 3682 }, { "epoch": 0.5164411414148496, "grad_norm": 9.461845397949219, "learning_rate": 4.979564718729363e-06, "loss": 0.5223780870437622, "step": 3683 }, { "epoch": 0.5165813643693472, "grad_norm": 3.2974796295166016, "learning_rate": 4.97729414674941e-06, "loss": 0.5539143085479736, "step": 3684 }, { "epoch": 0.5167215873238449, "grad_norm": 2.8133811950683594, "learning_rate": 4.97502357945194e-06, "loss": 0.49767401814460754, "step": 3685 }, { "epoch": 0.5168618102783425, "grad_norm": 2.864253044128418, "learning_rate": 4.972753017305203e-06, "loss": 0.5200883150100708, "step": 3686 }, { "epoch": 0.5170020332328402, "grad_norm": 3.818406581878662, "learning_rate": 4.97048246077744e-06, "loss": 0.5587637424468994, "step": 3687 }, { "epoch": 0.5171422561873379, "grad_norm": 3.0592236518859863, "learning_rate": 4.968211910336892e-06, "loss": 0.5592978596687317, "step": 3688 }, { "epoch": 0.5172824791418356, "grad_norm": 2.4670231342315674, "learning_rate": 4.965941366451803e-06, "loss": 0.4676889181137085, "step": 3689 }, { "epoch": 0.5174227020963331, "grad_norm": 2.108250379562378, "learning_rate": 4.963670829590411e-06, "loss": 0.40130722522735596, "step": 3690 }, { "epoch": 0.5175629250508308, "grad_norm": 3.305180549621582, "learning_rate": 4.961400300220958e-06, "loss": 0.4939461350440979, "step": 3691 }, { "epoch": 0.5177031480053285, "grad_norm": 4.6825456619262695, "learning_rate": 4.9591297788116785e-06, "loss": 0.6032110452651978, "step": 3692 }, { "epoch": 0.5178433709598261, "grad_norm": 2.3596503734588623, "learning_rate": 4.956859265830806e-06, "loss": 0.5056846737861633, "step": 3693 }, { "epoch": 0.5179835939143238, "grad_norm": 3.0503833293914795, "learning_rate": 4.954588761746579e-06, "loss": 0.6518237590789795, "step": 3694 }, { "epoch": 0.5181238168688215, "grad_norm": 3.549572467803955, "learning_rate": 4.9523182670272265e-06, "loss": 0.5502514839172363, "step": 3695 }, { "epoch": 0.518264039823319, "grad_norm": 2.318296432495117, "learning_rate": 4.950047782140976e-06, "loss": 0.6095368266105652, "step": 3696 }, { "epoch": 0.5184042627778167, "grad_norm": 3.056380271911621, "learning_rate": 4.9477773075560604e-06, "loss": 0.5498512983322144, "step": 3697 }, { "epoch": 0.5185444857323144, "grad_norm": 4.16161584854126, "learning_rate": 4.945506843740702e-06, "loss": 0.5107554197311401, "step": 3698 }, { "epoch": 0.518684708686812, "grad_norm": 3.4833812713623047, "learning_rate": 4.943236391163124e-06, "loss": 0.5363615155220032, "step": 3699 }, { "epoch": 0.5188249316413097, "grad_norm": 3.1225619316101074, "learning_rate": 4.940965950291551e-06, "loss": 0.5557488203048706, "step": 3700 }, { "epoch": 0.5189651545958074, "grad_norm": 3.1565890312194824, "learning_rate": 4.938695521594198e-06, "loss": 0.46609795093536377, "step": 3701 }, { "epoch": 0.519105377550305, "grad_norm": 2.700310707092285, "learning_rate": 4.936425105539281e-06, "loss": 0.4464257061481476, "step": 3702 }, { "epoch": 0.5192456005048026, "grad_norm": 3.0032715797424316, "learning_rate": 4.934154702595019e-06, "loss": 0.5556334853172302, "step": 3703 }, { "epoch": 0.5193858234593003, "grad_norm": 4.464064121246338, "learning_rate": 4.931884313229618e-06, "loss": 0.5938839912414551, "step": 3704 }, { "epoch": 0.519526046413798, "grad_norm": 6.865839958190918, "learning_rate": 4.929613937911286e-06, "loss": 0.4884178340435028, "step": 3705 }, { "epoch": 0.5196662693682956, "grad_norm": 2.3194572925567627, "learning_rate": 4.9273435771082316e-06, "loss": 0.4973716735839844, "step": 3706 }, { "epoch": 0.5198064923227932, "grad_norm": 4.211612701416016, "learning_rate": 4.925073231288655e-06, "loss": 0.5793259739875793, "step": 3707 }, { "epoch": 0.5199467152772909, "grad_norm": 3.0541810989379883, "learning_rate": 4.922802900920754e-06, "loss": 0.4893001616001129, "step": 3708 }, { "epoch": 0.5200869382317885, "grad_norm": 4.846775531768799, "learning_rate": 4.920532586472728e-06, "loss": 0.45847511291503906, "step": 3709 }, { "epoch": 0.5202271611862862, "grad_norm": 4.274244785308838, "learning_rate": 4.918262288412768e-06, "loss": 0.6146698594093323, "step": 3710 }, { "epoch": 0.5203673841407839, "grad_norm": 4.189661502838135, "learning_rate": 4.915992007209061e-06, "loss": 0.5075063705444336, "step": 3711 }, { "epoch": 0.5205076070952815, "grad_norm": 4.5124592781066895, "learning_rate": 4.913721743329797e-06, "loss": 0.6020373106002808, "step": 3712 }, { "epoch": 0.5206478300497791, "grad_norm": 3.438052177429199, "learning_rate": 4.911451497243156e-06, "loss": 0.5493963956832886, "step": 3713 }, { "epoch": 0.5207880530042768, "grad_norm": 2.6657800674438477, "learning_rate": 4.909181269417315e-06, "loss": 0.693135142326355, "step": 3714 }, { "epoch": 0.5209282759587744, "grad_norm": 10.887228965759277, "learning_rate": 4.906911060320454e-06, "loss": 0.5906328558921814, "step": 3715 }, { "epoch": 0.5210684989132721, "grad_norm": 2.6299362182617188, "learning_rate": 4.90464087042074e-06, "loss": 0.5994280576705933, "step": 3716 }, { "epoch": 0.5212087218677698, "grad_norm": 2.7176055908203125, "learning_rate": 4.902370700186338e-06, "loss": 0.4715789556503296, "step": 3717 }, { "epoch": 0.5213489448222675, "grad_norm": 7.705081939697266, "learning_rate": 4.900100550085416e-06, "loss": 0.46819114685058594, "step": 3718 }, { "epoch": 0.521489167776765, "grad_norm": 6.588381290435791, "learning_rate": 4.897830420586128e-06, "loss": 0.4571927785873413, "step": 3719 }, { "epoch": 0.5216293907312627, "grad_norm": 4.641317367553711, "learning_rate": 4.8955603121566335e-06, "loss": 0.45252811908721924, "step": 3720 }, { "epoch": 0.5217696136857604, "grad_norm": 3.1559643745422363, "learning_rate": 4.8932902252650805e-06, "loss": 0.5506260395050049, "step": 3721 }, { "epoch": 0.521909836640258, "grad_norm": 11.48876667022705, "learning_rate": 4.891020160379612e-06, "loss": 0.5595858097076416, "step": 3722 }, { "epoch": 0.5220500595947557, "grad_norm": 3.5635764598846436, "learning_rate": 4.888750117968374e-06, "loss": 0.5776615142822266, "step": 3723 }, { "epoch": 0.5221902825492533, "grad_norm": 2.263641834259033, "learning_rate": 4.8864800984995006e-06, "loss": 0.47552597522735596, "step": 3724 }, { "epoch": 0.5223305055037509, "grad_norm": 2.5290005207061768, "learning_rate": 4.884210102441122e-06, "loss": 0.5358926057815552, "step": 3725 }, { "epoch": 0.5224707284582486, "grad_norm": 2.708324670791626, "learning_rate": 4.881940130261369e-06, "loss": 0.5654772520065308, "step": 3726 }, { "epoch": 0.5226109514127463, "grad_norm": 2.9283056259155273, "learning_rate": 4.879670182428363e-06, "loss": 0.5368107557296753, "step": 3727 }, { "epoch": 0.5227511743672439, "grad_norm": 3.2407033443450928, "learning_rate": 4.877400259410217e-06, "loss": 0.5013733506202698, "step": 3728 }, { "epoch": 0.5228913973217416, "grad_norm": 5.781825542449951, "learning_rate": 4.875130361675048e-06, "loss": 0.5695680379867554, "step": 3729 }, { "epoch": 0.5230316202762392, "grad_norm": 8.21607780456543, "learning_rate": 4.87286048969096e-06, "loss": 0.6245911717414856, "step": 3730 }, { "epoch": 0.5231718432307368, "grad_norm": 4.597554683685303, "learning_rate": 4.870590643926054e-06, "loss": 0.5597590208053589, "step": 3731 }, { "epoch": 0.5233120661852345, "grad_norm": 5.18545389175415, "learning_rate": 4.8683208248484295e-06, "loss": 0.6434388756752014, "step": 3732 }, { "epoch": 0.5234522891397322, "grad_norm": 2.9165706634521484, "learning_rate": 4.866051032926174e-06, "loss": 0.4597373604774475, "step": 3733 }, { "epoch": 0.5235925120942299, "grad_norm": 2.8264243602752686, "learning_rate": 4.863781268627371e-06, "loss": 0.5947924852371216, "step": 3734 }, { "epoch": 0.5237327350487275, "grad_norm": 2.7288737297058105, "learning_rate": 4.8615115324201045e-06, "loss": 0.5466694235801697, "step": 3735 }, { "epoch": 0.5238729580032251, "grad_norm": 2.6011483669281006, "learning_rate": 4.859241824772445e-06, "loss": 0.622174859046936, "step": 3736 }, { "epoch": 0.5240131809577228, "grad_norm": 4.81309700012207, "learning_rate": 4.856972146152458e-06, "loss": 0.5914757251739502, "step": 3737 }, { "epoch": 0.5241534039122204, "grad_norm": 2.496577501296997, "learning_rate": 4.85470249702821e-06, "loss": 0.6172391176223755, "step": 3738 }, { "epoch": 0.5242936268667181, "grad_norm": 2.6836016178131104, "learning_rate": 4.852432877867754e-06, "loss": 0.506179690361023, "step": 3739 }, { "epoch": 0.5244338498212158, "grad_norm": 3.176788806915283, "learning_rate": 4.850163289139138e-06, "loss": 0.4505710303783417, "step": 3740 }, { "epoch": 0.5245740727757133, "grad_norm": 3.6902830600738525, "learning_rate": 4.847893731310407e-06, "loss": 0.5796558856964111, "step": 3741 }, { "epoch": 0.524714295730211, "grad_norm": 5.3790082931518555, "learning_rate": 4.845624204849598e-06, "loss": 0.6140174865722656, "step": 3742 }, { "epoch": 0.5248545186847087, "grad_norm": 2.328693151473999, "learning_rate": 4.843354710224737e-06, "loss": 0.5074416995048523, "step": 3743 }, { "epoch": 0.5249947416392063, "grad_norm": 29.317424774169922, "learning_rate": 4.841085247903854e-06, "loss": 0.5525817275047302, "step": 3744 }, { "epoch": 0.525134964593704, "grad_norm": 11.296463966369629, "learning_rate": 4.8388158183549624e-06, "loss": 0.4652268588542938, "step": 3745 }, { "epoch": 0.5252751875482017, "grad_norm": 3.349494457244873, "learning_rate": 4.83654642204607e-06, "loss": 0.5417376756668091, "step": 3746 }, { "epoch": 0.5254154105026992, "grad_norm": 7.119697570800781, "learning_rate": 4.834277059445186e-06, "loss": 0.4714808762073517, "step": 3747 }, { "epoch": 0.5255556334571969, "grad_norm": 4.516857624053955, "learning_rate": 4.8320077310203015e-06, "loss": 0.4454078674316406, "step": 3748 }, { "epoch": 0.5256958564116946, "grad_norm": 2.7529358863830566, "learning_rate": 4.82973843723941e-06, "loss": 0.5621796250343323, "step": 3749 }, { "epoch": 0.5258360793661923, "grad_norm": 2.756913185119629, "learning_rate": 4.827469178570492e-06, "loss": 0.5505864024162292, "step": 3750 }, { "epoch": 0.5259763023206899, "grad_norm": 2.746457576751709, "learning_rate": 4.8251999554815195e-06, "loss": 0.5341349840164185, "step": 3751 }, { "epoch": 0.5261165252751876, "grad_norm": 15.632772445678711, "learning_rate": 4.8229307684404654e-06, "loss": 0.546320378780365, "step": 3752 }, { "epoch": 0.5262567482296852, "grad_norm": 2.406463146209717, "learning_rate": 4.820661617915288e-06, "loss": 0.5708648562431335, "step": 3753 }, { "epoch": 0.5263969711841828, "grad_norm": 4.320858478546143, "learning_rate": 4.818392504373937e-06, "loss": 0.5041147470474243, "step": 3754 }, { "epoch": 0.5265371941386805, "grad_norm": 2.1922574043273926, "learning_rate": 4.816123428284362e-06, "loss": 0.5003162622451782, "step": 3755 }, { "epoch": 0.5266774170931782, "grad_norm": 2.394972324371338, "learning_rate": 4.813854390114498e-06, "loss": 0.4469321370124817, "step": 3756 }, { "epoch": 0.5268176400476758, "grad_norm": 4.4419121742248535, "learning_rate": 4.811585390332272e-06, "loss": 0.5511387586593628, "step": 3757 }, { "epoch": 0.5269578630021735, "grad_norm": 7.202086448669434, "learning_rate": 4.809316429405612e-06, "loss": 0.4563004970550537, "step": 3758 }, { "epoch": 0.5270980859566711, "grad_norm": 6.2802276611328125, "learning_rate": 4.807047507802426e-06, "loss": 0.532829999923706, "step": 3759 }, { "epoch": 0.5272383089111687, "grad_norm": 8.536006927490234, "learning_rate": 4.8047786259906194e-06, "loss": 0.6223347187042236, "step": 3760 }, { "epoch": 0.5273785318656664, "grad_norm": 5.077049255371094, "learning_rate": 4.802509784438094e-06, "loss": 0.6095936298370361, "step": 3761 }, { "epoch": 0.5275187548201641, "grad_norm": 2.8451783657073975, "learning_rate": 4.800240983612736e-06, "loss": 0.5105364918708801, "step": 3762 }, { "epoch": 0.5276589777746618, "grad_norm": 2.8230538368225098, "learning_rate": 4.797972223982424e-06, "loss": 0.5333778858184814, "step": 3763 }, { "epoch": 0.5277992007291593, "grad_norm": 2.713942766189575, "learning_rate": 4.795703506015034e-06, "loss": 0.6280947923660278, "step": 3764 }, { "epoch": 0.527939423683657, "grad_norm": 2.1733436584472656, "learning_rate": 4.7934348301784276e-06, "loss": 0.5848480463027954, "step": 3765 }, { "epoch": 0.5280796466381547, "grad_norm": 3.4417073726654053, "learning_rate": 4.791166196940458e-06, "loss": 0.5349764227867126, "step": 3766 }, { "epoch": 0.5282198695926523, "grad_norm": 3.5030434131622314, "learning_rate": 4.788897606768974e-06, "loss": 0.5327814817428589, "step": 3767 }, { "epoch": 0.52836009254715, "grad_norm": 4.334936618804932, "learning_rate": 4.786629060131812e-06, "loss": 0.5236932039260864, "step": 3768 }, { "epoch": 0.5285003155016477, "grad_norm": 2.7201035022735596, "learning_rate": 4.784360557496797e-06, "loss": 0.628002941608429, "step": 3769 }, { "epoch": 0.5286405384561452, "grad_norm": 15.308038711547852, "learning_rate": 4.782092099331752e-06, "loss": 0.5344060063362122, "step": 3770 }, { "epoch": 0.5287807614106429, "grad_norm": 4.149139404296875, "learning_rate": 4.779823686104487e-06, "loss": 0.42603591084480286, "step": 3771 }, { "epoch": 0.5289209843651406, "grad_norm": 3.1521799564361572, "learning_rate": 4.777555318282798e-06, "loss": 0.4867863953113556, "step": 3772 }, { "epoch": 0.5290612073196382, "grad_norm": 3.3252832889556885, "learning_rate": 4.775286996334482e-06, "loss": 0.5144463777542114, "step": 3773 }, { "epoch": 0.5292014302741359, "grad_norm": 3.88550066947937, "learning_rate": 4.7730187207273176e-06, "loss": 0.566265344619751, "step": 3774 }, { "epoch": 0.5293416532286336, "grad_norm": 3.625182628631592, "learning_rate": 4.770750491929076e-06, "loss": 0.5586491823196411, "step": 3775 }, { "epoch": 0.5294818761831311, "grad_norm": 2.7824902534484863, "learning_rate": 4.768482310407523e-06, "loss": 0.4753039479255676, "step": 3776 }, { "epoch": 0.5296220991376288, "grad_norm": 2.6162121295928955, "learning_rate": 4.766214176630411e-06, "loss": 0.48775941133499146, "step": 3777 }, { "epoch": 0.5297623220921265, "grad_norm": 9.748359680175781, "learning_rate": 4.763946091065479e-06, "loss": 0.5678355693817139, "step": 3778 }, { "epoch": 0.5299025450466242, "grad_norm": 14.210309982299805, "learning_rate": 4.7616780541804645e-06, "loss": 0.5111634135246277, "step": 3779 }, { "epoch": 0.5300427680011218, "grad_norm": 3.341243028640747, "learning_rate": 4.759410066443088e-06, "loss": 0.5540790557861328, "step": 3780 }, { "epoch": 0.5301829909556194, "grad_norm": 2.760603189468384, "learning_rate": 4.757142128321064e-06, "loss": 0.5200371742248535, "step": 3781 }, { "epoch": 0.530323213910117, "grad_norm": 3.3049802780151367, "learning_rate": 4.754874240282096e-06, "loss": 0.570176362991333, "step": 3782 }, { "epoch": 0.5304634368646147, "grad_norm": 3.2018613815307617, "learning_rate": 4.752606402793871e-06, "loss": 0.618640661239624, "step": 3783 }, { "epoch": 0.5306036598191124, "grad_norm": 2.428651809692383, "learning_rate": 4.750338616324077e-06, "loss": 0.5670793056488037, "step": 3784 }, { "epoch": 0.5307438827736101, "grad_norm": 3.9045512676239014, "learning_rate": 4.748070881340384e-06, "loss": 0.590747058391571, "step": 3785 }, { "epoch": 0.5308841057281077, "grad_norm": 8.073542594909668, "learning_rate": 4.745803198310449e-06, "loss": 0.4783129096031189, "step": 3786 }, { "epoch": 0.5310243286826053, "grad_norm": 4.081055164337158, "learning_rate": 4.743535567701926e-06, "loss": 0.45437490940093994, "step": 3787 }, { "epoch": 0.531164551637103, "grad_norm": 2.695646047592163, "learning_rate": 4.7412679899824545e-06, "loss": 0.5399607419967651, "step": 3788 }, { "epoch": 0.5313047745916006, "grad_norm": 2.822547435760498, "learning_rate": 4.739000465619658e-06, "loss": 0.5372512340545654, "step": 3789 }, { "epoch": 0.5314449975460983, "grad_norm": 4.1126813888549805, "learning_rate": 4.7367329950811596e-06, "loss": 0.5054349899291992, "step": 3790 }, { "epoch": 0.531585220500596, "grad_norm": 2.434171438217163, "learning_rate": 4.734465578834563e-06, "loss": 0.5866885781288147, "step": 3791 }, { "epoch": 0.5317254434550936, "grad_norm": 2.796990156173706, "learning_rate": 4.732198217347461e-06, "loss": 0.5263623595237732, "step": 3792 }, { "epoch": 0.5318656664095912, "grad_norm": 13.511326789855957, "learning_rate": 4.729930911087443e-06, "loss": 0.57868492603302, "step": 3793 }, { "epoch": 0.5320058893640889, "grad_norm": 3.7694053649902344, "learning_rate": 4.727663660522077e-06, "loss": 0.4832420349121094, "step": 3794 }, { "epoch": 0.5321461123185866, "grad_norm": 3.608461380004883, "learning_rate": 4.725396466118923e-06, "loss": 0.506763219833374, "step": 3795 }, { "epoch": 0.5322863352730842, "grad_norm": 5.139277935028076, "learning_rate": 4.723129328345533e-06, "loss": 0.6414849758148193, "step": 3796 }, { "epoch": 0.5324265582275819, "grad_norm": 2.3805742263793945, "learning_rate": 4.720862247669445e-06, "loss": 0.5923634171485901, "step": 3797 }, { "epoch": 0.5325667811820795, "grad_norm": 5.342935562133789, "learning_rate": 4.718595224558181e-06, "loss": 0.47906291484832764, "step": 3798 }, { "epoch": 0.5327070041365771, "grad_norm": 3.353792428970337, "learning_rate": 4.716328259479259e-06, "loss": 0.5056573152542114, "step": 3799 }, { "epoch": 0.5328472270910748, "grad_norm": 2.3446555137634277, "learning_rate": 4.714061352900179e-06, "loss": 0.5402300357818604, "step": 3800 }, { "epoch": 0.5329874500455725, "grad_norm": 3.0014989376068115, "learning_rate": 4.711794505288431e-06, "loss": 0.6237901449203491, "step": 3801 }, { "epoch": 0.5331276730000701, "grad_norm": 3.521787405014038, "learning_rate": 4.709527717111494e-06, "loss": 0.4535491466522217, "step": 3802 }, { "epoch": 0.5332678959545678, "grad_norm": 2.903573751449585, "learning_rate": 4.7072609888368315e-06, "loss": 0.5725162029266357, "step": 3803 }, { "epoch": 0.5334081189090654, "grad_norm": 10.624937057495117, "learning_rate": 4.704994320931898e-06, "loss": 0.5428894758224487, "step": 3804 }, { "epoch": 0.533548341863563, "grad_norm": 4.173122882843018, "learning_rate": 4.7027277138641345e-06, "loss": 0.5699974298477173, "step": 3805 }, { "epoch": 0.5336885648180607, "grad_norm": 2.848811388015747, "learning_rate": 4.700461168100967e-06, "loss": 0.44117259979248047, "step": 3806 }, { "epoch": 0.5338287877725584, "grad_norm": 5.534966945648193, "learning_rate": 4.6981946841098135e-06, "loss": 0.5710549354553223, "step": 3807 }, { "epoch": 0.533969010727056, "grad_norm": 2.335587739944458, "learning_rate": 4.695928262358077e-06, "loss": 0.6270958185195923, "step": 3808 }, { "epoch": 0.5341092336815537, "grad_norm": 3.109241485595703, "learning_rate": 4.693661903313143e-06, "loss": 0.49666744470596313, "step": 3809 }, { "epoch": 0.5342494566360513, "grad_norm": 5.394981384277344, "learning_rate": 4.691395607442395e-06, "loss": 0.599351167678833, "step": 3810 }, { "epoch": 0.534389679590549, "grad_norm": 3.6272315979003906, "learning_rate": 4.689129375213193e-06, "loss": 0.5323525667190552, "step": 3811 }, { "epoch": 0.5345299025450466, "grad_norm": 3.4086341857910156, "learning_rate": 4.6868632070928865e-06, "loss": 0.5091713070869446, "step": 3812 }, { "epoch": 0.5346701254995443, "grad_norm": 4.788164138793945, "learning_rate": 4.684597103548817e-06, "loss": 0.5924607515335083, "step": 3813 }, { "epoch": 0.534810348454042, "grad_norm": 6.488022804260254, "learning_rate": 4.6823310650483075e-06, "loss": 0.6385833024978638, "step": 3814 }, { "epoch": 0.5349505714085396, "grad_norm": 2.969395399093628, "learning_rate": 4.680065092058667e-06, "loss": 0.553216814994812, "step": 3815 }, { "epoch": 0.5350907943630372, "grad_norm": 3.0825090408325195, "learning_rate": 4.677799185047195e-06, "loss": 0.5604538321495056, "step": 3816 }, { "epoch": 0.5352310173175349, "grad_norm": 3.9834964275360107, "learning_rate": 4.675533344481175e-06, "loss": 0.471149742603302, "step": 3817 }, { "epoch": 0.5353712402720325, "grad_norm": 3.3511762619018555, "learning_rate": 4.673267570827875e-06, "loss": 0.4930531680583954, "step": 3818 }, { "epoch": 0.5355114632265302, "grad_norm": 3.5105977058410645, "learning_rate": 4.671001864554555e-06, "loss": 0.43707531690597534, "step": 3819 }, { "epoch": 0.5356516861810279, "grad_norm": 2.8267815113067627, "learning_rate": 4.668736226128453e-06, "loss": 0.4829471707344055, "step": 3820 }, { "epoch": 0.5357919091355254, "grad_norm": 3.7471277713775635, "learning_rate": 4.666470656016801e-06, "loss": 0.5219061374664307, "step": 3821 }, { "epoch": 0.5359321320900231, "grad_norm": 2.7093098163604736, "learning_rate": 4.6642051546868124e-06, "loss": 0.5974481105804443, "step": 3822 }, { "epoch": 0.5360723550445208, "grad_norm": 4.493639945983887, "learning_rate": 4.661939722605686e-06, "loss": 0.45764556527137756, "step": 3823 }, { "epoch": 0.5362125779990184, "grad_norm": 4.441500186920166, "learning_rate": 4.659674360240609e-06, "loss": 0.48653653264045715, "step": 3824 }, { "epoch": 0.5363528009535161, "grad_norm": 3.1742329597473145, "learning_rate": 4.657409068058753e-06, "loss": 0.5237146615982056, "step": 3825 }, { "epoch": 0.5364930239080138, "grad_norm": 3.362583637237549, "learning_rate": 4.655143846527273e-06, "loss": 0.49726617336273193, "step": 3826 }, { "epoch": 0.5366332468625113, "grad_norm": 45.4394416809082, "learning_rate": 4.652878696113313e-06, "loss": 0.5320953726768494, "step": 3827 }, { "epoch": 0.536773469817009, "grad_norm": 2.1495842933654785, "learning_rate": 4.650613617284002e-06, "loss": 0.5749385356903076, "step": 3828 }, { "epoch": 0.5369136927715067, "grad_norm": 2.978360414505005, "learning_rate": 4.64834861050645e-06, "loss": 0.5180363655090332, "step": 3829 }, { "epoch": 0.5370539157260044, "grad_norm": 3.1894145011901855, "learning_rate": 4.646083676247757e-06, "loss": 0.5128007531166077, "step": 3830 }, { "epoch": 0.537194138680502, "grad_norm": 3.066305160522461, "learning_rate": 4.643818814975007e-06, "loss": 0.578129768371582, "step": 3831 }, { "epoch": 0.5373343616349997, "grad_norm": 2.5400941371917725, "learning_rate": 4.641554027155265e-06, "loss": 0.4610801339149475, "step": 3832 }, { "epoch": 0.5374745845894973, "grad_norm": 2.8845956325531006, "learning_rate": 4.639289313255587e-06, "loss": 0.5172762274742126, "step": 3833 }, { "epoch": 0.5376148075439949, "grad_norm": 7.056511402130127, "learning_rate": 4.63702467374301e-06, "loss": 0.5873295664787292, "step": 3834 }, { "epoch": 0.5377550304984926, "grad_norm": 3.6521594524383545, "learning_rate": 4.634760109084556e-06, "loss": 0.5479153394699097, "step": 3835 }, { "epoch": 0.5378952534529903, "grad_norm": 3.4920573234558105, "learning_rate": 4.632495619747232e-06, "loss": 0.5707718133926392, "step": 3836 }, { "epoch": 0.538035476407488, "grad_norm": 3.4001073837280273, "learning_rate": 4.63023120619803e-06, "loss": 0.542129635810852, "step": 3837 }, { "epoch": 0.5381756993619855, "grad_norm": 3.7959089279174805, "learning_rate": 4.627966868903922e-06, "loss": 0.4467918276786804, "step": 3838 }, { "epoch": 0.5383159223164832, "grad_norm": 2.651526927947998, "learning_rate": 4.625702608331875e-06, "loss": 0.5135402679443359, "step": 3839 }, { "epoch": 0.5384561452709808, "grad_norm": 4.010829925537109, "learning_rate": 4.623438424948827e-06, "loss": 0.5732081532478333, "step": 3840 }, { "epoch": 0.5385963682254785, "grad_norm": 5.955575942993164, "learning_rate": 4.6211743192217105e-06, "loss": 0.5360873937606812, "step": 3841 }, { "epoch": 0.5387365911799762, "grad_norm": 4.268319606781006, "learning_rate": 4.618910291617436e-06, "loss": 0.5191072225570679, "step": 3842 }, { "epoch": 0.5388768141344739, "grad_norm": 2.5040817260742188, "learning_rate": 4.616646342602899e-06, "loss": 0.5950367450714111, "step": 3843 }, { "epoch": 0.5390170370889714, "grad_norm": 4.4832329750061035, "learning_rate": 4.614382472644981e-06, "loss": 0.5756803750991821, "step": 3844 }, { "epoch": 0.5391572600434691, "grad_norm": 2.892076015472412, "learning_rate": 4.612118682210545e-06, "loss": 0.5876474380493164, "step": 3845 }, { "epoch": 0.5392974829979668, "grad_norm": 2.333709478378296, "learning_rate": 4.609854971766439e-06, "loss": 0.6198415160179138, "step": 3846 }, { "epoch": 0.5394377059524644, "grad_norm": 2.974865436553955, "learning_rate": 4.607591341779493e-06, "loss": 0.5527521371841431, "step": 3847 }, { "epoch": 0.5395779289069621, "grad_norm": 5.441627025604248, "learning_rate": 4.605327792716521e-06, "loss": 0.4516969323158264, "step": 3848 }, { "epoch": 0.5397181518614598, "grad_norm": 7.295733451843262, "learning_rate": 4.603064325044321e-06, "loss": 0.5038537979125977, "step": 3849 }, { "epoch": 0.5398583748159573, "grad_norm": 4.8110761642456055, "learning_rate": 4.600800939229672e-06, "loss": 0.5744192600250244, "step": 3850 }, { "epoch": 0.539998597770455, "grad_norm": 6.299613952636719, "learning_rate": 4.598537635739342e-06, "loss": 0.49635398387908936, "step": 3851 }, { "epoch": 0.5401388207249527, "grad_norm": 3.2427823543548584, "learning_rate": 4.596274415040074e-06, "loss": 0.4955602288246155, "step": 3852 }, { "epoch": 0.5402790436794503, "grad_norm": 9.387189865112305, "learning_rate": 4.594011277598599e-06, "loss": 0.5324641466140747, "step": 3853 }, { "epoch": 0.540419266633948, "grad_norm": 3.1353871822357178, "learning_rate": 4.5917482238816306e-06, "loss": 0.6455280184745789, "step": 3854 }, { "epoch": 0.5405594895884456, "grad_norm": 9.420174598693848, "learning_rate": 4.589485254355863e-06, "loss": 0.5294681787490845, "step": 3855 }, { "epoch": 0.5406997125429432, "grad_norm": 3.546748638153076, "learning_rate": 4.587222369487974e-06, "loss": 0.49587517976760864, "step": 3856 }, { "epoch": 0.5408399354974409, "grad_norm": 6.136088848114014, "learning_rate": 4.5849595697446245e-06, "loss": 0.5372352004051208, "step": 3857 }, { "epoch": 0.5409801584519386, "grad_norm": 11.122061729431152, "learning_rate": 4.582696855592458e-06, "loss": 0.5555184483528137, "step": 3858 }, { "epoch": 0.5411203814064363, "grad_norm": 6.926913738250732, "learning_rate": 4.580434227498099e-06, "loss": 0.5436369180679321, "step": 3859 }, { "epoch": 0.5412606043609339, "grad_norm": 4.007737159729004, "learning_rate": 4.578171685928157e-06, "loss": 0.6570053100585938, "step": 3860 }, { "epoch": 0.5414008273154315, "grad_norm": 2.844897747039795, "learning_rate": 4.57590923134922e-06, "loss": 0.3930038809776306, "step": 3861 }, { "epoch": 0.5415410502699292, "grad_norm": 3.7099456787109375, "learning_rate": 4.573646864227859e-06, "loss": 0.555191159248352, "step": 3862 }, { "epoch": 0.5416812732244268, "grad_norm": 3.614269971847534, "learning_rate": 4.571384585030629e-06, "loss": 0.5834492444992065, "step": 3863 }, { "epoch": 0.5418214961789245, "grad_norm": 2.18658447265625, "learning_rate": 4.569122394224066e-06, "loss": 0.5438559055328369, "step": 3864 }, { "epoch": 0.5419617191334222, "grad_norm": 3.0032753944396973, "learning_rate": 4.5668602922746875e-06, "loss": 0.4675655961036682, "step": 3865 }, { "epoch": 0.5421019420879198, "grad_norm": 4.95501708984375, "learning_rate": 4.56459827964899e-06, "loss": 0.47918614745140076, "step": 3866 }, { "epoch": 0.5422421650424174, "grad_norm": 2.382162570953369, "learning_rate": 4.562336356813458e-06, "loss": 0.5288135409355164, "step": 3867 }, { "epoch": 0.5423823879969151, "grad_norm": 2.3772575855255127, "learning_rate": 4.560074524234552e-06, "loss": 0.6178255081176758, "step": 3868 }, { "epoch": 0.5425226109514127, "grad_norm": 3.831251382827759, "learning_rate": 4.557812782378714e-06, "loss": 0.5180943608283997, "step": 3869 }, { "epoch": 0.5426628339059104, "grad_norm": 2.6787924766540527, "learning_rate": 4.5555511317123716e-06, "loss": 0.5469485521316528, "step": 3870 }, { "epoch": 0.5428030568604081, "grad_norm": 8.560882568359375, "learning_rate": 4.5532895727019285e-06, "loss": 0.5904945135116577, "step": 3871 }, { "epoch": 0.5429432798149058, "grad_norm": 18.64812660217285, "learning_rate": 4.551028105813773e-06, "loss": 0.5430804491043091, "step": 3872 }, { "epoch": 0.5430835027694033, "grad_norm": 3.1354129314422607, "learning_rate": 4.548766731514273e-06, "loss": 0.46269160509109497, "step": 3873 }, { "epoch": 0.543223725723901, "grad_norm": 2.565706253051758, "learning_rate": 4.546505450269778e-06, "loss": 0.5839953422546387, "step": 3874 }, { "epoch": 0.5433639486783987, "grad_norm": 2.9163405895233154, "learning_rate": 4.544244262546616e-06, "loss": 0.47824737429618835, "step": 3875 }, { "epoch": 0.5435041716328963, "grad_norm": 3.04830002784729, "learning_rate": 4.541983168811099e-06, "loss": 0.5360156297683716, "step": 3876 }, { "epoch": 0.543644394587394, "grad_norm": 2.864793300628662, "learning_rate": 4.539722169529519e-06, "loss": 0.48765552043914795, "step": 3877 }, { "epoch": 0.5437846175418916, "grad_norm": 2.7722818851470947, "learning_rate": 4.537461265168147e-06, "loss": 0.5968467593193054, "step": 3878 }, { "epoch": 0.5439248404963892, "grad_norm": 7.515896320343018, "learning_rate": 4.535200456193234e-06, "loss": 0.4891037344932556, "step": 3879 }, { "epoch": 0.5440650634508869, "grad_norm": 4.948946475982666, "learning_rate": 4.532939743071013e-06, "loss": 0.46709486842155457, "step": 3880 }, { "epoch": 0.5442052864053846, "grad_norm": 4.261990547180176, "learning_rate": 4.530679126267698e-06, "loss": 0.5698726177215576, "step": 3881 }, { "epoch": 0.5443455093598822, "grad_norm": 3.6399245262145996, "learning_rate": 4.52841860624948e-06, "loss": 0.5195905566215515, "step": 3882 }, { "epoch": 0.5444857323143799, "grad_norm": 7.283273696899414, "learning_rate": 4.526158183482532e-06, "loss": 0.4624922573566437, "step": 3883 }, { "epoch": 0.5446259552688775, "grad_norm": 3.2676124572753906, "learning_rate": 4.523897858433009e-06, "loss": 0.5102161765098572, "step": 3884 }, { "epoch": 0.5447661782233751, "grad_norm": 3.3285224437713623, "learning_rate": 4.521637631567041e-06, "loss": 0.49530044198036194, "step": 3885 }, { "epoch": 0.5449064011778728, "grad_norm": 3.707932710647583, "learning_rate": 4.519377503350742e-06, "loss": 0.5893164277076721, "step": 3886 }, { "epoch": 0.5450466241323705, "grad_norm": 3.6326441764831543, "learning_rate": 4.517117474250203e-06, "loss": 0.43496793508529663, "step": 3887 }, { "epoch": 0.5451868470868682, "grad_norm": 3.0124740600585938, "learning_rate": 4.514857544731497e-06, "loss": 0.5461873412132263, "step": 3888 }, { "epoch": 0.5453270700413658, "grad_norm": 3.0788958072662354, "learning_rate": 4.512597715260673e-06, "loss": 0.5454460382461548, "step": 3889 }, { "epoch": 0.5454672929958634, "grad_norm": 5.286396026611328, "learning_rate": 4.510337986303764e-06, "loss": 0.5802019834518433, "step": 3890 }, { "epoch": 0.545607515950361, "grad_norm": 3.5756351947784424, "learning_rate": 4.5080783583267766e-06, "loss": 0.5104659795761108, "step": 3891 }, { "epoch": 0.5457477389048587, "grad_norm": 2.790480613708496, "learning_rate": 4.505818831795702e-06, "loss": 0.48681342601776123, "step": 3892 }, { "epoch": 0.5458879618593564, "grad_norm": 2.5247511863708496, "learning_rate": 4.503559407176509e-06, "loss": 0.5034767985343933, "step": 3893 }, { "epoch": 0.5460281848138541, "grad_norm": 4.472969055175781, "learning_rate": 4.5013000849351425e-06, "loss": 0.5464394092559814, "step": 3894 }, { "epoch": 0.5461684077683516, "grad_norm": 4.351816654205322, "learning_rate": 4.499040865537529e-06, "loss": 0.605273962020874, "step": 3895 }, { "epoch": 0.5463086307228493, "grad_norm": 5.648133277893066, "learning_rate": 4.496781749449572e-06, "loss": 0.6337476968765259, "step": 3896 }, { "epoch": 0.546448853677347, "grad_norm": 3.7133870124816895, "learning_rate": 4.494522737137157e-06, "loss": 0.5792871713638306, "step": 3897 }, { "epoch": 0.5465890766318446, "grad_norm": 7.951866149902344, "learning_rate": 4.492263829066146e-06, "loss": 0.44569969177246094, "step": 3898 }, { "epoch": 0.5467292995863423, "grad_norm": 3.773059368133545, "learning_rate": 4.490005025702377e-06, "loss": 0.6139797568321228, "step": 3899 }, { "epoch": 0.54686952254084, "grad_norm": 3.900265693664551, "learning_rate": 4.48774632751167e-06, "loss": 0.6213607788085938, "step": 3900 }, { "epoch": 0.5470097454953375, "grad_norm": 3.203922986984253, "learning_rate": 4.485487734959823e-06, "loss": 0.5068884491920471, "step": 3901 }, { "epoch": 0.5471499684498352, "grad_norm": 3.3221542835235596, "learning_rate": 4.483229248512611e-06, "loss": 0.4775336980819702, "step": 3902 }, { "epoch": 0.5472901914043329, "grad_norm": 2.7042274475097656, "learning_rate": 4.480970868635786e-06, "loss": 0.547369122505188, "step": 3903 }, { "epoch": 0.5474304143588306, "grad_norm": 3.019989252090454, "learning_rate": 4.478712595795083e-06, "loss": 0.5785881280899048, "step": 3904 }, { "epoch": 0.5475706373133282, "grad_norm": 2.74710750579834, "learning_rate": 4.476454430456207e-06, "loss": 0.5695447325706482, "step": 3905 }, { "epoch": 0.5477108602678259, "grad_norm": 9.479671478271484, "learning_rate": 4.474196373084848e-06, "loss": 0.41917991638183594, "step": 3906 }, { "epoch": 0.5478510832223235, "grad_norm": 2.1489450931549072, "learning_rate": 4.471938424146671e-06, "loss": 0.511598527431488, "step": 3907 }, { "epoch": 0.5479913061768211, "grad_norm": 4.388660430908203, "learning_rate": 4.469680584107317e-06, "loss": 0.45855966210365295, "step": 3908 }, { "epoch": 0.5481315291313188, "grad_norm": 1.829828143119812, "learning_rate": 4.467422853432407e-06, "loss": 0.4836762845516205, "step": 3909 }, { "epoch": 0.5482717520858165, "grad_norm": 3.021040678024292, "learning_rate": 4.465165232587541e-06, "loss": 0.4328608512878418, "step": 3910 }, { "epoch": 0.5484119750403141, "grad_norm": 3.030297040939331, "learning_rate": 4.46290772203829e-06, "loss": 0.6214273571968079, "step": 3911 }, { "epoch": 0.5485521979948117, "grad_norm": 3.2798891067504883, "learning_rate": 4.460650322250208e-06, "loss": 0.5270444750785828, "step": 3912 }, { "epoch": 0.5486924209493094, "grad_norm": 4.241734981536865, "learning_rate": 4.458393033688826e-06, "loss": 0.5198062658309937, "step": 3913 }, { "epoch": 0.548832643903807, "grad_norm": 3.417266607284546, "learning_rate": 4.4561358568196476e-06, "loss": 0.4782823920249939, "step": 3914 }, { "epoch": 0.5489728668583047, "grad_norm": 3.638183355331421, "learning_rate": 4.453878792108158e-06, "loss": 0.4342770576477051, "step": 3915 }, { "epoch": 0.5491130898128024, "grad_norm": 3.961106061935425, "learning_rate": 4.451621840019817e-06, "loss": 0.4831967055797577, "step": 3916 }, { "epoch": 0.5492533127673, "grad_norm": 2.9033915996551514, "learning_rate": 4.449365001020059e-06, "loss": 0.4709562659263611, "step": 3917 }, { "epoch": 0.5493935357217976, "grad_norm": 2.841064453125, "learning_rate": 4.447108275574304e-06, "loss": 0.5161193013191223, "step": 3918 }, { "epoch": 0.5495337586762953, "grad_norm": 3.6656198501586914, "learning_rate": 4.444851664147938e-06, "loss": 0.5081015229225159, "step": 3919 }, { "epoch": 0.549673981630793, "grad_norm": 3.5604941844940186, "learning_rate": 4.442595167206326e-06, "loss": 0.603289008140564, "step": 3920 }, { "epoch": 0.5498142045852906, "grad_norm": 9.103374481201172, "learning_rate": 4.440338785214817e-06, "loss": 0.45373600721359253, "step": 3921 }, { "epoch": 0.5499544275397883, "grad_norm": 7.838127613067627, "learning_rate": 4.438082518638727e-06, "loss": 0.589637815952301, "step": 3922 }, { "epoch": 0.550094650494286, "grad_norm": 2.5179498195648193, "learning_rate": 4.435826367943349e-06, "loss": 0.4950316548347473, "step": 3923 }, { "epoch": 0.5502348734487835, "grad_norm": 2.3989880084991455, "learning_rate": 4.43357033359396e-06, "loss": 0.5002807378768921, "step": 3924 }, { "epoch": 0.5503750964032812, "grad_norm": 2.1327545642852783, "learning_rate": 4.431314416055806e-06, "loss": 0.46642377972602844, "step": 3925 }, { "epoch": 0.5505153193577789, "grad_norm": 2.641489028930664, "learning_rate": 4.429058615794107e-06, "loss": 0.5360321998596191, "step": 3926 }, { "epoch": 0.5506555423122765, "grad_norm": 3.02000093460083, "learning_rate": 4.4268029332740694e-06, "loss": 0.5978673696517944, "step": 3927 }, { "epoch": 0.5507957652667742, "grad_norm": 4.155297756195068, "learning_rate": 4.424547368960863e-06, "loss": 0.527008593082428, "step": 3928 }, { "epoch": 0.5509359882212719, "grad_norm": 3.5001676082611084, "learning_rate": 4.42229192331964e-06, "loss": 0.5406355857849121, "step": 3929 }, { "epoch": 0.5510762111757694, "grad_norm": 3.6917262077331543, "learning_rate": 4.420036596815529e-06, "loss": 0.4919963479042053, "step": 3930 }, { "epoch": 0.5512164341302671, "grad_norm": 2.567748546600342, "learning_rate": 4.417781389913629e-06, "loss": 0.483420193195343, "step": 3931 }, { "epoch": 0.5513566570847648, "grad_norm": 2.690000534057617, "learning_rate": 4.415526303079018e-06, "loss": 0.5382400751113892, "step": 3932 }, { "epoch": 0.5514968800392624, "grad_norm": 2.456136465072632, "learning_rate": 4.4132713367767495e-06, "loss": 0.617455244064331, "step": 3933 }, { "epoch": 0.5516371029937601, "grad_norm": 4.242199420928955, "learning_rate": 4.411016491471849e-06, "loss": 0.5272125005722046, "step": 3934 }, { "epoch": 0.5517773259482577, "grad_norm": 2.3907129764556885, "learning_rate": 4.408761767629322e-06, "loss": 0.5912363529205322, "step": 3935 }, { "epoch": 0.5519175489027554, "grad_norm": 2.9323713779449463, "learning_rate": 4.406507165714144e-06, "loss": 0.614210844039917, "step": 3936 }, { "epoch": 0.552057771857253, "grad_norm": 5.225855827331543, "learning_rate": 4.404252686191265e-06, "loss": 0.5478175282478333, "step": 3937 }, { "epoch": 0.5521979948117507, "grad_norm": 5.350481033325195, "learning_rate": 4.401998329525618e-06, "loss": 0.5193759202957153, "step": 3938 }, { "epoch": 0.5523382177662484, "grad_norm": 38.23011016845703, "learning_rate": 4.399744096182102e-06, "loss": 0.6098389625549316, "step": 3939 }, { "epoch": 0.552478440720746, "grad_norm": 2.929302930831909, "learning_rate": 4.39748998662559e-06, "loss": 0.44823241233825684, "step": 3940 }, { "epoch": 0.5526186636752436, "grad_norm": 3.852389097213745, "learning_rate": 4.3952360013209386e-06, "loss": 0.5799646377563477, "step": 3941 }, { "epoch": 0.5527588866297413, "grad_norm": 3.3126041889190674, "learning_rate": 4.392982140732971e-06, "loss": 0.5649900436401367, "step": 3942 }, { "epoch": 0.5528991095842389, "grad_norm": 2.303072452545166, "learning_rate": 4.3907284053264835e-06, "loss": 0.508337676525116, "step": 3943 }, { "epoch": 0.5530393325387366, "grad_norm": 3.458221912384033, "learning_rate": 4.388474795566254e-06, "loss": 0.49847304821014404, "step": 3944 }, { "epoch": 0.5531795554932343, "grad_norm": 3.5546863079071045, "learning_rate": 4.3862213119170296e-06, "loss": 0.5449822545051575, "step": 3945 }, { "epoch": 0.553319778447732, "grad_norm": 2.3882715702056885, "learning_rate": 4.383967954843529e-06, "loss": 0.47308170795440674, "step": 3946 }, { "epoch": 0.5534600014022295, "grad_norm": 2.7407519817352295, "learning_rate": 4.381714724810452e-06, "loss": 0.4220075309276581, "step": 3947 }, { "epoch": 0.5536002243567272, "grad_norm": 2.6124751567840576, "learning_rate": 4.379461622282466e-06, "loss": 0.5113365054130554, "step": 3948 }, { "epoch": 0.5537404473112248, "grad_norm": 4.751893520355225, "learning_rate": 4.377208647724212e-06, "loss": 0.5138885974884033, "step": 3949 }, { "epoch": 0.5538806702657225, "grad_norm": 2.5187618732452393, "learning_rate": 4.374955801600312e-06, "loss": 0.5574960708618164, "step": 3950 }, { "epoch": 0.5540208932202202, "grad_norm": 3.8368964195251465, "learning_rate": 4.372703084375354e-06, "loss": 0.5911325216293335, "step": 3951 }, { "epoch": 0.5541611161747177, "grad_norm": 11.243659973144531, "learning_rate": 4.370450496513897e-06, "loss": 0.515789806842804, "step": 3952 }, { "epoch": 0.5543013391292154, "grad_norm": 5.42919397354126, "learning_rate": 4.368198038480487e-06, "loss": 0.46164554357528687, "step": 3953 }, { "epoch": 0.5544415620837131, "grad_norm": 28.878395080566406, "learning_rate": 4.365945710739628e-06, "loss": 0.4930064082145691, "step": 3954 }, { "epoch": 0.5545817850382108, "grad_norm": 4.309056282043457, "learning_rate": 4.363693513755803e-06, "loss": 0.4954928159713745, "step": 3955 }, { "epoch": 0.5547220079927084, "grad_norm": 3.859707832336426, "learning_rate": 4.361441447993473e-06, "loss": 0.5743151903152466, "step": 3956 }, { "epoch": 0.5548622309472061, "grad_norm": 3.4798600673675537, "learning_rate": 4.359189513917062e-06, "loss": 0.5155022740364075, "step": 3957 }, { "epoch": 0.5550024539017037, "grad_norm": 2.771209478378296, "learning_rate": 4.356937711990978e-06, "loss": 0.5948038101196289, "step": 3958 }, { "epoch": 0.5551426768562013, "grad_norm": 25.4786376953125, "learning_rate": 4.354686042679593e-06, "loss": 0.5184618830680847, "step": 3959 }, { "epoch": 0.555282899810699, "grad_norm": 7.299346923828125, "learning_rate": 4.352434506447252e-06, "loss": 0.5589107871055603, "step": 3960 }, { "epoch": 0.5554231227651967, "grad_norm": 3.622695207595825, "learning_rate": 4.3501831037582805e-06, "loss": 0.5341253280639648, "step": 3961 }, { "epoch": 0.5555633457196943, "grad_norm": 4.431001663208008, "learning_rate": 4.347931835076968e-06, "loss": 0.5656461715698242, "step": 3962 }, { "epoch": 0.555703568674192, "grad_norm": 3.1208088397979736, "learning_rate": 4.345680700867577e-06, "loss": 0.5153782963752747, "step": 3963 }, { "epoch": 0.5558437916286896, "grad_norm": 2.9095916748046875, "learning_rate": 4.343429701594352e-06, "loss": 0.3725879192352295, "step": 3964 }, { "epoch": 0.5559840145831872, "grad_norm": 3.064432382583618, "learning_rate": 4.341178837721497e-06, "loss": 0.5113638043403625, "step": 3965 }, { "epoch": 0.5561242375376849, "grad_norm": 4.815274715423584, "learning_rate": 4.338928109713193e-06, "loss": 0.50025874376297, "step": 3966 }, { "epoch": 0.5562644604921826, "grad_norm": 6.642940998077393, "learning_rate": 4.336677518033596e-06, "loss": 0.5514588952064514, "step": 3967 }, { "epoch": 0.5564046834466803, "grad_norm": 2.485116958618164, "learning_rate": 4.334427063146832e-06, "loss": 0.6046525239944458, "step": 3968 }, { "epoch": 0.5565449064011778, "grad_norm": 7.272888660430908, "learning_rate": 4.332176745516995e-06, "loss": 0.55140221118927, "step": 3969 }, { "epoch": 0.5566851293556755, "grad_norm": 2.6265387535095215, "learning_rate": 4.3299265656081565e-06, "loss": 0.4707874655723572, "step": 3970 }, { "epoch": 0.5568253523101732, "grad_norm": 3.1703710556030273, "learning_rate": 4.327676523884358e-06, "loss": 0.5697631239891052, "step": 3971 }, { "epoch": 0.5569655752646708, "grad_norm": 3.124438524246216, "learning_rate": 4.3254266208096065e-06, "loss": 0.4705754220485687, "step": 3972 }, { "epoch": 0.5571057982191685, "grad_norm": 3.0219173431396484, "learning_rate": 4.3231768568478904e-06, "loss": 0.5605061054229736, "step": 3973 }, { "epoch": 0.5572460211736662, "grad_norm": 3.007124900817871, "learning_rate": 4.320927232463162e-06, "loss": 0.5528008937835693, "step": 3974 }, { "epoch": 0.5573862441281637, "grad_norm": 3.295118808746338, "learning_rate": 4.318677748119347e-06, "loss": 0.4543652832508087, "step": 3975 }, { "epoch": 0.5575264670826614, "grad_norm": 2.8399510383605957, "learning_rate": 4.316428404280345e-06, "loss": 0.4886501133441925, "step": 3976 }, { "epoch": 0.5576666900371591, "grad_norm": 5.518484115600586, "learning_rate": 4.314179201410022e-06, "loss": 0.44118666648864746, "step": 3977 }, { "epoch": 0.5578069129916567, "grad_norm": 10.698789596557617, "learning_rate": 4.3119301399722154e-06, "loss": 0.5094638466835022, "step": 3978 }, { "epoch": 0.5579471359461544, "grad_norm": 2.9835948944091797, "learning_rate": 4.309681220430739e-06, "loss": 0.4627450704574585, "step": 3979 }, { "epoch": 0.5580873589006521, "grad_norm": 3.1585428714752197, "learning_rate": 4.30743244324937e-06, "loss": 0.5286569595336914, "step": 3980 }, { "epoch": 0.5582275818551496, "grad_norm": 3.373505115509033, "learning_rate": 4.305183808891861e-06, "loss": 0.5067076683044434, "step": 3981 }, { "epoch": 0.5583678048096473, "grad_norm": 2.642577648162842, "learning_rate": 4.302935317821934e-06, "loss": 0.6185622215270996, "step": 3982 }, { "epoch": 0.558508027764145, "grad_norm": 5.296581745147705, "learning_rate": 4.300686970503281e-06, "loss": 0.5875359773635864, "step": 3983 }, { "epoch": 0.5586482507186427, "grad_norm": 2.254201889038086, "learning_rate": 4.298438767399562e-06, "loss": 0.5837975740432739, "step": 3984 }, { "epoch": 0.5587884736731403, "grad_norm": 3.0840041637420654, "learning_rate": 4.296190708974415e-06, "loss": 0.5739191770553589, "step": 3985 }, { "epoch": 0.558928696627638, "grad_norm": 3.9623732566833496, "learning_rate": 4.293942795691438e-06, "loss": 0.5862715244293213, "step": 3986 }, { "epoch": 0.5590689195821356, "grad_norm": 3.1652963161468506, "learning_rate": 4.291695028014208e-06, "loss": 0.6226147413253784, "step": 3987 }, { "epoch": 0.5592091425366332, "grad_norm": 3.0347115993499756, "learning_rate": 4.289447406406266e-06, "loss": 0.5704355239868164, "step": 3988 }, { "epoch": 0.5593493654911309, "grad_norm": 2.118030309677124, "learning_rate": 4.287199931331124e-06, "loss": 0.43033769726753235, "step": 3989 }, { "epoch": 0.5594895884456286, "grad_norm": 3.921552896499634, "learning_rate": 4.284952603252267e-06, "loss": 0.5077389478683472, "step": 3990 }, { "epoch": 0.5596298114001262, "grad_norm": 4.840326309204102, "learning_rate": 4.282705422633146e-06, "loss": 0.6471073627471924, "step": 3991 }, { "epoch": 0.5597700343546238, "grad_norm": 3.347756862640381, "learning_rate": 4.2804583899371815e-06, "loss": 0.4586896598339081, "step": 3992 }, { "epoch": 0.5599102573091215, "grad_norm": 4.507205009460449, "learning_rate": 4.278211505627769e-06, "loss": 0.5561323761940002, "step": 3993 }, { "epoch": 0.5600504802636191, "grad_norm": 3.2309277057647705, "learning_rate": 4.275964770168266e-06, "loss": 0.4733954668045044, "step": 3994 }, { "epoch": 0.5601907032181168, "grad_norm": 2.3189454078674316, "learning_rate": 4.273718184022001e-06, "loss": 0.38307374715805054, "step": 3995 }, { "epoch": 0.5603309261726145, "grad_norm": 8.52550983428955, "learning_rate": 4.271471747652279e-06, "loss": 0.5492513179779053, "step": 3996 }, { "epoch": 0.5604711491271122, "grad_norm": 3.781151294708252, "learning_rate": 4.269225461522365e-06, "loss": 0.621525764465332, "step": 3997 }, { "epoch": 0.5606113720816097, "grad_norm": 3.75688099861145, "learning_rate": 4.266979326095495e-06, "loss": 0.5162628293037415, "step": 3998 }, { "epoch": 0.5607515950361074, "grad_norm": 6.911566734313965, "learning_rate": 4.2647333418348794e-06, "loss": 0.4598273038864136, "step": 3999 }, { "epoch": 0.5608918179906051, "grad_norm": 2.3168535232543945, "learning_rate": 4.262487509203691e-06, "loss": 0.5203428268432617, "step": 4000 }, { "epoch": 0.5610320409451027, "grad_norm": 3.6025047302246094, "learning_rate": 4.260241828665072e-06, "loss": 0.5157415866851807, "step": 4001 }, { "epoch": 0.5611722638996004, "grad_norm": 2.5155463218688965, "learning_rate": 4.257996300682139e-06, "loss": 0.6844241619110107, "step": 4002 }, { "epoch": 0.5613124868540981, "grad_norm": 4.282206058502197, "learning_rate": 4.255750925717971e-06, "loss": 0.5345407724380493, "step": 4003 }, { "epoch": 0.5614527098085956, "grad_norm": 2.5687015056610107, "learning_rate": 4.253505704235616e-06, "loss": 0.5884969234466553, "step": 4004 }, { "epoch": 0.5615929327630933, "grad_norm": 6.2186808586120605, "learning_rate": 4.251260636698096e-06, "loss": 0.4879082143306732, "step": 4005 }, { "epoch": 0.561733155717591, "grad_norm": 4.358339309692383, "learning_rate": 4.2490157235683945e-06, "loss": 0.5631494522094727, "step": 4006 }, { "epoch": 0.5618733786720886, "grad_norm": 3.8673481941223145, "learning_rate": 4.2467709653094645e-06, "loss": 0.513087272644043, "step": 4007 }, { "epoch": 0.5620136016265863, "grad_norm": 2.4770967960357666, "learning_rate": 4.244526362384232e-06, "loss": 0.5492590665817261, "step": 4008 }, { "epoch": 0.5621538245810839, "grad_norm": 3.5124623775482178, "learning_rate": 4.242281915255586e-06, "loss": 0.4916427433490753, "step": 4009 }, { "epoch": 0.5622940475355815, "grad_norm": 2.963545322418213, "learning_rate": 4.240037624386382e-06, "loss": 0.5353685617446899, "step": 4010 }, { "epoch": 0.5624342704900792, "grad_norm": 2.822659969329834, "learning_rate": 4.2377934902394505e-06, "loss": 0.4975616931915283, "step": 4011 }, { "epoch": 0.5625744934445769, "grad_norm": 2.716008186340332, "learning_rate": 4.235549513277583e-06, "loss": 0.4419533610343933, "step": 4012 }, { "epoch": 0.5627147163990746, "grad_norm": 3.3468241691589355, "learning_rate": 4.233305693963537e-06, "loss": 0.5101169943809509, "step": 4013 }, { "epoch": 0.5628549393535722, "grad_norm": 3.4793341159820557, "learning_rate": 4.231062032760049e-06, "loss": 0.4898996949195862, "step": 4014 }, { "epoch": 0.5629951623080698, "grad_norm": 2.7707977294921875, "learning_rate": 4.228818530129809e-06, "loss": 0.5340731739997864, "step": 4015 }, { "epoch": 0.5631353852625675, "grad_norm": 2.532254219055176, "learning_rate": 4.226575186535484e-06, "loss": 0.5305583477020264, "step": 4016 }, { "epoch": 0.5632756082170651, "grad_norm": 3.091278553009033, "learning_rate": 4.2243320024397035e-06, "loss": 0.5046675801277161, "step": 4017 }, { "epoch": 0.5634158311715628, "grad_norm": 4.419100284576416, "learning_rate": 4.222088978305063e-06, "loss": 0.5020978450775146, "step": 4018 }, { "epoch": 0.5635560541260605, "grad_norm": 3.8940985202789307, "learning_rate": 4.219846114594132e-06, "loss": 0.5067443251609802, "step": 4019 }, { "epoch": 0.5636962770805581, "grad_norm": 2.706737756729126, "learning_rate": 4.2176034117694395e-06, "loss": 0.5259050130844116, "step": 4020 }, { "epoch": 0.5638365000350557, "grad_norm": 3.10794997215271, "learning_rate": 4.215360870293482e-06, "loss": 0.5608267784118652, "step": 4021 }, { "epoch": 0.5639767229895534, "grad_norm": 5.345795154571533, "learning_rate": 4.213118490628728e-06, "loss": 0.6261716485023499, "step": 4022 }, { "epoch": 0.564116945944051, "grad_norm": 3.56490421295166, "learning_rate": 4.210876273237609e-06, "loss": 0.5632247924804688, "step": 4023 }, { "epoch": 0.5642571688985487, "grad_norm": 5.472055435180664, "learning_rate": 4.2086342185825216e-06, "loss": 0.4807048439979553, "step": 4024 }, { "epoch": 0.5643973918530464, "grad_norm": 5.275096893310547, "learning_rate": 4.2063923271258326e-06, "loss": 0.49719399213790894, "step": 4025 }, { "epoch": 0.5645376148075439, "grad_norm": 5.517698287963867, "learning_rate": 4.204150599329872e-06, "loss": 0.5870274305343628, "step": 4026 }, { "epoch": 0.5646778377620416, "grad_norm": 3.8354973793029785, "learning_rate": 4.201909035656937e-06, "loss": 0.4638013243675232, "step": 4027 }, { "epoch": 0.5648180607165393, "grad_norm": 4.538815021514893, "learning_rate": 4.199667636569293e-06, "loss": 0.5237152576446533, "step": 4028 }, { "epoch": 0.564958283671037, "grad_norm": 3.3260107040405273, "learning_rate": 4.197426402529168e-06, "loss": 0.44104036688804626, "step": 4029 }, { "epoch": 0.5650985066255346, "grad_norm": 2.491133213043213, "learning_rate": 4.195185333998757e-06, "loss": 0.47245949506759644, "step": 4030 }, { "epoch": 0.5652387295800323, "grad_norm": 3.80487322807312, "learning_rate": 4.192944431440224e-06, "loss": 0.4522397816181183, "step": 4031 }, { "epoch": 0.5653789525345299, "grad_norm": 7.633970260620117, "learning_rate": 4.190703695315695e-06, "loss": 0.5357961654663086, "step": 4032 }, { "epoch": 0.5655191754890275, "grad_norm": 4.462482452392578, "learning_rate": 4.188463126087261e-06, "loss": 0.5581026077270508, "step": 4033 }, { "epoch": 0.5656593984435252, "grad_norm": 2.749624490737915, "learning_rate": 4.186222724216984e-06, "loss": 0.5534788370132446, "step": 4034 }, { "epoch": 0.5657996213980229, "grad_norm": 3.712918758392334, "learning_rate": 4.1839824901668866e-06, "loss": 0.5156274437904358, "step": 4035 }, { "epoch": 0.5659398443525205, "grad_norm": 2.625267267227173, "learning_rate": 4.181742424398956e-06, "loss": 0.5335948467254639, "step": 4036 }, { "epoch": 0.5660800673070182, "grad_norm": 3.1668343544006348, "learning_rate": 4.17950252737515e-06, "loss": 0.5580194592475891, "step": 4037 }, { "epoch": 0.5662202902615158, "grad_norm": 6.080994606018066, "learning_rate": 4.177262799557388e-06, "loss": 0.5619170665740967, "step": 4038 }, { "epoch": 0.5663605132160134, "grad_norm": 2.753643035888672, "learning_rate": 4.175023241407552e-06, "loss": 0.49942076206207275, "step": 4039 }, { "epoch": 0.5665007361705111, "grad_norm": 7.352983474731445, "learning_rate": 4.172783853387497e-06, "loss": 0.5142922401428223, "step": 4040 }, { "epoch": 0.5666409591250088, "grad_norm": 6.107021331787109, "learning_rate": 4.170544635959035e-06, "loss": 0.5827980041503906, "step": 4041 }, { "epoch": 0.5667811820795065, "grad_norm": 3.1489131450653076, "learning_rate": 4.168305589583944e-06, "loss": 0.5691184401512146, "step": 4042 }, { "epoch": 0.566921405034004, "grad_norm": 3.2257437705993652, "learning_rate": 4.1660667147239734e-06, "loss": 0.5202795267105103, "step": 4043 }, { "epoch": 0.5670616279885017, "grad_norm": 2.8501007556915283, "learning_rate": 4.163828011840826e-06, "loss": 0.5432920455932617, "step": 4044 }, { "epoch": 0.5672018509429994, "grad_norm": 14.930992126464844, "learning_rate": 4.161589481396181e-06, "loss": 0.5264945030212402, "step": 4045 }, { "epoch": 0.567342073897497, "grad_norm": 4.10505485534668, "learning_rate": 4.159351123851676e-06, "loss": 0.5665394067764282, "step": 4046 }, { "epoch": 0.5674822968519947, "grad_norm": 2.9173853397369385, "learning_rate": 4.157112939668908e-06, "loss": 0.43186652660369873, "step": 4047 }, { "epoch": 0.5676225198064924, "grad_norm": 2.8019208908081055, "learning_rate": 4.154874929309451e-06, "loss": 0.5536936521530151, "step": 4048 }, { "epoch": 0.5677627427609899, "grad_norm": 2.802155017852783, "learning_rate": 4.152637093234831e-06, "loss": 0.5514081716537476, "step": 4049 }, { "epoch": 0.5679029657154876, "grad_norm": 3.322183847427368, "learning_rate": 4.150399431906542e-06, "loss": 0.5383419990539551, "step": 4050 }, { "epoch": 0.5680431886699853, "grad_norm": 3.9235944747924805, "learning_rate": 4.148161945786048e-06, "loss": 0.5474236011505127, "step": 4051 }, { "epoch": 0.5681834116244829, "grad_norm": 2.692639112472534, "learning_rate": 4.1459246353347695e-06, "loss": 0.45126873254776, "step": 4052 }, { "epoch": 0.5683236345789806, "grad_norm": 3.1260862350463867, "learning_rate": 4.143687501014089e-06, "loss": 0.505005955696106, "step": 4053 }, { "epoch": 0.5684638575334783, "grad_norm": 5.407512187957764, "learning_rate": 4.141450543285362e-06, "loss": 0.46031951904296875, "step": 4054 }, { "epoch": 0.5686040804879758, "grad_norm": 2.7211990356445312, "learning_rate": 4.139213762609901e-06, "loss": 0.5166410207748413, "step": 4055 }, { "epoch": 0.5687443034424735, "grad_norm": 11.951533317565918, "learning_rate": 4.1369771594489785e-06, "loss": 0.4583852291107178, "step": 4056 }, { "epoch": 0.5688845263969712, "grad_norm": 5.955143451690674, "learning_rate": 4.134740734263843e-06, "loss": 0.47307252883911133, "step": 4057 }, { "epoch": 0.5690247493514689, "grad_norm": 3.1261067390441895, "learning_rate": 4.132504487515694e-06, "loss": 0.515160322189331, "step": 4058 }, { "epoch": 0.5691649723059665, "grad_norm": 4.13126802444458, "learning_rate": 4.130268419665696e-06, "loss": 0.5287954807281494, "step": 4059 }, { "epoch": 0.5693051952604642, "grad_norm": 3.8733503818511963, "learning_rate": 4.128032531174986e-06, "loss": 0.5550782680511475, "step": 4060 }, { "epoch": 0.5694454182149618, "grad_norm": 3.309600353240967, "learning_rate": 4.125796822504652e-06, "loss": 0.45613232254981995, "step": 4061 }, { "epoch": 0.5695856411694594, "grad_norm": 3.174168825149536, "learning_rate": 4.123561294115751e-06, "loss": 0.5099959373474121, "step": 4062 }, { "epoch": 0.5697258641239571, "grad_norm": 3.472465991973877, "learning_rate": 4.121325946469304e-06, "loss": 0.4532400667667389, "step": 4063 }, { "epoch": 0.5698660870784548, "grad_norm": 3.4407191276550293, "learning_rate": 4.119090780026291e-06, "loss": 0.48738062381744385, "step": 4064 }, { "epoch": 0.5700063100329524, "grad_norm": 4.621581554412842, "learning_rate": 4.1168557952476565e-06, "loss": 0.5657431483268738, "step": 4065 }, { "epoch": 0.57014653298745, "grad_norm": 25.665075302124023, "learning_rate": 4.114620992594308e-06, "loss": 0.5149795413017273, "step": 4066 }, { "epoch": 0.5702867559419477, "grad_norm": 2.6855275630950928, "learning_rate": 4.112386372527115e-06, "loss": 0.5125418305397034, "step": 4067 }, { "epoch": 0.5704269788964453, "grad_norm": 2.9915144443511963, "learning_rate": 4.110151935506907e-06, "loss": 0.45342153310775757, "step": 4068 }, { "epoch": 0.570567201850943, "grad_norm": 3.1535708904266357, "learning_rate": 4.107917681994481e-06, "loss": 0.46054625511169434, "step": 4069 }, { "epoch": 0.5707074248054407, "grad_norm": 11.282730102539062, "learning_rate": 4.1056836124505925e-06, "loss": 0.4130423069000244, "step": 4070 }, { "epoch": 0.5708476477599383, "grad_norm": 3.3221843242645264, "learning_rate": 4.103449727335956e-06, "loss": 0.48935338854789734, "step": 4071 }, { "epoch": 0.5709878707144359, "grad_norm": 3.5625619888305664, "learning_rate": 4.1012160271112565e-06, "loss": 0.5123608112335205, "step": 4072 }, { "epoch": 0.5711280936689336, "grad_norm": 10.297258377075195, "learning_rate": 4.098982512237135e-06, "loss": 0.5580488443374634, "step": 4073 }, { "epoch": 0.5712683166234312, "grad_norm": 3.3515193462371826, "learning_rate": 4.096749183174191e-06, "loss": 0.6149047613143921, "step": 4074 }, { "epoch": 0.5714085395779289, "grad_norm": 3.317218065261841, "learning_rate": 4.0945160403829945e-06, "loss": 0.46338963508605957, "step": 4075 }, { "epoch": 0.5715487625324266, "grad_norm": 2.9714794158935547, "learning_rate": 4.09228308432407e-06, "loss": 0.5135154724121094, "step": 4076 }, { "epoch": 0.5716889854869243, "grad_norm": 2.4533982276916504, "learning_rate": 4.090050315457909e-06, "loss": 0.5255056619644165, "step": 4077 }, { "epoch": 0.5718292084414218, "grad_norm": 3.364553689956665, "learning_rate": 4.08781773424496e-06, "loss": 0.6152592897415161, "step": 4078 }, { "epoch": 0.5719694313959195, "grad_norm": 3.2909364700317383, "learning_rate": 4.085585341145631e-06, "loss": 0.5991331338882446, "step": 4079 }, { "epoch": 0.5721096543504172, "grad_norm": 3.660181999206543, "learning_rate": 4.083353136620299e-06, "loss": 0.5629077553749084, "step": 4080 }, { "epoch": 0.5722498773049148, "grad_norm": 9.728118896484375, "learning_rate": 4.081121121129296e-06, "loss": 0.3472108840942383, "step": 4081 }, { "epoch": 0.5723901002594125, "grad_norm": 4.888747215270996, "learning_rate": 4.078889295132914e-06, "loss": 0.6692629456520081, "step": 4082 }, { "epoch": 0.5725303232139101, "grad_norm": 2.925691604614258, "learning_rate": 4.076657659091413e-06, "loss": 0.4626062512397766, "step": 4083 }, { "epoch": 0.5726705461684077, "grad_norm": 2.4978442192077637, "learning_rate": 4.074426213465007e-06, "loss": 0.39937520027160645, "step": 4084 }, { "epoch": 0.5728107691229054, "grad_norm": 3.8914642333984375, "learning_rate": 4.07219495871387e-06, "loss": 0.5238268375396729, "step": 4085 }, { "epoch": 0.5729509920774031, "grad_norm": 3.3368592262268066, "learning_rate": 4.0699638952981454e-06, "loss": 0.5926934480667114, "step": 4086 }, { "epoch": 0.5730912150319007, "grad_norm": 3.7717583179473877, "learning_rate": 4.067733023677929e-06, "loss": 0.5422059893608093, "step": 4087 }, { "epoch": 0.5732314379863984, "grad_norm": 3.723858594894409, "learning_rate": 4.065502344313277e-06, "loss": 0.5720205307006836, "step": 4088 }, { "epoch": 0.573371660940896, "grad_norm": 3.4135591983795166, "learning_rate": 4.063271857664212e-06, "loss": 0.6343152523040771, "step": 4089 }, { "epoch": 0.5735118838953936, "grad_norm": 3.925553321838379, "learning_rate": 4.061041564190712e-06, "loss": 0.47463327646255493, "step": 4090 }, { "epoch": 0.5736521068498913, "grad_norm": 3.4028875827789307, "learning_rate": 4.058811464352714e-06, "loss": 0.513318657875061, "step": 4091 }, { "epoch": 0.573792329804389, "grad_norm": 6.411593437194824, "learning_rate": 4.056581558610122e-06, "loss": 0.519135594367981, "step": 4092 }, { "epoch": 0.5739325527588867, "grad_norm": 3.2515690326690674, "learning_rate": 4.054351847422793e-06, "loss": 0.47956228256225586, "step": 4093 }, { "epoch": 0.5740727757133843, "grad_norm": 3.2208170890808105, "learning_rate": 4.052122331250544e-06, "loss": 0.5265282988548279, "step": 4094 }, { "epoch": 0.5742129986678819, "grad_norm": 3.2642784118652344, "learning_rate": 4.04989301055316e-06, "loss": 0.46310174465179443, "step": 4095 }, { "epoch": 0.5743532216223796, "grad_norm": 3.181745767593384, "learning_rate": 4.047663885790375e-06, "loss": 0.5907776355743408, "step": 4096 }, { "epoch": 0.5744934445768772, "grad_norm": 2.963029623031616, "learning_rate": 4.045434957421887e-06, "loss": 0.5361472368240356, "step": 4097 }, { "epoch": 0.5746336675313749, "grad_norm": 6.057513236999512, "learning_rate": 4.0432062259073575e-06, "loss": 0.5313870310783386, "step": 4098 }, { "epoch": 0.5747738904858726, "grad_norm": 2.4399421215057373, "learning_rate": 4.040977691706404e-06, "loss": 0.5790433883666992, "step": 4099 }, { "epoch": 0.5749141134403701, "grad_norm": 4.100008487701416, "learning_rate": 4.038749355278597e-06, "loss": 0.4289432764053345, "step": 4100 }, { "epoch": 0.5750543363948678, "grad_norm": 3.905219554901123, "learning_rate": 4.03652121708348e-06, "loss": 0.5120317935943604, "step": 4101 }, { "epoch": 0.5751945593493655, "grad_norm": 2.8125057220458984, "learning_rate": 4.034293277580543e-06, "loss": 0.549470067024231, "step": 4102 }, { "epoch": 0.5753347823038631, "grad_norm": 3.9111568927764893, "learning_rate": 4.03206553722924e-06, "loss": 0.5318489074707031, "step": 4103 }, { "epoch": 0.5754750052583608, "grad_norm": 2.716190814971924, "learning_rate": 4.029837996488987e-06, "loss": 0.6554157137870789, "step": 4104 }, { "epoch": 0.5756152282128585, "grad_norm": 3.5985894203186035, "learning_rate": 4.027610655819153e-06, "loss": 0.5034215450286865, "step": 4105 }, { "epoch": 0.575755451167356, "grad_norm": 2.5933079719543457, "learning_rate": 4.0253835156790715e-06, "loss": 0.5914987325668335, "step": 4106 }, { "epoch": 0.5758956741218537, "grad_norm": 2.4494006633758545, "learning_rate": 4.023156576528029e-06, "loss": 0.49043017625808716, "step": 4107 }, { "epoch": 0.5760358970763514, "grad_norm": 4.148082256317139, "learning_rate": 4.020929838825272e-06, "loss": 0.5848387479782104, "step": 4108 }, { "epoch": 0.5761761200308491, "grad_norm": 2.93638014793396, "learning_rate": 4.01870330303001e-06, "loss": 0.5421127676963806, "step": 4109 }, { "epoch": 0.5763163429853467, "grad_norm": 2.7229998111724854, "learning_rate": 4.016476969601407e-06, "loss": 0.5873182415962219, "step": 4110 }, { "epoch": 0.5764565659398444, "grad_norm": 2.2729854583740234, "learning_rate": 4.014250838998582e-06, "loss": 0.44806382060050964, "step": 4111 }, { "epoch": 0.576596788894342, "grad_norm": 4.377781867980957, "learning_rate": 4.0120249116806224e-06, "loss": 0.5419905185699463, "step": 4112 }, { "epoch": 0.5767370118488396, "grad_norm": 3.362595319747925, "learning_rate": 4.009799188106562e-06, "loss": 0.482620507478714, "step": 4113 }, { "epoch": 0.5768772348033373, "grad_norm": 5.601868629455566, "learning_rate": 4.0075736687353976e-06, "loss": 0.4897598624229431, "step": 4114 }, { "epoch": 0.577017457757835, "grad_norm": 2.7852280139923096, "learning_rate": 4.005348354026087e-06, "loss": 0.5743094682693481, "step": 4115 }, { "epoch": 0.5771576807123326, "grad_norm": 3.011096477508545, "learning_rate": 4.003123244437543e-06, "loss": 0.5627833604812622, "step": 4116 }, { "epoch": 0.5772979036668303, "grad_norm": 2.61482310295105, "learning_rate": 4.000898340428632e-06, "loss": 0.4235353469848633, "step": 4117 }, { "epoch": 0.5774381266213279, "grad_norm": 2.780301809310913, "learning_rate": 3.9986736424581875e-06, "loss": 0.4811422526836395, "step": 4118 }, { "epoch": 0.5775783495758255, "grad_norm": 2.789754629135132, "learning_rate": 3.996449150984992e-06, "loss": 0.6534761190414429, "step": 4119 }, { "epoch": 0.5777185725303232, "grad_norm": 4.449388027191162, "learning_rate": 3.994224866467786e-06, "loss": 0.479677677154541, "step": 4120 }, { "epoch": 0.5778587954848209, "grad_norm": 2.5080883502960205, "learning_rate": 3.992000789365275e-06, "loss": 0.47233664989471436, "step": 4121 }, { "epoch": 0.5779990184393186, "grad_norm": 5.256181240081787, "learning_rate": 3.989776920136113e-06, "loss": 0.4751368761062622, "step": 4122 }, { "epoch": 0.5781392413938161, "grad_norm": 3.1507019996643066, "learning_rate": 3.987553259238913e-06, "loss": 0.500329852104187, "step": 4123 }, { "epoch": 0.5782794643483138, "grad_norm": 3.7159836292266846, "learning_rate": 3.985329807132252e-06, "loss": 0.5241758227348328, "step": 4124 }, { "epoch": 0.5784196873028115, "grad_norm": 2.876922845840454, "learning_rate": 3.983106564274656e-06, "loss": 0.46534058451652527, "step": 4125 }, { "epoch": 0.5785599102573091, "grad_norm": 2.4964423179626465, "learning_rate": 3.980883531124607e-06, "loss": 0.3835398852825165, "step": 4126 }, { "epoch": 0.5787001332118068, "grad_norm": 6.3340864181518555, "learning_rate": 3.978660708140552e-06, "loss": 0.4504207968711853, "step": 4127 }, { "epoch": 0.5788403561663045, "grad_norm": 3.3042476177215576, "learning_rate": 3.976438095780889e-06, "loss": 0.5650078654289246, "step": 4128 }, { "epoch": 0.578980579120802, "grad_norm": 2.449472188949585, "learning_rate": 3.97421569450397e-06, "loss": 0.5527181625366211, "step": 4129 }, { "epoch": 0.5791208020752997, "grad_norm": 4.210290431976318, "learning_rate": 3.971993504768111e-06, "loss": 0.5789567828178406, "step": 4130 }, { "epoch": 0.5792610250297974, "grad_norm": 2.4076192378997803, "learning_rate": 3.969771527031579e-06, "loss": 0.5318318009376526, "step": 4131 }, { "epoch": 0.579401247984295, "grad_norm": 3.0459022521972656, "learning_rate": 3.967549761752596e-06, "loss": 0.5364704132080078, "step": 4132 }, { "epoch": 0.5795414709387927, "grad_norm": 6.022916316986084, "learning_rate": 3.9653282093893464e-06, "loss": 0.5429417490959167, "step": 4133 }, { "epoch": 0.5796816938932904, "grad_norm": 5.870087623596191, "learning_rate": 3.963106870399963e-06, "loss": 0.5227692723274231, "step": 4134 }, { "epoch": 0.5798219168477879, "grad_norm": 5.049280643463135, "learning_rate": 3.9608857452425436e-06, "loss": 0.5685380697250366, "step": 4135 }, { "epoch": 0.5799621398022856, "grad_norm": 4.381989479064941, "learning_rate": 3.958664834375134e-06, "loss": 0.5485374331474304, "step": 4136 }, { "epoch": 0.5801023627567833, "grad_norm": 3.5796823501586914, "learning_rate": 3.956444138255737e-06, "loss": 0.5451476573944092, "step": 4137 }, { "epoch": 0.580242585711281, "grad_norm": 2.7186450958251953, "learning_rate": 3.9542236573423164e-06, "loss": 0.5132446885108948, "step": 4138 }, { "epoch": 0.5803828086657786, "grad_norm": 3.4243292808532715, "learning_rate": 3.952003392092787e-06, "loss": 0.5980234146118164, "step": 4139 }, { "epoch": 0.5805230316202762, "grad_norm": 3.74318265914917, "learning_rate": 3.949783342965017e-06, "loss": 0.5351474285125732, "step": 4140 }, { "epoch": 0.5806632545747739, "grad_norm": 3.934255361557007, "learning_rate": 3.947563510416838e-06, "loss": 0.4964054226875305, "step": 4141 }, { "epoch": 0.5808034775292715, "grad_norm": 2.5800867080688477, "learning_rate": 3.94534389490603e-06, "loss": 0.6076622605323792, "step": 4142 }, { "epoch": 0.5809437004837692, "grad_norm": 6.537347793579102, "learning_rate": 3.943124496890328e-06, "loss": 0.46899086236953735, "step": 4143 }, { "epoch": 0.5810839234382669, "grad_norm": 2.3009073734283447, "learning_rate": 3.940905316827428e-06, "loss": 0.5363288521766663, "step": 4144 }, { "epoch": 0.5812241463927645, "grad_norm": 2.7878684997558594, "learning_rate": 3.938686355174977e-06, "loss": 0.47721612453460693, "step": 4145 }, { "epoch": 0.5813643693472621, "grad_norm": 25.027626037597656, "learning_rate": 3.9364676123905755e-06, "loss": 0.559613823890686, "step": 4146 }, { "epoch": 0.5815045923017598, "grad_norm": 3.456604242324829, "learning_rate": 3.934249088931784e-06, "loss": 0.5665650367736816, "step": 4147 }, { "epoch": 0.5816448152562574, "grad_norm": 7.8299994468688965, "learning_rate": 3.932030785256113e-06, "loss": 0.41715899109840393, "step": 4148 }, { "epoch": 0.5817850382107551, "grad_norm": 9.785177230834961, "learning_rate": 3.929812701821028e-06, "loss": 0.4608486592769623, "step": 4149 }, { "epoch": 0.5819252611652528, "grad_norm": 2.9264283180236816, "learning_rate": 3.927594839083953e-06, "loss": 0.45607519149780273, "step": 4150 }, { "epoch": 0.5820654841197505, "grad_norm": 3.292477607727051, "learning_rate": 3.925377197502262e-06, "loss": 0.45996469259262085, "step": 4151 }, { "epoch": 0.582205707074248, "grad_norm": 3.547835111618042, "learning_rate": 3.923159777533284e-06, "loss": 0.529281497001648, "step": 4152 }, { "epoch": 0.5823459300287457, "grad_norm": 3.989295482635498, "learning_rate": 3.920942579634308e-06, "loss": 0.5347046852111816, "step": 4153 }, { "epoch": 0.5824861529832434, "grad_norm": 3.5073368549346924, "learning_rate": 3.9187256042625705e-06, "loss": 0.515035092830658, "step": 4154 }, { "epoch": 0.582626375937741, "grad_norm": 3.2605817317962646, "learning_rate": 3.916508851875262e-06, "loss": 0.5509920120239258, "step": 4155 }, { "epoch": 0.5827665988922387, "grad_norm": 2.809239149093628, "learning_rate": 3.914292322929534e-06, "loss": 0.6000749468803406, "step": 4156 }, { "epoch": 0.5829068218467363, "grad_norm": 7.044718265533447, "learning_rate": 3.912076017882485e-06, "loss": 0.5453749895095825, "step": 4157 }, { "epoch": 0.5830470448012339, "grad_norm": 10.812948226928711, "learning_rate": 3.909859937191166e-06, "loss": 0.5252714157104492, "step": 4158 }, { "epoch": 0.5831872677557316, "grad_norm": 3.131136655807495, "learning_rate": 3.907644081312593e-06, "loss": 0.595772922039032, "step": 4159 }, { "epoch": 0.5833274907102293, "grad_norm": 3.89052152633667, "learning_rate": 3.905428450703725e-06, "loss": 0.5959212779998779, "step": 4160 }, { "epoch": 0.5834677136647269, "grad_norm": 2.7150657176971436, "learning_rate": 3.903213045821472e-06, "loss": 0.5379699468612671, "step": 4161 }, { "epoch": 0.5836079366192246, "grad_norm": 5.823609352111816, "learning_rate": 3.900997867122713e-06, "loss": 0.542300283908844, "step": 4162 }, { "epoch": 0.5837481595737222, "grad_norm": 3.4316861629486084, "learning_rate": 3.89878291506426e-06, "loss": 0.5309576988220215, "step": 4163 }, { "epoch": 0.5838883825282198, "grad_norm": 3.3441321849823, "learning_rate": 3.896568190102898e-06, "loss": 0.5878811478614807, "step": 4164 }, { "epoch": 0.5840286054827175, "grad_norm": 7.098116874694824, "learning_rate": 3.894353692695351e-06, "loss": 0.6099565029144287, "step": 4165 }, { "epoch": 0.5841688284372152, "grad_norm": 2.8728771209716797, "learning_rate": 3.8921394232982995e-06, "loss": 0.5522712469100952, "step": 4166 }, { "epoch": 0.5843090513917129, "grad_norm": 4.090889930725098, "learning_rate": 3.889925382368383e-06, "loss": 0.5739958882331848, "step": 4167 }, { "epoch": 0.5844492743462105, "grad_norm": 2.707253932952881, "learning_rate": 3.887711570362186e-06, "loss": 0.48468679189682007, "step": 4168 }, { "epoch": 0.5845894973007081, "grad_norm": 6.6093926429748535, "learning_rate": 3.885497987736248e-06, "loss": 0.5680230259895325, "step": 4169 }, { "epoch": 0.5847297202552058, "grad_norm": 2.5321176052093506, "learning_rate": 3.883284634947066e-06, "loss": 0.5027399659156799, "step": 4170 }, { "epoch": 0.5848699432097034, "grad_norm": 2.1856753826141357, "learning_rate": 3.881071512451085e-06, "loss": 0.5813214778900146, "step": 4171 }, { "epoch": 0.5850101661642011, "grad_norm": 2.9052658081054688, "learning_rate": 3.878858620704699e-06, "loss": 0.5487319231033325, "step": 4172 }, { "epoch": 0.5851503891186988, "grad_norm": 3.522336959838867, "learning_rate": 3.8766459601642635e-06, "loss": 0.533974289894104, "step": 4173 }, { "epoch": 0.5852906120731964, "grad_norm": 5.999110221862793, "learning_rate": 3.8744335312860815e-06, "loss": 0.38486310839653015, "step": 4174 }, { "epoch": 0.585430835027694, "grad_norm": 3.8472917079925537, "learning_rate": 3.8722213345264035e-06, "loss": 0.5313677787780762, "step": 4175 }, { "epoch": 0.5855710579821917, "grad_norm": 3.1977288722991943, "learning_rate": 3.870009370341443e-06, "loss": 0.5272695422172546, "step": 4176 }, { "epoch": 0.5857112809366893, "grad_norm": 2.5502378940582275, "learning_rate": 3.867797639187358e-06, "loss": 0.5736607909202576, "step": 4177 }, { "epoch": 0.585851503891187, "grad_norm": 4.134174346923828, "learning_rate": 3.865586141520256e-06, "loss": 0.5080665349960327, "step": 4178 }, { "epoch": 0.5859917268456847, "grad_norm": 4.349358081817627, "learning_rate": 3.863374877796205e-06, "loss": 0.5236660242080688, "step": 4179 }, { "epoch": 0.5861319498001822, "grad_norm": 3.8427791595458984, "learning_rate": 3.861163848471218e-06, "loss": 0.5983158349990845, "step": 4180 }, { "epoch": 0.5862721727546799, "grad_norm": 2.934234380722046, "learning_rate": 3.8589530540012595e-06, "loss": 0.4190900921821594, "step": 4181 }, { "epoch": 0.5864123957091776, "grad_norm": 7.929488182067871, "learning_rate": 3.856742494842252e-06, "loss": 0.5383700132369995, "step": 4182 }, { "epoch": 0.5865526186636753, "grad_norm": 6.054075241088867, "learning_rate": 3.854532171450065e-06, "loss": 0.507307231426239, "step": 4183 }, { "epoch": 0.5866928416181729, "grad_norm": 2.9772226810455322, "learning_rate": 3.852322084280514e-06, "loss": 0.512312114238739, "step": 4184 }, { "epoch": 0.5868330645726706, "grad_norm": 2.389390468597412, "learning_rate": 3.850112233789378e-06, "loss": 0.5586613416671753, "step": 4185 }, { "epoch": 0.5869732875271682, "grad_norm": 3.294590711593628, "learning_rate": 3.847902620432378e-06, "loss": 0.43468165397644043, "step": 4186 }, { "epoch": 0.5871135104816658, "grad_norm": 4.097659587860107, "learning_rate": 3.845693244665188e-06, "loss": 0.5096931457519531, "step": 4187 }, { "epoch": 0.5872537334361635, "grad_norm": 3.1251988410949707, "learning_rate": 3.843484106943435e-06, "loss": 0.5346824526786804, "step": 4188 }, { "epoch": 0.5873939563906612, "grad_norm": 2.283250331878662, "learning_rate": 3.841275207722693e-06, "loss": 0.47975456714630127, "step": 4189 }, { "epoch": 0.5875341793451588, "grad_norm": 3.84660267829895, "learning_rate": 3.839066547458492e-06, "loss": 0.5057746767997742, "step": 4190 }, { "epoch": 0.5876744022996565, "grad_norm": 2.825204610824585, "learning_rate": 3.836858126606312e-06, "loss": 0.5461519956588745, "step": 4191 }, { "epoch": 0.5878146252541541, "grad_norm": 2.6809604167938232, "learning_rate": 3.8346499456215755e-06, "loss": 0.47803300619125366, "step": 4192 }, { "epoch": 0.5879548482086517, "grad_norm": 4.26801061630249, "learning_rate": 3.832442004959668e-06, "loss": 0.49476340413093567, "step": 4193 }, { "epoch": 0.5880950711631494, "grad_norm": 2.711836814880371, "learning_rate": 3.8302343050759175e-06, "loss": 0.5256617665290833, "step": 4194 }, { "epoch": 0.5882352941176471, "grad_norm": 3.9826879501342773, "learning_rate": 3.828026846425601e-06, "loss": 0.5787928104400635, "step": 4195 }, { "epoch": 0.5883755170721447, "grad_norm": 3.309420347213745, "learning_rate": 3.825819629463953e-06, "loss": 0.5660369396209717, "step": 4196 }, { "epoch": 0.5885157400266423, "grad_norm": 3.1602628231048584, "learning_rate": 3.823612654646152e-06, "loss": 0.5221859812736511, "step": 4197 }, { "epoch": 0.58865596298114, "grad_norm": 2.5757088661193848, "learning_rate": 3.821405922427328e-06, "loss": 0.43893295526504517, "step": 4198 }, { "epoch": 0.5887961859356377, "grad_norm": 2.704533576965332, "learning_rate": 3.819199433262563e-06, "loss": 0.6236251592636108, "step": 4199 }, { "epoch": 0.5889364088901353, "grad_norm": 3.0130467414855957, "learning_rate": 3.816993187606887e-06, "loss": 0.4611266851425171, "step": 4200 }, { "epoch": 0.589076631844633, "grad_norm": 4.351582050323486, "learning_rate": 3.814787185915278e-06, "loss": 0.49494752287864685, "step": 4201 }, { "epoch": 0.5892168547991307, "grad_norm": 4.555775165557861, "learning_rate": 3.8125814286426703e-06, "loss": 0.47814813256263733, "step": 4202 }, { "epoch": 0.5893570777536282, "grad_norm": 2.940519332885742, "learning_rate": 3.8103759162439403e-06, "loss": 0.5451829433441162, "step": 4203 }, { "epoch": 0.5894973007081259, "grad_norm": 3.0844357013702393, "learning_rate": 3.8081706491739166e-06, "loss": 0.4973866641521454, "step": 4204 }, { "epoch": 0.5896375236626236, "grad_norm": 3.109874725341797, "learning_rate": 3.80596562788738e-06, "loss": 0.4632493555545807, "step": 4205 }, { "epoch": 0.5897777466171212, "grad_norm": 2.9899489879608154, "learning_rate": 3.8037608528390558e-06, "loss": 0.5495700836181641, "step": 4206 }, { "epoch": 0.5899179695716189, "grad_norm": 3.8951382637023926, "learning_rate": 3.8015563244836216e-06, "loss": 0.5465565919876099, "step": 4207 }, { "epoch": 0.5900581925261166, "grad_norm": 3.6825687885284424, "learning_rate": 3.7993520432757048e-06, "loss": 0.4820742905139923, "step": 4208 }, { "epoch": 0.5901984154806141, "grad_norm": 2.7219631671905518, "learning_rate": 3.7971480096698786e-06, "loss": 0.4902624189853668, "step": 4209 }, { "epoch": 0.5903386384351118, "grad_norm": 4.035872936248779, "learning_rate": 3.7949442241206672e-06, "loss": 0.49148136377334595, "step": 4210 }, { "epoch": 0.5904788613896095, "grad_norm": 3.253988742828369, "learning_rate": 3.7927406870825455e-06, "loss": 0.5062993764877319, "step": 4211 }, { "epoch": 0.5906190843441071, "grad_norm": 4.064863681793213, "learning_rate": 3.790537399009933e-06, "loss": 0.5387281179428101, "step": 4212 }, { "epoch": 0.5907593072986048, "grad_norm": 3.556687116622925, "learning_rate": 3.7883343603572005e-06, "loss": 0.4995042383670807, "step": 4213 }, { "epoch": 0.5908995302531024, "grad_norm": 5.4112725257873535, "learning_rate": 3.786131571578668e-06, "loss": 0.6563344597816467, "step": 4214 }, { "epoch": 0.5910397532076, "grad_norm": 4.061412811279297, "learning_rate": 3.7839290331286004e-06, "loss": 0.4935677647590637, "step": 4215 }, { "epoch": 0.5911799761620977, "grad_norm": 3.269148588180542, "learning_rate": 3.781726745461215e-06, "loss": 0.5766551494598389, "step": 4216 }, { "epoch": 0.5913201991165954, "grad_norm": 4.159206390380859, "learning_rate": 3.7795247090306767e-06, "loss": 0.5753316879272461, "step": 4217 }, { "epoch": 0.5914604220710931, "grad_norm": 7.102402210235596, "learning_rate": 3.777322924291096e-06, "loss": 0.5303224325180054, "step": 4218 }, { "epoch": 0.5916006450255907, "grad_norm": 3.853898525238037, "learning_rate": 3.7751213916965324e-06, "loss": 0.5110304355621338, "step": 4219 }, { "epoch": 0.5917408679800883, "grad_norm": 3.8016226291656494, "learning_rate": 3.7729201117009974e-06, "loss": 0.5631788969039917, "step": 4220 }, { "epoch": 0.591881090934586, "grad_norm": 2.2695844173431396, "learning_rate": 3.7707190847584426e-06, "loss": 0.5934891700744629, "step": 4221 }, { "epoch": 0.5920213138890836, "grad_norm": 4.5191569328308105, "learning_rate": 3.7685183113227763e-06, "loss": 0.5005789399147034, "step": 4222 }, { "epoch": 0.5921615368435813, "grad_norm": 4.683962345123291, "learning_rate": 3.766317791847848e-06, "loss": 0.6198642253875732, "step": 4223 }, { "epoch": 0.592301759798079, "grad_norm": 6.163943290710449, "learning_rate": 3.764117526787457e-06, "loss": 0.5371771454811096, "step": 4224 }, { "epoch": 0.5924419827525766, "grad_norm": 10.934410095214844, "learning_rate": 3.7619175165953514e-06, "loss": 0.5257010459899902, "step": 4225 }, { "epoch": 0.5925822057070742, "grad_norm": 2.929539442062378, "learning_rate": 3.7597177617252247e-06, "loss": 0.44496050477027893, "step": 4226 }, { "epoch": 0.5927224286615719, "grad_norm": 2.7149734497070312, "learning_rate": 3.7575182626307172e-06, "loss": 0.6046779751777649, "step": 4227 }, { "epoch": 0.5928626516160695, "grad_norm": 3.125507116317749, "learning_rate": 3.7553190197654204e-06, "loss": 0.5117534399032593, "step": 4228 }, { "epoch": 0.5930028745705672, "grad_norm": 2.8428401947021484, "learning_rate": 3.7531200335828686e-06, "loss": 0.5611445903778076, "step": 4229 }, { "epoch": 0.5931430975250649, "grad_norm": 3.9427125453948975, "learning_rate": 3.750921304536545e-06, "loss": 0.6385523676872253, "step": 4230 }, { "epoch": 0.5932833204795626, "grad_norm": 4.319864273071289, "learning_rate": 3.7487228330798806e-06, "loss": 0.5437814593315125, "step": 4231 }, { "epoch": 0.5934235434340601, "grad_norm": 3.043220043182373, "learning_rate": 3.746524619666252e-06, "loss": 0.5573315024375916, "step": 4232 }, { "epoch": 0.5935637663885578, "grad_norm": 4.278153896331787, "learning_rate": 3.7443266647489817e-06, "loss": 0.5101573467254639, "step": 4233 }, { "epoch": 0.5937039893430555, "grad_norm": 3.091643810272217, "learning_rate": 3.7421289687813423e-06, "loss": 0.4407026469707489, "step": 4234 }, { "epoch": 0.5938442122975531, "grad_norm": 3.136167287826538, "learning_rate": 3.739931532216549e-06, "loss": 0.593259334564209, "step": 4235 }, { "epoch": 0.5939844352520508, "grad_norm": 3.43442964553833, "learning_rate": 3.737734355507766e-06, "loss": 0.4978208839893341, "step": 4236 }, { "epoch": 0.5941246582065484, "grad_norm": 5.01821756362915, "learning_rate": 3.7355374391081043e-06, "loss": 0.508173406124115, "step": 4237 }, { "epoch": 0.594264881161046, "grad_norm": 4.508781909942627, "learning_rate": 3.733340783470619e-06, "loss": 0.487968772649765, "step": 4238 }, { "epoch": 0.5944051041155437, "grad_norm": 7.303092002868652, "learning_rate": 3.731144389048312e-06, "loss": 0.5396111011505127, "step": 4239 }, { "epoch": 0.5945453270700414, "grad_norm": 5.797494411468506, "learning_rate": 3.7289482562941336e-06, "loss": 0.6212571859359741, "step": 4240 }, { "epoch": 0.594685550024539, "grad_norm": 3.363584041595459, "learning_rate": 3.726752385660978e-06, "loss": 0.48280879855155945, "step": 4241 }, { "epoch": 0.5948257729790367, "grad_norm": 2.671417713165283, "learning_rate": 3.724556777601684e-06, "loss": 0.5270507335662842, "step": 4242 }, { "epoch": 0.5949659959335343, "grad_norm": 4.86995792388916, "learning_rate": 3.72236143256904e-06, "loss": 0.4705313742160797, "step": 4243 }, { "epoch": 0.595106218888032, "grad_norm": 3.935685634613037, "learning_rate": 3.7201663510157785e-06, "loss": 0.5497356653213501, "step": 4244 }, { "epoch": 0.5952464418425296, "grad_norm": 3.9831442832946777, "learning_rate": 3.7179715333945765e-06, "loss": 0.4896336793899536, "step": 4245 }, { "epoch": 0.5953866647970273, "grad_norm": 3.316962957382202, "learning_rate": 3.7157769801580568e-06, "loss": 0.44095104932785034, "step": 4246 }, { "epoch": 0.595526887751525, "grad_norm": 10.801313400268555, "learning_rate": 3.7135826917587902e-06, "loss": 0.5325961112976074, "step": 4247 }, { "epoch": 0.5956671107060226, "grad_norm": 2.7231791019439697, "learning_rate": 3.7113886686492894e-06, "loss": 0.5346698760986328, "step": 4248 }, { "epoch": 0.5958073336605202, "grad_norm": 5.436159133911133, "learning_rate": 3.709194911282015e-06, "loss": 0.5222165584564209, "step": 4249 }, { "epoch": 0.5959475566150179, "grad_norm": 2.7282304763793945, "learning_rate": 3.7070014201093713e-06, "loss": 0.5419431328773499, "step": 4250 }, { "epoch": 0.5960877795695155, "grad_norm": 4.042804718017578, "learning_rate": 3.704808195583708e-06, "loss": 0.6134201288223267, "step": 4251 }, { "epoch": 0.5962280025240132, "grad_norm": 5.432494640350342, "learning_rate": 3.7026152381573198e-06, "loss": 0.49091482162475586, "step": 4252 }, { "epoch": 0.5963682254785109, "grad_norm": 2.817751407623291, "learning_rate": 3.7004225482824476e-06, "loss": 0.46807220578193665, "step": 4253 }, { "epoch": 0.5965084484330084, "grad_norm": 3.6963632106781006, "learning_rate": 3.6982301264112762e-06, "loss": 0.6104984283447266, "step": 4254 }, { "epoch": 0.5966486713875061, "grad_norm": 5.161866188049316, "learning_rate": 3.696037972995934e-06, "loss": 0.5083611607551575, "step": 4255 }, { "epoch": 0.5967888943420038, "grad_norm": 2.605548858642578, "learning_rate": 3.693846088488494e-06, "loss": 0.4581278860569, "step": 4256 }, { "epoch": 0.5969291172965014, "grad_norm": 7.085521697998047, "learning_rate": 3.6916544733409787e-06, "loss": 0.4858968257904053, "step": 4257 }, { "epoch": 0.5970693402509991, "grad_norm": 5.0192766189575195, "learning_rate": 3.6894631280053474e-06, "loss": 0.654350221157074, "step": 4258 }, { "epoch": 0.5972095632054968, "grad_norm": 5.230441570281982, "learning_rate": 3.6872720529335083e-06, "loss": 0.62712562084198, "step": 4259 }, { "epoch": 0.5973497861599943, "grad_norm": 10.11974811553955, "learning_rate": 3.685081248577314e-06, "loss": 0.5284289121627808, "step": 4260 }, { "epoch": 0.597490009114492, "grad_norm": 2.6743581295013428, "learning_rate": 3.6828907153885597e-06, "loss": 0.46108758449554443, "step": 4261 }, { "epoch": 0.5976302320689897, "grad_norm": 7.195588111877441, "learning_rate": 3.6807004538189843e-06, "loss": 0.5359959602355957, "step": 4262 }, { "epoch": 0.5977704550234874, "grad_norm": 2.367194414138794, "learning_rate": 3.678510464320274e-06, "loss": 0.5893877148628235, "step": 4263 }, { "epoch": 0.597910677977985, "grad_norm": 5.100632190704346, "learning_rate": 3.6763207473440553e-06, "loss": 0.5126495957374573, "step": 4264 }, { "epoch": 0.5980509009324827, "grad_norm": 3.062061309814453, "learning_rate": 3.6741313033418996e-06, "loss": 0.5394078493118286, "step": 4265 }, { "epoch": 0.5981911238869803, "grad_norm": 3.332991123199463, "learning_rate": 3.6719421327653225e-06, "loss": 0.4710885286331177, "step": 4266 }, { "epoch": 0.5983313468414779, "grad_norm": 3.5013577938079834, "learning_rate": 3.6697532360657837e-06, "loss": 0.5234699845314026, "step": 4267 }, { "epoch": 0.5984715697959756, "grad_norm": 3.1607160568237305, "learning_rate": 3.6675646136946836e-06, "loss": 0.5569585561752319, "step": 4268 }, { "epoch": 0.5986117927504733, "grad_norm": 2.9958853721618652, "learning_rate": 3.665376266103369e-06, "loss": 0.45714831352233887, "step": 4269 }, { "epoch": 0.5987520157049709, "grad_norm": 6.204871654510498, "learning_rate": 3.6631881937431314e-06, "loss": 0.6004616022109985, "step": 4270 }, { "epoch": 0.5988922386594685, "grad_norm": 2.268268585205078, "learning_rate": 3.6610003970651993e-06, "loss": 0.42060720920562744, "step": 4271 }, { "epoch": 0.5990324616139662, "grad_norm": 13.244317054748535, "learning_rate": 3.6588128765207496e-06, "loss": 0.5139650106430054, "step": 4272 }, { "epoch": 0.5991726845684638, "grad_norm": 2.557184934616089, "learning_rate": 3.656625632560904e-06, "loss": 0.493774950504303, "step": 4273 }, { "epoch": 0.5993129075229615, "grad_norm": 2.7395410537719727, "learning_rate": 3.6544386656367194e-06, "loss": 0.5680415034294128, "step": 4274 }, { "epoch": 0.5994531304774592, "grad_norm": 2.2940680980682373, "learning_rate": 3.6522519761992027e-06, "loss": 0.5034136772155762, "step": 4275 }, { "epoch": 0.5995933534319569, "grad_norm": 3.4084439277648926, "learning_rate": 3.6500655646993024e-06, "loss": 0.5432031154632568, "step": 4276 }, { "epoch": 0.5997335763864544, "grad_norm": 5.424866199493408, "learning_rate": 3.647879431587905e-06, "loss": 0.522397518157959, "step": 4277 }, { "epoch": 0.5998737993409521, "grad_norm": 2.757427215576172, "learning_rate": 3.6456935773158454e-06, "loss": 0.4725245535373688, "step": 4278 }, { "epoch": 0.6000140222954498, "grad_norm": 21.790388107299805, "learning_rate": 3.6435080023338986e-06, "loss": 0.6432359218597412, "step": 4279 }, { "epoch": 0.6001542452499474, "grad_norm": 8.024653434753418, "learning_rate": 3.6413227070927803e-06, "loss": 0.5990763902664185, "step": 4280 }, { "epoch": 0.6002944682044451, "grad_norm": 5.9091715812683105, "learning_rate": 3.6391376920431533e-06, "loss": 0.5716519951820374, "step": 4281 }, { "epoch": 0.6004346911589428, "grad_norm": 5.003997802734375, "learning_rate": 3.6369529576356156e-06, "loss": 0.5165714025497437, "step": 4282 }, { "epoch": 0.6005749141134403, "grad_norm": 4.736269950866699, "learning_rate": 3.634768504320714e-06, "loss": 0.6475069522857666, "step": 4283 }, { "epoch": 0.600715137067938, "grad_norm": 3.8387303352355957, "learning_rate": 3.632584332548935e-06, "loss": 0.5618948936462402, "step": 4284 }, { "epoch": 0.6008553600224357, "grad_norm": 2.886467933654785, "learning_rate": 3.6304004427707052e-06, "loss": 0.5065294504165649, "step": 4285 }, { "epoch": 0.6009955829769333, "grad_norm": 2.7760491371154785, "learning_rate": 3.628216835436394e-06, "loss": 0.5696806311607361, "step": 4286 }, { "epoch": 0.601135805931431, "grad_norm": 8.209821701049805, "learning_rate": 3.626033510996315e-06, "loss": 0.4870327115058899, "step": 4287 }, { "epoch": 0.6012760288859287, "grad_norm": 3.088367462158203, "learning_rate": 3.623850469900719e-06, "loss": 0.527654767036438, "step": 4288 }, { "epoch": 0.6014162518404262, "grad_norm": 2.972559690475464, "learning_rate": 3.621667712599803e-06, "loss": 0.4722664952278137, "step": 4289 }, { "epoch": 0.6015564747949239, "grad_norm": 3.2932493686676025, "learning_rate": 3.619485239543703e-06, "loss": 0.6234164237976074, "step": 4290 }, { "epoch": 0.6016966977494216, "grad_norm": 5.108495712280273, "learning_rate": 3.6173030511824956e-06, "loss": 0.5467909574508667, "step": 4291 }, { "epoch": 0.6018369207039193, "grad_norm": 4.303611755371094, "learning_rate": 3.6151211479662e-06, "loss": 0.5579670667648315, "step": 4292 }, { "epoch": 0.6019771436584169, "grad_norm": 3.255830764770508, "learning_rate": 3.612939530344778e-06, "loss": 0.49957531690597534, "step": 4293 }, { "epoch": 0.6021173666129145, "grad_norm": 2.8145787715911865, "learning_rate": 3.6107581987681297e-06, "loss": 0.5317919254302979, "step": 4294 }, { "epoch": 0.6022575895674122, "grad_norm": 8.376843452453613, "learning_rate": 3.6085771536860963e-06, "loss": 0.561768651008606, "step": 4295 }, { "epoch": 0.6023978125219098, "grad_norm": 3.7347023487091064, "learning_rate": 3.6063963955484636e-06, "loss": 0.5080644488334656, "step": 4296 }, { "epoch": 0.6025380354764075, "grad_norm": 4.205036163330078, "learning_rate": 3.6042159248049535e-06, "loss": 0.5157773494720459, "step": 4297 }, { "epoch": 0.6026782584309052, "grad_norm": 3.0323355197906494, "learning_rate": 3.602035741905232e-06, "loss": 0.5291768312454224, "step": 4298 }, { "epoch": 0.6028184813854028, "grad_norm": 5.762127876281738, "learning_rate": 3.5998558472989044e-06, "loss": 0.5709868669509888, "step": 4299 }, { "epoch": 0.6029587043399004, "grad_norm": 4.043422698974609, "learning_rate": 3.5976762414355147e-06, "loss": 0.5800819396972656, "step": 4300 }, { "epoch": 0.6030989272943981, "grad_norm": 3.274644374847412, "learning_rate": 3.595496924764553e-06, "loss": 0.458240270614624, "step": 4301 }, { "epoch": 0.6032391502488957, "grad_norm": 2.9428906440734863, "learning_rate": 3.5933178977354444e-06, "loss": 0.484557181596756, "step": 4302 }, { "epoch": 0.6033793732033934, "grad_norm": 2.1668944358825684, "learning_rate": 3.591139160797553e-06, "loss": 0.4678003191947937, "step": 4303 }, { "epoch": 0.6035195961578911, "grad_norm": 2.905574321746826, "learning_rate": 3.588960714400192e-06, "loss": 0.5211994051933289, "step": 4304 }, { "epoch": 0.6036598191123888, "grad_norm": 4.990530967712402, "learning_rate": 3.5867825589926046e-06, "loss": 0.5286946296691895, "step": 4305 }, { "epoch": 0.6038000420668863, "grad_norm": 3.3726425170898438, "learning_rate": 3.5846046950239775e-06, "loss": 0.5140981078147888, "step": 4306 }, { "epoch": 0.603940265021384, "grad_norm": 3.1442575454711914, "learning_rate": 3.582427122943441e-06, "loss": 0.5101184248924255, "step": 4307 }, { "epoch": 0.6040804879758817, "grad_norm": 3.3632802963256836, "learning_rate": 3.580249843200061e-06, "loss": 0.5013014078140259, "step": 4308 }, { "epoch": 0.6042207109303793, "grad_norm": 3.101992130279541, "learning_rate": 3.5780728562428413e-06, "loss": 0.5706943273544312, "step": 4309 }, { "epoch": 0.604360933884877, "grad_norm": 3.280921459197998, "learning_rate": 3.5758961625207323e-06, "loss": 0.5127245187759399, "step": 4310 }, { "epoch": 0.6045011568393746, "grad_norm": 4.420734882354736, "learning_rate": 3.5737197624826183e-06, "loss": 0.4689461290836334, "step": 4311 }, { "epoch": 0.6046413797938722, "grad_norm": 4.23787260055542, "learning_rate": 3.571543656577324e-06, "loss": 0.5938757658004761, "step": 4312 }, { "epoch": 0.6047816027483699, "grad_norm": 3.245011329650879, "learning_rate": 3.5693678452536163e-06, "loss": 0.5450952053070068, "step": 4313 }, { "epoch": 0.6049218257028676, "grad_norm": 3.1589601039886475, "learning_rate": 3.5671923289601957e-06, "loss": 0.5717504024505615, "step": 4314 }, { "epoch": 0.6050620486573652, "grad_norm": 3.1980559825897217, "learning_rate": 3.5650171081457074e-06, "loss": 0.5901009440422058, "step": 4315 }, { "epoch": 0.6052022716118629, "grad_norm": 2.8795671463012695, "learning_rate": 3.5628421832587345e-06, "loss": 0.5581543445587158, "step": 4316 }, { "epoch": 0.6053424945663605, "grad_norm": 4.10107421875, "learning_rate": 3.5606675547477953e-06, "loss": 0.38286951184272766, "step": 4317 }, { "epoch": 0.6054827175208581, "grad_norm": 5.5173420906066895, "learning_rate": 3.558493223061352e-06, "loss": 0.5249398946762085, "step": 4318 }, { "epoch": 0.6056229404753558, "grad_norm": 5.653965473175049, "learning_rate": 3.556319188647803e-06, "loss": 0.49483561515808105, "step": 4319 }, { "epoch": 0.6057631634298535, "grad_norm": 8.421281814575195, "learning_rate": 3.5541454519554835e-06, "loss": 0.5617009997367859, "step": 4320 }, { "epoch": 0.6059033863843512, "grad_norm": 3.043588399887085, "learning_rate": 3.5519720134326742e-06, "loss": 0.5240437984466553, "step": 4321 }, { "epoch": 0.6060436093388488, "grad_norm": 4.363377571105957, "learning_rate": 3.5497988735275862e-06, "loss": 0.5315422415733337, "step": 4322 }, { "epoch": 0.6061838322933464, "grad_norm": 3.1857144832611084, "learning_rate": 3.5476260326883715e-06, "loss": 0.4860422611236572, "step": 4323 }, { "epoch": 0.606324055247844, "grad_norm": 3.0619354248046875, "learning_rate": 3.5454534913631257e-06, "loss": 0.46105003356933594, "step": 4324 }, { "epoch": 0.6064642782023417, "grad_norm": 3.8738694190979004, "learning_rate": 3.5432812499998755e-06, "loss": 0.5133410096168518, "step": 4325 }, { "epoch": 0.6066045011568394, "grad_norm": 9.010090827941895, "learning_rate": 3.5411093090465865e-06, "loss": 0.4553574025630951, "step": 4326 }, { "epoch": 0.6067447241113371, "grad_norm": 3.0779576301574707, "learning_rate": 3.53893766895117e-06, "loss": 0.5465319752693176, "step": 4327 }, { "epoch": 0.6068849470658346, "grad_norm": 392.6852722167969, "learning_rate": 3.536766330161466e-06, "loss": 0.52524733543396, "step": 4328 }, { "epoch": 0.6070251700203323, "grad_norm": 2.677464723587036, "learning_rate": 3.5345952931252548e-06, "loss": 0.503594160079956, "step": 4329 }, { "epoch": 0.60716539297483, "grad_norm": 5.729082107543945, "learning_rate": 3.5324245582902593e-06, "loss": 0.5857303738594055, "step": 4330 }, { "epoch": 0.6073056159293276, "grad_norm": 3.0035336017608643, "learning_rate": 3.5302541261041356e-06, "loss": 0.5784155130386353, "step": 4331 }, { "epoch": 0.6074458388838253, "grad_norm": 4.002302169799805, "learning_rate": 3.5280839970144754e-06, "loss": 0.5979744791984558, "step": 4332 }, { "epoch": 0.607586061838323, "grad_norm": 5.550018787384033, "learning_rate": 3.5259141714688144e-06, "loss": 0.4504721760749817, "step": 4333 }, { "epoch": 0.6077262847928205, "grad_norm": 5.122446537017822, "learning_rate": 3.523744649914621e-06, "loss": 0.5328431725502014, "step": 4334 }, { "epoch": 0.6078665077473182, "grad_norm": 4.9166364669799805, "learning_rate": 3.5215754327993002e-06, "loss": 0.4689093828201294, "step": 4335 }, { "epoch": 0.6080067307018159, "grad_norm": 4.058987617492676, "learning_rate": 3.519406520570199e-06, "loss": 0.49679869413375854, "step": 4336 }, { "epoch": 0.6081469536563135, "grad_norm": 4.570886611938477, "learning_rate": 3.517237913674597e-06, "loss": 0.5931733846664429, "step": 4337 }, { "epoch": 0.6082871766108112, "grad_norm": 7.3851470947265625, "learning_rate": 3.5150696125597104e-06, "loss": 0.4085165560245514, "step": 4338 }, { "epoch": 0.6084273995653089, "grad_norm": 6.432590007781982, "learning_rate": 3.512901617672699e-06, "loss": 0.5601102709770203, "step": 4339 }, { "epoch": 0.6085676225198065, "grad_norm": 4.630557060241699, "learning_rate": 3.510733929460649e-06, "loss": 0.570615828037262, "step": 4340 }, { "epoch": 0.6087078454743041, "grad_norm": 6.072206974029541, "learning_rate": 3.5085665483705955e-06, "loss": 0.5142519474029541, "step": 4341 }, { "epoch": 0.6088480684288018, "grad_norm": 4.94839334487915, "learning_rate": 3.5063994748495e-06, "loss": 0.5241928100585938, "step": 4342 }, { "epoch": 0.6089882913832995, "grad_norm": 8.23720645904541, "learning_rate": 3.5042327093442636e-06, "loss": 0.5529475212097168, "step": 4343 }, { "epoch": 0.6091285143377971, "grad_norm": 3.877269744873047, "learning_rate": 3.502066252301728e-06, "loss": 0.5099683403968811, "step": 4344 }, { "epoch": 0.6092687372922948, "grad_norm": 3.392984390258789, "learning_rate": 3.4999001041686664e-06, "loss": 0.5244184136390686, "step": 4345 }, { "epoch": 0.6094089602467924, "grad_norm": 4.423203945159912, "learning_rate": 3.497734265391788e-06, "loss": 0.553155779838562, "step": 4346 }, { "epoch": 0.60954918320129, "grad_norm": 2.451767683029175, "learning_rate": 3.4955687364177445e-06, "loss": 0.486090749502182, "step": 4347 }, { "epoch": 0.6096894061557877, "grad_norm": 2.468762159347534, "learning_rate": 3.493403517693116e-06, "loss": 0.5080887079238892, "step": 4348 }, { "epoch": 0.6098296291102854, "grad_norm": 3.137962818145752, "learning_rate": 3.4912386096644214e-06, "loss": 0.48755908012390137, "step": 4349 }, { "epoch": 0.609969852064783, "grad_norm": 3.344080686569214, "learning_rate": 3.489074012778119e-06, "loss": 0.5287498235702515, "step": 4350 }, { "epoch": 0.6101100750192806, "grad_norm": 3.3469650745391846, "learning_rate": 3.486909727480599e-06, "loss": 0.5239434838294983, "step": 4351 }, { "epoch": 0.6102502979737783, "grad_norm": 2.491021156311035, "learning_rate": 3.484745754218186e-06, "loss": 0.5140776634216309, "step": 4352 }, { "epoch": 0.610390520928276, "grad_norm": 2.2725727558135986, "learning_rate": 3.482582093437146e-06, "loss": 0.48701274394989014, "step": 4353 }, { "epoch": 0.6105307438827736, "grad_norm": 3.0028951168060303, "learning_rate": 3.4804187455836763e-06, "loss": 0.42160487174987793, "step": 4354 }, { "epoch": 0.6106709668372713, "grad_norm": 32.29433822631836, "learning_rate": 3.4782557111039074e-06, "loss": 0.36057695746421814, "step": 4355 }, { "epoch": 0.610811189791769, "grad_norm": 3.136857271194458, "learning_rate": 3.4760929904439133e-06, "loss": 0.6132028102874756, "step": 4356 }, { "epoch": 0.6109514127462665, "grad_norm": 4.293585300445557, "learning_rate": 3.473930584049696e-06, "loss": 0.5197864770889282, "step": 4357 }, { "epoch": 0.6110916357007642, "grad_norm": 4.3410186767578125, "learning_rate": 3.471768492367192e-06, "loss": 0.5067036151885986, "step": 4358 }, { "epoch": 0.6112318586552619, "grad_norm": 2.178628921508789, "learning_rate": 3.469606715842282e-06, "loss": 0.4727417230606079, "step": 4359 }, { "epoch": 0.6113720816097595, "grad_norm": 3.3057680130004883, "learning_rate": 3.467445254920772e-06, "loss": 0.4853031039237976, "step": 4360 }, { "epoch": 0.6115123045642572, "grad_norm": 3.6642134189605713, "learning_rate": 3.465284110048405e-06, "loss": 0.5592470765113831, "step": 4361 }, { "epoch": 0.6116525275187549, "grad_norm": 4.264212608337402, "learning_rate": 3.4631232816708636e-06, "loss": 0.45732972025871277, "step": 4362 }, { "epoch": 0.6117927504732524, "grad_norm": 13.051300048828125, "learning_rate": 3.460962770233762e-06, "loss": 0.4824175238609314, "step": 4363 }, { "epoch": 0.6119329734277501, "grad_norm": 2.91695499420166, "learning_rate": 3.458802576182644e-06, "loss": 0.529853105545044, "step": 4364 }, { "epoch": 0.6120731963822478, "grad_norm": 2.5476787090301514, "learning_rate": 3.4566426999629986e-06, "loss": 0.4758157730102539, "step": 4365 }, { "epoch": 0.6122134193367454, "grad_norm": 4.322200775146484, "learning_rate": 3.4544831420202417e-06, "loss": 0.5280072689056396, "step": 4366 }, { "epoch": 0.6123536422912431, "grad_norm": 4.742125988006592, "learning_rate": 3.4523239027997224e-06, "loss": 0.41340339183807373, "step": 4367 }, { "epoch": 0.6124938652457407, "grad_norm": 9.460969924926758, "learning_rate": 3.4501649827467322e-06, "loss": 0.4098787009716034, "step": 4368 }, { "epoch": 0.6126340882002383, "grad_norm": 2.76574444770813, "learning_rate": 3.4480063823064857e-06, "loss": 0.5371221899986267, "step": 4369 }, { "epoch": 0.612774311154736, "grad_norm": 3.111330270767212, "learning_rate": 3.4458481019241443e-06, "loss": 0.4521692395210266, "step": 4370 }, { "epoch": 0.6129145341092337, "grad_norm": 3.299431085586548, "learning_rate": 3.443690142044792e-06, "loss": 0.526758074760437, "step": 4371 }, { "epoch": 0.6130547570637314, "grad_norm": 2.617666244506836, "learning_rate": 3.4415325031134506e-06, "loss": 0.5106743574142456, "step": 4372 }, { "epoch": 0.613194980018229, "grad_norm": 2.882397413253784, "learning_rate": 3.4393751855750805e-06, "loss": 0.5698574781417847, "step": 4373 }, { "epoch": 0.6133352029727266, "grad_norm": 2.9796998500823975, "learning_rate": 3.43721818987457e-06, "loss": 0.44316139817237854, "step": 4374 }, { "epoch": 0.6134754259272243, "grad_norm": 3.43009877204895, "learning_rate": 3.4350615164567397e-06, "loss": 0.5180514454841614, "step": 4375 }, { "epoch": 0.6136156488817219, "grad_norm": 3.9374992847442627, "learning_rate": 3.4329051657663516e-06, "loss": 0.4076390266418457, "step": 4376 }, { "epoch": 0.6137558718362196, "grad_norm": 3.567958354949951, "learning_rate": 3.430749138248094e-06, "loss": 0.6046712398529053, "step": 4377 }, { "epoch": 0.6138960947907173, "grad_norm": 2.887263059616089, "learning_rate": 3.4285934343465887e-06, "loss": 0.5112869739532471, "step": 4378 }, { "epoch": 0.6140363177452149, "grad_norm": 3.2686378955841064, "learning_rate": 3.426438054506398e-06, "loss": 0.4488030672073364, "step": 4379 }, { "epoch": 0.6141765406997125, "grad_norm": 3.715498208999634, "learning_rate": 3.42428299917201e-06, "loss": 0.4922490119934082, "step": 4380 }, { "epoch": 0.6143167636542102, "grad_norm": 4.052423000335693, "learning_rate": 3.4221282687878455e-06, "loss": 0.5555672645568848, "step": 4381 }, { "epoch": 0.6144569866087078, "grad_norm": 4.9203643798828125, "learning_rate": 3.419973863798266e-06, "loss": 0.5007569789886475, "step": 4382 }, { "epoch": 0.6145972095632055, "grad_norm": 2.936964511871338, "learning_rate": 3.417819784647558e-06, "loss": 0.5090334415435791, "step": 4383 }, { "epoch": 0.6147374325177032, "grad_norm": 3.524402618408203, "learning_rate": 3.4156660317799423e-06, "loss": 0.5400187969207764, "step": 4384 }, { "epoch": 0.6148776554722007, "grad_norm": 4.64504337310791, "learning_rate": 3.413512605639577e-06, "loss": 0.4891171157360077, "step": 4385 }, { "epoch": 0.6150178784266984, "grad_norm": 3.5736851692199707, "learning_rate": 3.4113595066705497e-06, "loss": 0.48431408405303955, "step": 4386 }, { "epoch": 0.6151581013811961, "grad_norm": 4.371265888214111, "learning_rate": 3.4092067353168757e-06, "loss": 0.42875003814697266, "step": 4387 }, { "epoch": 0.6152983243356938, "grad_norm": 1.9679428339004517, "learning_rate": 3.4070542920225135e-06, "loss": 0.47808682918548584, "step": 4388 }, { "epoch": 0.6154385472901914, "grad_norm": 3.5179789066314697, "learning_rate": 3.4049021772313463e-06, "loss": 0.6045442819595337, "step": 4389 }, { "epoch": 0.6155787702446891, "grad_norm": 3.6540918350219727, "learning_rate": 3.4027503913871872e-06, "loss": 0.5157318115234375, "step": 4390 }, { "epoch": 0.6157189931991867, "grad_norm": 7.682851314544678, "learning_rate": 3.400598934933791e-06, "loss": 0.567836344242096, "step": 4391 }, { "epoch": 0.6158592161536843, "grad_norm": 2.2542877197265625, "learning_rate": 3.3984478083148364e-06, "loss": 0.5468382239341736, "step": 4392 }, { "epoch": 0.615999439108182, "grad_norm": 6.989112854003906, "learning_rate": 3.3962970119739353e-06, "loss": 0.5519511103630066, "step": 4393 }, { "epoch": 0.6161396620626797, "grad_norm": 4.990973949432373, "learning_rate": 3.3941465463546365e-06, "loss": 0.6051112413406372, "step": 4394 }, { "epoch": 0.6162798850171773, "grad_norm": 3.1061253547668457, "learning_rate": 3.3919964119004156e-06, "loss": 0.6530172824859619, "step": 4395 }, { "epoch": 0.616420107971675, "grad_norm": 2.863468647003174, "learning_rate": 3.3898466090546782e-06, "loss": 0.5723251104354858, "step": 4396 }, { "epoch": 0.6165603309261726, "grad_norm": 6.211491584777832, "learning_rate": 3.38769713826077e-06, "loss": 0.5280580520629883, "step": 4397 }, { "epoch": 0.6167005538806702, "grad_norm": 3.3124308586120605, "learning_rate": 3.38554799996196e-06, "loss": 0.5065866708755493, "step": 4398 }, { "epoch": 0.6168407768351679, "grad_norm": 4.3700785636901855, "learning_rate": 3.383399194601449e-06, "loss": 0.5843079090118408, "step": 4399 }, { "epoch": 0.6169809997896656, "grad_norm": 3.329113006591797, "learning_rate": 3.3812507226223777e-06, "loss": 0.5539280772209167, "step": 4400 }, { "epoch": 0.6171212227441633, "grad_norm": 19.591215133666992, "learning_rate": 3.379102584467806e-06, "loss": 0.5985002517700195, "step": 4401 }, { "epoch": 0.6172614456986608, "grad_norm": 5.118175029754639, "learning_rate": 3.376954780580736e-06, "loss": 0.5864999890327454, "step": 4402 }, { "epoch": 0.6174016686531585, "grad_norm": 2.3908207416534424, "learning_rate": 3.3748073114040925e-06, "loss": 0.5469523072242737, "step": 4403 }, { "epoch": 0.6175418916076562, "grad_norm": 2.5057969093322754, "learning_rate": 3.372660177380734e-06, "loss": 0.5337415933609009, "step": 4404 }, { "epoch": 0.6176821145621538, "grad_norm": 6.926529407501221, "learning_rate": 3.370513378953454e-06, "loss": 0.4634416103363037, "step": 4405 }, { "epoch": 0.6178223375166515, "grad_norm": 2.4389147758483887, "learning_rate": 3.3683669165649715e-06, "loss": 0.5083307027816772, "step": 4406 }, { "epoch": 0.6179625604711492, "grad_norm": 3.3601760864257812, "learning_rate": 3.366220790657935e-06, "loss": 0.5445807576179504, "step": 4407 }, { "epoch": 0.6181027834256467, "grad_norm": 4.3364787101745605, "learning_rate": 3.3640750016749315e-06, "loss": 0.4783152937889099, "step": 4408 }, { "epoch": 0.6182430063801444, "grad_norm": 2.5396783351898193, "learning_rate": 3.3619295500584713e-06, "loss": 0.4218592345714569, "step": 4409 }, { "epoch": 0.6183832293346421, "grad_norm": 4.949409484863281, "learning_rate": 3.3597844362509956e-06, "loss": 0.5602822303771973, "step": 4410 }, { "epoch": 0.6185234522891397, "grad_norm": 2.834503650665283, "learning_rate": 3.3576396606948822e-06, "loss": 0.506887674331665, "step": 4411 }, { "epoch": 0.6186636752436374, "grad_norm": 2.665518045425415, "learning_rate": 3.355495223832432e-06, "loss": 0.5199077129364014, "step": 4412 }, { "epoch": 0.6188038981981351, "grad_norm": 2.168519973754883, "learning_rate": 3.353351126105876e-06, "loss": 0.5234017372131348, "step": 4413 }, { "epoch": 0.6189441211526326, "grad_norm": 5.216181755065918, "learning_rate": 3.3512073679573835e-06, "loss": 0.4830370545387268, "step": 4414 }, { "epoch": 0.6190843441071303, "grad_norm": 3.4975526332855225, "learning_rate": 3.3490639498290456e-06, "loss": 0.5401315093040466, "step": 4415 }, { "epoch": 0.619224567061628, "grad_norm": 3.774808645248413, "learning_rate": 3.3469208721628844e-06, "loss": 0.5390588045120239, "step": 4416 }, { "epoch": 0.6193647900161257, "grad_norm": 3.5380380153656006, "learning_rate": 3.3447781354008568e-06, "loss": 0.5466750264167786, "step": 4417 }, { "epoch": 0.6195050129706233, "grad_norm": 3.079267978668213, "learning_rate": 3.342635739984844e-06, "loss": 0.6258511543273926, "step": 4418 }, { "epoch": 0.619645235925121, "grad_norm": 5.357597351074219, "learning_rate": 3.3404936863566574e-06, "loss": 0.466153085231781, "step": 4419 }, { "epoch": 0.6197854588796186, "grad_norm": 3.649845838546753, "learning_rate": 3.3383519749580423e-06, "loss": 0.5760751366615295, "step": 4420 }, { "epoch": 0.6199256818341162, "grad_norm": 2.7482151985168457, "learning_rate": 3.336210606230669e-06, "loss": 0.5528920292854309, "step": 4421 }, { "epoch": 0.6200659047886139, "grad_norm": 2.354851484298706, "learning_rate": 3.3340695806161366e-06, "loss": 0.5677916407585144, "step": 4422 }, { "epoch": 0.6202061277431116, "grad_norm": 7.655630111694336, "learning_rate": 3.3319288985559795e-06, "loss": 0.5280295610427856, "step": 4423 }, { "epoch": 0.6203463506976092, "grad_norm": 3.55111026763916, "learning_rate": 3.3297885604916542e-06, "loss": 0.5085619688034058, "step": 4424 }, { "epoch": 0.6204865736521068, "grad_norm": 5.493398666381836, "learning_rate": 3.3276485668645482e-06, "loss": 0.4634000062942505, "step": 4425 }, { "epoch": 0.6206267966066045, "grad_norm": 2.732407808303833, "learning_rate": 3.3255089181159822e-06, "loss": 0.5276943445205688, "step": 4426 }, { "epoch": 0.6207670195611021, "grad_norm": 2.8319220542907715, "learning_rate": 3.3233696146872007e-06, "loss": 0.6183457374572754, "step": 4427 }, { "epoch": 0.6209072425155998, "grad_norm": 3.045860767364502, "learning_rate": 3.3212306570193774e-06, "loss": 0.535625159740448, "step": 4428 }, { "epoch": 0.6210474654700975, "grad_norm": 3.651193380355835, "learning_rate": 3.3190920455536203e-06, "loss": 0.5305765867233276, "step": 4429 }, { "epoch": 0.6211876884245952, "grad_norm": 2.6552631855010986, "learning_rate": 3.3169537807309566e-06, "loss": 0.5666120052337646, "step": 4430 }, { "epoch": 0.6213279113790927, "grad_norm": 4.352001190185547, "learning_rate": 3.314815862992352e-06, "loss": 0.5302808880805969, "step": 4431 }, { "epoch": 0.6214681343335904, "grad_norm": 5.5608625411987305, "learning_rate": 3.312678292778694e-06, "loss": 0.4918123483657837, "step": 4432 }, { "epoch": 0.621608357288088, "grad_norm": 3.380376100540161, "learning_rate": 3.310541070530797e-06, "loss": 0.5641294717788696, "step": 4433 }, { "epoch": 0.6217485802425857, "grad_norm": 3.9688940048217773, "learning_rate": 3.308404196689413e-06, "loss": 0.4897843599319458, "step": 4434 }, { "epoch": 0.6218888031970834, "grad_norm": 2.6442322731018066, "learning_rate": 3.3062676716952126e-06, "loss": 0.5258398652076721, "step": 4435 }, { "epoch": 0.6220290261515811, "grad_norm": 5.089476585388184, "learning_rate": 3.304131495988796e-06, "loss": 0.4638746976852417, "step": 4436 }, { "epoch": 0.6221692491060786, "grad_norm": 4.321326732635498, "learning_rate": 3.301995670010698e-06, "loss": 0.5350538492202759, "step": 4437 }, { "epoch": 0.6223094720605763, "grad_norm": 38.155853271484375, "learning_rate": 3.2998601942013746e-06, "loss": 0.6068137884140015, "step": 4438 }, { "epoch": 0.622449695015074, "grad_norm": 2.666019916534424, "learning_rate": 3.297725069001209e-06, "loss": 0.5794429779052734, "step": 4439 }, { "epoch": 0.6225899179695716, "grad_norm": 3.2063517570495605, "learning_rate": 3.2955902948505193e-06, "loss": 0.5968704223632812, "step": 4440 }, { "epoch": 0.6227301409240693, "grad_norm": 3.080974578857422, "learning_rate": 3.293455872189544e-06, "loss": 0.5547575950622559, "step": 4441 }, { "epoch": 0.6228703638785669, "grad_norm": 3.372791051864624, "learning_rate": 3.2913218014584493e-06, "loss": 0.5150191187858582, "step": 4442 }, { "epoch": 0.6230105868330645, "grad_norm": 3.431577444076538, "learning_rate": 3.2891880830973354e-06, "loss": 0.5592387914657593, "step": 4443 }, { "epoch": 0.6231508097875622, "grad_norm": 4.622566223144531, "learning_rate": 3.2870547175462255e-06, "loss": 0.4235078990459442, "step": 4444 }, { "epoch": 0.6232910327420599, "grad_norm": 22.955604553222656, "learning_rate": 3.2849217052450656e-06, "loss": 0.576117992401123, "step": 4445 }, { "epoch": 0.6234312556965576, "grad_norm": 7.243651866912842, "learning_rate": 3.2827890466337386e-06, "loss": 0.5160692930221558, "step": 4446 }, { "epoch": 0.6235714786510552, "grad_norm": 2.8977644443511963, "learning_rate": 3.2806567421520473e-06, "loss": 0.4100725054740906, "step": 4447 }, { "epoch": 0.6237117016055528, "grad_norm": 3.7198545932769775, "learning_rate": 3.278524792239721e-06, "loss": 0.6036342978477478, "step": 4448 }, { "epoch": 0.6238519245600505, "grad_norm": 3.1376469135284424, "learning_rate": 3.276393197336424e-06, "loss": 0.4430023431777954, "step": 4449 }, { "epoch": 0.6239921475145481, "grad_norm": 3.3385415077209473, "learning_rate": 3.274261957881737e-06, "loss": 0.4825226664543152, "step": 4450 }, { "epoch": 0.6241323704690458, "grad_norm": 8.7688570022583, "learning_rate": 3.2721310743151723e-06, "loss": 0.5096516609191895, "step": 4451 }, { "epoch": 0.6242725934235435, "grad_norm": 2.5681257247924805, "learning_rate": 3.270000547076172e-06, "loss": 0.5671024322509766, "step": 4452 }, { "epoch": 0.6244128163780411, "grad_norm": 2.8121728897094727, "learning_rate": 3.2678703766041e-06, "loss": 0.4841645359992981, "step": 4453 }, { "epoch": 0.6245530393325387, "grad_norm": 3.1315219402313232, "learning_rate": 3.2657405633382438e-06, "loss": 0.6135094165802002, "step": 4454 }, { "epoch": 0.6246932622870364, "grad_norm": 3.475311040878296, "learning_rate": 3.263611107717828e-06, "loss": 0.5498216152191162, "step": 4455 }, { "epoch": 0.624833485241534, "grad_norm": 2.7465031147003174, "learning_rate": 3.2614820101819933e-06, "loss": 0.5618351697921753, "step": 4456 }, { "epoch": 0.6249737081960317, "grad_norm": 5.175955295562744, "learning_rate": 3.259353271169809e-06, "loss": 0.5168293714523315, "step": 4457 }, { "epoch": 0.6251139311505294, "grad_norm": 2.1326074600219727, "learning_rate": 3.2572248911202745e-06, "loss": 0.5165388584136963, "step": 4458 }, { "epoch": 0.6252541541050269, "grad_norm": 3.1874401569366455, "learning_rate": 3.2550968704723096e-06, "loss": 0.5594111084938049, "step": 4459 }, { "epoch": 0.6253943770595246, "grad_norm": 9.013935089111328, "learning_rate": 3.252969209664766e-06, "loss": 0.45296716690063477, "step": 4460 }, { "epoch": 0.6255346000140223, "grad_norm": 2.525843381881714, "learning_rate": 3.2508419091364157e-06, "loss": 0.5470787286758423, "step": 4461 }, { "epoch": 0.62567482296852, "grad_norm": 2.552518367767334, "learning_rate": 3.248714969325957e-06, "loss": 0.5652984380722046, "step": 4462 }, { "epoch": 0.6258150459230176, "grad_norm": 3.111297607421875, "learning_rate": 3.246588390672018e-06, "loss": 0.5438829064369202, "step": 4463 }, { "epoch": 0.6259552688775153, "grad_norm": 3.1773130893707275, "learning_rate": 3.2444621736131493e-06, "loss": 0.5153018236160278, "step": 4464 }, { "epoch": 0.6260954918320129, "grad_norm": 3.8135128021240234, "learning_rate": 3.2423363185878244e-06, "loss": 0.50178062915802, "step": 4465 }, { "epoch": 0.6262357147865105, "grad_norm": 4.349682807922363, "learning_rate": 3.24021082603445e-06, "loss": 0.48670029640197754, "step": 4466 }, { "epoch": 0.6263759377410082, "grad_norm": 3.99350905418396, "learning_rate": 3.2380856963913497e-06, "loss": 0.44776540994644165, "step": 4467 }, { "epoch": 0.6265161606955059, "grad_norm": 2.584648370742798, "learning_rate": 3.2359609300967743e-06, "loss": 0.574580192565918, "step": 4468 }, { "epoch": 0.6266563836500035, "grad_norm": 3.596550703048706, "learning_rate": 3.2338365275889055e-06, "loss": 0.7006189823150635, "step": 4469 }, { "epoch": 0.6267966066045012, "grad_norm": 2.5667152404785156, "learning_rate": 3.2317124893058426e-06, "loss": 0.5295615196228027, "step": 4470 }, { "epoch": 0.6269368295589988, "grad_norm": 4.345460414886475, "learning_rate": 3.2295888156856115e-06, "loss": 0.5713436007499695, "step": 4471 }, { "epoch": 0.6270770525134964, "grad_norm": 4.717643737792969, "learning_rate": 3.2274655071661675e-06, "loss": 0.48577094078063965, "step": 4472 }, { "epoch": 0.6272172754679941, "grad_norm": 5.3887434005737305, "learning_rate": 3.225342564185385e-06, "loss": 0.5531561970710754, "step": 4473 }, { "epoch": 0.6273574984224918, "grad_norm": 5.145909786224365, "learning_rate": 3.2232199871810644e-06, "loss": 0.5584739446640015, "step": 4474 }, { "epoch": 0.6274977213769894, "grad_norm": 5.777095794677734, "learning_rate": 3.2210977765909346e-06, "loss": 0.5770618915557861, "step": 4475 }, { "epoch": 0.6276379443314871, "grad_norm": 2.814276933670044, "learning_rate": 3.2189759328526436e-06, "loss": 0.5042634606361389, "step": 4476 }, { "epoch": 0.6277781672859847, "grad_norm": 2.2959089279174805, "learning_rate": 3.216854456403764e-06, "loss": 0.42485061287879944, "step": 4477 }, { "epoch": 0.6279183902404823, "grad_norm": 4.33745813369751, "learning_rate": 3.2147333476817987e-06, "loss": 0.45997554063796997, "step": 4478 }, { "epoch": 0.62805861319498, "grad_norm": 4.30255126953125, "learning_rate": 3.2126126071241683e-06, "loss": 0.5519971251487732, "step": 4479 }, { "epoch": 0.6281988361494777, "grad_norm": 5.829178333282471, "learning_rate": 3.210492235168219e-06, "loss": 0.47335249185562134, "step": 4480 }, { "epoch": 0.6283390591039754, "grad_norm": 2.5500009059906006, "learning_rate": 3.2083722322512238e-06, "loss": 0.5371897220611572, "step": 4481 }, { "epoch": 0.6284792820584729, "grad_norm": 4.7299981117248535, "learning_rate": 3.2062525988103775e-06, "loss": 0.5147431492805481, "step": 4482 }, { "epoch": 0.6286195050129706, "grad_norm": 9.883743286132812, "learning_rate": 3.2041333352827958e-06, "loss": 0.5753330588340759, "step": 4483 }, { "epoch": 0.6287597279674683, "grad_norm": 2.4393365383148193, "learning_rate": 3.2020144421055256e-06, "loss": 0.5575814247131348, "step": 4484 }, { "epoch": 0.6288999509219659, "grad_norm": 2.924896240234375, "learning_rate": 3.19989591971553e-06, "loss": 0.5894044041633606, "step": 4485 }, { "epoch": 0.6290401738764636, "grad_norm": 5.839181900024414, "learning_rate": 3.197777768549698e-06, "loss": 0.5025752186775208, "step": 4486 }, { "epoch": 0.6291803968309613, "grad_norm": 5.329989433288574, "learning_rate": 3.195659989044846e-06, "loss": 0.5024300813674927, "step": 4487 }, { "epoch": 0.6293206197854588, "grad_norm": 3.282616138458252, "learning_rate": 3.193542581637705e-06, "loss": 0.5856927037239075, "step": 4488 }, { "epoch": 0.6294608427399565, "grad_norm": 4.708305358886719, "learning_rate": 3.1914255467649412e-06, "loss": 0.6243894100189209, "step": 4489 }, { "epoch": 0.6296010656944542, "grad_norm": 3.7531659603118896, "learning_rate": 3.189308884863134e-06, "loss": 0.5903648734092712, "step": 4490 }, { "epoch": 0.6297412886489518, "grad_norm": 5.260195255279541, "learning_rate": 3.1871925963687867e-06, "loss": 0.5348634123802185, "step": 4491 }, { "epoch": 0.6298815116034495, "grad_norm": 3.197786331176758, "learning_rate": 3.1850766817183333e-06, "loss": 0.5569134950637817, "step": 4492 }, { "epoch": 0.6300217345579472, "grad_norm": 3.5257070064544678, "learning_rate": 3.182961141348123e-06, "loss": 0.5619943737983704, "step": 4493 }, { "epoch": 0.6301619575124447, "grad_norm": 6.120665073394775, "learning_rate": 3.1808459756944286e-06, "loss": 0.5408024787902832, "step": 4494 }, { "epoch": 0.6303021804669424, "grad_norm": 3.0917279720306396, "learning_rate": 3.178731185193451e-06, "loss": 0.5894778370857239, "step": 4495 }, { "epoch": 0.6304424034214401, "grad_norm": 4.529132843017578, "learning_rate": 3.1766167702813092e-06, "loss": 0.46959054470062256, "step": 4496 }, { "epoch": 0.6305826263759378, "grad_norm": 4.9626359939575195, "learning_rate": 3.1745027313940437e-06, "loss": 0.5230653285980225, "step": 4497 }, { "epoch": 0.6307228493304354, "grad_norm": 4.176667213439941, "learning_rate": 3.1723890689676217e-06, "loss": 0.44777292013168335, "step": 4498 }, { "epoch": 0.630863072284933, "grad_norm": 3.5119872093200684, "learning_rate": 3.1702757834379303e-06, "loss": 0.5454528331756592, "step": 4499 }, { "epoch": 0.6310032952394307, "grad_norm": 2.876966714859009, "learning_rate": 3.168162875240777e-06, "loss": 0.6247603893280029, "step": 4500 }, { "epoch": 0.6311435181939283, "grad_norm": 3.4930505752563477, "learning_rate": 3.1660503448118963e-06, "loss": 0.6068757772445679, "step": 4501 }, { "epoch": 0.631283741148426, "grad_norm": 3.156111478805542, "learning_rate": 3.1639381925869404e-06, "loss": 0.5170309543609619, "step": 4502 }, { "epoch": 0.6314239641029237, "grad_norm": 4.380551338195801, "learning_rate": 3.1618264190014846e-06, "loss": 0.3988894820213318, "step": 4503 }, { "epoch": 0.6315641870574213, "grad_norm": 3.639425039291382, "learning_rate": 3.1597150244910304e-06, "loss": 0.5321402549743652, "step": 4504 }, { "epoch": 0.6317044100119189, "grad_norm": 3.2789719104766846, "learning_rate": 3.1576040094909938e-06, "loss": 0.4663957953453064, "step": 4505 }, { "epoch": 0.6318446329664166, "grad_norm": 4.10980224609375, "learning_rate": 3.1554933744367154e-06, "loss": 0.38670673966407776, "step": 4506 }, { "epoch": 0.6319848559209142, "grad_norm": 3.851841926574707, "learning_rate": 3.153383119763462e-06, "loss": 0.5203408002853394, "step": 4507 }, { "epoch": 0.6321250788754119, "grad_norm": 5.1278605461120605, "learning_rate": 3.1512732459064168e-06, "loss": 0.5212576389312744, "step": 4508 }, { "epoch": 0.6322653018299096, "grad_norm": 55.1197395324707, "learning_rate": 3.1491637533006823e-06, "loss": 0.522658109664917, "step": 4509 }, { "epoch": 0.6324055247844073, "grad_norm": 3.599344491958618, "learning_rate": 3.1470546423812918e-06, "loss": 0.43160977959632874, "step": 4510 }, { "epoch": 0.6325457477389048, "grad_norm": 2.4408504962921143, "learning_rate": 3.1449459135831904e-06, "loss": 0.44149890542030334, "step": 4511 }, { "epoch": 0.6326859706934025, "grad_norm": 10.446513175964355, "learning_rate": 3.1428375673412474e-06, "loss": 0.5323289036750793, "step": 4512 }, { "epoch": 0.6328261936479002, "grad_norm": 3.147268772125244, "learning_rate": 3.140729604090257e-06, "loss": 0.5233398675918579, "step": 4513 }, { "epoch": 0.6329664166023978, "grad_norm": 3.423138380050659, "learning_rate": 3.138622024264929e-06, "loss": 0.5394982099533081, "step": 4514 }, { "epoch": 0.6331066395568955, "grad_norm": 3.5908193588256836, "learning_rate": 3.136514828299895e-06, "loss": 0.5618835091590881, "step": 4515 }, { "epoch": 0.6332468625113931, "grad_norm": 11.75060749053955, "learning_rate": 3.134408016629712e-06, "loss": 0.5036769509315491, "step": 4516 }, { "epoch": 0.6333870854658907, "grad_norm": 3.3281896114349365, "learning_rate": 3.132301589688851e-06, "loss": 0.49542221426963806, "step": 4517 }, { "epoch": 0.6335273084203884, "grad_norm": 13.485429763793945, "learning_rate": 3.1301955479117117e-06, "loss": 0.5188854932785034, "step": 4518 }, { "epoch": 0.6336675313748861, "grad_norm": 3.5882716178894043, "learning_rate": 3.128089891732607e-06, "loss": 0.5441709160804749, "step": 4519 }, { "epoch": 0.6338077543293837, "grad_norm": 2.8393702507019043, "learning_rate": 3.1259846215857714e-06, "loss": 0.5749962329864502, "step": 4520 }, { "epoch": 0.6339479772838814, "grad_norm": 2.477809429168701, "learning_rate": 3.1238797379053663e-06, "loss": 0.5691388249397278, "step": 4521 }, { "epoch": 0.634088200238379, "grad_norm": 11.599637031555176, "learning_rate": 3.121775241125466e-06, "loss": 0.4928818643093109, "step": 4522 }, { "epoch": 0.6342284231928766, "grad_norm": 4.837113380432129, "learning_rate": 3.1196711316800653e-06, "loss": 0.44625598192214966, "step": 4523 }, { "epoch": 0.6343686461473743, "grad_norm": 4.87996244430542, "learning_rate": 3.1175674100030863e-06, "loss": 0.4983184337615967, "step": 4524 }, { "epoch": 0.634508869101872, "grad_norm": 2.9339561462402344, "learning_rate": 3.115464076528364e-06, "loss": 0.4775316119194031, "step": 4525 }, { "epoch": 0.6346490920563697, "grad_norm": 3.7930307388305664, "learning_rate": 3.113361131689653e-06, "loss": 0.6180366277694702, "step": 4526 }, { "epoch": 0.6347893150108673, "grad_norm": 5.203307151794434, "learning_rate": 3.1112585759206354e-06, "loss": 0.5303912162780762, "step": 4527 }, { "epoch": 0.6349295379653649, "grad_norm": 3.289754629135132, "learning_rate": 3.1091564096549055e-06, "loss": 0.5471566915512085, "step": 4528 }, { "epoch": 0.6350697609198626, "grad_norm": 3.819451332092285, "learning_rate": 3.107054633325978e-06, "loss": 0.5438446998596191, "step": 4529 }, { "epoch": 0.6352099838743602, "grad_norm": 5.596309185028076, "learning_rate": 3.104953247367294e-06, "loss": 0.6180546283721924, "step": 4530 }, { "epoch": 0.6353502068288579, "grad_norm": 3.6939544677734375, "learning_rate": 3.102852252212205e-06, "loss": 0.4758089482784271, "step": 4531 }, { "epoch": 0.6354904297833556, "grad_norm": 3.763362407684326, "learning_rate": 3.100751648293985e-06, "loss": 0.5538613796234131, "step": 4532 }, { "epoch": 0.6356306527378532, "grad_norm": 3.4016871452331543, "learning_rate": 3.0986514360458335e-06, "loss": 0.5877932906150818, "step": 4533 }, { "epoch": 0.6357708756923508, "grad_norm": 4.844815254211426, "learning_rate": 3.096551615900861e-06, "loss": 0.5784193277359009, "step": 4534 }, { "epoch": 0.6359110986468485, "grad_norm": 3.4798851013183594, "learning_rate": 3.0944521882920984e-06, "loss": 0.5357503890991211, "step": 4535 }, { "epoch": 0.6360513216013461, "grad_norm": 4.670624732971191, "learning_rate": 3.0923531536525013e-06, "loss": 0.5300746560096741, "step": 4536 }, { "epoch": 0.6361915445558438, "grad_norm": 3.4808788299560547, "learning_rate": 3.0902545124149386e-06, "loss": 0.44292151927948, "step": 4537 }, { "epoch": 0.6363317675103415, "grad_norm": 10.959028244018555, "learning_rate": 3.088156265012199e-06, "loss": 0.4824651777744293, "step": 4538 }, { "epoch": 0.636471990464839, "grad_norm": 6.934995651245117, "learning_rate": 3.086058411876992e-06, "loss": 0.4698575735092163, "step": 4539 }, { "epoch": 0.6366122134193367, "grad_norm": 3.623624324798584, "learning_rate": 3.0839609534419455e-06, "loss": 0.5455907583236694, "step": 4540 }, { "epoch": 0.6367524363738344, "grad_norm": 4.385073661804199, "learning_rate": 3.0818638901396026e-06, "loss": 0.5213181376457214, "step": 4541 }, { "epoch": 0.6368926593283321, "grad_norm": 3.695410966873169, "learning_rate": 3.0797672224024305e-06, "loss": 0.5460332632064819, "step": 4542 }, { "epoch": 0.6370328822828297, "grad_norm": 2.4996488094329834, "learning_rate": 3.0776709506628105e-06, "loss": 0.5103140473365784, "step": 4543 }, { "epoch": 0.6371731052373274, "grad_norm": 4.938892364501953, "learning_rate": 3.0755750753530418e-06, "loss": 0.4398510456085205, "step": 4544 }, { "epoch": 0.637313328191825, "grad_norm": 3.1516833305358887, "learning_rate": 3.0734795969053465e-06, "loss": 0.42589104175567627, "step": 4545 }, { "epoch": 0.6374535511463226, "grad_norm": 3.506251573562622, "learning_rate": 3.071384515751862e-06, "loss": 0.5300464630126953, "step": 4546 }, { "epoch": 0.6375937741008203, "grad_norm": 3.222630739212036, "learning_rate": 3.0692898323246393e-06, "loss": 0.4974116384983063, "step": 4547 }, { "epoch": 0.637733997055318, "grad_norm": 4.627317428588867, "learning_rate": 3.067195547055658e-06, "loss": 0.45847731828689575, "step": 4548 }, { "epoch": 0.6378742200098156, "grad_norm": 3.1852304935455322, "learning_rate": 3.0651016603768036e-06, "loss": 0.6015554666519165, "step": 4549 }, { "epoch": 0.6380144429643133, "grad_norm": 2.3854403495788574, "learning_rate": 3.06300817271989e-06, "loss": 0.5307072401046753, "step": 4550 }, { "epoch": 0.6381546659188109, "grad_norm": 5.9479146003723145, "learning_rate": 3.060915084516643e-06, "loss": 0.5027850866317749, "step": 4551 }, { "epoch": 0.6382948888733085, "grad_norm": 2.868560314178467, "learning_rate": 3.0588223961987035e-06, "loss": 0.5572876930236816, "step": 4552 }, { "epoch": 0.6384351118278062, "grad_norm": 5.524557590484619, "learning_rate": 3.056730108197638e-06, "loss": 0.5769549012184143, "step": 4553 }, { "epoch": 0.6385753347823039, "grad_norm": 3.8035621643066406, "learning_rate": 3.0546382209449242e-06, "loss": 0.48870500922203064, "step": 4554 }, { "epoch": 0.6387155577368016, "grad_norm": 10.741347312927246, "learning_rate": 3.0525467348719564e-06, "loss": 0.5849298238754272, "step": 4555 }, { "epoch": 0.6388557806912991, "grad_norm": 3.433025598526001, "learning_rate": 3.050455650410053e-06, "loss": 0.5197784900665283, "step": 4556 }, { "epoch": 0.6389960036457968, "grad_norm": 4.86279821395874, "learning_rate": 3.0483649679904432e-06, "loss": 0.5183659195899963, "step": 4557 }, { "epoch": 0.6391362266002945, "grad_norm": 4.387615203857422, "learning_rate": 3.0462746880442728e-06, "loss": 0.5588985681533813, "step": 4558 }, { "epoch": 0.6392764495547921, "grad_norm": 6.879127025604248, "learning_rate": 3.0441848110026123e-06, "loss": 0.5911357998847961, "step": 4559 }, { "epoch": 0.6394166725092898, "grad_norm": 4.63122034072876, "learning_rate": 3.0420953372964408e-06, "loss": 0.543468177318573, "step": 4560 }, { "epoch": 0.6395568954637875, "grad_norm": 3.691620111465454, "learning_rate": 3.0400062673566556e-06, "loss": 0.6332094669342041, "step": 4561 }, { "epoch": 0.639697118418285, "grad_norm": 4.910253524780273, "learning_rate": 3.0379176016140764e-06, "loss": 0.5512463450431824, "step": 4562 }, { "epoch": 0.6398373413727827, "grad_norm": 3.939788341522217, "learning_rate": 3.0358293404994343e-06, "loss": 0.5053335428237915, "step": 4563 }, { "epoch": 0.6399775643272804, "grad_norm": 3.6579580307006836, "learning_rate": 3.033741484443376e-06, "loss": 0.6029421091079712, "step": 4564 }, { "epoch": 0.640117787281778, "grad_norm": 2.6491620540618896, "learning_rate": 3.03165403387647e-06, "loss": 0.5777411460876465, "step": 4565 }, { "epoch": 0.6402580102362757, "grad_norm": 4.96092414855957, "learning_rate": 3.029566989229198e-06, "loss": 0.47559040784835815, "step": 4566 }, { "epoch": 0.6403982331907734, "grad_norm": 12.259575843811035, "learning_rate": 3.027480350931954e-06, "loss": 0.6017410755157471, "step": 4567 }, { "epoch": 0.6405384561452709, "grad_norm": 2.6353747844696045, "learning_rate": 3.025394119415058e-06, "loss": 0.5488537549972534, "step": 4568 }, { "epoch": 0.6406786790997686, "grad_norm": 14.8826322555542, "learning_rate": 3.0233082951087358e-06, "loss": 0.5813072919845581, "step": 4569 }, { "epoch": 0.6408189020542663, "grad_norm": 7.8889641761779785, "learning_rate": 3.0212228784431365e-06, "loss": 0.6182852387428284, "step": 4570 }, { "epoch": 0.640959125008764, "grad_norm": 5.157565593719482, "learning_rate": 3.0191378698483226e-06, "loss": 0.5417834520339966, "step": 4571 }, { "epoch": 0.6410993479632616, "grad_norm": 2.891400098800659, "learning_rate": 3.017053269754271e-06, "loss": 0.5784962177276611, "step": 4572 }, { "epoch": 0.6412395709177592, "grad_norm": 5.680213928222656, "learning_rate": 3.014969078590875e-06, "loss": 0.5061461329460144, "step": 4573 }, { "epoch": 0.6413797938722569, "grad_norm": 3.43263840675354, "learning_rate": 3.0128852967879473e-06, "loss": 0.46646082401275635, "step": 4574 }, { "epoch": 0.6415200168267545, "grad_norm": 4.393283843994141, "learning_rate": 3.0108019247752107e-06, "loss": 0.44688335061073303, "step": 4575 }, { "epoch": 0.6416602397812522, "grad_norm": 3.885430335998535, "learning_rate": 3.008718962982306e-06, "loss": 0.5396462678909302, "step": 4576 }, { "epoch": 0.6418004627357499, "grad_norm": 6.118513584136963, "learning_rate": 3.0066364118387915e-06, "loss": 0.44623661041259766, "step": 4577 }, { "epoch": 0.6419406856902475, "grad_norm": 3.476773262023926, "learning_rate": 3.0045542717741337e-06, "loss": 0.5186189413070679, "step": 4578 }, { "epoch": 0.6420809086447451, "grad_norm": 3.138201951980591, "learning_rate": 3.002472543217726e-06, "loss": 0.42133164405822754, "step": 4579 }, { "epoch": 0.6422211315992428, "grad_norm": 4.3909711837768555, "learning_rate": 3.000391226598866e-06, "loss": 0.5491501688957214, "step": 4580 }, { "epoch": 0.6423613545537404, "grad_norm": 3.231043577194214, "learning_rate": 2.9983103223467695e-06, "loss": 0.4940143823623657, "step": 4581 }, { "epoch": 0.6425015775082381, "grad_norm": 3.8631036281585693, "learning_rate": 2.9962298308905723e-06, "loss": 0.5118458867073059, "step": 4582 }, { "epoch": 0.6426418004627358, "grad_norm": 3.089874505996704, "learning_rate": 2.9941497526593193e-06, "loss": 0.46489304304122925, "step": 4583 }, { "epoch": 0.6427820234172335, "grad_norm": 4.846523761749268, "learning_rate": 2.99207008808197e-06, "loss": 0.5117122530937195, "step": 4584 }, { "epoch": 0.642922246371731, "grad_norm": 3.343773126602173, "learning_rate": 2.9899908375874032e-06, "loss": 0.46377435326576233, "step": 4585 }, { "epoch": 0.6430624693262287, "grad_norm": 5.064394950866699, "learning_rate": 2.9879120016044093e-06, "loss": 0.5335850715637207, "step": 4586 }, { "epoch": 0.6432026922807264, "grad_norm": 10.73849105834961, "learning_rate": 2.985833580561691e-06, "loss": 0.4907667636871338, "step": 4587 }, { "epoch": 0.643342915235224, "grad_norm": 4.279040336608887, "learning_rate": 2.9837555748878715e-06, "loss": 0.548393964767456, "step": 4588 }, { "epoch": 0.6434831381897217, "grad_norm": 3.841613531112671, "learning_rate": 2.981677985011483e-06, "loss": 0.46831241250038147, "step": 4589 }, { "epoch": 0.6436233611442194, "grad_norm": 3.4931888580322266, "learning_rate": 2.9796008113609744e-06, "loss": 0.5669542551040649, "step": 4590 }, { "epoch": 0.6437635840987169, "grad_norm": 2.5408248901367188, "learning_rate": 2.9775240543647088e-06, "loss": 0.4501962661743164, "step": 4591 }, { "epoch": 0.6439038070532146, "grad_norm": 3.296234369277954, "learning_rate": 2.9754477144509608e-06, "loss": 0.5200299620628357, "step": 4592 }, { "epoch": 0.6440440300077123, "grad_norm": 6.543043613433838, "learning_rate": 2.973371792047922e-06, "loss": 0.5480801463127136, "step": 4593 }, { "epoch": 0.6441842529622099, "grad_norm": 5.711801528930664, "learning_rate": 2.971296287583698e-06, "loss": 0.41924750804901123, "step": 4594 }, { "epoch": 0.6443244759167076, "grad_norm": 2.5297536849975586, "learning_rate": 2.9692212014863054e-06, "loss": 0.43356087803840637, "step": 4595 }, { "epoch": 0.6444646988712052, "grad_norm": 6.978431224822998, "learning_rate": 2.967146534183677e-06, "loss": 0.5011351108551025, "step": 4596 }, { "epoch": 0.6446049218257028, "grad_norm": 3.5065720081329346, "learning_rate": 2.9650722861036585e-06, "loss": 0.5146995782852173, "step": 4597 }, { "epoch": 0.6447451447802005, "grad_norm": 3.600975513458252, "learning_rate": 2.962998457674008e-06, "loss": 0.5517584085464478, "step": 4598 }, { "epoch": 0.6448853677346982, "grad_norm": 4.777724742889404, "learning_rate": 2.960925049322399e-06, "loss": 0.5092725157737732, "step": 4599 }, { "epoch": 0.6450255906891958, "grad_norm": 7.268141269683838, "learning_rate": 2.958852061476418e-06, "loss": 0.5416723489761353, "step": 4600 }, { "epoch": 0.6451658136436935, "grad_norm": 2.210664987564087, "learning_rate": 2.956779494563563e-06, "loss": 0.5406408309936523, "step": 4601 }, { "epoch": 0.6453060365981911, "grad_norm": 3.1517293453216553, "learning_rate": 2.9547073490112475e-06, "loss": 0.41757041215896606, "step": 4602 }, { "epoch": 0.6454462595526888, "grad_norm": 4.033198833465576, "learning_rate": 2.9526356252467973e-06, "loss": 0.4918196499347687, "step": 4603 }, { "epoch": 0.6455864825071864, "grad_norm": 3.194596290588379, "learning_rate": 2.950564323697449e-06, "loss": 0.47039422392845154, "step": 4604 }, { "epoch": 0.6457267054616841, "grad_norm": 2.7644636631011963, "learning_rate": 2.9484934447903564e-06, "loss": 0.5067324638366699, "step": 4605 }, { "epoch": 0.6458669284161818, "grad_norm": 7.509579181671143, "learning_rate": 2.9464229889525824e-06, "loss": 0.5590142011642456, "step": 4606 }, { "epoch": 0.6460071513706794, "grad_norm": 3.8777899742126465, "learning_rate": 2.944352956611105e-06, "loss": 0.5009183883666992, "step": 4607 }, { "epoch": 0.646147374325177, "grad_norm": 3.189242362976074, "learning_rate": 2.9422833481928143e-06, "loss": 0.48779764771461487, "step": 4608 }, { "epoch": 0.6462875972796747, "grad_norm": 2.713113307952881, "learning_rate": 2.940214164124511e-06, "loss": 0.5625003576278687, "step": 4609 }, { "epoch": 0.6464278202341723, "grad_norm": 3.8166353702545166, "learning_rate": 2.9381454048329106e-06, "loss": 0.6209107637405396, "step": 4610 }, { "epoch": 0.64656804318867, "grad_norm": 8.436570167541504, "learning_rate": 2.9360770707446425e-06, "loss": 0.5480406284332275, "step": 4611 }, { "epoch": 0.6467082661431677, "grad_norm": 3.446197986602783, "learning_rate": 2.934009162286243e-06, "loss": 0.5335330963134766, "step": 4612 }, { "epoch": 0.6468484890976652, "grad_norm": 3.8347630500793457, "learning_rate": 2.9319416798841647e-06, "loss": 0.4810408651828766, "step": 4613 }, { "epoch": 0.6469887120521629, "grad_norm": 8.5382080078125, "learning_rate": 2.929874623964775e-06, "loss": 0.5600728988647461, "step": 4614 }, { "epoch": 0.6471289350066606, "grad_norm": 3.5787434577941895, "learning_rate": 2.9278079949543437e-06, "loss": 0.5363603234291077, "step": 4615 }, { "epoch": 0.6472691579611582, "grad_norm": 2.627685785293579, "learning_rate": 2.925741793279063e-06, "loss": 0.5094026327133179, "step": 4616 }, { "epoch": 0.6474093809156559, "grad_norm": 5.3430047035217285, "learning_rate": 2.923676019365033e-06, "loss": 0.5566840171813965, "step": 4617 }, { "epoch": 0.6475496038701536, "grad_norm": 2.8618874549865723, "learning_rate": 2.9216106736382632e-06, "loss": 0.5532984137535095, "step": 4618 }, { "epoch": 0.6476898268246511, "grad_norm": 2.4233837127685547, "learning_rate": 2.919545756524677e-06, "loss": 0.5672628283500671, "step": 4619 }, { "epoch": 0.6478300497791488, "grad_norm": 6.40850830078125, "learning_rate": 2.9174812684501114e-06, "loss": 0.5512567758560181, "step": 4620 }, { "epoch": 0.6479702727336465, "grad_norm": 4.733154296875, "learning_rate": 2.9154172098403098e-06, "loss": 0.5963808298110962, "step": 4621 }, { "epoch": 0.6481104956881442, "grad_norm": 3.2703821659088135, "learning_rate": 2.913353581120932e-06, "loss": 0.5130338072776794, "step": 4622 }, { "epoch": 0.6482507186426418, "grad_norm": 3.1659798622131348, "learning_rate": 2.9112903827175475e-06, "loss": 0.4691338539123535, "step": 4623 }, { "epoch": 0.6483909415971395, "grad_norm": 3.155179023742676, "learning_rate": 2.9092276150556377e-06, "loss": 0.4491007924079895, "step": 4624 }, { "epoch": 0.6485311645516371, "grad_norm": 2.843263626098633, "learning_rate": 2.9071652785605888e-06, "loss": 0.5412982702255249, "step": 4625 }, { "epoch": 0.6486713875061347, "grad_norm": 2.6153764724731445, "learning_rate": 2.905103373657711e-06, "loss": 0.4753892719745636, "step": 4626 }, { "epoch": 0.6488116104606324, "grad_norm": 3.5758910179138184, "learning_rate": 2.9030419007722123e-06, "loss": 0.5034069418907166, "step": 4627 }, { "epoch": 0.6489518334151301, "grad_norm": 3.119760036468506, "learning_rate": 2.90098086032922e-06, "loss": 0.48857784271240234, "step": 4628 }, { "epoch": 0.6490920563696277, "grad_norm": 2.861854314804077, "learning_rate": 2.8989202527537684e-06, "loss": 0.4508187174797058, "step": 4629 }, { "epoch": 0.6492322793241253, "grad_norm": 3.477670907974243, "learning_rate": 2.8968600784708063e-06, "loss": 0.5110782384872437, "step": 4630 }, { "epoch": 0.649372502278623, "grad_norm": 4.657568454742432, "learning_rate": 2.8948003379051835e-06, "loss": 0.5803484320640564, "step": 4631 }, { "epoch": 0.6495127252331206, "grad_norm": 2.553445339202881, "learning_rate": 2.8927410314816773e-06, "loss": 0.4456366300582886, "step": 4632 }, { "epoch": 0.6496529481876183, "grad_norm": 4.122863292694092, "learning_rate": 2.8906821596249586e-06, "loss": 0.3935984671115875, "step": 4633 }, { "epoch": 0.649793171142116, "grad_norm": 4.094315528869629, "learning_rate": 2.888623722759617e-06, "loss": 0.5244082808494568, "step": 4634 }, { "epoch": 0.6499333940966137, "grad_norm": 2.795388698577881, "learning_rate": 2.886565721310152e-06, "loss": 0.46008187532424927, "step": 4635 }, { "epoch": 0.6500736170511112, "grad_norm": 3.38706111907959, "learning_rate": 2.884508155700971e-06, "loss": 0.5144001245498657, "step": 4636 }, { "epoch": 0.6502138400056089, "grad_norm": 2.745579481124878, "learning_rate": 2.882451026356394e-06, "loss": 0.5370796918869019, "step": 4637 }, { "epoch": 0.6503540629601066, "grad_norm": 3.6330928802490234, "learning_rate": 2.8803943337006518e-06, "loss": 0.45077329874038696, "step": 4638 }, { "epoch": 0.6504942859146042, "grad_norm": 3.0919551849365234, "learning_rate": 2.8783380781578775e-06, "loss": 0.5550532937049866, "step": 4639 }, { "epoch": 0.6506345088691019, "grad_norm": 3.55403208732605, "learning_rate": 2.8762822601521258e-06, "loss": 0.4787296652793884, "step": 4640 }, { "epoch": 0.6507747318235996, "grad_norm": 3.4741017818450928, "learning_rate": 2.8742268801073513e-06, "loss": 0.5146169662475586, "step": 4641 }, { "epoch": 0.6509149547780971, "grad_norm": 12.402832984924316, "learning_rate": 2.8721719384474234e-06, "loss": 0.5238983631134033, "step": 4642 }, { "epoch": 0.6510551777325948, "grad_norm": 3.142500638961792, "learning_rate": 2.8701174355961203e-06, "loss": 0.4639626741409302, "step": 4643 }, { "epoch": 0.6511954006870925, "grad_norm": 4.126129627227783, "learning_rate": 2.86806337197713e-06, "loss": 0.4233885407447815, "step": 4644 }, { "epoch": 0.6513356236415901, "grad_norm": 10.87448787689209, "learning_rate": 2.8660097480140446e-06, "loss": 0.4923739731311798, "step": 4645 }, { "epoch": 0.6514758465960878, "grad_norm": 5.354680061340332, "learning_rate": 2.863956564130377e-06, "loss": 0.5495113134384155, "step": 4646 }, { "epoch": 0.6516160695505855, "grad_norm": 8.029767990112305, "learning_rate": 2.8619038207495364e-06, "loss": 0.5929782390594482, "step": 4647 }, { "epoch": 0.651756292505083, "grad_norm": 5.047513008117676, "learning_rate": 2.8598515182948505e-06, "loss": 0.6304958462715149, "step": 4648 }, { "epoch": 0.6518965154595807, "grad_norm": 3.801427125930786, "learning_rate": 2.8577996571895506e-06, "loss": 0.41223281621932983, "step": 4649 }, { "epoch": 0.6520367384140784, "grad_norm": 8.090839385986328, "learning_rate": 2.8557482378567836e-06, "loss": 0.5030729174613953, "step": 4650 }, { "epoch": 0.6521769613685761, "grad_norm": 3.290536642074585, "learning_rate": 2.8536972607195927e-06, "loss": 0.47849419713020325, "step": 4651 }, { "epoch": 0.6523171843230737, "grad_norm": 4.625120162963867, "learning_rate": 2.8516467262009474e-06, "loss": 0.48246923089027405, "step": 4652 }, { "epoch": 0.6524574072775713, "grad_norm": 3.3308489322662354, "learning_rate": 2.84959663472371e-06, "loss": 0.5778183937072754, "step": 4653 }, { "epoch": 0.652597630232069, "grad_norm": 6.0249552726745605, "learning_rate": 2.8475469867106596e-06, "loss": 0.5216958522796631, "step": 4654 }, { "epoch": 0.6527378531865666, "grad_norm": 2.7211501598358154, "learning_rate": 2.8454977825844836e-06, "loss": 0.505547285079956, "step": 4655 }, { "epoch": 0.6528780761410643, "grad_norm": 3.326005458831787, "learning_rate": 2.8434490227677773e-06, "loss": 0.5831983089447021, "step": 4656 }, { "epoch": 0.653018299095562, "grad_norm": 5.696163177490234, "learning_rate": 2.841400707683038e-06, "loss": 0.5701087713241577, "step": 4657 }, { "epoch": 0.6531585220500596, "grad_norm": 3.176292896270752, "learning_rate": 2.8393528377526847e-06, "loss": 0.48717886209487915, "step": 4658 }, { "epoch": 0.6532987450045572, "grad_norm": 4.364287853240967, "learning_rate": 2.837305413399031e-06, "loss": 0.5027626156806946, "step": 4659 }, { "epoch": 0.6534389679590549, "grad_norm": 3.38448166847229, "learning_rate": 2.8352584350443056e-06, "loss": 0.6127946376800537, "step": 4660 }, { "epoch": 0.6535791909135525, "grad_norm": 5.061066627502441, "learning_rate": 2.8332119031106453e-06, "loss": 0.5594420433044434, "step": 4661 }, { "epoch": 0.6537194138680502, "grad_norm": 3.4456911087036133, "learning_rate": 2.8311658180200946e-06, "loss": 0.5736854672431946, "step": 4662 }, { "epoch": 0.6538596368225479, "grad_norm": 4.593075275421143, "learning_rate": 2.8291201801945987e-06, "loss": 0.5439862012863159, "step": 4663 }, { "epoch": 0.6539998597770456, "grad_norm": 2.314990997314453, "learning_rate": 2.827074990056026e-06, "loss": 0.49289119243621826, "step": 4664 }, { "epoch": 0.6541400827315431, "grad_norm": 3.6503896713256836, "learning_rate": 2.825030248026133e-06, "loss": 0.49156320095062256, "step": 4665 }, { "epoch": 0.6542803056860408, "grad_norm": 2.6015894412994385, "learning_rate": 2.8229859545266038e-06, "loss": 0.4932098388671875, "step": 4666 }, { "epoch": 0.6544205286405385, "grad_norm": 3.054598808288574, "learning_rate": 2.8209421099790135e-06, "loss": 0.4955604076385498, "step": 4667 }, { "epoch": 0.6545607515950361, "grad_norm": 4.229910850524902, "learning_rate": 2.8188987148048537e-06, "loss": 0.5225043296813965, "step": 4668 }, { "epoch": 0.6547009745495338, "grad_norm": 6.720818519592285, "learning_rate": 2.8168557694255206e-06, "loss": 0.410196453332901, "step": 4669 }, { "epoch": 0.6548411975040314, "grad_norm": 4.841334342956543, "learning_rate": 2.8148132742623204e-06, "loss": 0.505167543888092, "step": 4670 }, { "epoch": 0.654981420458529, "grad_norm": 3.2981879711151123, "learning_rate": 2.812771229736457e-06, "loss": 0.5412457585334778, "step": 4671 }, { "epoch": 0.6551216434130267, "grad_norm": 8.363436698913574, "learning_rate": 2.810729636269058e-06, "loss": 0.4356226325035095, "step": 4672 }, { "epoch": 0.6552618663675244, "grad_norm": 2.9418742656707764, "learning_rate": 2.808688494281141e-06, "loss": 0.5253241062164307, "step": 4673 }, { "epoch": 0.655402089322022, "grad_norm": 2.826990842819214, "learning_rate": 2.8066478041936408e-06, "loss": 0.5413251519203186, "step": 4674 }, { "epoch": 0.6555423122765197, "grad_norm": 4.071405410766602, "learning_rate": 2.804607566427396e-06, "loss": 0.5640581846237183, "step": 4675 }, { "epoch": 0.6556825352310173, "grad_norm": 4.827805519104004, "learning_rate": 2.8025677814031538e-06, "loss": 0.547391951084137, "step": 4676 }, { "epoch": 0.6558227581855149, "grad_norm": 2.2866039276123047, "learning_rate": 2.8005284495415597e-06, "loss": 0.5498425960540771, "step": 4677 }, { "epoch": 0.6559629811400126, "grad_norm": 5.543872356414795, "learning_rate": 2.7984895712631815e-06, "loss": 0.5570154190063477, "step": 4678 }, { "epoch": 0.6561032040945103, "grad_norm": 2.9481914043426514, "learning_rate": 2.7964511469884776e-06, "loss": 0.5252083539962769, "step": 4679 }, { "epoch": 0.656243427049008, "grad_norm": 4.565572261810303, "learning_rate": 2.7944131771378213e-06, "loss": 0.579634428024292, "step": 4680 }, { "epoch": 0.6563836500035056, "grad_norm": 2.4778170585632324, "learning_rate": 2.7923756621314914e-06, "loss": 0.5110382437705994, "step": 4681 }, { "epoch": 0.6565238729580032, "grad_norm": 3.273404359817505, "learning_rate": 2.790338602389672e-06, "loss": 0.5259023904800415, "step": 4682 }, { "epoch": 0.6566640959125009, "grad_norm": 3.8429267406463623, "learning_rate": 2.7883019983324485e-06, "loss": 0.5041826963424683, "step": 4683 }, { "epoch": 0.6568043188669985, "grad_norm": 6.858582019805908, "learning_rate": 2.7862658503798247e-06, "loss": 0.5632836818695068, "step": 4684 }, { "epoch": 0.6569445418214962, "grad_norm": 3.6643359661102295, "learning_rate": 2.7842301589516964e-06, "loss": 0.5888611078262329, "step": 4685 }, { "epoch": 0.6570847647759939, "grad_norm": 5.445550918579102, "learning_rate": 2.7821949244678735e-06, "loss": 0.5937893390655518, "step": 4686 }, { "epoch": 0.6572249877304914, "grad_norm": 2.996742010116577, "learning_rate": 2.78016014734807e-06, "loss": 0.5691148042678833, "step": 4687 }, { "epoch": 0.6573652106849891, "grad_norm": 3.7484774589538574, "learning_rate": 2.778125828011906e-06, "loss": 0.5075305700302124, "step": 4688 }, { "epoch": 0.6575054336394868, "grad_norm": 3.0997231006622314, "learning_rate": 2.776091966878902e-06, "loss": 0.5497939586639404, "step": 4689 }, { "epoch": 0.6576456565939844, "grad_norm": 3.9162814617156982, "learning_rate": 2.774058564368496e-06, "loss": 0.4942696690559387, "step": 4690 }, { "epoch": 0.6577858795484821, "grad_norm": 2.83705472946167, "learning_rate": 2.7720256209000175e-06, "loss": 0.5208339691162109, "step": 4691 }, { "epoch": 0.6579261025029798, "grad_norm": 4.3974223136901855, "learning_rate": 2.769993136892709e-06, "loss": 0.5110378265380859, "step": 4692 }, { "epoch": 0.6580663254574773, "grad_norm": 6.578734397888184, "learning_rate": 2.767961112765719e-06, "loss": 0.6172537803649902, "step": 4693 }, { "epoch": 0.658206548411975, "grad_norm": 7.734459400177002, "learning_rate": 2.7659295489380967e-06, "loss": 0.7073037028312683, "step": 4694 }, { "epoch": 0.6583467713664727, "grad_norm": 4.372302055358887, "learning_rate": 2.7638984458288e-06, "loss": 0.513258695602417, "step": 4695 }, { "epoch": 0.6584869943209704, "grad_norm": 2.8740265369415283, "learning_rate": 2.7618678038566925e-06, "loss": 0.4833511412143707, "step": 4696 }, { "epoch": 0.658627217275468, "grad_norm": 4.743146896362305, "learning_rate": 2.7598376234405342e-06, "loss": 0.5195581912994385, "step": 4697 }, { "epoch": 0.6587674402299657, "grad_norm": 13.385137557983398, "learning_rate": 2.757807904999006e-06, "loss": 0.5669560432434082, "step": 4698 }, { "epoch": 0.6589076631844633, "grad_norm": 4.887311935424805, "learning_rate": 2.7557786489506755e-06, "loss": 0.4796289801597595, "step": 4699 }, { "epoch": 0.6590478861389609, "grad_norm": 4.048730850219727, "learning_rate": 2.7537498557140273e-06, "loss": 0.4517330825328827, "step": 4700 }, { "epoch": 0.6591881090934586, "grad_norm": 12.56187915802002, "learning_rate": 2.7517215257074465e-06, "loss": 0.6490424871444702, "step": 4701 }, { "epoch": 0.6593283320479563, "grad_norm": 2.9657163619995117, "learning_rate": 2.749693659349224e-06, "loss": 0.5801593661308289, "step": 4702 }, { "epoch": 0.6594685550024539, "grad_norm": 2.884732484817505, "learning_rate": 2.747666257057549e-06, "loss": 0.4631577134132385, "step": 4703 }, { "epoch": 0.6596087779569515, "grad_norm": 2.596967935562134, "learning_rate": 2.745639319250527e-06, "loss": 0.45912042260169983, "step": 4704 }, { "epoch": 0.6597490009114492, "grad_norm": 8.722127914428711, "learning_rate": 2.7436128463461554e-06, "loss": 0.49593067169189453, "step": 4705 }, { "epoch": 0.6598892238659468, "grad_norm": 3.8837385177612305, "learning_rate": 2.741586838762343e-06, "loss": 0.5129404067993164, "step": 4706 }, { "epoch": 0.6600294468204445, "grad_norm": 4.206849575042725, "learning_rate": 2.7395612969168994e-06, "loss": 0.5888767242431641, "step": 4707 }, { "epoch": 0.6601696697749422, "grad_norm": 5.077737331390381, "learning_rate": 2.7375362212275436e-06, "loss": 0.4211668372154236, "step": 4708 }, { "epoch": 0.6603098927294399, "grad_norm": 3.6022534370422363, "learning_rate": 2.735511612111886e-06, "loss": 0.5422689914703369, "step": 4709 }, { "epoch": 0.6604501156839374, "grad_norm": 2.736562967300415, "learning_rate": 2.7334874699874582e-06, "loss": 0.45419004559516907, "step": 4710 }, { "epoch": 0.6605903386384351, "grad_norm": 4.0417046546936035, "learning_rate": 2.73146379527168e-06, "loss": 0.508700966835022, "step": 4711 }, { "epoch": 0.6607305615929328, "grad_norm": 3.3809967041015625, "learning_rate": 2.729440588381883e-06, "loss": 0.5300126075744629, "step": 4712 }, { "epoch": 0.6608707845474304, "grad_norm": 2.4920973777770996, "learning_rate": 2.727417849735301e-06, "loss": 0.5438709259033203, "step": 4713 }, { "epoch": 0.6610110075019281, "grad_norm": 6.0350518226623535, "learning_rate": 2.7253955797490727e-06, "loss": 0.4727175831794739, "step": 4714 }, { "epoch": 0.6611512304564258, "grad_norm": 2.649177312850952, "learning_rate": 2.7233737788402313e-06, "loss": 0.5153254270553589, "step": 4715 }, { "epoch": 0.6612914534109233, "grad_norm": 5.236975193023682, "learning_rate": 2.7213524474257292e-06, "loss": 0.5450668334960938, "step": 4716 }, { "epoch": 0.661431676365421, "grad_norm": 4.53408670425415, "learning_rate": 2.719331585922406e-06, "loss": 0.5103886127471924, "step": 4717 }, { "epoch": 0.6615718993199187, "grad_norm": 5.001863479614258, "learning_rate": 2.717311194747013e-06, "loss": 0.48535996675491333, "step": 4718 }, { "epoch": 0.6617121222744163, "grad_norm": 11.92739486694336, "learning_rate": 2.715291274316204e-06, "loss": 0.4778858423233032, "step": 4719 }, { "epoch": 0.661852345228914, "grad_norm": 4.361655235290527, "learning_rate": 2.713271825046536e-06, "loss": 0.5296663045883179, "step": 4720 }, { "epoch": 0.6619925681834117, "grad_norm": 4.875682830810547, "learning_rate": 2.7112528473544608e-06, "loss": 0.5078023076057434, "step": 4721 }, { "epoch": 0.6621327911379092, "grad_norm": 3.8321754932403564, "learning_rate": 2.7092343416563482e-06, "loss": 0.5693057775497437, "step": 4722 }, { "epoch": 0.6622730140924069, "grad_norm": 3.7585177421569824, "learning_rate": 2.7072163083684568e-06, "loss": 0.5917450189590454, "step": 4723 }, { "epoch": 0.6624132370469046, "grad_norm": 4.222884654998779, "learning_rate": 2.705198747906952e-06, "loss": 0.4935736656188965, "step": 4724 }, { "epoch": 0.6625534600014023, "grad_norm": 3.375009536743164, "learning_rate": 2.7031816606879057e-06, "loss": 0.5014129877090454, "step": 4725 }, { "epoch": 0.6626936829558999, "grad_norm": 17.39280891418457, "learning_rate": 2.7011650471272875e-06, "loss": 0.4997760057449341, "step": 4726 }, { "epoch": 0.6628339059103975, "grad_norm": 4.911688327789307, "learning_rate": 2.6991489076409716e-06, "loss": 0.46873676776885986, "step": 4727 }, { "epoch": 0.6629741288648952, "grad_norm": 4.743355751037598, "learning_rate": 2.697133242644735e-06, "loss": 0.5077283382415771, "step": 4728 }, { "epoch": 0.6631143518193928, "grad_norm": 3.6611034870147705, "learning_rate": 2.695118052554251e-06, "loss": 0.557799220085144, "step": 4729 }, { "epoch": 0.6632545747738905, "grad_norm": 2.5390138626098633, "learning_rate": 2.693103337785106e-06, "loss": 0.4530395269393921, "step": 4730 }, { "epoch": 0.6633947977283882, "grad_norm": 3.309009313583374, "learning_rate": 2.6910890987527772e-06, "loss": 0.49567848443984985, "step": 4731 }, { "epoch": 0.6635350206828858, "grad_norm": 3.576688051223755, "learning_rate": 2.689075335872651e-06, "loss": 0.579155445098877, "step": 4732 }, { "epoch": 0.6636752436373834, "grad_norm": 3.97904372215271, "learning_rate": 2.6870620495600107e-06, "loss": 0.5235631465911865, "step": 4733 }, { "epoch": 0.6638154665918811, "grad_norm": 3.2229390144348145, "learning_rate": 2.685049240230048e-06, "loss": 0.5602333545684814, "step": 4734 }, { "epoch": 0.6639556895463787, "grad_norm": 4.583631992340088, "learning_rate": 2.6830369082978443e-06, "loss": 0.46824750304222107, "step": 4735 }, { "epoch": 0.6640959125008764, "grad_norm": 4.583066463470459, "learning_rate": 2.681025054178399e-06, "loss": 0.5520234107971191, "step": 4736 }, { "epoch": 0.6642361354553741, "grad_norm": 10.64261531829834, "learning_rate": 2.679013678286598e-06, "loss": 0.49289530515670776, "step": 4737 }, { "epoch": 0.6643763584098717, "grad_norm": 4.065668106079102, "learning_rate": 2.677002781037238e-06, "loss": 0.40536466240882874, "step": 4738 }, { "epoch": 0.6645165813643693, "grad_norm": 6.819350719451904, "learning_rate": 2.6749923628450113e-06, "loss": 0.5286064743995667, "step": 4739 }, { "epoch": 0.664656804318867, "grad_norm": 3.0698933601379395, "learning_rate": 2.672982424124518e-06, "loss": 0.5436713099479675, "step": 4740 }, { "epoch": 0.6647970272733646, "grad_norm": 5.359074592590332, "learning_rate": 2.6709729652902473e-06, "loss": 0.5327661037445068, "step": 4741 }, { "epoch": 0.6649372502278623, "grad_norm": 5.4655890464782715, "learning_rate": 2.6689639867566065e-06, "loss": 0.5421764850616455, "step": 4742 }, { "epoch": 0.66507747318236, "grad_norm": 3.375284194946289, "learning_rate": 2.666955488937889e-06, "loss": 0.5033813714981079, "step": 4743 }, { "epoch": 0.6652176961368576, "grad_norm": 3.933248519897461, "learning_rate": 2.664947472248295e-06, "loss": 0.4685783386230469, "step": 4744 }, { "epoch": 0.6653579190913552, "grad_norm": 3.1357221603393555, "learning_rate": 2.662939937101927e-06, "loss": 0.5244773030281067, "step": 4745 }, { "epoch": 0.6654981420458529, "grad_norm": 3.4910783767700195, "learning_rate": 2.660932883912787e-06, "loss": 0.5278463363647461, "step": 4746 }, { "epoch": 0.6656383650003506, "grad_norm": 3.563873052597046, "learning_rate": 2.6589263130947717e-06, "loss": 0.48640376329421997, "step": 4747 }, { "epoch": 0.6657785879548482, "grad_norm": 3.37205171585083, "learning_rate": 2.6569202250616914e-06, "loss": 0.4661897122859955, "step": 4748 }, { "epoch": 0.6659188109093459, "grad_norm": 5.142269134521484, "learning_rate": 2.6549146202272436e-06, "loss": 0.4802935719490051, "step": 4749 }, { "epoch": 0.6660590338638435, "grad_norm": 3.237274408340454, "learning_rate": 2.6529094990050325e-06, "loss": 0.5592241287231445, "step": 4750 }, { "epoch": 0.6661992568183411, "grad_norm": 8.459436416625977, "learning_rate": 2.6509048618085625e-06, "loss": 0.6071795225143433, "step": 4751 }, { "epoch": 0.6663394797728388, "grad_norm": 2.9328808784484863, "learning_rate": 2.648900709051237e-06, "loss": 0.5270739793777466, "step": 4752 }, { "epoch": 0.6664797027273365, "grad_norm": 3.2371819019317627, "learning_rate": 2.6468970411463603e-06, "loss": 0.4940847158432007, "step": 4753 }, { "epoch": 0.6666199256818341, "grad_norm": 2.5373215675354004, "learning_rate": 2.644893858507137e-06, "loss": 0.515301525592804, "step": 4754 }, { "epoch": 0.6667601486363318, "grad_norm": 3.752417802810669, "learning_rate": 2.6428911615466668e-06, "loss": 0.5892224311828613, "step": 4755 }, { "epoch": 0.6669003715908294, "grad_norm": 4.980935096740723, "learning_rate": 2.64088895067796e-06, "loss": 0.504404604434967, "step": 4756 }, { "epoch": 0.667040594545327, "grad_norm": 3.1125295162200928, "learning_rate": 2.6388872263139137e-06, "loss": 0.49969762563705444, "step": 4757 }, { "epoch": 0.6671808174998247, "grad_norm": 4.328795909881592, "learning_rate": 2.636885988867334e-06, "loss": 0.55653315782547, "step": 4758 }, { "epoch": 0.6673210404543224, "grad_norm": 2.9409945011138916, "learning_rate": 2.6348852387509226e-06, "loss": 0.4181804656982422, "step": 4759 }, { "epoch": 0.6674612634088201, "grad_norm": 4.267690181732178, "learning_rate": 2.6328849763772845e-06, "loss": 0.49649181962013245, "step": 4760 }, { "epoch": 0.6676014863633176, "grad_norm": 3.957911729812622, "learning_rate": 2.6308852021589152e-06, "loss": 0.5252160429954529, "step": 4761 }, { "epoch": 0.6677417093178153, "grad_norm": 4.521373271942139, "learning_rate": 2.6288859165082232e-06, "loss": 0.5662617683410645, "step": 4762 }, { "epoch": 0.667881932272313, "grad_norm": 8.541211128234863, "learning_rate": 2.6268871198375023e-06, "loss": 0.5232138633728027, "step": 4763 }, { "epoch": 0.6680221552268106, "grad_norm": 4.187668323516846, "learning_rate": 2.6248888125589546e-06, "loss": 0.48174750804901123, "step": 4764 }, { "epoch": 0.6681623781813083, "grad_norm": 4.103507041931152, "learning_rate": 2.622890995084677e-06, "loss": 0.633766233921051, "step": 4765 }, { "epoch": 0.668302601135806, "grad_norm": 2.777517795562744, "learning_rate": 2.6208936678266705e-06, "loss": 0.5799857378005981, "step": 4766 }, { "epoch": 0.6684428240903035, "grad_norm": 2.755025625228882, "learning_rate": 2.6188968311968255e-06, "loss": 0.6154336929321289, "step": 4767 }, { "epoch": 0.6685830470448012, "grad_norm": 2.6681838035583496, "learning_rate": 2.6169004856069434e-06, "loss": 0.5139024257659912, "step": 4768 }, { "epoch": 0.6687232699992989, "grad_norm": 3.6520564556121826, "learning_rate": 2.614904631468713e-06, "loss": 0.5587884783744812, "step": 4769 }, { "epoch": 0.6688634929537965, "grad_norm": 3.249176025390625, "learning_rate": 2.6129092691937284e-06, "loss": 0.6075422763824463, "step": 4770 }, { "epoch": 0.6690037159082942, "grad_norm": 5.104902744293213, "learning_rate": 2.6109143991934815e-06, "loss": 0.6034702062606812, "step": 4771 }, { "epoch": 0.6691439388627919, "grad_norm": 2.0251128673553467, "learning_rate": 2.608920021879362e-06, "loss": 0.5205020904541016, "step": 4772 }, { "epoch": 0.6692841618172894, "grad_norm": 2.8940837383270264, "learning_rate": 2.6069261376626557e-06, "loss": 0.5275982618331909, "step": 4773 }, { "epoch": 0.6694243847717871, "grad_norm": 11.990861892700195, "learning_rate": 2.6049327469545526e-06, "loss": 0.4931638836860657, "step": 4774 }, { "epoch": 0.6695646077262848, "grad_norm": 2.8230156898498535, "learning_rate": 2.6029398501661337e-06, "loss": 0.5027969479560852, "step": 4775 }, { "epoch": 0.6697048306807825, "grad_norm": 2.916290283203125, "learning_rate": 2.600947447708382e-06, "loss": 0.5006073117256165, "step": 4776 }, { "epoch": 0.6698450536352801, "grad_norm": 4.828611373901367, "learning_rate": 2.5989555399921786e-06, "loss": 0.5080156922340393, "step": 4777 }, { "epoch": 0.6699852765897778, "grad_norm": 3.9564805030822754, "learning_rate": 2.596964127428302e-06, "loss": 0.4878372251987457, "step": 4778 }, { "epoch": 0.6701254995442754, "grad_norm": 4.519982814788818, "learning_rate": 2.5949732104274295e-06, "loss": 0.5068855285644531, "step": 4779 }, { "epoch": 0.670265722498773, "grad_norm": 3.6319260597229004, "learning_rate": 2.592982789400137e-06, "loss": 0.3924826979637146, "step": 4780 }, { "epoch": 0.6704059454532707, "grad_norm": 5.419456958770752, "learning_rate": 2.5909928647568928e-06, "loss": 0.4659704864025116, "step": 4781 }, { "epoch": 0.6705461684077684, "grad_norm": 2.8361549377441406, "learning_rate": 2.589003436908068e-06, "loss": 0.5637799501419067, "step": 4782 }, { "epoch": 0.670686391362266, "grad_norm": 3.007934808731079, "learning_rate": 2.5870145062639302e-06, "loss": 0.5205404758453369, "step": 4783 }, { "epoch": 0.6708266143167636, "grad_norm": 3.461129903793335, "learning_rate": 2.5850260732346436e-06, "loss": 0.5255550146102905, "step": 4784 }, { "epoch": 0.6709668372712613, "grad_norm": 5.043612480163574, "learning_rate": 2.583038138230271e-06, "loss": 0.5816975831985474, "step": 4785 }, { "epoch": 0.671107060225759, "grad_norm": 3.0696184635162354, "learning_rate": 2.5810507016607733e-06, "loss": 0.505108118057251, "step": 4786 }, { "epoch": 0.6712472831802566, "grad_norm": 3.143866539001465, "learning_rate": 2.579063763936001e-06, "loss": 0.5356022715568542, "step": 4787 }, { "epoch": 0.6713875061347543, "grad_norm": 2.74387526512146, "learning_rate": 2.577077325465716e-06, "loss": 0.4940146505832672, "step": 4788 }, { "epoch": 0.671527729089252, "grad_norm": 2.9285497665405273, "learning_rate": 2.575091386659563e-06, "loss": 0.4369744062423706, "step": 4789 }, { "epoch": 0.6716679520437495, "grad_norm": 3.0694375038146973, "learning_rate": 2.5731059479270916e-06, "loss": 0.5316941738128662, "step": 4790 }, { "epoch": 0.6718081749982472, "grad_norm": 2.9539239406585693, "learning_rate": 2.5711210096777468e-06, "loss": 0.4632180631160736, "step": 4791 }, { "epoch": 0.6719483979527449, "grad_norm": 4.43001127243042, "learning_rate": 2.5691365723208694e-06, "loss": 0.5116490125656128, "step": 4792 }, { "epoch": 0.6720886209072425, "grad_norm": 8.505478858947754, "learning_rate": 2.567152636265697e-06, "loss": 0.5196220278739929, "step": 4793 }, { "epoch": 0.6722288438617402, "grad_norm": 4.341197490692139, "learning_rate": 2.565169201921368e-06, "loss": 0.5770226716995239, "step": 4794 }, { "epoch": 0.6723690668162379, "grad_norm": 3.2978570461273193, "learning_rate": 2.5631862696969077e-06, "loss": 0.4173184037208557, "step": 4795 }, { "epoch": 0.6725092897707354, "grad_norm": 4.607219219207764, "learning_rate": 2.5612038400012474e-06, "loss": 0.5670974850654602, "step": 4796 }, { "epoch": 0.6726495127252331, "grad_norm": 10.625837326049805, "learning_rate": 2.5592219132432104e-06, "loss": 0.4839217960834503, "step": 4797 }, { "epoch": 0.6727897356797308, "grad_norm": 2.800532579421997, "learning_rate": 2.5572404898315162e-06, "loss": 0.4919317066669464, "step": 4798 }, { "epoch": 0.6729299586342284, "grad_norm": 4.200119972229004, "learning_rate": 2.5552595701747827e-06, "loss": 0.4962958097457886, "step": 4799 }, { "epoch": 0.6730701815887261, "grad_norm": 4.1756205558776855, "learning_rate": 2.5532791546815237e-06, "loss": 0.5187957286834717, "step": 4800 }, { "epoch": 0.6732104045432237, "grad_norm": 3.8704216480255127, "learning_rate": 2.5512992437601434e-06, "loss": 0.4430951476097107, "step": 4801 }, { "epoch": 0.6733506274977213, "grad_norm": 3.246574640274048, "learning_rate": 2.5493198378189497e-06, "loss": 0.4885433614253998, "step": 4802 }, { "epoch": 0.673490850452219, "grad_norm": 4.128013610839844, "learning_rate": 2.5473409372661427e-06, "loss": 0.5051131248474121, "step": 4803 }, { "epoch": 0.6736310734067167, "grad_norm": 6.07921838760376, "learning_rate": 2.545362542509818e-06, "loss": 0.5412439703941345, "step": 4804 }, { "epoch": 0.6737712963612144, "grad_norm": 4.859851837158203, "learning_rate": 2.543384653957968e-06, "loss": 0.49531328678131104, "step": 4805 }, { "epoch": 0.673911519315712, "grad_norm": 4.239319801330566, "learning_rate": 2.5414072720184823e-06, "loss": 0.46908754110336304, "step": 4806 }, { "epoch": 0.6740517422702096, "grad_norm": 3.594747543334961, "learning_rate": 2.5394303970991395e-06, "loss": 0.5564543008804321, "step": 4807 }, { "epoch": 0.6741919652247073, "grad_norm": 3.8485336303710938, "learning_rate": 2.5374540296076206e-06, "loss": 0.5861043334007263, "step": 4808 }, { "epoch": 0.6743321881792049, "grad_norm": 3.2724952697753906, "learning_rate": 2.5354781699514992e-06, "loss": 0.5232746601104736, "step": 4809 }, { "epoch": 0.6744724111337026, "grad_norm": 3.932342052459717, "learning_rate": 2.5335028185382444e-06, "loss": 0.5403317213058472, "step": 4810 }, { "epoch": 0.6746126340882003, "grad_norm": 4.8524065017700195, "learning_rate": 2.531527975775221e-06, "loss": 0.5623407363891602, "step": 4811 }, { "epoch": 0.6747528570426979, "grad_norm": 5.379786968231201, "learning_rate": 2.5295536420696876e-06, "loss": 0.4083050489425659, "step": 4812 }, { "epoch": 0.6748930799971955, "grad_norm": 12.7589693069458, "learning_rate": 2.527579817828799e-06, "loss": 0.5057212114334106, "step": 4813 }, { "epoch": 0.6750333029516932, "grad_norm": 5.838781356811523, "learning_rate": 2.525606503459607e-06, "loss": 0.5084441900253296, "step": 4814 }, { "epoch": 0.6751735259061908, "grad_norm": 2.631533145904541, "learning_rate": 2.5236336993690512e-06, "loss": 0.4520748257637024, "step": 4815 }, { "epoch": 0.6753137488606885, "grad_norm": 4.548409938812256, "learning_rate": 2.521661405963973e-06, "loss": 0.4724732041358948, "step": 4816 }, { "epoch": 0.6754539718151862, "grad_norm": 7.476758003234863, "learning_rate": 2.519689623651106e-06, "loss": 0.544010579586029, "step": 4817 }, { "epoch": 0.6755941947696837, "grad_norm": 6.7860307693481445, "learning_rate": 2.517718352837079e-06, "loss": 0.6020662188529968, "step": 4818 }, { "epoch": 0.6757344177241814, "grad_norm": 3.2483878135681152, "learning_rate": 2.515747593928414e-06, "loss": 0.5300530195236206, "step": 4819 }, { "epoch": 0.6758746406786791, "grad_norm": 6.274958610534668, "learning_rate": 2.51377734733153e-06, "loss": 0.4126049280166626, "step": 4820 }, { "epoch": 0.6760148636331768, "grad_norm": 4.813990592956543, "learning_rate": 2.511807613452736e-06, "loss": 0.49820476770401, "step": 4821 }, { "epoch": 0.6761550865876744, "grad_norm": 3.8682119846343994, "learning_rate": 2.5098383926982385e-06, "loss": 0.5670312643051147, "step": 4822 }, { "epoch": 0.6762953095421721, "grad_norm": 8.030102729797363, "learning_rate": 2.507869685474138e-06, "loss": 0.3411078453063965, "step": 4823 }, { "epoch": 0.6764355324966697, "grad_norm": 4.446186065673828, "learning_rate": 2.505901492186429e-06, "loss": 0.5602853298187256, "step": 4824 }, { "epoch": 0.6765757554511673, "grad_norm": 2.8130950927734375, "learning_rate": 2.503933813240999e-06, "loss": 0.516994833946228, "step": 4825 }, { "epoch": 0.676715978405665, "grad_norm": 2.5844297409057617, "learning_rate": 2.5019666490436323e-06, "loss": 0.5507842898368835, "step": 4826 }, { "epoch": 0.6768562013601627, "grad_norm": 3.711894989013672, "learning_rate": 2.5000000000000015e-06, "loss": 0.42020002007484436, "step": 4827 }, { "epoch": 0.6769964243146603, "grad_norm": 4.320291519165039, "learning_rate": 2.4980338665156765e-06, "loss": 0.5857341289520264, "step": 4828 }, { "epoch": 0.677136647269158, "grad_norm": 2.8824453353881836, "learning_rate": 2.496068248996123e-06, "loss": 0.45232880115509033, "step": 4829 }, { "epoch": 0.6772768702236556, "grad_norm": 2.7558844089508057, "learning_rate": 2.4941031478466963e-06, "loss": 0.570382833480835, "step": 4830 }, { "epoch": 0.6774170931781532, "grad_norm": 4.277312755584717, "learning_rate": 2.4921385634726474e-06, "loss": 0.42686399817466736, "step": 4831 }, { "epoch": 0.6775573161326509, "grad_norm": 6.517733097076416, "learning_rate": 2.4901744962791208e-06, "loss": 0.49375951290130615, "step": 4832 }, { "epoch": 0.6776975390871486, "grad_norm": 5.8593316078186035, "learning_rate": 2.488210946671154e-06, "loss": 0.48856469988822937, "step": 4833 }, { "epoch": 0.6778377620416463, "grad_norm": 2.936267852783203, "learning_rate": 2.4862479150536755e-06, "loss": 0.4901163578033447, "step": 4834 }, { "epoch": 0.6779779849961439, "grad_norm": 2.9432621002197266, "learning_rate": 2.4842854018315098e-06, "loss": 0.5733290910720825, "step": 4835 }, { "epoch": 0.6781182079506415, "grad_norm": 3.227635383605957, "learning_rate": 2.4823234074093742e-06, "loss": 0.4693663418292999, "step": 4836 }, { "epoch": 0.6782584309051392, "grad_norm": 2.619466781616211, "learning_rate": 2.4803619321918784e-06, "loss": 0.480824738740921, "step": 4837 }, { "epoch": 0.6783986538596368, "grad_norm": 3.6910879611968994, "learning_rate": 2.478400976583525e-06, "loss": 0.5406762361526489, "step": 4838 }, { "epoch": 0.6785388768141345, "grad_norm": 14.456538200378418, "learning_rate": 2.4764405409887117e-06, "loss": 0.5459368228912354, "step": 4839 }, { "epoch": 0.6786790997686322, "grad_norm": 2.6508092880249023, "learning_rate": 2.474480625811722e-06, "loss": 0.4767268896102905, "step": 4840 }, { "epoch": 0.6788193227231297, "grad_norm": 23.189807891845703, "learning_rate": 2.4725212314567406e-06, "loss": 0.555021345615387, "step": 4841 }, { "epoch": 0.6789595456776274, "grad_norm": 9.446385383605957, "learning_rate": 2.470562358327839e-06, "loss": 0.5834802389144897, "step": 4842 }, { "epoch": 0.6790997686321251, "grad_norm": 3.0191147327423096, "learning_rate": 2.4686040068289855e-06, "loss": 0.5009649395942688, "step": 4843 }, { "epoch": 0.6792399915866227, "grad_norm": 11.722987174987793, "learning_rate": 2.466646177364037e-06, "loss": 0.4809597134590149, "step": 4844 }, { "epoch": 0.6793802145411204, "grad_norm": 3.86112642288208, "learning_rate": 2.4646888703367455e-06, "loss": 0.4875228703022003, "step": 4845 }, { "epoch": 0.6795204374956181, "grad_norm": 5.6524810791015625, "learning_rate": 2.4627320861507552e-06, "loss": 0.5980832576751709, "step": 4846 }, { "epoch": 0.6796606604501156, "grad_norm": 3.0335161685943604, "learning_rate": 2.460775825209598e-06, "loss": 0.42714741826057434, "step": 4847 }, { "epoch": 0.6798008834046133, "grad_norm": 2.857538938522339, "learning_rate": 2.458820087916703e-06, "loss": 0.4548846483230591, "step": 4848 }, { "epoch": 0.679941106359111, "grad_norm": 14.435075759887695, "learning_rate": 2.4568648746753898e-06, "loss": 0.5539060831069946, "step": 4849 }, { "epoch": 0.6800813293136087, "grad_norm": 3.1637954711914062, "learning_rate": 2.4549101858888696e-06, "loss": 0.6082087755203247, "step": 4850 }, { "epoch": 0.6802215522681063, "grad_norm": 3.145172595977783, "learning_rate": 2.452956021960246e-06, "loss": 0.5181729793548584, "step": 4851 }, { "epoch": 0.680361775222604, "grad_norm": 2.409182071685791, "learning_rate": 2.4510023832925133e-06, "loss": 0.5211811065673828, "step": 4852 }, { "epoch": 0.6805019981771016, "grad_norm": 9.634934425354004, "learning_rate": 2.449049270288561e-06, "loss": 0.5081818699836731, "step": 4853 }, { "epoch": 0.6806422211315992, "grad_norm": 3.1993789672851562, "learning_rate": 2.4470966833511623e-06, "loss": 0.6051338911056519, "step": 4854 }, { "epoch": 0.6807824440860969, "grad_norm": 31.610292434692383, "learning_rate": 2.44514462288299e-06, "loss": 0.5726683139801025, "step": 4855 }, { "epoch": 0.6809226670405946, "grad_norm": 3.058058500289917, "learning_rate": 2.4431930892866046e-06, "loss": 0.516686737537384, "step": 4856 }, { "epoch": 0.6810628899950922, "grad_norm": 6.729375839233398, "learning_rate": 2.4412420829644584e-06, "loss": 0.46471625566482544, "step": 4857 }, { "epoch": 0.6812031129495898, "grad_norm": 4.516079902648926, "learning_rate": 2.4392916043188958e-06, "loss": 0.46155762672424316, "step": 4858 }, { "epoch": 0.6813433359040875, "grad_norm": 3.038745641708374, "learning_rate": 2.437341653752154e-06, "loss": 0.4687580466270447, "step": 4859 }, { "epoch": 0.6814835588585851, "grad_norm": 3.948678493499756, "learning_rate": 2.4353922316663544e-06, "loss": 0.3886597752571106, "step": 4860 }, { "epoch": 0.6816237818130828, "grad_norm": 6.233626365661621, "learning_rate": 2.433443338463516e-06, "loss": 0.6103321313858032, "step": 4861 }, { "epoch": 0.6817640047675805, "grad_norm": 6.350139141082764, "learning_rate": 2.431494974545547e-06, "loss": 0.5236015319824219, "step": 4862 }, { "epoch": 0.6819042277220781, "grad_norm": 3.697996139526367, "learning_rate": 2.4295471403142468e-06, "loss": 0.4615943431854248, "step": 4863 }, { "epoch": 0.6820444506765757, "grad_norm": 4.278684139251709, "learning_rate": 2.4275998361713045e-06, "loss": 0.44856780767440796, "step": 4864 }, { "epoch": 0.6821846736310734, "grad_norm": 3.464022397994995, "learning_rate": 2.425653062518302e-06, "loss": 0.5104566216468811, "step": 4865 }, { "epoch": 0.682324896585571, "grad_norm": 3.530945062637329, "learning_rate": 2.4237068197567054e-06, "loss": 0.5401558876037598, "step": 4866 }, { "epoch": 0.6824651195400687, "grad_norm": 5.386903762817383, "learning_rate": 2.421761108287883e-06, "loss": 0.5201096534729004, "step": 4867 }, { "epoch": 0.6826053424945664, "grad_norm": 3.721834421157837, "learning_rate": 2.419815928513081e-06, "loss": 0.6116287112236023, "step": 4868 }, { "epoch": 0.6827455654490641, "grad_norm": 5.419979572296143, "learning_rate": 2.417871280833444e-06, "loss": 0.49674299359321594, "step": 4869 }, { "epoch": 0.6828857884035616, "grad_norm": 4.280259132385254, "learning_rate": 2.4159271656500044e-06, "loss": 0.6501238346099854, "step": 4870 }, { "epoch": 0.6830260113580593, "grad_norm": 7.57030725479126, "learning_rate": 2.4139835833636867e-06, "loss": 0.5081369280815125, "step": 4871 }, { "epoch": 0.683166234312557, "grad_norm": 7.7831549644470215, "learning_rate": 2.4120405343752972e-06, "loss": 0.5537049770355225, "step": 4872 }, { "epoch": 0.6833064572670546, "grad_norm": 3.953376531600952, "learning_rate": 2.410098019085547e-06, "loss": 0.5390557646751404, "step": 4873 }, { "epoch": 0.6834466802215523, "grad_norm": 3.071408987045288, "learning_rate": 2.4081560378950235e-06, "loss": 0.5124627351760864, "step": 4874 }, { "epoch": 0.6835869031760499, "grad_norm": 2.4960379600524902, "learning_rate": 2.4062145912042108e-06, "loss": 0.4744543433189392, "step": 4875 }, { "epoch": 0.6837271261305475, "grad_norm": 3.067621946334839, "learning_rate": 2.4042736794134807e-06, "loss": 0.4727621078491211, "step": 4876 }, { "epoch": 0.6838673490850452, "grad_norm": 3.788834810256958, "learning_rate": 2.4023333029230967e-06, "loss": 0.47706854343414307, "step": 4877 }, { "epoch": 0.6840075720395429, "grad_norm": 3.5506174564361572, "learning_rate": 2.4003934621332088e-06, "loss": 0.5420253872871399, "step": 4878 }, { "epoch": 0.6841477949940405, "grad_norm": 4.884449481964111, "learning_rate": 2.398454157443861e-06, "loss": 0.6100333333015442, "step": 4879 }, { "epoch": 0.6842880179485382, "grad_norm": 12.252497673034668, "learning_rate": 2.39651538925498e-06, "loss": 0.38803645968437195, "step": 4880 }, { "epoch": 0.6844282409030358, "grad_norm": 5.27692985534668, "learning_rate": 2.3945771579663875e-06, "loss": 0.5347400903701782, "step": 4881 }, { "epoch": 0.6845684638575334, "grad_norm": 2.73854398727417, "learning_rate": 2.3926394639777935e-06, "loss": 0.4746529459953308, "step": 4882 }, { "epoch": 0.6847086868120311, "grad_norm": 11.353429794311523, "learning_rate": 2.390702307688795e-06, "loss": 0.46982693672180176, "step": 4883 }, { "epoch": 0.6848489097665288, "grad_norm": 6.297850131988525, "learning_rate": 2.3887656894988815e-06, "loss": 0.4680822491645813, "step": 4884 }, { "epoch": 0.6849891327210265, "grad_norm": 3.1293721199035645, "learning_rate": 2.3868296098074294e-06, "loss": 0.5141074657440186, "step": 4885 }, { "epoch": 0.6851293556755241, "grad_norm": 3.456514835357666, "learning_rate": 2.3848940690137006e-06, "loss": 0.5372536182403564, "step": 4886 }, { "epoch": 0.6852695786300217, "grad_norm": 11.072083473205566, "learning_rate": 2.382959067516856e-06, "loss": 0.529628574848175, "step": 4887 }, { "epoch": 0.6854098015845194, "grad_norm": 4.073847770690918, "learning_rate": 2.381024605715933e-06, "loss": 0.5426230430603027, "step": 4888 }, { "epoch": 0.685550024539017, "grad_norm": 9.691109657287598, "learning_rate": 2.379090684009866e-06, "loss": 0.5069397687911987, "step": 4889 }, { "epoch": 0.6856902474935147, "grad_norm": 3.9144933223724365, "learning_rate": 2.377157302797475e-06, "loss": 0.537947416305542, "step": 4890 }, { "epoch": 0.6858304704480124, "grad_norm": 3.9098336696624756, "learning_rate": 2.3752244624774714e-06, "loss": 0.5130112171173096, "step": 4891 }, { "epoch": 0.68597069340251, "grad_norm": 3.3075199127197266, "learning_rate": 2.3732921634484466e-06, "loss": 0.47245916724205017, "step": 4892 }, { "epoch": 0.6861109163570076, "grad_norm": 4.94387674331665, "learning_rate": 2.3713604061088946e-06, "loss": 0.5453199148178101, "step": 4893 }, { "epoch": 0.6862511393115053, "grad_norm": 3.499825954437256, "learning_rate": 2.3694291908571837e-06, "loss": 0.5025410652160645, "step": 4894 }, { "epoch": 0.686391362266003, "grad_norm": 2.5968406200408936, "learning_rate": 2.3674985180915775e-06, "loss": 0.5157837867736816, "step": 4895 }, { "epoch": 0.6865315852205006, "grad_norm": 3.7881429195404053, "learning_rate": 2.365568388210228e-06, "loss": 0.47927504777908325, "step": 4896 }, { "epoch": 0.6866718081749983, "grad_norm": 20.002342224121094, "learning_rate": 2.3636388016111742e-06, "loss": 0.444660484790802, "step": 4897 }, { "epoch": 0.6868120311294958, "grad_norm": 3.1815569400787354, "learning_rate": 2.3617097586923383e-06, "loss": 0.49641451239585876, "step": 4898 }, { "epoch": 0.6869522540839935, "grad_norm": 4.07049036026001, "learning_rate": 2.3597812598515406e-06, "loss": 0.5404731035232544, "step": 4899 }, { "epoch": 0.6870924770384912, "grad_norm": 3.4726343154907227, "learning_rate": 2.3578533054864792e-06, "loss": 0.47606706619262695, "step": 4900 }, { "epoch": 0.6872326999929889, "grad_norm": 7.835651874542236, "learning_rate": 2.3559258959947455e-06, "loss": 0.5756901502609253, "step": 4901 }, { "epoch": 0.6873729229474865, "grad_norm": 9.155969619750977, "learning_rate": 2.3539990317738165e-06, "loss": 0.49354368448257446, "step": 4902 }, { "epoch": 0.6875131459019842, "grad_norm": 3.279282808303833, "learning_rate": 2.352072713221058e-06, "loss": 0.449550986289978, "step": 4903 }, { "epoch": 0.6876533688564818, "grad_norm": 3.867410182952881, "learning_rate": 2.3501469407337217e-06, "loss": 0.5347285270690918, "step": 4904 }, { "epoch": 0.6877935918109794, "grad_norm": 3.5115063190460205, "learning_rate": 2.3482217147089505e-06, "loss": 0.5635762214660645, "step": 4905 }, { "epoch": 0.6879338147654771, "grad_norm": 4.113376617431641, "learning_rate": 2.3462970355437653e-06, "loss": 0.5091534852981567, "step": 4906 }, { "epoch": 0.6880740377199748, "grad_norm": 5.332093238830566, "learning_rate": 2.344372903635089e-06, "loss": 0.4604344964027405, "step": 4907 }, { "epoch": 0.6882142606744724, "grad_norm": 4.711037635803223, "learning_rate": 2.342449319379716e-06, "loss": 0.5622693300247192, "step": 4908 }, { "epoch": 0.6883544836289701, "grad_norm": 3.6676976680755615, "learning_rate": 2.3405262831743385e-06, "loss": 0.49291449785232544, "step": 4909 }, { "epoch": 0.6884947065834677, "grad_norm": 5.970433712005615, "learning_rate": 2.3386037954155318e-06, "loss": 0.5202226042747498, "step": 4910 }, { "epoch": 0.6886349295379653, "grad_norm": 3.6362006664276123, "learning_rate": 2.3366818564997594e-06, "loss": 0.5083484649658203, "step": 4911 }, { "epoch": 0.688775152492463, "grad_norm": 3.6565823554992676, "learning_rate": 2.3347604668233664e-06, "loss": 0.4491133689880371, "step": 4912 }, { "epoch": 0.6889153754469607, "grad_norm": 3.055086851119995, "learning_rate": 2.3328396267825952e-06, "loss": 0.4648146331310272, "step": 4913 }, { "epoch": 0.6890555984014584, "grad_norm": 3.010990619659424, "learning_rate": 2.3309193367735645e-06, "loss": 0.5538939237594604, "step": 4914 }, { "epoch": 0.6891958213559559, "grad_norm": 3.7524728775024414, "learning_rate": 2.3289995971922834e-06, "loss": 0.5049986243247986, "step": 4915 }, { "epoch": 0.6893360443104536, "grad_norm": 3.8908803462982178, "learning_rate": 2.32708040843465e-06, "loss": 0.42709898948669434, "step": 4916 }, { "epoch": 0.6894762672649513, "grad_norm": 4.375957012176514, "learning_rate": 2.325161770896447e-06, "loss": 0.4995153546333313, "step": 4917 }, { "epoch": 0.6896164902194489, "grad_norm": 6.371071815490723, "learning_rate": 2.3232436849733375e-06, "loss": 0.5635653138160706, "step": 4918 }, { "epoch": 0.6897567131739466, "grad_norm": 3.476328134536743, "learning_rate": 2.321326151060884e-06, "loss": 0.43405622243881226, "step": 4919 }, { "epoch": 0.6898969361284443, "grad_norm": 3.677692413330078, "learning_rate": 2.3194091695545223e-06, "loss": 0.5073335766792297, "step": 4920 }, { "epoch": 0.6900371590829418, "grad_norm": 3.262521266937256, "learning_rate": 2.317492740849581e-06, "loss": 0.5599099397659302, "step": 4921 }, { "epoch": 0.6901773820374395, "grad_norm": 3.4493093490600586, "learning_rate": 2.315576865341273e-06, "loss": 0.44392573833465576, "step": 4922 }, { "epoch": 0.6903176049919372, "grad_norm": 2.646655559539795, "learning_rate": 2.313661543424699e-06, "loss": 0.49776917695999146, "step": 4923 }, { "epoch": 0.6904578279464348, "grad_norm": 9.787553787231445, "learning_rate": 2.3117467754948385e-06, "loss": 0.47529587149620056, "step": 4924 }, { "epoch": 0.6905980509009325, "grad_norm": 3.363729238510132, "learning_rate": 2.30983256194657e-06, "loss": 0.4606279134750366, "step": 4925 }, { "epoch": 0.6907382738554302, "grad_norm": 4.894830703735352, "learning_rate": 2.307918903174643e-06, "loss": 0.49715733528137207, "step": 4926 }, { "epoch": 0.6908784968099277, "grad_norm": 4.172333240509033, "learning_rate": 2.306005799573702e-06, "loss": 0.5789893865585327, "step": 4927 }, { "epoch": 0.6910187197644254, "grad_norm": 5.106904029846191, "learning_rate": 2.3040932515382745e-06, "loss": 0.6415104866027832, "step": 4928 }, { "epoch": 0.6911589427189231, "grad_norm": 6.316769599914551, "learning_rate": 2.302181259462775e-06, "loss": 0.5027713775634766, "step": 4929 }, { "epoch": 0.6912991656734208, "grad_norm": 4.225222587585449, "learning_rate": 2.3002698237414957e-06, "loss": 0.5078080892562866, "step": 4930 }, { "epoch": 0.6914393886279184, "grad_norm": 3.2179529666900635, "learning_rate": 2.2983589447686274e-06, "loss": 0.5257837176322937, "step": 4931 }, { "epoch": 0.691579611582416, "grad_norm": 5.27841854095459, "learning_rate": 2.296448622938231e-06, "loss": 0.5445905327796936, "step": 4932 }, { "epoch": 0.6917198345369137, "grad_norm": 3.3660426139831543, "learning_rate": 2.294538858644269e-06, "loss": 0.4843892455101013, "step": 4933 }, { "epoch": 0.6918600574914113, "grad_norm": 5.217193603515625, "learning_rate": 2.292629652280573e-06, "loss": 0.5204019546508789, "step": 4934 }, { "epoch": 0.692000280445909, "grad_norm": 9.268086433410645, "learning_rate": 2.2907210042408694e-06, "loss": 0.4352607727050781, "step": 4935 }, { "epoch": 0.6921405034004067, "grad_norm": 3.0301513671875, "learning_rate": 2.288812914918766e-06, "loss": 0.5602885484695435, "step": 4936 }, { "epoch": 0.6922807263549043, "grad_norm": 4.094366550445557, "learning_rate": 2.286905384707759e-06, "loss": 0.4209773540496826, "step": 4937 }, { "epoch": 0.6924209493094019, "grad_norm": 6.8083343505859375, "learning_rate": 2.2849984140012194e-06, "loss": 0.5416450500488281, "step": 4938 }, { "epoch": 0.6925611722638996, "grad_norm": 3.2942240238189697, "learning_rate": 2.283092003192418e-06, "loss": 0.49441462755203247, "step": 4939 }, { "epoch": 0.6927013952183972, "grad_norm": 3.905590534210205, "learning_rate": 2.281186152674497e-06, "loss": 0.4721209704875946, "step": 4940 }, { "epoch": 0.6928416181728949, "grad_norm": 2.907646417617798, "learning_rate": 2.279280862840489e-06, "loss": 0.5434422492980957, "step": 4941 }, { "epoch": 0.6929818411273926, "grad_norm": 3.6583235263824463, "learning_rate": 2.2773761340833095e-06, "loss": 0.5903235673904419, "step": 4942 }, { "epoch": 0.6931220640818903, "grad_norm": 3.7135226726531982, "learning_rate": 2.275471966795762e-06, "loss": 0.575687050819397, "step": 4943 }, { "epoch": 0.6932622870363878, "grad_norm": 4.995103359222412, "learning_rate": 2.2735683613705244e-06, "loss": 0.4308755695819855, "step": 4944 }, { "epoch": 0.6934025099908855, "grad_norm": 4.0357255935668945, "learning_rate": 2.271665318200173e-06, "loss": 0.4830300211906433, "step": 4945 }, { "epoch": 0.6935427329453832, "grad_norm": 3.8165149688720703, "learning_rate": 2.2697628376771546e-06, "loss": 0.5239605903625488, "step": 4946 }, { "epoch": 0.6936829558998808, "grad_norm": 9.129464149475098, "learning_rate": 2.267860920193808e-06, "loss": 0.5203483700752258, "step": 4947 }, { "epoch": 0.6938231788543785, "grad_norm": 7.7227396965026855, "learning_rate": 2.265959566142354e-06, "loss": 0.4904075264930725, "step": 4948 }, { "epoch": 0.6939634018088762, "grad_norm": 4.649674892425537, "learning_rate": 2.2640587759148978e-06, "loss": 0.5642215609550476, "step": 4949 }, { "epoch": 0.6941036247633737, "grad_norm": 3.204089403152466, "learning_rate": 2.2621585499034233e-06, "loss": 0.45275282859802246, "step": 4950 }, { "epoch": 0.6942438477178714, "grad_norm": 2.851008176803589, "learning_rate": 2.2602588884998076e-06, "loss": 0.42356476187705994, "step": 4951 }, { "epoch": 0.6943840706723691, "grad_norm": 4.443209648132324, "learning_rate": 2.258359792095803e-06, "loss": 0.5670186877250671, "step": 4952 }, { "epoch": 0.6945242936268667, "grad_norm": 3.1599652767181396, "learning_rate": 2.2564612610830477e-06, "loss": 0.4997449517250061, "step": 4953 }, { "epoch": 0.6946645165813644, "grad_norm": 3.9371769428253174, "learning_rate": 2.254563295853065e-06, "loss": 0.5504145622253418, "step": 4954 }, { "epoch": 0.694804739535862, "grad_norm": 3.2314932346343994, "learning_rate": 2.2526658967972613e-06, "loss": 0.46194058656692505, "step": 4955 }, { "epoch": 0.6949449624903596, "grad_norm": 4.407285213470459, "learning_rate": 2.2507690643069212e-06, "loss": 0.40187638998031616, "step": 4956 }, { "epoch": 0.6950851854448573, "grad_norm": 4.9579997062683105, "learning_rate": 2.2488727987732233e-06, "loss": 0.5903260111808777, "step": 4957 }, { "epoch": 0.695225408399355, "grad_norm": 3.6136186122894287, "learning_rate": 2.2469771005872164e-06, "loss": 0.5047597885131836, "step": 4958 }, { "epoch": 0.6953656313538527, "grad_norm": 7.617583274841309, "learning_rate": 2.2450819701398413e-06, "loss": 0.5932986736297607, "step": 4959 }, { "epoch": 0.6955058543083503, "grad_norm": 2.752000331878662, "learning_rate": 2.2431874078219177e-06, "loss": 0.46814048290252686, "step": 4960 }, { "epoch": 0.6956460772628479, "grad_norm": 4.566577911376953, "learning_rate": 2.2412934140241503e-06, "loss": 0.5317187309265137, "step": 4961 }, { "epoch": 0.6957863002173456, "grad_norm": 3.969799757003784, "learning_rate": 2.239399989137125e-06, "loss": 0.5216381549835205, "step": 4962 }, { "epoch": 0.6959265231718432, "grad_norm": 3.2192957401275635, "learning_rate": 2.2375071335513127e-06, "loss": 0.531000018119812, "step": 4963 }, { "epoch": 0.6960667461263409, "grad_norm": 2.6816279888153076, "learning_rate": 2.2356148476570604e-06, "loss": 0.49486321210861206, "step": 4964 }, { "epoch": 0.6962069690808386, "grad_norm": 3.9828333854675293, "learning_rate": 2.2337231318446084e-06, "loss": 0.47585529088974, "step": 4965 }, { "epoch": 0.6963471920353362, "grad_norm": 4.918485164642334, "learning_rate": 2.2318319865040695e-06, "loss": 0.5333828330039978, "step": 4966 }, { "epoch": 0.6964874149898338, "grad_norm": 2.4449565410614014, "learning_rate": 2.229941412025443e-06, "loss": 0.5016036033630371, "step": 4967 }, { "epoch": 0.6966276379443315, "grad_norm": 4.3855695724487305, "learning_rate": 2.228051408798611e-06, "loss": 0.4692313075065613, "step": 4968 }, { "epoch": 0.6967678608988291, "grad_norm": 4.307188510894775, "learning_rate": 2.226161977213339e-06, "loss": 0.4878777265548706, "step": 4969 }, { "epoch": 0.6969080838533268, "grad_norm": 3.1598637104034424, "learning_rate": 2.2242731176592663e-06, "loss": 0.5968049764633179, "step": 4970 }, { "epoch": 0.6970483068078245, "grad_norm": 3.5721123218536377, "learning_rate": 2.2223848305259286e-06, "loss": 0.42805811762809753, "step": 4971 }, { "epoch": 0.697188529762322, "grad_norm": 4.21822452545166, "learning_rate": 2.22049711620273e-06, "loss": 0.4143572449684143, "step": 4972 }, { "epoch": 0.6973287527168197, "grad_norm": 4.761046409606934, "learning_rate": 2.2186099750789635e-06, "loss": 0.5050883293151855, "step": 4973 }, { "epoch": 0.6974689756713174, "grad_norm": 7.321340560913086, "learning_rate": 2.2167234075438025e-06, "loss": 0.4581674337387085, "step": 4974 }, { "epoch": 0.697609198625815, "grad_norm": 4.60781192779541, "learning_rate": 2.214837413986304e-06, "loss": 0.5965158939361572, "step": 4975 }, { "epoch": 0.6977494215803127, "grad_norm": 4.403909683227539, "learning_rate": 2.2129519947953986e-06, "loss": 0.5380023717880249, "step": 4976 }, { "epoch": 0.6978896445348104, "grad_norm": 3.0102663040161133, "learning_rate": 2.211067150359912e-06, "loss": 0.49199771881103516, "step": 4977 }, { "epoch": 0.698029867489308, "grad_norm": 3.989398717880249, "learning_rate": 2.2091828810685385e-06, "loss": 0.5160092115402222, "step": 4978 }, { "epoch": 0.6981700904438056, "grad_norm": 5.139846324920654, "learning_rate": 2.207299187309861e-06, "loss": 0.3934178352355957, "step": 4979 }, { "epoch": 0.6983103133983033, "grad_norm": 4.431629180908203, "learning_rate": 2.205416069472342e-06, "loss": 0.5212866067886353, "step": 4980 }, { "epoch": 0.698450536352801, "grad_norm": 2.483492612838745, "learning_rate": 2.2035335279443265e-06, "loss": 0.5392153263092041, "step": 4981 }, { "epoch": 0.6985907593072986, "grad_norm": 3.1700358390808105, "learning_rate": 2.201651563114034e-06, "loss": 0.5642462968826294, "step": 4982 }, { "epoch": 0.6987309822617963, "grad_norm": 2.711028814315796, "learning_rate": 2.199770175369577e-06, "loss": 0.4654773473739624, "step": 4983 }, { "epoch": 0.6988712052162939, "grad_norm": 3.1315317153930664, "learning_rate": 2.1978893650989373e-06, "loss": 0.46680712699890137, "step": 4984 }, { "epoch": 0.6990114281707915, "grad_norm": 2.6245365142822266, "learning_rate": 2.1960091326899853e-06, "loss": 0.5109986662864685, "step": 4985 }, { "epoch": 0.6991516511252892, "grad_norm": 2.739173650741577, "learning_rate": 2.194129478530468e-06, "loss": 0.536286473274231, "step": 4986 }, { "epoch": 0.6992918740797869, "grad_norm": 3.005063056945801, "learning_rate": 2.192250403008017e-06, "loss": 0.5350573062896729, "step": 4987 }, { "epoch": 0.6994320970342846, "grad_norm": 3.22656512260437, "learning_rate": 2.1903719065101368e-06, "loss": 0.4783850312232971, "step": 4988 }, { "epoch": 0.6995723199887821, "grad_norm": 7.131155967712402, "learning_rate": 2.188493989424226e-06, "loss": 0.48956298828125, "step": 4989 }, { "epoch": 0.6997125429432798, "grad_norm": 41.710330963134766, "learning_rate": 2.186616652137547e-06, "loss": 0.47787734866142273, "step": 4990 }, { "epoch": 0.6998527658977775, "grad_norm": 2.1850507259368896, "learning_rate": 2.18473989503726e-06, "loss": 0.45323190093040466, "step": 4991 }, { "epoch": 0.6999929888522751, "grad_norm": 5.781021595001221, "learning_rate": 2.18286371851039e-06, "loss": 0.5539984703063965, "step": 4992 }, { "epoch": 0.7001332118067728, "grad_norm": 4.05133056640625, "learning_rate": 2.1809881229438525e-06, "loss": 0.5441876649856567, "step": 4993 }, { "epoch": 0.7002734347612705, "grad_norm": 3.546631336212158, "learning_rate": 2.1791131087244378e-06, "loss": 0.5487803816795349, "step": 4994 }, { "epoch": 0.700413657715768, "grad_norm": 3.947667360305786, "learning_rate": 2.177238676238822e-06, "loss": 0.501177191734314, "step": 4995 }, { "epoch": 0.7005538806702657, "grad_norm": 2.8727822303771973, "learning_rate": 2.175364825873551e-06, "loss": 0.5684878826141357, "step": 4996 }, { "epoch": 0.7006941036247634, "grad_norm": 4.480300426483154, "learning_rate": 2.1734915580150646e-06, "loss": 0.4691062569618225, "step": 4997 }, { "epoch": 0.700834326579261, "grad_norm": 3.7691800594329834, "learning_rate": 2.1716188730496703e-06, "loss": 0.49404409527778625, "step": 4998 }, { "epoch": 0.7009745495337587, "grad_norm": 7.948136329650879, "learning_rate": 2.169746771363561e-06, "loss": 0.4934214949607849, "step": 4999 }, { "epoch": 0.7011147724882564, "grad_norm": 4.120518207550049, "learning_rate": 2.167875253342809e-06, "loss": 0.38260871171951294, "step": 5000 }, { "epoch": 0.7012549954427539, "grad_norm": 3.0291008949279785, "learning_rate": 2.1660043193733677e-06, "loss": 0.4600101709365845, "step": 5001 }, { "epoch": 0.7013952183972516, "grad_norm": 3.7677266597747803, "learning_rate": 2.1641339698410623e-06, "loss": 0.5804144144058228, "step": 5002 }, { "epoch": 0.7015354413517493, "grad_norm": 3.4547579288482666, "learning_rate": 2.162264205131611e-06, "loss": 0.622725248336792, "step": 5003 }, { "epoch": 0.701675664306247, "grad_norm": 3.1637279987335205, "learning_rate": 2.160395025630597e-06, "loss": 0.6204310059547424, "step": 5004 }, { "epoch": 0.7018158872607446, "grad_norm": 6.144287586212158, "learning_rate": 2.1585264317234928e-06, "loss": 0.4779796004295349, "step": 5005 }, { "epoch": 0.7019561102152423, "grad_norm": 2.7762062549591064, "learning_rate": 2.1566584237956457e-06, "loss": 0.5226896405220032, "step": 5006 }, { "epoch": 0.7020963331697399, "grad_norm": 3.572819471359253, "learning_rate": 2.1547910022322855e-06, "loss": 0.49119535088539124, "step": 5007 }, { "epoch": 0.7022365561242375, "grad_norm": 3.338249683380127, "learning_rate": 2.1529241674185138e-06, "loss": 0.5661191344261169, "step": 5008 }, { "epoch": 0.7023767790787352, "grad_norm": 4.174626350402832, "learning_rate": 2.151057919739322e-06, "loss": 0.5025029182434082, "step": 5009 }, { "epoch": 0.7025170020332329, "grad_norm": 2.9727089405059814, "learning_rate": 2.149192259579571e-06, "loss": 0.4765373468399048, "step": 5010 }, { "epoch": 0.7026572249877305, "grad_norm": 2.872758626937866, "learning_rate": 2.1473271873240047e-06, "loss": 0.4113134741783142, "step": 5011 }, { "epoch": 0.7027974479422281, "grad_norm": 3.8846848011016846, "learning_rate": 2.1454627033572463e-06, "loss": 0.5046918988227844, "step": 5012 }, { "epoch": 0.7029376708967258, "grad_norm": 6.991748809814453, "learning_rate": 2.1435988080637977e-06, "loss": 0.5223676562309265, "step": 5013 }, { "epoch": 0.7030778938512234, "grad_norm": 4.172706604003906, "learning_rate": 2.141735501828033e-06, "loss": 0.487444669008255, "step": 5014 }, { "epoch": 0.7032181168057211, "grad_norm": 3.41387677192688, "learning_rate": 2.139872785034217e-06, "loss": 0.5846660137176514, "step": 5015 }, { "epoch": 0.7033583397602188, "grad_norm": 3.4881532192230225, "learning_rate": 2.1380106580664824e-06, "loss": 0.5336882472038269, "step": 5016 }, { "epoch": 0.7034985627147164, "grad_norm": 7.98138952255249, "learning_rate": 2.136149121308843e-06, "loss": 0.4921847879886627, "step": 5017 }, { "epoch": 0.703638785669214, "grad_norm": 3.5247642993927, "learning_rate": 2.134288175145194e-06, "loss": 0.5128257870674133, "step": 5018 }, { "epoch": 0.7037790086237117, "grad_norm": 3.2511565685272217, "learning_rate": 2.132427819959308e-06, "loss": 0.5586692690849304, "step": 5019 }, { "epoch": 0.7039192315782093, "grad_norm": 2.784438133239746, "learning_rate": 2.1305680561348287e-06, "loss": 0.588442325592041, "step": 5020 }, { "epoch": 0.704059454532707, "grad_norm": 3.72786545753479, "learning_rate": 2.1287088840552906e-06, "loss": 0.5059741735458374, "step": 5021 }, { "epoch": 0.7041996774872047, "grad_norm": 5.31446647644043, "learning_rate": 2.1268503041040915e-06, "loss": 0.5030714273452759, "step": 5022 }, { "epoch": 0.7043399004417024, "grad_norm": 8.556818962097168, "learning_rate": 2.1249923166645237e-06, "loss": 0.5111775398254395, "step": 5023 }, { "epoch": 0.7044801233961999, "grad_norm": 4.615720748901367, "learning_rate": 2.1231349221197407e-06, "loss": 0.4877849817276001, "step": 5024 }, { "epoch": 0.7046203463506976, "grad_norm": 2.960907459259033, "learning_rate": 2.1212781208527845e-06, "loss": 0.40101832151412964, "step": 5025 }, { "epoch": 0.7047605693051953, "grad_norm": 3.0494332313537598, "learning_rate": 2.1194219132465706e-06, "loss": 0.4316365718841553, "step": 5026 }, { "epoch": 0.7049007922596929, "grad_norm": 2.552475929260254, "learning_rate": 2.1175662996838954e-06, "loss": 0.565014123916626, "step": 5027 }, { "epoch": 0.7050410152141906, "grad_norm": 3.1077756881713867, "learning_rate": 2.115711280547425e-06, "loss": 0.5524141788482666, "step": 5028 }, { "epoch": 0.7051812381686882, "grad_norm": 4.457350254058838, "learning_rate": 2.113856856219716e-06, "loss": 0.557729959487915, "step": 5029 }, { "epoch": 0.7053214611231858, "grad_norm": 5.322007656097412, "learning_rate": 2.1120030270831887e-06, "loss": 0.5401488542556763, "step": 5030 }, { "epoch": 0.7054616840776835, "grad_norm": 7.195562362670898, "learning_rate": 2.110149793520148e-06, "loss": 0.5227566957473755, "step": 5031 }, { "epoch": 0.7056019070321812, "grad_norm": 5.9441423416137695, "learning_rate": 2.1082971559127756e-06, "loss": 0.4684901833534241, "step": 5032 }, { "epoch": 0.7057421299866788, "grad_norm": 3.8735063076019287, "learning_rate": 2.1064451146431316e-06, "loss": 0.42832857370376587, "step": 5033 }, { "epoch": 0.7058823529411765, "grad_norm": 5.869025707244873, "learning_rate": 2.1045936700931434e-06, "loss": 0.42121565341949463, "step": 5034 }, { "epoch": 0.7060225758956741, "grad_norm": 6.592525005340576, "learning_rate": 2.102742822644631e-06, "loss": 0.6070078611373901, "step": 5035 }, { "epoch": 0.7061627988501717, "grad_norm": 2.408019781112671, "learning_rate": 2.1008925726792783e-06, "loss": 0.5027766823768616, "step": 5036 }, { "epoch": 0.7063030218046694, "grad_norm": 5.117385387420654, "learning_rate": 2.0990429205786522e-06, "loss": 0.5626915097236633, "step": 5037 }, { "epoch": 0.7064432447591671, "grad_norm": 4.979034423828125, "learning_rate": 2.097193866724195e-06, "loss": 0.5288701057434082, "step": 5038 }, { "epoch": 0.7065834677136648, "grad_norm": 3.571533203125, "learning_rate": 2.095345411497226e-06, "loss": 0.609449565410614, "step": 5039 }, { "epoch": 0.7067236906681624, "grad_norm": 3.5284979343414307, "learning_rate": 2.0934975552789365e-06, "loss": 0.4925859868526459, "step": 5040 }, { "epoch": 0.70686391362266, "grad_norm": 2.4538443088531494, "learning_rate": 2.0916502984504057e-06, "loss": 0.5241632461547852, "step": 5041 }, { "epoch": 0.7070041365771577, "grad_norm": 2.9775452613830566, "learning_rate": 2.089803641392575e-06, "loss": 0.5411254167556763, "step": 5042 }, { "epoch": 0.7071443595316553, "grad_norm": 5.713850498199463, "learning_rate": 2.0879575844862715e-06, "loss": 0.5179258584976196, "step": 5043 }, { "epoch": 0.707284582486153, "grad_norm": 3.877927780151367, "learning_rate": 2.086112128112196e-06, "loss": 0.4411795139312744, "step": 5044 }, { "epoch": 0.7074248054406507, "grad_norm": 4.33328914642334, "learning_rate": 2.0842672726509266e-06, "loss": 0.4865095913410187, "step": 5045 }, { "epoch": 0.7075650283951482, "grad_norm": 2.9600136280059814, "learning_rate": 2.082423018482912e-06, "loss": 0.4257189631462097, "step": 5046 }, { "epoch": 0.7077052513496459, "grad_norm": 3.113671064376831, "learning_rate": 2.080579365988487e-06, "loss": 0.5695337057113647, "step": 5047 }, { "epoch": 0.7078454743041436, "grad_norm": 2.219057559967041, "learning_rate": 2.0787363155478522e-06, "loss": 0.46976232528686523, "step": 5048 }, { "epoch": 0.7079856972586412, "grad_norm": 3.4295544624328613, "learning_rate": 2.07689386754109e-06, "loss": 0.4640660285949707, "step": 5049 }, { "epoch": 0.7081259202131389, "grad_norm": 10.730766296386719, "learning_rate": 2.0750520223481556e-06, "loss": 0.5375840663909912, "step": 5050 }, { "epoch": 0.7082661431676366, "grad_norm": 3.260012149810791, "learning_rate": 2.073210780348883e-06, "loss": 0.5238343477249146, "step": 5051 }, { "epoch": 0.7084063661221341, "grad_norm": 4.017599105834961, "learning_rate": 2.0713701419229785e-06, "loss": 0.5081558227539062, "step": 5052 }, { "epoch": 0.7085465890766318, "grad_norm": 4.316701412200928, "learning_rate": 2.0695301074500285e-06, "loss": 0.4632825553417206, "step": 5053 }, { "epoch": 0.7086868120311295, "grad_norm": 3.159461259841919, "learning_rate": 2.067690677309485e-06, "loss": 0.43863701820373535, "step": 5054 }, { "epoch": 0.7088270349856272, "grad_norm": 4.763708591461182, "learning_rate": 2.065851851880691e-06, "loss": 0.46524739265441895, "step": 5055 }, { "epoch": 0.7089672579401248, "grad_norm": 3.0780293941497803, "learning_rate": 2.0640136315428482e-06, "loss": 0.5299510359764099, "step": 5056 }, { "epoch": 0.7091074808946225, "grad_norm": 4.0586442947387695, "learning_rate": 2.0621760166750456e-06, "loss": 0.5065937042236328, "step": 5057 }, { "epoch": 0.7092477038491201, "grad_norm": 3.752671718597412, "learning_rate": 2.0603390076562406e-06, "loss": 0.5010038018226624, "step": 5058 }, { "epoch": 0.7093879268036177, "grad_norm": 3.2495877742767334, "learning_rate": 2.0585026048652717e-06, "loss": 0.5292290449142456, "step": 5059 }, { "epoch": 0.7095281497581154, "grad_norm": 5.292101860046387, "learning_rate": 2.056666808680843e-06, "loss": 0.5360878705978394, "step": 5060 }, { "epoch": 0.7096683727126131, "grad_norm": 3.8488962650299072, "learning_rate": 2.054831619481545e-06, "loss": 0.5048678517341614, "step": 5061 }, { "epoch": 0.7098085956671107, "grad_norm": 3.0115714073181152, "learning_rate": 2.0529970376458336e-06, "loss": 0.40996530652046204, "step": 5062 }, { "epoch": 0.7099488186216083, "grad_norm": 3.1085071563720703, "learning_rate": 2.051163063552044e-06, "loss": 0.44526395201683044, "step": 5063 }, { "epoch": 0.710089041576106, "grad_norm": 10.768806457519531, "learning_rate": 2.0493296975783855e-06, "loss": 0.5945934057235718, "step": 5064 }, { "epoch": 0.7102292645306036, "grad_norm": 3.234675407409668, "learning_rate": 2.0474969401029427e-06, "loss": 0.4953642189502716, "step": 5065 }, { "epoch": 0.7103694874851013, "grad_norm": 2.391995429992676, "learning_rate": 2.04566479150367e-06, "loss": 0.5160952806472778, "step": 5066 }, { "epoch": 0.710509710439599, "grad_norm": 4.538173198699951, "learning_rate": 2.0438332521584046e-06, "loss": 0.6231352090835571, "step": 5067 }, { "epoch": 0.7106499333940967, "grad_norm": 3.279254198074341, "learning_rate": 2.0420023224448505e-06, "loss": 0.4801023304462433, "step": 5068 }, { "epoch": 0.7107901563485942, "grad_norm": 3.0122928619384766, "learning_rate": 2.0401720027405887e-06, "loss": 0.5463634729385376, "step": 5069 }, { "epoch": 0.7109303793030919, "grad_norm": 3.99855375289917, "learning_rate": 2.0383422934230756e-06, "loss": 0.5131015181541443, "step": 5070 }, { "epoch": 0.7110706022575896, "grad_norm": 4.1059112548828125, "learning_rate": 2.0365131948696425e-06, "loss": 0.41351473331451416, "step": 5071 }, { "epoch": 0.7112108252120872, "grad_norm": 3.261326789855957, "learning_rate": 2.0346847074574866e-06, "loss": 0.4349546432495117, "step": 5072 }, { "epoch": 0.7113510481665849, "grad_norm": 2.559063673019409, "learning_rate": 2.032856831563694e-06, "loss": 0.5028873682022095, "step": 5073 }, { "epoch": 0.7114912711210826, "grad_norm": 4.386312484741211, "learning_rate": 2.0310295675652093e-06, "loss": 0.5311900973320007, "step": 5074 }, { "epoch": 0.7116314940755801, "grad_norm": 6.614984035491943, "learning_rate": 2.02920291583886e-06, "loss": 0.5375654697418213, "step": 5075 }, { "epoch": 0.7117717170300778, "grad_norm": 5.857995510101318, "learning_rate": 2.027376876761345e-06, "loss": 0.46971848607063293, "step": 5076 }, { "epoch": 0.7119119399845755, "grad_norm": 3.5991170406341553, "learning_rate": 2.0255514507092393e-06, "loss": 0.5633533000946045, "step": 5077 }, { "epoch": 0.7120521629390731, "grad_norm": 4.062709331512451, "learning_rate": 2.0237266380589828e-06, "loss": 0.5362170338630676, "step": 5078 }, { "epoch": 0.7121923858935708, "grad_norm": 3.9502880573272705, "learning_rate": 2.0219024391869026e-06, "loss": 0.42735594511032104, "step": 5079 }, { "epoch": 0.7123326088480685, "grad_norm": 5.504505157470703, "learning_rate": 2.0200788544691848e-06, "loss": 0.5040328502655029, "step": 5080 }, { "epoch": 0.712472831802566, "grad_norm": 3.6076862812042236, "learning_rate": 2.018255884281902e-06, "loss": 0.4904055893421173, "step": 5081 }, { "epoch": 0.7126130547570637, "grad_norm": 4.293129920959473, "learning_rate": 2.0164335290009904e-06, "loss": 0.4244358241558075, "step": 5082 }, { "epoch": 0.7127532777115614, "grad_norm": 4.337080955505371, "learning_rate": 2.0146117890022633e-06, "loss": 0.614330530166626, "step": 5083 }, { "epoch": 0.712893500666059, "grad_norm": 4.572638034820557, "learning_rate": 2.012790664661407e-06, "loss": 0.5197265148162842, "step": 5084 }, { "epoch": 0.7130337236205567, "grad_norm": 3.97749662399292, "learning_rate": 2.0109701563539823e-06, "loss": 0.6337307691574097, "step": 5085 }, { "epoch": 0.7131739465750543, "grad_norm": 3.4619827270507812, "learning_rate": 2.0091502644554163e-06, "loss": 0.4769766628742218, "step": 5086 }, { "epoch": 0.713314169529552, "grad_norm": 4.793755054473877, "learning_rate": 2.0073309893410204e-06, "loss": 0.516648530960083, "step": 5087 }, { "epoch": 0.7134543924840496, "grad_norm": 3.1614232063293457, "learning_rate": 2.0055123313859676e-06, "loss": 0.5415052175521851, "step": 5088 }, { "epoch": 0.7135946154385473, "grad_norm": 4.526422500610352, "learning_rate": 2.003694290965309e-06, "loss": 0.5863705277442932, "step": 5089 }, { "epoch": 0.713734838393045, "grad_norm": 6.50278902053833, "learning_rate": 2.0018768684539684e-06, "loss": 0.5287213921546936, "step": 5090 }, { "epoch": 0.7138750613475426, "grad_norm": 6.707530498504639, "learning_rate": 2.0000600642267436e-06, "loss": 0.5176650285720825, "step": 5091 }, { "epoch": 0.7140152843020402, "grad_norm": 3.3819680213928223, "learning_rate": 1.998243878658297e-06, "loss": 0.5418423414230347, "step": 5092 }, { "epoch": 0.7141555072565379, "grad_norm": 8.434831619262695, "learning_rate": 1.996428312123176e-06, "loss": 0.4792669415473938, "step": 5093 }, { "epoch": 0.7142957302110355, "grad_norm": 5.044737339019775, "learning_rate": 1.994613364995788e-06, "loss": 0.5205070972442627, "step": 5094 }, { "epoch": 0.7144359531655332, "grad_norm": 4.492254257202148, "learning_rate": 1.992799037650421e-06, "loss": 0.42864900827407837, "step": 5095 }, { "epoch": 0.7145761761200309, "grad_norm": 3.4428110122680664, "learning_rate": 1.9909853304612315e-06, "loss": 0.5202651023864746, "step": 5096 }, { "epoch": 0.7147163990745286, "grad_norm": 3.29703426361084, "learning_rate": 1.9891722438022505e-06, "loss": 0.5115723609924316, "step": 5097 }, { "epoch": 0.7148566220290261, "grad_norm": 4.9496049880981445, "learning_rate": 1.9873597780473748e-06, "loss": 0.553993821144104, "step": 5098 }, { "epoch": 0.7149968449835238, "grad_norm": 4.204538345336914, "learning_rate": 1.985547933570385e-06, "loss": 0.464127779006958, "step": 5099 }, { "epoch": 0.7151370679380215, "grad_norm": 3.550562858581543, "learning_rate": 1.9837367107449203e-06, "loss": 0.5320548415184021, "step": 5100 }, { "epoch": 0.7152772908925191, "grad_norm": 5.0955095291137695, "learning_rate": 1.9819261099445e-06, "loss": 0.4914928674697876, "step": 5101 }, { "epoch": 0.7154175138470168, "grad_norm": 3.8553614616394043, "learning_rate": 1.980116131542513e-06, "loss": 0.5867730379104614, "step": 5102 }, { "epoch": 0.7155577368015144, "grad_norm": 4.332511901855469, "learning_rate": 1.9783067759122213e-06, "loss": 0.509107232093811, "step": 5103 }, { "epoch": 0.715697959756012, "grad_norm": 4.196460247039795, "learning_rate": 1.9764980434267524e-06, "loss": 0.5522372722625732, "step": 5104 }, { "epoch": 0.7158381827105097, "grad_norm": 3.5997323989868164, "learning_rate": 1.974689934459116e-06, "loss": 0.5150279998779297, "step": 5105 }, { "epoch": 0.7159784056650074, "grad_norm": 3.0065057277679443, "learning_rate": 1.9728824493821825e-06, "loss": 0.5801147222518921, "step": 5106 }, { "epoch": 0.716118628619505, "grad_norm": 11.500252723693848, "learning_rate": 1.9710755885686992e-06, "loss": 0.44738441705703735, "step": 5107 }, { "epoch": 0.7162588515740027, "grad_norm": 5.481103897094727, "learning_rate": 1.969269352391284e-06, "loss": 0.5255283713340759, "step": 5108 }, { "epoch": 0.7163990745285003, "grad_norm": 5.903370380401611, "learning_rate": 1.967463741222426e-06, "loss": 0.5153067708015442, "step": 5109 }, { "epoch": 0.7165392974829979, "grad_norm": 3.5357532501220703, "learning_rate": 1.965658755434485e-06, "loss": 0.5337188243865967, "step": 5110 }, { "epoch": 0.7166795204374956, "grad_norm": 2.9289112091064453, "learning_rate": 1.9638543953996935e-06, "loss": 0.4835110604763031, "step": 5111 }, { "epoch": 0.7168197433919933, "grad_norm": 3.218977212905884, "learning_rate": 1.962050661490148e-06, "loss": 0.3956332802772522, "step": 5112 }, { "epoch": 0.716959966346491, "grad_norm": 3.000314474105835, "learning_rate": 1.960247554077828e-06, "loss": 0.550283670425415, "step": 5113 }, { "epoch": 0.7171001893009886, "grad_norm": 4.097677230834961, "learning_rate": 1.9584450735345723e-06, "loss": 0.6358420848846436, "step": 5114 }, { "epoch": 0.7172404122554862, "grad_norm": 3.1045491695404053, "learning_rate": 1.956643220232096e-06, "loss": 0.3732856512069702, "step": 5115 }, { "epoch": 0.7173806352099839, "grad_norm": 2.769301414489746, "learning_rate": 1.9548419945419854e-06, "loss": 0.5181647539138794, "step": 5116 }, { "epoch": 0.7175208581644815, "grad_norm": 7.926904678344727, "learning_rate": 1.9530413968356967e-06, "loss": 0.5253871083259583, "step": 5117 }, { "epoch": 0.7176610811189792, "grad_norm": 3.6859939098358154, "learning_rate": 1.9512414274845504e-06, "loss": 0.558382511138916, "step": 5118 }, { "epoch": 0.7178013040734769, "grad_norm": 3.495746374130249, "learning_rate": 1.9494420868597506e-06, "loss": 0.545646607875824, "step": 5119 }, { "epoch": 0.7179415270279744, "grad_norm": 3.294027090072632, "learning_rate": 1.947643375332359e-06, "loss": 0.42393895983695984, "step": 5120 }, { "epoch": 0.7180817499824721, "grad_norm": 4.001428604125977, "learning_rate": 1.945845293273313e-06, "loss": 0.5675532817840576, "step": 5121 }, { "epoch": 0.7182219729369698, "grad_norm": 3.2870686054229736, "learning_rate": 1.944047841053421e-06, "loss": 0.49156689643859863, "step": 5122 }, { "epoch": 0.7183621958914674, "grad_norm": 4.29088020324707, "learning_rate": 1.942251019043362e-06, "loss": 0.3941410183906555, "step": 5123 }, { "epoch": 0.7185024188459651, "grad_norm": 5.198469161987305, "learning_rate": 1.940454827613677e-06, "loss": 0.4831527769565582, "step": 5124 }, { "epoch": 0.7186426418004628, "grad_norm": 3.4013333320617676, "learning_rate": 1.9386592671347916e-06, "loss": 0.5680550336837769, "step": 5125 }, { "epoch": 0.7187828647549603, "grad_norm": 3.862333059310913, "learning_rate": 1.936864337976987e-06, "loss": 0.5318245887756348, "step": 5126 }, { "epoch": 0.718923087709458, "grad_norm": 4.6623687744140625, "learning_rate": 1.9350700405104217e-06, "loss": 0.5274761319160461, "step": 5127 }, { "epoch": 0.7190633106639557, "grad_norm": 3.9166910648345947, "learning_rate": 1.9332763751051233e-06, "loss": 0.4814152121543884, "step": 5128 }, { "epoch": 0.7192035336184534, "grad_norm": 6.1438164710998535, "learning_rate": 1.9314833421309885e-06, "loss": 0.4138436019420624, "step": 5129 }, { "epoch": 0.719343756572951, "grad_norm": 3.164721727371216, "learning_rate": 1.9296909419577795e-06, "loss": 0.5206105709075928, "step": 5130 }, { "epoch": 0.7194839795274487, "grad_norm": 3.6486611366271973, "learning_rate": 1.927899174955138e-06, "loss": 0.54069983959198, "step": 5131 }, { "epoch": 0.7196242024819463, "grad_norm": 13.233052253723145, "learning_rate": 1.9261080414925635e-06, "loss": 0.4651597738265991, "step": 5132 }, { "epoch": 0.7197644254364439, "grad_norm": 2.4419190883636475, "learning_rate": 1.9243175419394327e-06, "loss": 0.5541539192199707, "step": 5133 }, { "epoch": 0.7199046483909416, "grad_norm": 3.756516456604004, "learning_rate": 1.922527676664988e-06, "loss": 0.4871880114078522, "step": 5134 }, { "epoch": 0.7200448713454393, "grad_norm": 4.113722324371338, "learning_rate": 1.9207384460383426e-06, "loss": 0.5755829811096191, "step": 5135 }, { "epoch": 0.7201850942999369, "grad_norm": 3.862283229827881, "learning_rate": 1.9189498504284786e-06, "loss": 0.4709697961807251, "step": 5136 }, { "epoch": 0.7203253172544346, "grad_norm": 3.974292039871216, "learning_rate": 1.917161890204248e-06, "loss": 0.530775249004364, "step": 5137 }, { "epoch": 0.7204655402089322, "grad_norm": 3.425670623779297, "learning_rate": 1.915374565734366e-06, "loss": 0.4098769426345825, "step": 5138 }, { "epoch": 0.7206057631634298, "grad_norm": 3.2107136249542236, "learning_rate": 1.913587877387428e-06, "loss": 0.5171990990638733, "step": 5139 }, { "epoch": 0.7207459861179275, "grad_norm": 5.274971961975098, "learning_rate": 1.911801825531886e-06, "loss": 0.5498239994049072, "step": 5140 }, { "epoch": 0.7208862090724252, "grad_norm": 2.2727584838867188, "learning_rate": 1.9100164105360685e-06, "loss": 0.47424763441085815, "step": 5141 }, { "epoch": 0.7210264320269228, "grad_norm": 5.022190093994141, "learning_rate": 1.9082316327681697e-06, "loss": 0.5473207831382751, "step": 5142 }, { "epoch": 0.7211666549814204, "grad_norm": 2.7526891231536865, "learning_rate": 1.9064474925962561e-06, "loss": 0.5402240753173828, "step": 5143 }, { "epoch": 0.7213068779359181, "grad_norm": 3.8190600872039795, "learning_rate": 1.904663990388253e-06, "loss": 0.5148981809616089, "step": 5144 }, { "epoch": 0.7214471008904157, "grad_norm": 5.62952184677124, "learning_rate": 1.902881126511969e-06, "loss": 0.5101479291915894, "step": 5145 }, { "epoch": 0.7215873238449134, "grad_norm": 3.5597212314605713, "learning_rate": 1.9010989013350672e-06, "loss": 0.3973737955093384, "step": 5146 }, { "epoch": 0.7217275467994111, "grad_norm": 5.155908107757568, "learning_rate": 1.8993173152250865e-06, "loss": 0.3964534401893616, "step": 5147 }, { "epoch": 0.7218677697539088, "grad_norm": 2.4828295707702637, "learning_rate": 1.8975363685494324e-06, "loss": 0.5054188966751099, "step": 5148 }, { "epoch": 0.7220079927084063, "grad_norm": 3.7977988719940186, "learning_rate": 1.8957560616753801e-06, "loss": 0.5359276533126831, "step": 5149 }, { "epoch": 0.722148215662904, "grad_norm": 2.485379934310913, "learning_rate": 1.8939763949700657e-06, "loss": 0.4248904287815094, "step": 5150 }, { "epoch": 0.7222884386174017, "grad_norm": 4.439633369445801, "learning_rate": 1.8921973688005053e-06, "loss": 0.47239500284194946, "step": 5151 }, { "epoch": 0.7224286615718993, "grad_norm": 3.7003281116485596, "learning_rate": 1.8904189835335718e-06, "loss": 0.47752586007118225, "step": 5152 }, { "epoch": 0.722568884526397, "grad_norm": 3.7786242961883545, "learning_rate": 1.8886412395360116e-06, "loss": 0.498546302318573, "step": 5153 }, { "epoch": 0.7227091074808947, "grad_norm": 3.8448779582977295, "learning_rate": 1.8868641371744383e-06, "loss": 0.41099753975868225, "step": 5154 }, { "epoch": 0.7228493304353922, "grad_norm": 3.9874379634857178, "learning_rate": 1.885087676815332e-06, "loss": 0.45514556765556335, "step": 5155 }, { "epoch": 0.7229895533898899, "grad_norm": 2.5709943771362305, "learning_rate": 1.883311858825041e-06, "loss": 0.4921885132789612, "step": 5156 }, { "epoch": 0.7231297763443876, "grad_norm": 2.77347993850708, "learning_rate": 1.8815366835697835e-06, "loss": 0.4626319110393524, "step": 5157 }, { "epoch": 0.7232699992988852, "grad_norm": 3.8220489025115967, "learning_rate": 1.8797621514156382e-06, "loss": 0.5288197994232178, "step": 5158 }, { "epoch": 0.7234102222533829, "grad_norm": 4.554314613342285, "learning_rate": 1.8779882627285583e-06, "loss": 0.49722108244895935, "step": 5159 }, { "epoch": 0.7235504452078805, "grad_norm": 7.463874340057373, "learning_rate": 1.8762150178743615e-06, "loss": 0.46867597103118896, "step": 5160 }, { "epoch": 0.7236906681623781, "grad_norm": 4.190147399902344, "learning_rate": 1.8744424172187325e-06, "loss": 0.48564380407333374, "step": 5161 }, { "epoch": 0.7238308911168758, "grad_norm": 4.355142116546631, "learning_rate": 1.8726704611272245e-06, "loss": 0.5564368963241577, "step": 5162 }, { "epoch": 0.7239711140713735, "grad_norm": 3.8069968223571777, "learning_rate": 1.870899149965258e-06, "loss": 0.46486443281173706, "step": 5163 }, { "epoch": 0.7241113370258712, "grad_norm": 3.9415476322174072, "learning_rate": 1.869128484098116e-06, "loss": 0.6066210865974426, "step": 5164 }, { "epoch": 0.7242515599803688, "grad_norm": 2.6495349407196045, "learning_rate": 1.8673584638909536e-06, "loss": 0.4289039075374603, "step": 5165 }, { "epoch": 0.7243917829348664, "grad_norm": 4.584846496582031, "learning_rate": 1.8655890897087913e-06, "loss": 0.5402697324752808, "step": 5166 }, { "epoch": 0.7245320058893641, "grad_norm": 3.871731996536255, "learning_rate": 1.8638203619165158e-06, "loss": 0.4790053367614746, "step": 5167 }, { "epoch": 0.7246722288438617, "grad_norm": 9.185256004333496, "learning_rate": 1.86205228087888e-06, "loss": 0.4389585256576538, "step": 5168 }, { "epoch": 0.7248124517983594, "grad_norm": 4.256779670715332, "learning_rate": 1.8602848469605067e-06, "loss": 0.4719676673412323, "step": 5169 }, { "epoch": 0.7249526747528571, "grad_norm": 5.307985305786133, "learning_rate": 1.8585180605258774e-06, "loss": 0.45862826704978943, "step": 5170 }, { "epoch": 0.7250928977073547, "grad_norm": 3.644641876220703, "learning_rate": 1.856751921939352e-06, "loss": 0.3907647728919983, "step": 5171 }, { "epoch": 0.7252331206618523, "grad_norm": 3.2716875076293945, "learning_rate": 1.8549864315651455e-06, "loss": 0.5719670057296753, "step": 5172 }, { "epoch": 0.72537334361635, "grad_norm": 4.915655612945557, "learning_rate": 1.8532215897673451e-06, "loss": 0.6158810257911682, "step": 5173 }, { "epoch": 0.7255135665708476, "grad_norm": 2.7762134075164795, "learning_rate": 1.8514573969099038e-06, "loss": 0.5571304559707642, "step": 5174 }, { "epoch": 0.7256537895253453, "grad_norm": 3.249220132827759, "learning_rate": 1.8496938533566389e-06, "loss": 0.4638804793357849, "step": 5175 }, { "epoch": 0.725794012479843, "grad_norm": 4.3452019691467285, "learning_rate": 1.8479309594712352e-06, "loss": 0.5229121446609497, "step": 5176 }, { "epoch": 0.7259342354343405, "grad_norm": 4.6044697761535645, "learning_rate": 1.846168715617246e-06, "loss": 0.5582090616226196, "step": 5177 }, { "epoch": 0.7260744583888382, "grad_norm": 3.711031198501587, "learning_rate": 1.8444071221580833e-06, "loss": 0.4084041714668274, "step": 5178 }, { "epoch": 0.7262146813433359, "grad_norm": 3.453821897506714, "learning_rate": 1.8426461794570315e-06, "loss": 0.4824126362800598, "step": 5179 }, { "epoch": 0.7263549042978336, "grad_norm": 4.788595199584961, "learning_rate": 1.840885887877239e-06, "loss": 0.49627864360809326, "step": 5180 }, { "epoch": 0.7264951272523312, "grad_norm": 5.080749034881592, "learning_rate": 1.839126247781719e-06, "loss": 0.5583826303482056, "step": 5181 }, { "epoch": 0.7266353502068289, "grad_norm": 3.7343924045562744, "learning_rate": 1.837367259533352e-06, "loss": 0.5163661241531372, "step": 5182 }, { "epoch": 0.7267755731613265, "grad_norm": 4.749850273132324, "learning_rate": 1.8356089234948838e-06, "loss": 0.4767634868621826, "step": 5183 }, { "epoch": 0.7269157961158241, "grad_norm": 7.267282009124756, "learning_rate": 1.833851240028922e-06, "loss": 0.422027051448822, "step": 5184 }, { "epoch": 0.7270560190703218, "grad_norm": 2.6680610179901123, "learning_rate": 1.832094209497945e-06, "loss": 0.5574028491973877, "step": 5185 }, { "epoch": 0.7271962420248195, "grad_norm": 2.9105818271636963, "learning_rate": 1.8303378322642928e-06, "loss": 0.43877309560775757, "step": 5186 }, { "epoch": 0.7273364649793171, "grad_norm": 3.309558868408203, "learning_rate": 1.8285821086901733e-06, "loss": 0.5765730142593384, "step": 5187 }, { "epoch": 0.7274766879338148, "grad_norm": 5.424366474151611, "learning_rate": 1.826827039137658e-06, "loss": 0.5346532464027405, "step": 5188 }, { "epoch": 0.7276169108883124, "grad_norm": 22.915273666381836, "learning_rate": 1.825072623968685e-06, "loss": 0.616058349609375, "step": 5189 }, { "epoch": 0.72775713384281, "grad_norm": 4.699312686920166, "learning_rate": 1.8233188635450537e-06, "loss": 0.4382252097129822, "step": 5190 }, { "epoch": 0.7278973567973077, "grad_norm": 3.7634787559509277, "learning_rate": 1.8215657582284324e-06, "loss": 0.4617495536804199, "step": 5191 }, { "epoch": 0.7280375797518054, "grad_norm": 3.3308064937591553, "learning_rate": 1.8198133083803533e-06, "loss": 0.48955217003822327, "step": 5192 }, { "epoch": 0.7281778027063031, "grad_norm": 3.850520610809326, "learning_rate": 1.8180615143622126e-06, "loss": 0.5023770332336426, "step": 5193 }, { "epoch": 0.7283180256608007, "grad_norm": 3.125499725341797, "learning_rate": 1.8163103765352723e-06, "loss": 0.5727767944335938, "step": 5194 }, { "epoch": 0.7284582486152983, "grad_norm": 3.680049180984497, "learning_rate": 1.8145598952606586e-06, "loss": 0.5131218433380127, "step": 5195 }, { "epoch": 0.728598471569796, "grad_norm": 3.6688170433044434, "learning_rate": 1.8128100708993634e-06, "loss": 0.5665874481201172, "step": 5196 }, { "epoch": 0.7287386945242936, "grad_norm": 3.8297791481018066, "learning_rate": 1.811060903812239e-06, "loss": 0.5260907411575317, "step": 5197 }, { "epoch": 0.7288789174787913, "grad_norm": 6.118453502655029, "learning_rate": 1.8093123943600073e-06, "loss": 0.5541563034057617, "step": 5198 }, { "epoch": 0.729019140433289, "grad_norm": 3.291297197341919, "learning_rate": 1.8075645429032511e-06, "loss": 0.544317364692688, "step": 5199 }, { "epoch": 0.7291593633877865, "grad_norm": 3.7261641025543213, "learning_rate": 1.80581734980242e-06, "loss": 0.5618921518325806, "step": 5200 }, { "epoch": 0.7292995863422842, "grad_norm": 3.3024661540985107, "learning_rate": 1.8040708154178267e-06, "loss": 0.5671887397766113, "step": 5201 }, { "epoch": 0.7294398092967819, "grad_norm": 2.3410539627075195, "learning_rate": 1.802324940109647e-06, "loss": 0.4877272844314575, "step": 5202 }, { "epoch": 0.7295800322512795, "grad_norm": 3.9170329570770264, "learning_rate": 1.8005797242379242e-06, "loss": 0.4922964572906494, "step": 5203 }, { "epoch": 0.7297202552057772, "grad_norm": 5.100419044494629, "learning_rate": 1.79883516816256e-06, "loss": 0.47099369764328003, "step": 5204 }, { "epoch": 0.7298604781602749, "grad_norm": 5.062653541564941, "learning_rate": 1.7970912722433248e-06, "loss": 0.48654311895370483, "step": 5205 }, { "epoch": 0.7300007011147724, "grad_norm": 3.7145605087280273, "learning_rate": 1.7953480368398507e-06, "loss": 0.5760952830314636, "step": 5206 }, { "epoch": 0.7301409240692701, "grad_norm": 3.256625175476074, "learning_rate": 1.793605462311635e-06, "loss": 0.45596909523010254, "step": 5207 }, { "epoch": 0.7302811470237678, "grad_norm": 3.8119468688964844, "learning_rate": 1.7918635490180375e-06, "loss": 0.505588173866272, "step": 5208 }, { "epoch": 0.7304213699782655, "grad_norm": 3.583465814590454, "learning_rate": 1.7901222973182842e-06, "loss": 0.46832215785980225, "step": 5209 }, { "epoch": 0.7305615929327631, "grad_norm": 5.76995325088501, "learning_rate": 1.7883817075714587e-06, "loss": 0.5062117576599121, "step": 5210 }, { "epoch": 0.7307018158872608, "grad_norm": 7.412212371826172, "learning_rate": 1.7866417801365132e-06, "loss": 0.5533974766731262, "step": 5211 }, { "epoch": 0.7308420388417584, "grad_norm": 3.8052773475646973, "learning_rate": 1.7849025153722627e-06, "loss": 0.5277038812637329, "step": 5212 }, { "epoch": 0.730982261796256, "grad_norm": 6.520743370056152, "learning_rate": 1.783163913637385e-06, "loss": 0.4757198095321655, "step": 5213 }, { "epoch": 0.7311224847507537, "grad_norm": 7.663017272949219, "learning_rate": 1.78142597529042e-06, "loss": 0.5057488679885864, "step": 5214 }, { "epoch": 0.7312627077052514, "grad_norm": 2.9881765842437744, "learning_rate": 1.7796887006897728e-06, "loss": 0.468712717294693, "step": 5215 }, { "epoch": 0.731402930659749, "grad_norm": 3.1853432655334473, "learning_rate": 1.7779520901937124e-06, "loss": 0.5426362752914429, "step": 5216 }, { "epoch": 0.7315431536142466, "grad_norm": 7.500711917877197, "learning_rate": 1.7762161441603649e-06, "loss": 0.5095472931861877, "step": 5217 }, { "epoch": 0.7316833765687443, "grad_norm": 18.28873634338379, "learning_rate": 1.7744808629477256e-06, "loss": 0.4973079562187195, "step": 5218 }, { "epoch": 0.7318235995232419, "grad_norm": 5.564632415771484, "learning_rate": 1.7727462469136508e-06, "loss": 0.5248265266418457, "step": 5219 }, { "epoch": 0.7319638224777396, "grad_norm": 3.941685199737549, "learning_rate": 1.7710122964158593e-06, "loss": 0.5679107308387756, "step": 5220 }, { "epoch": 0.7321040454322373, "grad_norm": 2.4279744625091553, "learning_rate": 1.7692790118119329e-06, "loss": 0.45874422788619995, "step": 5221 }, { "epoch": 0.732244268386735, "grad_norm": 8.15238094329834, "learning_rate": 1.7675463934593172e-06, "loss": 0.47041019797325134, "step": 5222 }, { "epoch": 0.7323844913412325, "grad_norm": 3.8711585998535156, "learning_rate": 1.7658144417153173e-06, "loss": 0.5357686281204224, "step": 5223 }, { "epoch": 0.7325247142957302, "grad_norm": 4.837149143218994, "learning_rate": 1.7640831569371025e-06, "loss": 0.5283686518669128, "step": 5224 }, { "epoch": 0.7326649372502279, "grad_norm": 6.239952564239502, "learning_rate": 1.7623525394817065e-06, "loss": 0.4661555290222168, "step": 5225 }, { "epoch": 0.7328051602047255, "grad_norm": 3.3116118907928467, "learning_rate": 1.7606225897060225e-06, "loss": 0.46555230021476746, "step": 5226 }, { "epoch": 0.7329453831592232, "grad_norm": 3.6912684440612793, "learning_rate": 1.7588933079668074e-06, "loss": 0.5175095200538635, "step": 5227 }, { "epoch": 0.7330856061137209, "grad_norm": 4.527490139007568, "learning_rate": 1.7571646946206805e-06, "loss": 0.5072892904281616, "step": 5228 }, { "epoch": 0.7332258290682184, "grad_norm": 4.155828952789307, "learning_rate": 1.7554367500241248e-06, "loss": 0.576283872127533, "step": 5229 }, { "epoch": 0.7333660520227161, "grad_norm": 3.4456679821014404, "learning_rate": 1.7537094745334792e-06, "loss": 0.5033249258995056, "step": 5230 }, { "epoch": 0.7335062749772138, "grad_norm": 5.488832950592041, "learning_rate": 1.751982868504951e-06, "loss": 0.47264137864112854, "step": 5231 }, { "epoch": 0.7336464979317114, "grad_norm": 3.1517276763916016, "learning_rate": 1.7502569322946078e-06, "loss": 0.5643545389175415, "step": 5232 }, { "epoch": 0.7337867208862091, "grad_norm": 5.0550947189331055, "learning_rate": 1.7485316662583774e-06, "loss": 0.5194208025932312, "step": 5233 }, { "epoch": 0.7339269438407067, "grad_norm": 4.324305057525635, "learning_rate": 1.7468070707520517e-06, "loss": 0.46367549896240234, "step": 5234 }, { "epoch": 0.7340671667952043, "grad_norm": 4.932511329650879, "learning_rate": 1.7450831461312834e-06, "loss": 0.4199219346046448, "step": 5235 }, { "epoch": 0.734207389749702, "grad_norm": 3.4270107746124268, "learning_rate": 1.743359892751587e-06, "loss": 0.5806059837341309, "step": 5236 }, { "epoch": 0.7343476127041997, "grad_norm": 4.715740203857422, "learning_rate": 1.741637310968336e-06, "loss": 0.48865312337875366, "step": 5237 }, { "epoch": 0.7344878356586974, "grad_norm": 4.778567314147949, "learning_rate": 1.7399154011367686e-06, "loss": 0.5097386837005615, "step": 5238 }, { "epoch": 0.734628058613195, "grad_norm": 2.7226901054382324, "learning_rate": 1.7381941636119843e-06, "loss": 0.48889198899269104, "step": 5239 }, { "epoch": 0.7347682815676926, "grad_norm": 4.012801170349121, "learning_rate": 1.7364735987489423e-06, "loss": 0.5161731243133545, "step": 5240 }, { "epoch": 0.7349085045221903, "grad_norm": 4.069191932678223, "learning_rate": 1.7347537069024646e-06, "loss": 0.43697869777679443, "step": 5241 }, { "epoch": 0.7350487274766879, "grad_norm": 2.7479095458984375, "learning_rate": 1.7330344884272342e-06, "loss": 0.47079455852508545, "step": 5242 }, { "epoch": 0.7351889504311856, "grad_norm": 4.2453837394714355, "learning_rate": 1.7313159436777926e-06, "loss": 0.5337293148040771, "step": 5243 }, { "epoch": 0.7353291733856833, "grad_norm": 2.8082902431488037, "learning_rate": 1.729598073008546e-06, "loss": 0.4972257614135742, "step": 5244 }, { "epoch": 0.7354693963401809, "grad_norm": 5.750405788421631, "learning_rate": 1.7278808767737592e-06, "loss": 0.46400389075279236, "step": 5245 }, { "epoch": 0.7356096192946785, "grad_norm": 3.7520625591278076, "learning_rate": 1.7261643553275604e-06, "loss": 0.49338358640670776, "step": 5246 }, { "epoch": 0.7357498422491762, "grad_norm": 3.653529644012451, "learning_rate": 1.7244485090239349e-06, "loss": 0.5197138786315918, "step": 5247 }, { "epoch": 0.7358900652036738, "grad_norm": 8.60651969909668, "learning_rate": 1.7227333382167344e-06, "loss": 0.4833301603794098, "step": 5248 }, { "epoch": 0.7360302881581715, "grad_norm": 4.665688991546631, "learning_rate": 1.7210188432596636e-06, "loss": 0.460631400346756, "step": 5249 }, { "epoch": 0.7361705111126692, "grad_norm": 49.732505798339844, "learning_rate": 1.7193050245062943e-06, "loss": 0.5291991829872131, "step": 5250 }, { "epoch": 0.7363107340671668, "grad_norm": 3.420771598815918, "learning_rate": 1.7175918823100556e-06, "loss": 0.5300562381744385, "step": 5251 }, { "epoch": 0.7364509570216644, "grad_norm": 3.807896137237549, "learning_rate": 1.7158794170242393e-06, "loss": 0.5522304177284241, "step": 5252 }, { "epoch": 0.7365911799761621, "grad_norm": 4.037988662719727, "learning_rate": 1.7141676290019954e-06, "loss": 0.5245538353919983, "step": 5253 }, { "epoch": 0.7367314029306598, "grad_norm": 4.602289199829102, "learning_rate": 1.7124565185963372e-06, "loss": 0.5485166907310486, "step": 5254 }, { "epoch": 0.7368716258851574, "grad_norm": 3.0955095291137695, "learning_rate": 1.710746086160131e-06, "loss": 0.45522814989089966, "step": 5255 }, { "epoch": 0.7370118488396551, "grad_norm": 7.798027992248535, "learning_rate": 1.7090363320461162e-06, "loss": 0.5253046751022339, "step": 5256 }, { "epoch": 0.7371520717941527, "grad_norm": 3.7557661533355713, "learning_rate": 1.7073272566068783e-06, "loss": 0.46461957693099976, "step": 5257 }, { "epoch": 0.7372922947486503, "grad_norm": 2.837174892425537, "learning_rate": 1.7056188601948714e-06, "loss": 0.5109313726425171, "step": 5258 }, { "epoch": 0.737432517703148, "grad_norm": 4.755286693572998, "learning_rate": 1.7039111431624077e-06, "loss": 0.5059289336204529, "step": 5259 }, { "epoch": 0.7375727406576457, "grad_norm": 4.668543338775635, "learning_rate": 1.702204105861659e-06, "loss": 0.5043450593948364, "step": 5260 }, { "epoch": 0.7377129636121433, "grad_norm": 3.4473624229431152, "learning_rate": 1.7004977486446562e-06, "loss": 0.5117362141609192, "step": 5261 }, { "epoch": 0.737853186566641, "grad_norm": 3.8580639362335205, "learning_rate": 1.6987920718632927e-06, "loss": 0.4819282293319702, "step": 5262 }, { "epoch": 0.7379934095211386, "grad_norm": 3.592275619506836, "learning_rate": 1.6970870758693165e-06, "loss": 0.5785678029060364, "step": 5263 }, { "epoch": 0.7381336324756362, "grad_norm": 14.892951011657715, "learning_rate": 1.6953827610143391e-06, "loss": 0.4542447626590729, "step": 5264 }, { "epoch": 0.7382738554301339, "grad_norm": 3.3213448524475098, "learning_rate": 1.6936791276498316e-06, "loss": 0.4849679172039032, "step": 5265 }, { "epoch": 0.7384140783846316, "grad_norm": 3.2350053787231445, "learning_rate": 1.691976176127123e-06, "loss": 0.4252512454986572, "step": 5266 }, { "epoch": 0.7385543013391292, "grad_norm": 30.78666114807129, "learning_rate": 1.6902739067974023e-06, "loss": 0.5049140453338623, "step": 5267 }, { "epoch": 0.7386945242936269, "grad_norm": 5.297360420227051, "learning_rate": 1.68857232001172e-06, "loss": 0.4916132688522339, "step": 5268 }, { "epoch": 0.7388347472481245, "grad_norm": 3.4582974910736084, "learning_rate": 1.6868714161209798e-06, "loss": 0.5022696852684021, "step": 5269 }, { "epoch": 0.7389749702026222, "grad_norm": 5.574541091918945, "learning_rate": 1.6851711954759497e-06, "loss": 0.42104965448379517, "step": 5270 }, { "epoch": 0.7391151931571198, "grad_norm": 4.313268184661865, "learning_rate": 1.683471658427257e-06, "loss": 0.5338942408561707, "step": 5271 }, { "epoch": 0.7392554161116175, "grad_norm": 4.972386360168457, "learning_rate": 1.681772805325385e-06, "loss": 0.5191807746887207, "step": 5272 }, { "epoch": 0.7393956390661152, "grad_norm": 3.4655184745788574, "learning_rate": 1.6800746365206783e-06, "loss": 0.503909170627594, "step": 5273 }, { "epoch": 0.7395358620206127, "grad_norm": 4.441891670227051, "learning_rate": 1.6783771523633414e-06, "loss": 0.41623955965042114, "step": 5274 }, { "epoch": 0.7396760849751104, "grad_norm": 7.569739818572998, "learning_rate": 1.6766803532034304e-06, "loss": 0.4740332365036011, "step": 5275 }, { "epoch": 0.7398163079296081, "grad_norm": 24.094572067260742, "learning_rate": 1.6749842393908722e-06, "loss": 0.5419222116470337, "step": 5276 }, { "epoch": 0.7399565308841057, "grad_norm": 4.747381687164307, "learning_rate": 1.6732888112754408e-06, "loss": 0.4760213792324066, "step": 5277 }, { "epoch": 0.7400967538386034, "grad_norm": 3.330085039138794, "learning_rate": 1.6715940692067756e-06, "loss": 0.4856198728084564, "step": 5278 }, { "epoch": 0.7402369767931011, "grad_norm": 2.6544718742370605, "learning_rate": 1.6699000135343724e-06, "loss": 0.38422590494155884, "step": 5279 }, { "epoch": 0.7403771997475986, "grad_norm": 14.683616638183594, "learning_rate": 1.6682066446075873e-06, "loss": 0.452619731426239, "step": 5280 }, { "epoch": 0.7405174227020963, "grad_norm": 3.6007862091064453, "learning_rate": 1.6665139627756284e-06, "loss": 0.5093599557876587, "step": 5281 }, { "epoch": 0.740657645656594, "grad_norm": 5.918630599975586, "learning_rate": 1.6648219683875733e-06, "loss": 0.48517507314682007, "step": 5282 }, { "epoch": 0.7407978686110916, "grad_norm": 4.725396156311035, "learning_rate": 1.663130661792346e-06, "loss": 0.5866571664810181, "step": 5283 }, { "epoch": 0.7409380915655893, "grad_norm": 3.7032930850982666, "learning_rate": 1.6614400433387363e-06, "loss": 0.5070709586143494, "step": 5284 }, { "epoch": 0.741078314520087, "grad_norm": 4.1734771728515625, "learning_rate": 1.6597501133753895e-06, "loss": 0.5537222027778625, "step": 5285 }, { "epoch": 0.7412185374745845, "grad_norm": 3.580986738204956, "learning_rate": 1.6580608722508096e-06, "loss": 0.5000881552696228, "step": 5286 }, { "epoch": 0.7413587604290822, "grad_norm": 3.6445531845092773, "learning_rate": 1.656372320313358e-06, "loss": 0.5208995342254639, "step": 5287 }, { "epoch": 0.7414989833835799, "grad_norm": 3.0938987731933594, "learning_rate": 1.654684457911256e-06, "loss": 0.4792613089084625, "step": 5288 }, { "epoch": 0.7416392063380776, "grad_norm": 2.755040407180786, "learning_rate": 1.6529972853925753e-06, "loss": 0.5328675508499146, "step": 5289 }, { "epoch": 0.7417794292925752, "grad_norm": 3.724374532699585, "learning_rate": 1.6513108031052577e-06, "loss": 0.5355938076972961, "step": 5290 }, { "epoch": 0.7419196522470728, "grad_norm": 4.958353519439697, "learning_rate": 1.6496250113970912e-06, "loss": 0.4778830409049988, "step": 5291 }, { "epoch": 0.7420598752015705, "grad_norm": 6.333384990692139, "learning_rate": 1.6479399106157278e-06, "loss": 0.507308304309845, "step": 5292 }, { "epoch": 0.7422000981560681, "grad_norm": 3.9830825328826904, "learning_rate": 1.6462555011086757e-06, "loss": 0.4579923152923584, "step": 5293 }, { "epoch": 0.7423403211105658, "grad_norm": 4.27938985824585, "learning_rate": 1.6445717832233005e-06, "loss": 0.469076544046402, "step": 5294 }, { "epoch": 0.7424805440650635, "grad_norm": 16.951204299926758, "learning_rate": 1.6428887573068203e-06, "loss": 0.5339738130569458, "step": 5295 }, { "epoch": 0.7426207670195611, "grad_norm": 4.574956893920898, "learning_rate": 1.6412064237063219e-06, "loss": 0.49756208062171936, "step": 5296 }, { "epoch": 0.7427609899740587, "grad_norm": 4.09345817565918, "learning_rate": 1.639524782768737e-06, "loss": 0.5505663156509399, "step": 5297 }, { "epoch": 0.7429012129285564, "grad_norm": 4.34266471862793, "learning_rate": 1.637843834840862e-06, "loss": 0.5521926879882812, "step": 5298 }, { "epoch": 0.743041435883054, "grad_norm": 5.541738510131836, "learning_rate": 1.6361635802693481e-06, "loss": 0.4898008704185486, "step": 5299 }, { "epoch": 0.7431816588375517, "grad_norm": 6.3326640129089355, "learning_rate": 1.634484019400705e-06, "loss": 0.5591399669647217, "step": 5300 }, { "epoch": 0.7433218817920494, "grad_norm": 7.5581159591674805, "learning_rate": 1.6328051525812932e-06, "loss": 0.5142932534217834, "step": 5301 }, { "epoch": 0.7434621047465471, "grad_norm": 2.687516689300537, "learning_rate": 1.6311269801573414e-06, "loss": 0.555594801902771, "step": 5302 }, { "epoch": 0.7436023277010446, "grad_norm": 2.6051387786865234, "learning_rate": 1.629449502474924e-06, "loss": 0.549201250076294, "step": 5303 }, { "epoch": 0.7437425506555423, "grad_norm": 7.08030366897583, "learning_rate": 1.627772719879978e-06, "loss": 0.5305189490318298, "step": 5304 }, { "epoch": 0.74388277361004, "grad_norm": 3.405181646347046, "learning_rate": 1.6260966327182958e-06, "loss": 0.49283769726753235, "step": 5305 }, { "epoch": 0.7440229965645376, "grad_norm": 3.061814069747925, "learning_rate": 1.624421241335528e-06, "loss": 0.4173639118671417, "step": 5306 }, { "epoch": 0.7441632195190353, "grad_norm": 3.915198564529419, "learning_rate": 1.622746546077175e-06, "loss": 0.5483347177505493, "step": 5307 }, { "epoch": 0.744303442473533, "grad_norm": 3.011281967163086, "learning_rate": 1.6210725472886058e-06, "loss": 0.5643962621688843, "step": 5308 }, { "epoch": 0.7444436654280305, "grad_norm": 3.7578914165496826, "learning_rate": 1.6193992453150332e-06, "loss": 0.4738375246524811, "step": 5309 }, { "epoch": 0.7445838883825282, "grad_norm": 2.8713595867156982, "learning_rate": 1.6177266405015336e-06, "loss": 0.48550084233283997, "step": 5310 }, { "epoch": 0.7447241113370259, "grad_norm": 3.2815518379211426, "learning_rate": 1.616054733193037e-06, "loss": 0.5391052961349487, "step": 5311 }, { "epoch": 0.7448643342915235, "grad_norm": 3.4486284255981445, "learning_rate": 1.614383523734333e-06, "loss": 0.542851984500885, "step": 5312 }, { "epoch": 0.7450045572460212, "grad_norm": 12.267385482788086, "learning_rate": 1.6127130124700597e-06, "loss": 0.5221970081329346, "step": 5313 }, { "epoch": 0.7451447802005188, "grad_norm": 2.949704885482788, "learning_rate": 1.6110431997447224e-06, "loss": 0.4331735074520111, "step": 5314 }, { "epoch": 0.7452850031550164, "grad_norm": 3.87307071685791, "learning_rate": 1.6093740859026692e-06, "loss": 0.42069685459136963, "step": 5315 }, { "epoch": 0.7454252261095141, "grad_norm": 2.6190826892852783, "learning_rate": 1.6077056712881185e-06, "loss": 0.43900546431541443, "step": 5316 }, { "epoch": 0.7455654490640118, "grad_norm": 3.0780913829803467, "learning_rate": 1.6060379562451307e-06, "loss": 0.4894309341907501, "step": 5317 }, { "epoch": 0.7457056720185095, "grad_norm": 5.033456802368164, "learning_rate": 1.604370941117631e-06, "loss": 0.6087955236434937, "step": 5318 }, { "epoch": 0.7458458949730071, "grad_norm": 19.47418212890625, "learning_rate": 1.6027046262493972e-06, "loss": 0.5168706774711609, "step": 5319 }, { "epoch": 0.7459861179275047, "grad_norm": 4.857751846313477, "learning_rate": 1.601039011984064e-06, "loss": 0.5312580466270447, "step": 5320 }, { "epoch": 0.7461263408820024, "grad_norm": 3.9900102615356445, "learning_rate": 1.5993740986651163e-06, "loss": 0.4794546365737915, "step": 5321 }, { "epoch": 0.7462665638365, "grad_norm": 3.9419422149658203, "learning_rate": 1.5977098866359054e-06, "loss": 0.4556724727153778, "step": 5322 }, { "epoch": 0.7464067867909977, "grad_norm": 3.947286605834961, "learning_rate": 1.5960463762396256e-06, "loss": 0.524212658405304, "step": 5323 }, { "epoch": 0.7465470097454954, "grad_norm": 2.1232922077178955, "learning_rate": 1.5943835678193343e-06, "loss": 0.45421427488327026, "step": 5324 }, { "epoch": 0.746687232699993, "grad_norm": 5.608750343322754, "learning_rate": 1.5927214617179426e-06, "loss": 0.5718281865119934, "step": 5325 }, { "epoch": 0.7468274556544906, "grad_norm": 4.0837602615356445, "learning_rate": 1.5910600582782165e-06, "loss": 0.5180896520614624, "step": 5326 }, { "epoch": 0.7469676786089883, "grad_norm": 2.8781633377075195, "learning_rate": 1.5893993578427735e-06, "loss": 0.5580347776412964, "step": 5327 }, { "epoch": 0.7471079015634859, "grad_norm": 4.192365646362305, "learning_rate": 1.5877393607540947e-06, "loss": 0.49681785702705383, "step": 5328 }, { "epoch": 0.7472481245179836, "grad_norm": 4.215516567230225, "learning_rate": 1.5860800673545067e-06, "loss": 0.5630797743797302, "step": 5329 }, { "epoch": 0.7473883474724813, "grad_norm": 11.08145809173584, "learning_rate": 1.5844214779861961e-06, "loss": 0.5517994165420532, "step": 5330 }, { "epoch": 0.7475285704269788, "grad_norm": 3.65865159034729, "learning_rate": 1.5827635929912045e-06, "loss": 0.5466411113739014, "step": 5331 }, { "epoch": 0.7476687933814765, "grad_norm": 3.343644142150879, "learning_rate": 1.5811064127114274e-06, "loss": 0.49747514724731445, "step": 5332 }, { "epoch": 0.7478090163359742, "grad_norm": 4.591821193695068, "learning_rate": 1.5794499374886108e-06, "loss": 0.5282902121543884, "step": 5333 }, { "epoch": 0.7479492392904719, "grad_norm": 6.183858871459961, "learning_rate": 1.5777941676643649e-06, "loss": 0.48679956793785095, "step": 5334 }, { "epoch": 0.7480894622449695, "grad_norm": 4.599566459655762, "learning_rate": 1.5761391035801448e-06, "loss": 0.6316024661064148, "step": 5335 }, { "epoch": 0.7482296851994672, "grad_norm": 3.2075181007385254, "learning_rate": 1.574484745577265e-06, "loss": 0.4432644844055176, "step": 5336 }, { "epoch": 0.7483699081539648, "grad_norm": 4.054751873016357, "learning_rate": 1.5728310939968932e-06, "loss": 0.5234924554824829, "step": 5337 }, { "epoch": 0.7485101311084624, "grad_norm": 3.287384510040283, "learning_rate": 1.5711781491800537e-06, "loss": 0.5116086602210999, "step": 5338 }, { "epoch": 0.7486503540629601, "grad_norm": 3.1851327419281006, "learning_rate": 1.5695259114676175e-06, "loss": 0.4068976640701294, "step": 5339 }, { "epoch": 0.7487905770174578, "grad_norm": 3.8074560165405273, "learning_rate": 1.5678743812003228e-06, "loss": 0.3764667510986328, "step": 5340 }, { "epoch": 0.7489307999719554, "grad_norm": 4.33280611038208, "learning_rate": 1.566223558718748e-06, "loss": 0.5226150155067444, "step": 5341 }, { "epoch": 0.7490710229264531, "grad_norm": 4.417002201080322, "learning_rate": 1.5645734443633342e-06, "loss": 0.5028011798858643, "step": 5342 }, { "epoch": 0.7492112458809507, "grad_norm": 33.61679458618164, "learning_rate": 1.5629240384743743e-06, "loss": 0.48948970437049866, "step": 5343 }, { "epoch": 0.7493514688354483, "grad_norm": 6.75856876373291, "learning_rate": 1.5612753413920162e-06, "loss": 0.48567885160446167, "step": 5344 }, { "epoch": 0.749491691789946, "grad_norm": 3.076014757156372, "learning_rate": 1.5596273534562557e-06, "loss": 0.5317301750183105, "step": 5345 }, { "epoch": 0.7496319147444437, "grad_norm": 4.344799995422363, "learning_rate": 1.5579800750069535e-06, "loss": 0.4040253162384033, "step": 5346 }, { "epoch": 0.7497721376989414, "grad_norm": 4.607762336730957, "learning_rate": 1.5563335063838108e-06, "loss": 0.5029723644256592, "step": 5347 }, { "epoch": 0.7499123606534389, "grad_norm": 4.005958557128906, "learning_rate": 1.5546876479263956e-06, "loss": 0.527950644493103, "step": 5348 }, { "epoch": 0.7500525836079366, "grad_norm": 4.234867095947266, "learning_rate": 1.5530424999741183e-06, "loss": 0.49779462814331055, "step": 5349 }, { "epoch": 0.7501928065624343, "grad_norm": 3.4348740577697754, "learning_rate": 1.5513980628662494e-06, "loss": 0.4439297914505005, "step": 5350 }, { "epoch": 0.7503330295169319, "grad_norm": 4.085529327392578, "learning_rate": 1.5497543369419099e-06, "loss": 0.49227628111839294, "step": 5351 }, { "epoch": 0.7504732524714296, "grad_norm": 4.499435901641846, "learning_rate": 1.5481113225400774e-06, "loss": 0.5307598114013672, "step": 5352 }, { "epoch": 0.7506134754259273, "grad_norm": 4.370985984802246, "learning_rate": 1.5464690199995752e-06, "loss": 0.5572865605354309, "step": 5353 }, { "epoch": 0.7507536983804248, "grad_norm": 3.631276845932007, "learning_rate": 1.544827429659092e-06, "loss": 0.49387019872665405, "step": 5354 }, { "epoch": 0.7508939213349225, "grad_norm": 2.9436142444610596, "learning_rate": 1.5431865518571577e-06, "loss": 0.5216313600540161, "step": 5355 }, { "epoch": 0.7510341442894202, "grad_norm": 3.8856732845306396, "learning_rate": 1.5415463869321611e-06, "loss": 0.44100672006607056, "step": 5356 }, { "epoch": 0.7511743672439178, "grad_norm": 2.750434637069702, "learning_rate": 1.539906935222344e-06, "loss": 0.41713747382164, "step": 5357 }, { "epoch": 0.7513145901984155, "grad_norm": 3.528461456298828, "learning_rate": 1.5382681970658014e-06, "loss": 0.5590335726737976, "step": 5358 }, { "epoch": 0.7514548131529132, "grad_norm": 5.571569442749023, "learning_rate": 1.5366301728004756e-06, "loss": 0.5191071033477783, "step": 5359 }, { "epoch": 0.7515950361074107, "grad_norm": 2.7299678325653076, "learning_rate": 1.534992862764172e-06, "loss": 0.5145717263221741, "step": 5360 }, { "epoch": 0.7517352590619084, "grad_norm": 4.781228065490723, "learning_rate": 1.533356267294538e-06, "loss": 0.5918129682540894, "step": 5361 }, { "epoch": 0.7518754820164061, "grad_norm": 6.419785022735596, "learning_rate": 1.5317203867290804e-06, "loss": 0.5748369097709656, "step": 5362 }, { "epoch": 0.7520157049709038, "grad_norm": 3.8309102058410645, "learning_rate": 1.5300852214051564e-06, "loss": 0.43923279643058777, "step": 5363 }, { "epoch": 0.7521559279254014, "grad_norm": 4.206915378570557, "learning_rate": 1.5284507716599773e-06, "loss": 0.47892552614212036, "step": 5364 }, { "epoch": 0.7522961508798991, "grad_norm": 3.227891445159912, "learning_rate": 1.5268170378306007e-06, "loss": 0.5746601819992065, "step": 5365 }, { "epoch": 0.7524363738343967, "grad_norm": 2.340782642364502, "learning_rate": 1.5251840202539475e-06, "loss": 0.5295112133026123, "step": 5366 }, { "epoch": 0.7525765967888943, "grad_norm": 4.674508094787598, "learning_rate": 1.5235517192667804e-06, "loss": 0.5013182163238525, "step": 5367 }, { "epoch": 0.752716819743392, "grad_norm": 2.5579330921173096, "learning_rate": 1.52192013520572e-06, "loss": 0.5504592061042786, "step": 5368 }, { "epoch": 0.7528570426978897, "grad_norm": 2.863300085067749, "learning_rate": 1.5202892684072372e-06, "loss": 0.5247935056686401, "step": 5369 }, { "epoch": 0.7529972656523873, "grad_norm": 4.7574615478515625, "learning_rate": 1.5186591192076571e-06, "loss": 0.5631893873214722, "step": 5370 }, { "epoch": 0.7531374886068849, "grad_norm": 3.3500306606292725, "learning_rate": 1.5170296879431511e-06, "loss": 0.5018866658210754, "step": 5371 }, { "epoch": 0.7532777115613826, "grad_norm": 4.933248519897461, "learning_rate": 1.5154009749497523e-06, "loss": 0.5118314027786255, "step": 5372 }, { "epoch": 0.7534179345158802, "grad_norm": 3.128687858581543, "learning_rate": 1.513772980563335e-06, "loss": 0.46405577659606934, "step": 5373 }, { "epoch": 0.7535581574703779, "grad_norm": 2.4381468296051025, "learning_rate": 1.5121457051196326e-06, "loss": 0.568494439125061, "step": 5374 }, { "epoch": 0.7536983804248756, "grad_norm": 3.4679057598114014, "learning_rate": 1.510519148954227e-06, "loss": 0.4776161313056946, "step": 5375 }, { "epoch": 0.7538386033793733, "grad_norm": 3.2314352989196777, "learning_rate": 1.5088933124025534e-06, "loss": 0.4733870029449463, "step": 5376 }, { "epoch": 0.7539788263338708, "grad_norm": 7.027690410614014, "learning_rate": 1.5072681957998976e-06, "loss": 0.5908428430557251, "step": 5377 }, { "epoch": 0.7541190492883685, "grad_norm": 3.8031513690948486, "learning_rate": 1.5056437994813982e-06, "loss": 0.5171816349029541, "step": 5378 }, { "epoch": 0.7542592722428662, "grad_norm": 13.984526634216309, "learning_rate": 1.5040201237820407e-06, "loss": 0.5143730044364929, "step": 5379 }, { "epoch": 0.7543994951973638, "grad_norm": 2.494305372238159, "learning_rate": 1.5023971690366712e-06, "loss": 0.40162211656570435, "step": 5380 }, { "epoch": 0.7545397181518615, "grad_norm": 3.8858935832977295, "learning_rate": 1.5007749355799767e-06, "loss": 0.5343881845474243, "step": 5381 }, { "epoch": 0.7546799411063592, "grad_norm": 3.63470721244812, "learning_rate": 1.4991534237465017e-06, "loss": 0.5245133638381958, "step": 5382 }, { "epoch": 0.7548201640608567, "grad_norm": 5.019495010375977, "learning_rate": 1.4975326338706408e-06, "loss": 0.583106517791748, "step": 5383 }, { "epoch": 0.7549603870153544, "grad_norm": 3.510338068008423, "learning_rate": 1.4959125662866402e-06, "loss": 0.6014294028282166, "step": 5384 }, { "epoch": 0.7551006099698521, "grad_norm": 4.122913360595703, "learning_rate": 1.4942932213285926e-06, "loss": 0.5608779788017273, "step": 5385 }, { "epoch": 0.7552408329243497, "grad_norm": 3.304166793823242, "learning_rate": 1.4926745993304508e-06, "loss": 0.5438716411590576, "step": 5386 }, { "epoch": 0.7553810558788474, "grad_norm": 3.8324174880981445, "learning_rate": 1.491056700626009e-06, "loss": 0.47426092624664307, "step": 5387 }, { "epoch": 0.755521278833345, "grad_norm": 3.175553798675537, "learning_rate": 1.489439525548917e-06, "loss": 0.565229058265686, "step": 5388 }, { "epoch": 0.7556615017878426, "grad_norm": 4.920506477355957, "learning_rate": 1.4878230744326755e-06, "loss": 0.5940979719161987, "step": 5389 }, { "epoch": 0.7558017247423403, "grad_norm": 2.800318479537964, "learning_rate": 1.486207347610636e-06, "loss": 0.48478150367736816, "step": 5390 }, { "epoch": 0.755941947696838, "grad_norm": 3.5760433673858643, "learning_rate": 1.4845923454159955e-06, "loss": 0.5615043640136719, "step": 5391 }, { "epoch": 0.7560821706513356, "grad_norm": 6.693869590759277, "learning_rate": 1.4829780681818117e-06, "loss": 0.5329163074493408, "step": 5392 }, { "epoch": 0.7562223936058333, "grad_norm": 2.5478551387786865, "learning_rate": 1.4813645162409817e-06, "loss": 0.41844603419303894, "step": 5393 }, { "epoch": 0.7563626165603309, "grad_norm": 3.822709083557129, "learning_rate": 1.479751689926261e-06, "loss": 0.45218873023986816, "step": 5394 }, { "epoch": 0.7565028395148286, "grad_norm": 11.199152946472168, "learning_rate": 1.4781395895702522e-06, "loss": 0.5048352479934692, "step": 5395 }, { "epoch": 0.7566430624693262, "grad_norm": 5.604034900665283, "learning_rate": 1.4765282155054095e-06, "loss": 0.4434640407562256, "step": 5396 }, { "epoch": 0.7567832854238239, "grad_norm": 4.816522598266602, "learning_rate": 1.4749175680640321e-06, "loss": 0.5709434747695923, "step": 5397 }, { "epoch": 0.7569235083783216, "grad_norm": 4.022801399230957, "learning_rate": 1.4733076475782804e-06, "loss": 0.6215879917144775, "step": 5398 }, { "epoch": 0.7570637313328192, "grad_norm": 4.732491493225098, "learning_rate": 1.4716984543801532e-06, "loss": 0.495654433965683, "step": 5399 }, { "epoch": 0.7572039542873168, "grad_norm": 5.039902687072754, "learning_rate": 1.4700899888015058e-06, "loss": 0.5840198993682861, "step": 5400 }, { "epoch": 0.7573441772418145, "grad_norm": 26.438858032226562, "learning_rate": 1.468482251174042e-06, "loss": 0.5880329608917236, "step": 5401 }, { "epoch": 0.7574844001963121, "grad_norm": 4.123345375061035, "learning_rate": 1.466875241829317e-06, "loss": 0.47456154227256775, "step": 5402 }, { "epoch": 0.7576246231508098, "grad_norm": 3.92447829246521, "learning_rate": 1.4652689610987297e-06, "loss": 0.4639177620410919, "step": 5403 }, { "epoch": 0.7577648461053075, "grad_norm": 4.62714958190918, "learning_rate": 1.4636634093135394e-06, "loss": 0.5572137832641602, "step": 5404 }, { "epoch": 0.757905069059805, "grad_norm": 3.4029929637908936, "learning_rate": 1.4620585868048425e-06, "loss": 0.4839605689048767, "step": 5405 }, { "epoch": 0.7580452920143027, "grad_norm": 4.096949100494385, "learning_rate": 1.4604544939035987e-06, "loss": 0.47831279039382935, "step": 5406 }, { "epoch": 0.7581855149688004, "grad_norm": 12.911635398864746, "learning_rate": 1.458851130940604e-06, "loss": 0.5081448554992676, "step": 5407 }, { "epoch": 0.758325737923298, "grad_norm": 2.9869956970214844, "learning_rate": 1.4572484982465124e-06, "loss": 0.49657177925109863, "step": 5408 }, { "epoch": 0.7584659608777957, "grad_norm": 3.255312204360962, "learning_rate": 1.455646596151824e-06, "loss": 0.44663357734680176, "step": 5409 }, { "epoch": 0.7586061838322934, "grad_norm": 3.6248364448547363, "learning_rate": 1.4540454249868912e-06, "loss": 0.4741276502609253, "step": 5410 }, { "epoch": 0.758746406786791, "grad_norm": 4.567689895629883, "learning_rate": 1.4524449850819088e-06, "loss": 0.5809251070022583, "step": 5411 }, { "epoch": 0.7588866297412886, "grad_norm": 5.301245212554932, "learning_rate": 1.4508452767669312e-06, "loss": 0.45844149589538574, "step": 5412 }, { "epoch": 0.7590268526957863, "grad_norm": 6.749413013458252, "learning_rate": 1.4492463003718522e-06, "loss": 0.47157788276672363, "step": 5413 }, { "epoch": 0.759167075650284, "grad_norm": 7.843869209289551, "learning_rate": 1.4476480562264195e-06, "loss": 0.4797118008136749, "step": 5414 }, { "epoch": 0.7593072986047816, "grad_norm": 8.17703628540039, "learning_rate": 1.4460505446602298e-06, "loss": 0.6062208414077759, "step": 5415 }, { "epoch": 0.7594475215592793, "grad_norm": 3.6720082759857178, "learning_rate": 1.4444537660027286e-06, "loss": 0.5103371143341064, "step": 5416 }, { "epoch": 0.7595877445137769, "grad_norm": 3.3444926738739014, "learning_rate": 1.442857720583205e-06, "loss": 0.5122965574264526, "step": 5417 }, { "epoch": 0.7597279674682745, "grad_norm": 4.056909561157227, "learning_rate": 1.441262408730808e-06, "loss": 0.5770416259765625, "step": 5418 }, { "epoch": 0.7598681904227722, "grad_norm": 2.6081767082214355, "learning_rate": 1.4396678307745243e-06, "loss": 0.5343056917190552, "step": 5419 }, { "epoch": 0.7600084133772699, "grad_norm": 4.872474670410156, "learning_rate": 1.4380739870431949e-06, "loss": 0.5468713045120239, "step": 5420 }, { "epoch": 0.7601486363317675, "grad_norm": 3.56846022605896, "learning_rate": 1.4364808778655081e-06, "loss": 0.5026087760925293, "step": 5421 }, { "epoch": 0.7602888592862651, "grad_norm": 2.72456693649292, "learning_rate": 1.4348885035700023e-06, "loss": 0.5147280693054199, "step": 5422 }, { "epoch": 0.7604290822407628, "grad_norm": 4.065577030181885, "learning_rate": 1.4332968644850587e-06, "loss": 0.5385223627090454, "step": 5423 }, { "epoch": 0.7605693051952604, "grad_norm": 3.396247625350952, "learning_rate": 1.4317059609389168e-06, "loss": 0.523823618888855, "step": 5424 }, { "epoch": 0.7607095281497581, "grad_norm": 3.822807788848877, "learning_rate": 1.4301157932596538e-06, "loss": 0.5261605978012085, "step": 5425 }, { "epoch": 0.7608497511042558, "grad_norm": 9.510333061218262, "learning_rate": 1.4285263617752022e-06, "loss": 0.6453857421875, "step": 5426 }, { "epoch": 0.7609899740587535, "grad_norm": 6.317968368530273, "learning_rate": 1.42693766681334e-06, "loss": 0.5417706370353699, "step": 5427 }, { "epoch": 0.761130197013251, "grad_norm": 4.937497615814209, "learning_rate": 1.4253497087016955e-06, "loss": 0.49108293652534485, "step": 5428 }, { "epoch": 0.7612704199677487, "grad_norm": 3.124110460281372, "learning_rate": 1.4237624877677386e-06, "loss": 0.6095849871635437, "step": 5429 }, { "epoch": 0.7614106429222464, "grad_norm": 5.500062942504883, "learning_rate": 1.4221760043387978e-06, "loss": 0.4678942561149597, "step": 5430 }, { "epoch": 0.761550865876744, "grad_norm": 2.688910961151123, "learning_rate": 1.42059025874204e-06, "loss": 0.6046544909477234, "step": 5431 }, { "epoch": 0.7616910888312417, "grad_norm": 5.007282733917236, "learning_rate": 1.4190052513044844e-06, "loss": 0.42107516527175903, "step": 5432 }, { "epoch": 0.7618313117857394, "grad_norm": 3.2445945739746094, "learning_rate": 1.4174209823529966e-06, "loss": 0.5068099498748779, "step": 5433 }, { "epoch": 0.7619715347402369, "grad_norm": 5.130105972290039, "learning_rate": 1.4158374522142915e-06, "loss": 0.5385087132453918, "step": 5434 }, { "epoch": 0.7621117576947346, "grad_norm": 5.437238693237305, "learning_rate": 1.4142546612149299e-06, "loss": 0.5032269954681396, "step": 5435 }, { "epoch": 0.7622519806492323, "grad_norm": 5.857805252075195, "learning_rate": 1.4126726096813231e-06, "loss": 0.5609952211380005, "step": 5436 }, { "epoch": 0.76239220360373, "grad_norm": 2.5317461490631104, "learning_rate": 1.4110912979397219e-06, "loss": 0.5335845947265625, "step": 5437 }, { "epoch": 0.7625324265582276, "grad_norm": 3.04911470413208, "learning_rate": 1.4095107263162372e-06, "loss": 0.4335283935070038, "step": 5438 }, { "epoch": 0.7626726495127253, "grad_norm": 8.582624435424805, "learning_rate": 1.407930895136816e-06, "loss": 0.3799934387207031, "step": 5439 }, { "epoch": 0.7628128724672228, "grad_norm": 4.196160793304443, "learning_rate": 1.406351804727258e-06, "loss": 0.5242384672164917, "step": 5440 }, { "epoch": 0.7629530954217205, "grad_norm": 3.166962146759033, "learning_rate": 1.4047734554132092e-06, "loss": 0.4504934847354889, "step": 5441 }, { "epoch": 0.7630933183762182, "grad_norm": 2.8307671546936035, "learning_rate": 1.403195847520164e-06, "loss": 0.4565044045448303, "step": 5442 }, { "epoch": 0.7632335413307159, "grad_norm": 3.477853775024414, "learning_rate": 1.4016189813734587e-06, "loss": 0.5973983407020569, "step": 5443 }, { "epoch": 0.7633737642852135, "grad_norm": 16.432790756225586, "learning_rate": 1.4000428572982855e-06, "loss": 0.509194016456604, "step": 5444 }, { "epoch": 0.7635139872397111, "grad_norm": 2.975937604904175, "learning_rate": 1.3984674756196754e-06, "loss": 0.4738222658634186, "step": 5445 }, { "epoch": 0.7636542101942088, "grad_norm": 4.220099925994873, "learning_rate": 1.3968928366625095e-06, "loss": 0.5474120378494263, "step": 5446 }, { "epoch": 0.7637944331487064, "grad_norm": 12.280937194824219, "learning_rate": 1.3953189407515172e-06, "loss": 0.48984095454216003, "step": 5447 }, { "epoch": 0.7639346561032041, "grad_norm": 3.1837613582611084, "learning_rate": 1.393745788211273e-06, "loss": 0.49865108728408813, "step": 5448 }, { "epoch": 0.7640748790577018, "grad_norm": 3.2212870121002197, "learning_rate": 1.3921733793661957e-06, "loss": 0.46342799067497253, "step": 5449 }, { "epoch": 0.7642151020121994, "grad_norm": 2.980914354324341, "learning_rate": 1.3906017145405575e-06, "loss": 0.48863062262535095, "step": 5450 }, { "epoch": 0.764355324966697, "grad_norm": 4.110128402709961, "learning_rate": 1.3890307940584697e-06, "loss": 0.5473568439483643, "step": 5451 }, { "epoch": 0.7644955479211947, "grad_norm": 3.504720687866211, "learning_rate": 1.3874606182438944e-06, "loss": 0.4458231031894684, "step": 5452 }, { "epoch": 0.7646357708756923, "grad_norm": 2.4283649921417236, "learning_rate": 1.3858911874206394e-06, "loss": 0.5277286767959595, "step": 5453 }, { "epoch": 0.76477599383019, "grad_norm": 3.1292612552642822, "learning_rate": 1.3843225019123595e-06, "loss": 0.5202140808105469, "step": 5454 }, { "epoch": 0.7649162167846877, "grad_norm": 7.77416467666626, "learning_rate": 1.382754562042551e-06, "loss": 0.6178109645843506, "step": 5455 }, { "epoch": 0.7650564397391854, "grad_norm": 4.68165397644043, "learning_rate": 1.3811873681345655e-06, "loss": 0.5701515078544617, "step": 5456 }, { "epoch": 0.7651966626936829, "grad_norm": 3.2944564819335938, "learning_rate": 1.3796209205115918e-06, "loss": 0.5636783838272095, "step": 5457 }, { "epoch": 0.7653368856481806, "grad_norm": 3.616650342941284, "learning_rate": 1.3780552194966695e-06, "loss": 0.5828505158424377, "step": 5458 }, { "epoch": 0.7654771086026783, "grad_norm": 4.630557060241699, "learning_rate": 1.3764902654126838e-06, "loss": 0.44257086515426636, "step": 5459 }, { "epoch": 0.7656173315571759, "grad_norm": 2.8684322834014893, "learning_rate": 1.3749260585823665e-06, "loss": 0.45331770181655884, "step": 5460 }, { "epoch": 0.7657575545116736, "grad_norm": 10.194046020507812, "learning_rate": 1.37336259932829e-06, "loss": 0.5113852024078369, "step": 5461 }, { "epoch": 0.7658977774661712, "grad_norm": 4.317338943481445, "learning_rate": 1.3717998879728828e-06, "loss": 0.4578872621059418, "step": 5462 }, { "epoch": 0.7660380004206688, "grad_norm": 5.610615253448486, "learning_rate": 1.3702379248384063e-06, "loss": 0.40938127040863037, "step": 5463 }, { "epoch": 0.7661782233751665, "grad_norm": 4.009368419647217, "learning_rate": 1.3686767102469812e-06, "loss": 0.5307710766792297, "step": 5464 }, { "epoch": 0.7663184463296642, "grad_norm": 4.460838317871094, "learning_rate": 1.3671162445205615e-06, "loss": 0.43893367052078247, "step": 5465 }, { "epoch": 0.7664586692841618, "grad_norm": 7.536380767822266, "learning_rate": 1.3655565279809546e-06, "loss": 0.44789421558380127, "step": 5466 }, { "epoch": 0.7665988922386595, "grad_norm": 3.2176737785339355, "learning_rate": 1.3639975609498107e-06, "loss": 0.4650822579860687, "step": 5467 }, { "epoch": 0.7667391151931571, "grad_norm": 2.8941190242767334, "learning_rate": 1.3624393437486278e-06, "loss": 0.5340743064880371, "step": 5468 }, { "epoch": 0.7668793381476547, "grad_norm": 3.0757782459259033, "learning_rate": 1.360881876698742e-06, "loss": 0.5484014749526978, "step": 5469 }, { "epoch": 0.7670195611021524, "grad_norm": 3.6530039310455322, "learning_rate": 1.3593251601213458e-06, "loss": 0.5105280876159668, "step": 5470 }, { "epoch": 0.7671597840566501, "grad_norm": 4.7397027015686035, "learning_rate": 1.3577691943374677e-06, "loss": 0.5738314986228943, "step": 5471 }, { "epoch": 0.7673000070111478, "grad_norm": 4.533836364746094, "learning_rate": 1.3562139796679857e-06, "loss": 0.509008526802063, "step": 5472 }, { "epoch": 0.7674402299656454, "grad_norm": 2.5725009441375732, "learning_rate": 1.3546595164336218e-06, "loss": 0.5225328803062439, "step": 5473 }, { "epoch": 0.767580452920143, "grad_norm": 2.900040626525879, "learning_rate": 1.3531058049549444e-06, "loss": 0.4592171311378479, "step": 5474 }, { "epoch": 0.7677206758746407, "grad_norm": 5.420522689819336, "learning_rate": 1.3515528455523619e-06, "loss": 0.4360920488834381, "step": 5475 }, { "epoch": 0.7678608988291383, "grad_norm": 2.996537208557129, "learning_rate": 1.3500006385461368e-06, "loss": 0.45755741000175476, "step": 5476 }, { "epoch": 0.768001121783636, "grad_norm": 4.311678886413574, "learning_rate": 1.3484491842563668e-06, "loss": 0.5607264041900635, "step": 5477 }, { "epoch": 0.7681413447381337, "grad_norm": 2.9399619102478027, "learning_rate": 1.3468984830030003e-06, "loss": 0.4684440791606903, "step": 5478 }, { "epoch": 0.7682815676926312, "grad_norm": 4.991541862487793, "learning_rate": 1.3453485351058277e-06, "loss": 0.48344898223876953, "step": 5479 }, { "epoch": 0.7684217906471289, "grad_norm": 2.770878553390503, "learning_rate": 1.3437993408844874e-06, "loss": 0.4113768935203552, "step": 5480 }, { "epoch": 0.7685620136016266, "grad_norm": 3.855201005935669, "learning_rate": 1.3422509006584555e-06, "loss": 0.4619283378124237, "step": 5481 }, { "epoch": 0.7687022365561242, "grad_norm": 4.477468013763428, "learning_rate": 1.3407032147470633e-06, "loss": 0.48193255066871643, "step": 5482 }, { "epoch": 0.7688424595106219, "grad_norm": 3.2066171169281006, "learning_rate": 1.339156283469475e-06, "loss": 0.5439646244049072, "step": 5483 }, { "epoch": 0.7689826824651196, "grad_norm": 4.224981784820557, "learning_rate": 1.337610107144706e-06, "loss": 0.5907684564590454, "step": 5484 }, { "epoch": 0.7691229054196171, "grad_norm": 5.289248943328857, "learning_rate": 1.336064686091616e-06, "loss": 0.45946159958839417, "step": 5485 }, { "epoch": 0.7692631283741148, "grad_norm": 6.531676292419434, "learning_rate": 1.3345200206289077e-06, "loss": 0.4802522659301758, "step": 5486 }, { "epoch": 0.7694033513286125, "grad_norm": 4.303497791290283, "learning_rate": 1.3329761110751232e-06, "loss": 0.5448279976844788, "step": 5487 }, { "epoch": 0.7695435742831102, "grad_norm": 5.099175453186035, "learning_rate": 1.3314329577486601e-06, "loss": 0.4988410174846649, "step": 5488 }, { "epoch": 0.7696837972376078, "grad_norm": 3.5818417072296143, "learning_rate": 1.329890560967748e-06, "loss": 0.5724533796310425, "step": 5489 }, { "epoch": 0.7698240201921055, "grad_norm": 6.447774887084961, "learning_rate": 1.3283489210504675e-06, "loss": 0.5490584373474121, "step": 5490 }, { "epoch": 0.7699642431466031, "grad_norm": 4.8250956535339355, "learning_rate": 1.3268080383147414e-06, "loss": 0.5030728578567505, "step": 5491 }, { "epoch": 0.7701044661011007, "grad_norm": 4.209207057952881, "learning_rate": 1.325267913078338e-06, "loss": 0.5669568777084351, "step": 5492 }, { "epoch": 0.7702446890555984, "grad_norm": 3.142711639404297, "learning_rate": 1.3237285456588623e-06, "loss": 0.47378355264663696, "step": 5493 }, { "epoch": 0.7703849120100961, "grad_norm": 6.023349285125732, "learning_rate": 1.322189936373775e-06, "loss": 0.5277107357978821, "step": 5494 }, { "epoch": 0.7705251349645937, "grad_norm": 3.0230798721313477, "learning_rate": 1.3206520855403681e-06, "loss": 0.4817233085632324, "step": 5495 }, { "epoch": 0.7706653579190914, "grad_norm": 6.675667762756348, "learning_rate": 1.319114993475788e-06, "loss": 0.549767255783081, "step": 5496 }, { "epoch": 0.770805580873589, "grad_norm": 3.0945799350738525, "learning_rate": 1.3175786604970165e-06, "loss": 0.6503909230232239, "step": 5497 }, { "epoch": 0.7709458038280866, "grad_norm": 5.776696681976318, "learning_rate": 1.3160430869208817e-06, "loss": 0.4577791094779968, "step": 5498 }, { "epoch": 0.7710860267825843, "grad_norm": 4.324331283569336, "learning_rate": 1.3145082730640564e-06, "loss": 0.566195547580719, "step": 5499 }, { "epoch": 0.771226249737082, "grad_norm": 5.3958306312561035, "learning_rate": 1.3129742192430567e-06, "loss": 0.49194544553756714, "step": 5500 }, { "epoch": 0.7713664726915797, "grad_norm": 3.5445947647094727, "learning_rate": 1.3114409257742372e-06, "loss": 0.5213779211044312, "step": 5501 }, { "epoch": 0.7715066956460772, "grad_norm": 3.845872640609741, "learning_rate": 1.3099083929738038e-06, "loss": 0.47525134682655334, "step": 5502 }, { "epoch": 0.7716469186005749, "grad_norm": 4.099419593811035, "learning_rate": 1.308376621157798e-06, "loss": 0.47312411665916443, "step": 5503 }, { "epoch": 0.7717871415550726, "grad_norm": 4.791863441467285, "learning_rate": 1.306845610642109e-06, "loss": 0.44885772466659546, "step": 5504 }, { "epoch": 0.7719273645095702, "grad_norm": 3.1832714080810547, "learning_rate": 1.3053153617424663e-06, "loss": 0.5505659580230713, "step": 5505 }, { "epoch": 0.7720675874640679, "grad_norm": 4.669753551483154, "learning_rate": 1.3037858747744464e-06, "loss": 0.5180187225341797, "step": 5506 }, { "epoch": 0.7722078104185656, "grad_norm": 7.3501386642456055, "learning_rate": 1.3022571500534603e-06, "loss": 0.6423175930976868, "step": 5507 }, { "epoch": 0.7723480333730631, "grad_norm": 3.0845224857330322, "learning_rate": 1.3007291878947736e-06, "loss": 0.5337234735488892, "step": 5508 }, { "epoch": 0.7724882563275608, "grad_norm": 4.339407920837402, "learning_rate": 1.2992019886134837e-06, "loss": 0.4666946530342102, "step": 5509 }, { "epoch": 0.7726284792820585, "grad_norm": 4.871012210845947, "learning_rate": 1.2976755525245371e-06, "loss": 0.5874906778335571, "step": 5510 }, { "epoch": 0.7727687022365561, "grad_norm": 4.460752487182617, "learning_rate": 1.2961498799427214e-06, "loss": 0.5361853241920471, "step": 5511 }, { "epoch": 0.7729089251910538, "grad_norm": 2.9082159996032715, "learning_rate": 1.2946249711826674e-06, "loss": 0.4417589008808136, "step": 5512 }, { "epoch": 0.7730491481455515, "grad_norm": 5.856065273284912, "learning_rate": 1.2931008265588435e-06, "loss": 0.5605347752571106, "step": 5513 }, { "epoch": 0.773189371100049, "grad_norm": 3.705366611480713, "learning_rate": 1.2915774463855696e-06, "loss": 0.4767119884490967, "step": 5514 }, { "epoch": 0.7733295940545467, "grad_norm": 3.5444159507751465, "learning_rate": 1.2900548309769996e-06, "loss": 0.5003343820571899, "step": 5515 }, { "epoch": 0.7734698170090444, "grad_norm": 3.5371084213256836, "learning_rate": 1.288532980647133e-06, "loss": 0.4009619951248169, "step": 5516 }, { "epoch": 0.773610039963542, "grad_norm": 5.379794597625732, "learning_rate": 1.2870118957098127e-06, "loss": 0.6183332800865173, "step": 5517 }, { "epoch": 0.7737502629180397, "grad_norm": 3.9777276515960693, "learning_rate": 1.2854915764787229e-06, "loss": 0.53545081615448, "step": 5518 }, { "epoch": 0.7738904858725373, "grad_norm": 4.376078128814697, "learning_rate": 1.2839720232673864e-06, "loss": 0.4751810133457184, "step": 5519 }, { "epoch": 0.774030708827035, "grad_norm": 5.674665927886963, "learning_rate": 1.2824532363891756e-06, "loss": 0.5143548250198364, "step": 5520 }, { "epoch": 0.7741709317815326, "grad_norm": 3.7199394702911377, "learning_rate": 1.280935216157297e-06, "loss": 0.5378553867340088, "step": 5521 }, { "epoch": 0.7743111547360303, "grad_norm": 3.4045534133911133, "learning_rate": 1.2794179628848031e-06, "loss": 0.5199840068817139, "step": 5522 }, { "epoch": 0.774451377690528, "grad_norm": 3.2343006134033203, "learning_rate": 1.2779014768845876e-06, "loss": 0.4889373183250427, "step": 5523 }, { "epoch": 0.7745916006450256, "grad_norm": 4.522576332092285, "learning_rate": 1.2763857584693867e-06, "loss": 0.44591057300567627, "step": 5524 }, { "epoch": 0.7747318235995232, "grad_norm": 5.364109039306641, "learning_rate": 1.2748708079517763e-06, "loss": 0.5572710037231445, "step": 5525 }, { "epoch": 0.7748720465540209, "grad_norm": 3.1934735774993896, "learning_rate": 1.2733566256441777e-06, "loss": 0.5524474382400513, "step": 5526 }, { "epoch": 0.7750122695085185, "grad_norm": 4.0185651779174805, "learning_rate": 1.2718432118588465e-06, "loss": 0.5095342397689819, "step": 5527 }, { "epoch": 0.7751524924630162, "grad_norm": 2.8285202980041504, "learning_rate": 1.2703305669078902e-06, "loss": 0.3832630515098572, "step": 5528 }, { "epoch": 0.7752927154175139, "grad_norm": 8.773008346557617, "learning_rate": 1.2688186911032474e-06, "loss": 0.4908062219619751, "step": 5529 }, { "epoch": 0.7754329383720115, "grad_norm": 3.005730152130127, "learning_rate": 1.2673075847567046e-06, "loss": 0.4958786368370056, "step": 5530 }, { "epoch": 0.7755731613265091, "grad_norm": 5.060556888580322, "learning_rate": 1.265797248179888e-06, "loss": 0.5552115440368652, "step": 5531 }, { "epoch": 0.7757133842810068, "grad_norm": 4.28020715713501, "learning_rate": 1.2642876816842658e-06, "loss": 0.5928817391395569, "step": 5532 }, { "epoch": 0.7758536072355044, "grad_norm": 3.6783993244171143, "learning_rate": 1.2627788855811423e-06, "loss": 0.444058895111084, "step": 5533 }, { "epoch": 0.7759938301900021, "grad_norm": 5.604609489440918, "learning_rate": 1.2612708601816725e-06, "loss": 0.5033197402954102, "step": 5534 }, { "epoch": 0.7761340531444998, "grad_norm": 3.5303497314453125, "learning_rate": 1.2597636057968437e-06, "loss": 0.5384823083877563, "step": 5535 }, { "epoch": 0.7762742760989974, "grad_norm": 3.5225534439086914, "learning_rate": 1.2582571227374879e-06, "loss": 0.4575401246547699, "step": 5536 }, { "epoch": 0.776414499053495, "grad_norm": 3.655780792236328, "learning_rate": 1.2567514113142776e-06, "loss": 0.4621257781982422, "step": 5537 }, { "epoch": 0.7765547220079927, "grad_norm": 3.6173224449157715, "learning_rate": 1.2552464718377272e-06, "loss": 0.5095463991165161, "step": 5538 }, { "epoch": 0.7766949449624904, "grad_norm": 3.935035228729248, "learning_rate": 1.2537423046181902e-06, "loss": 0.5183992385864258, "step": 5539 }, { "epoch": 0.776835167916988, "grad_norm": 3.5793070793151855, "learning_rate": 1.2522389099658626e-06, "loss": 0.46017998456954956, "step": 5540 }, { "epoch": 0.7769753908714857, "grad_norm": 3.419093608856201, "learning_rate": 1.2507362881907782e-06, "loss": 0.4355102777481079, "step": 5541 }, { "epoch": 0.7771156138259833, "grad_norm": 7.678918838500977, "learning_rate": 1.2492344396028144e-06, "loss": 0.5155071020126343, "step": 5542 }, { "epoch": 0.7772558367804809, "grad_norm": 6.343621253967285, "learning_rate": 1.2477333645116874e-06, "loss": 0.577957272529602, "step": 5543 }, { "epoch": 0.7773960597349786, "grad_norm": 3.175907850265503, "learning_rate": 1.2462330632269549e-06, "loss": 0.5445085167884827, "step": 5544 }, { "epoch": 0.7775362826894763, "grad_norm": 5.373937606811523, "learning_rate": 1.2447335360580148e-06, "loss": 0.5010883808135986, "step": 5545 }, { "epoch": 0.777676505643974, "grad_norm": 5.361566066741943, "learning_rate": 1.2432347833141062e-06, "loss": 0.5124654173851013, "step": 5546 }, { "epoch": 0.7778167285984716, "grad_norm": 5.94467306137085, "learning_rate": 1.241736805304305e-06, "loss": 0.5952273607254028, "step": 5547 }, { "epoch": 0.7779569515529692, "grad_norm": 4.904468536376953, "learning_rate": 1.2402396023375306e-06, "loss": 0.4389380216598511, "step": 5548 }, { "epoch": 0.7780971745074668, "grad_norm": 12.02411937713623, "learning_rate": 1.2387431747225426e-06, "loss": 0.409298300743103, "step": 5549 }, { "epoch": 0.7782373974619645, "grad_norm": 3.5421173572540283, "learning_rate": 1.2372475227679398e-06, "loss": 0.3974836468696594, "step": 5550 }, { "epoch": 0.7783776204164622, "grad_norm": 2.9009807109832764, "learning_rate": 1.23575264678216e-06, "loss": 0.5116097927093506, "step": 5551 }, { "epoch": 0.7785178433709599, "grad_norm": 6.983077049255371, "learning_rate": 1.2342585470734853e-06, "loss": 0.5479324460029602, "step": 5552 }, { "epoch": 0.7786580663254575, "grad_norm": 14.091809272766113, "learning_rate": 1.2327652239500288e-06, "loss": 0.46366244554519653, "step": 5553 }, { "epoch": 0.7787982892799551, "grad_norm": 3.046626567840576, "learning_rate": 1.2312726777197549e-06, "loss": 0.3864712119102478, "step": 5554 }, { "epoch": 0.7789385122344528, "grad_norm": 4.7574381828308105, "learning_rate": 1.2297809086904588e-06, "loss": 0.5104802250862122, "step": 5555 }, { "epoch": 0.7790787351889504, "grad_norm": 4.519224643707275, "learning_rate": 1.2282899171697794e-06, "loss": 0.510155439376831, "step": 5556 }, { "epoch": 0.7792189581434481, "grad_norm": 2.864807367324829, "learning_rate": 1.226799703465194e-06, "loss": 0.5355327725410461, "step": 5557 }, { "epoch": 0.7793591810979458, "grad_norm": 3.341387987136841, "learning_rate": 1.2253102678840212e-06, "loss": 0.5898638367652893, "step": 5558 }, { "epoch": 0.7794994040524433, "grad_norm": 4.789461135864258, "learning_rate": 1.2238216107334171e-06, "loss": 0.4374809265136719, "step": 5559 }, { "epoch": 0.779639627006941, "grad_norm": 2.41806697845459, "learning_rate": 1.22233373232038e-06, "loss": 0.5809847116470337, "step": 5560 }, { "epoch": 0.7797798499614387, "grad_norm": 2.901890993118286, "learning_rate": 1.220846632951742e-06, "loss": 0.4318996071815491, "step": 5561 }, { "epoch": 0.7799200729159363, "grad_norm": 4.198658466339111, "learning_rate": 1.2193603129341814e-06, "loss": 0.37796422839164734, "step": 5562 }, { "epoch": 0.780060295870434, "grad_norm": 6.600633144378662, "learning_rate": 1.2178747725742108e-06, "loss": 0.6095434427261353, "step": 5563 }, { "epoch": 0.7802005188249317, "grad_norm": 6.763312816619873, "learning_rate": 1.2163900121781851e-06, "loss": 0.5501303672790527, "step": 5564 }, { "epoch": 0.7803407417794292, "grad_norm": 5.234115123748779, "learning_rate": 1.2149060320522965e-06, "loss": 0.463702917098999, "step": 5565 }, { "epoch": 0.7804809647339269, "grad_norm": 4.8143205642700195, "learning_rate": 1.2134228325025787e-06, "loss": 0.5766538381576538, "step": 5566 }, { "epoch": 0.7806211876884246, "grad_norm": 3.6361305713653564, "learning_rate": 1.2119404138348994e-06, "loss": 0.4889659285545349, "step": 5567 }, { "epoch": 0.7807614106429223, "grad_norm": 3.8053433895111084, "learning_rate": 1.2104587763549702e-06, "loss": 0.43652862310409546, "step": 5568 }, { "epoch": 0.7809016335974199, "grad_norm": 3.6072611808776855, "learning_rate": 1.2089779203683398e-06, "loss": 0.5350742936134338, "step": 5569 }, { "epoch": 0.7810418565519176, "grad_norm": 3.1383328437805176, "learning_rate": 1.207497846180396e-06, "loss": 0.5826475620269775, "step": 5570 }, { "epoch": 0.7811820795064152, "grad_norm": 3.7483136653900146, "learning_rate": 1.2060185540963648e-06, "loss": 0.4442409574985504, "step": 5571 }, { "epoch": 0.7813223024609128, "grad_norm": 3.747150421142578, "learning_rate": 1.204540044421313e-06, "loss": 0.5648239850997925, "step": 5572 }, { "epoch": 0.7814625254154105, "grad_norm": 2.85062837600708, "learning_rate": 1.203062317460142e-06, "loss": 0.5684167742729187, "step": 5573 }, { "epoch": 0.7816027483699082, "grad_norm": 4.113885879516602, "learning_rate": 1.2015853735175948e-06, "loss": 0.4512266516685486, "step": 5574 }, { "epoch": 0.7817429713244058, "grad_norm": 3.2824127674102783, "learning_rate": 1.2001092128982523e-06, "loss": 0.5639962553977966, "step": 5575 }, { "epoch": 0.7818831942789034, "grad_norm": 4.481908798217773, "learning_rate": 1.1986338359065348e-06, "loss": 0.46210789680480957, "step": 5576 }, { "epoch": 0.7820234172334011, "grad_norm": 3.18896746635437, "learning_rate": 1.197159242846699e-06, "loss": 0.5735477209091187, "step": 5577 }, { "epoch": 0.7821636401878987, "grad_norm": 5.678673267364502, "learning_rate": 1.1956854340228408e-06, "loss": 0.477384090423584, "step": 5578 }, { "epoch": 0.7823038631423964, "grad_norm": 3.378506898880005, "learning_rate": 1.1942124097388975e-06, "loss": 0.5474092960357666, "step": 5579 }, { "epoch": 0.7824440860968941, "grad_norm": 3.3014543056488037, "learning_rate": 1.1927401702986368e-06, "loss": 0.4273033142089844, "step": 5580 }, { "epoch": 0.7825843090513918, "grad_norm": 3.465623378753662, "learning_rate": 1.1912687160056723e-06, "loss": 0.6133954524993896, "step": 5581 }, { "epoch": 0.7827245320058893, "grad_norm": 4.346191883087158, "learning_rate": 1.1897980471634528e-06, "loss": 0.5226727724075317, "step": 5582 }, { "epoch": 0.782864754960387, "grad_norm": 9.420708656311035, "learning_rate": 1.1883281640752642e-06, "loss": 0.6169708371162415, "step": 5583 }, { "epoch": 0.7830049779148847, "grad_norm": 13.188850402832031, "learning_rate": 1.1868590670442315e-06, "loss": 0.6081726551055908, "step": 5584 }, { "epoch": 0.7831452008693823, "grad_norm": 3.8271443843841553, "learning_rate": 1.185390756373318e-06, "loss": 0.43927329778671265, "step": 5585 }, { "epoch": 0.78328542382388, "grad_norm": 7.307843208312988, "learning_rate": 1.1839232323653245e-06, "loss": 0.41348111629486084, "step": 5586 }, { "epoch": 0.7834256467783777, "grad_norm": 3.540679454803467, "learning_rate": 1.1824564953228872e-06, "loss": 0.4417613446712494, "step": 5587 }, { "epoch": 0.7835658697328752, "grad_norm": 3.596773624420166, "learning_rate": 1.1809905455484838e-06, "loss": 0.4724700450897217, "step": 5588 }, { "epoch": 0.7837060926873729, "grad_norm": 3.969395160675049, "learning_rate": 1.1795253833444275e-06, "loss": 0.4694662094116211, "step": 5589 }, { "epoch": 0.7838463156418706, "grad_norm": 4.290284156799316, "learning_rate": 1.178061009012869e-06, "loss": 0.5580288171768188, "step": 5590 }, { "epoch": 0.7839865385963682, "grad_norm": 2.838430643081665, "learning_rate": 1.176597422855798e-06, "loss": 0.5527315139770508, "step": 5591 }, { "epoch": 0.7841267615508659, "grad_norm": 3.267277956008911, "learning_rate": 1.1751346251750412e-06, "loss": 0.4483565092086792, "step": 5592 }, { "epoch": 0.7842669845053635, "grad_norm": 3.861138105392456, "learning_rate": 1.17367261627226e-06, "loss": 0.469906210899353, "step": 5593 }, { "epoch": 0.7844072074598611, "grad_norm": 4.124813079833984, "learning_rate": 1.1722113964489563e-06, "loss": 0.5688005685806274, "step": 5594 }, { "epoch": 0.7845474304143588, "grad_norm": 5.365574359893799, "learning_rate": 1.1707509660064687e-06, "loss": 0.4628967046737671, "step": 5595 }, { "epoch": 0.7846876533688565, "grad_norm": 2.999410629272461, "learning_rate": 1.1692913252459726e-06, "loss": 0.49585795402526855, "step": 5596 }, { "epoch": 0.7848278763233542, "grad_norm": 3.290234327316284, "learning_rate": 1.1678324744684799e-06, "loss": 0.4083753824234009, "step": 5597 }, { "epoch": 0.7849680992778518, "grad_norm": 2.945279359817505, "learning_rate": 1.1663744139748411e-06, "loss": 0.5252976417541504, "step": 5598 }, { "epoch": 0.7851083222323494, "grad_norm": 3.2953786849975586, "learning_rate": 1.1649171440657437e-06, "loss": 0.45789963006973267, "step": 5599 }, { "epoch": 0.7852485451868471, "grad_norm": 4.14083194732666, "learning_rate": 1.1634606650417084e-06, "loss": 0.5124430060386658, "step": 5600 }, { "epoch": 0.7853887681413447, "grad_norm": 4.551009178161621, "learning_rate": 1.1620049772030978e-06, "loss": 0.42173221707344055, "step": 5601 }, { "epoch": 0.7855289910958424, "grad_norm": 3.809446334838867, "learning_rate": 1.1605500808501087e-06, "loss": 0.4452342391014099, "step": 5602 }, { "epoch": 0.7856692140503401, "grad_norm": 3.54581880569458, "learning_rate": 1.1590959762827752e-06, "loss": 0.49235835671424866, "step": 5603 }, { "epoch": 0.7858094370048377, "grad_norm": 3.09023380279541, "learning_rate": 1.1576426638009685e-06, "loss": 0.4989256262779236, "step": 5604 }, { "epoch": 0.7859496599593353, "grad_norm": 2.5937764644622803, "learning_rate": 1.1561901437043976e-06, "loss": 0.498602032661438, "step": 5605 }, { "epoch": 0.786089882913833, "grad_norm": 3.80622935295105, "learning_rate": 1.1547384162926035e-06, "loss": 0.5084095001220703, "step": 5606 }, { "epoch": 0.7862301058683306, "grad_norm": 2.7746479511260986, "learning_rate": 1.153287481864968e-06, "loss": 0.48227202892303467, "step": 5607 }, { "epoch": 0.7863703288228283, "grad_norm": 5.737461566925049, "learning_rate": 1.151837340720709e-06, "loss": 0.48625648021698, "step": 5608 }, { "epoch": 0.786510551777326, "grad_norm": 3.563575029373169, "learning_rate": 1.150387993158879e-06, "loss": 0.4916036128997803, "step": 5609 }, { "epoch": 0.7866507747318237, "grad_norm": 4.153385162353516, "learning_rate": 1.1489394394783688e-06, "loss": 0.5038931369781494, "step": 5610 }, { "epoch": 0.7867909976863212, "grad_norm": 6.376258850097656, "learning_rate": 1.147491679977904e-06, "loss": 0.5249996185302734, "step": 5611 }, { "epoch": 0.7869312206408189, "grad_norm": 3.6186306476593018, "learning_rate": 1.1460447149560483e-06, "loss": 0.5287349820137024, "step": 5612 }, { "epoch": 0.7870714435953166, "grad_norm": 3.5120365619659424, "learning_rate": 1.1445985447111973e-06, "loss": 0.3952568769454956, "step": 5613 }, { "epoch": 0.7872116665498142, "grad_norm": 5.026336669921875, "learning_rate": 1.1431531695415875e-06, "loss": 0.49344778060913086, "step": 5614 }, { "epoch": 0.7873518895043119, "grad_norm": 4.526983737945557, "learning_rate": 1.1417085897452896e-06, "loss": 0.5252147912979126, "step": 5615 }, { "epoch": 0.7874921124588095, "grad_norm": 2.31546950340271, "learning_rate": 1.1402648056202098e-06, "loss": 0.4732339680194855, "step": 5616 }, { "epoch": 0.7876323354133071, "grad_norm": 9.275444984436035, "learning_rate": 1.1388218174640909e-06, "loss": 0.5671165585517883, "step": 5617 }, { "epoch": 0.7877725583678048, "grad_norm": 3.8546457290649414, "learning_rate": 1.1373796255745111e-06, "loss": 0.4734238386154175, "step": 5618 }, { "epoch": 0.7879127813223025, "grad_norm": 4.466890335083008, "learning_rate": 1.1359382302488858e-06, "loss": 0.5740751028060913, "step": 5619 }, { "epoch": 0.7880530042768001, "grad_norm": 5.10459041595459, "learning_rate": 1.1344976317844631e-06, "loss": 0.4509677290916443, "step": 5620 }, { "epoch": 0.7881932272312978, "grad_norm": 4.365662097930908, "learning_rate": 1.1330578304783285e-06, "loss": 0.48924723267555237, "step": 5621 }, { "epoch": 0.7883334501857954, "grad_norm": 5.002971172332764, "learning_rate": 1.1316188266274043e-06, "loss": 0.4730234146118164, "step": 5622 }, { "epoch": 0.788473673140293, "grad_norm": 5.0916361808776855, "learning_rate": 1.1301806205284465e-06, "loss": 0.6447902917861938, "step": 5623 }, { "epoch": 0.7886138960947907, "grad_norm": 4.075820446014404, "learning_rate": 1.1287432124780478e-06, "loss": 0.6102229356765747, "step": 5624 }, { "epoch": 0.7887541190492884, "grad_norm": 2.5811471939086914, "learning_rate": 1.127306602772637e-06, "loss": 0.4029887616634369, "step": 5625 }, { "epoch": 0.788894342003786, "grad_norm": 2.809501886367798, "learning_rate": 1.125870791708475e-06, "loss": 0.46367257833480835, "step": 5626 }, { "epoch": 0.7890345649582837, "grad_norm": 3.4107651710510254, "learning_rate": 1.1244357795816601e-06, "loss": 0.5997150540351868, "step": 5627 }, { "epoch": 0.7891747879127813, "grad_norm": 3.2797060012817383, "learning_rate": 1.1230015666881273e-06, "loss": 0.488552451133728, "step": 5628 }, { "epoch": 0.789315010867279, "grad_norm": 2.9404537677764893, "learning_rate": 1.1215681533236445e-06, "loss": 0.49039533734321594, "step": 5629 }, { "epoch": 0.7894552338217766, "grad_norm": 4.719537734985352, "learning_rate": 1.1201355397838158e-06, "loss": 0.5618080496788025, "step": 5630 }, { "epoch": 0.7895954567762743, "grad_norm": 4.240618705749512, "learning_rate": 1.1187037263640816e-06, "loss": 0.5517085194587708, "step": 5631 }, { "epoch": 0.789735679730772, "grad_norm": 3.4920239448547363, "learning_rate": 1.1172727133597121e-06, "loss": 0.5336120128631592, "step": 5632 }, { "epoch": 0.7898759026852695, "grad_norm": 3.5660338401794434, "learning_rate": 1.1158425010658192e-06, "loss": 0.500105619430542, "step": 5633 }, { "epoch": 0.7900161256397672, "grad_norm": 3.2389769554138184, "learning_rate": 1.1144130897773448e-06, "loss": 0.5429204702377319, "step": 5634 }, { "epoch": 0.7901563485942649, "grad_norm": 6.896806240081787, "learning_rate": 1.1129844797890687e-06, "loss": 0.5226645469665527, "step": 5635 }, { "epoch": 0.7902965715487625, "grad_norm": 4.236081123352051, "learning_rate": 1.111556671395604e-06, "loss": 0.48718371987342834, "step": 5636 }, { "epoch": 0.7904367945032602, "grad_norm": 6.06821870803833, "learning_rate": 1.110129664891399e-06, "loss": 0.5850547552108765, "step": 5637 }, { "epoch": 0.7905770174577579, "grad_norm": 4.438521862030029, "learning_rate": 1.1087034605707337e-06, "loss": 0.4624471366405487, "step": 5638 }, { "epoch": 0.7907172404122554, "grad_norm": 3.787689208984375, "learning_rate": 1.1072780587277294e-06, "loss": 0.6468764543533325, "step": 5639 }, { "epoch": 0.7908574633667531, "grad_norm": 5.506429195404053, "learning_rate": 1.1058534596563348e-06, "loss": 0.5353031754493713, "step": 5640 }, { "epoch": 0.7909976863212508, "grad_norm": 9.948488235473633, "learning_rate": 1.1044296636503365e-06, "loss": 0.5146392583847046, "step": 5641 }, { "epoch": 0.7911379092757485, "grad_norm": 3.532742738723755, "learning_rate": 1.1030066710033555e-06, "loss": 0.582490861415863, "step": 5642 }, { "epoch": 0.7912781322302461, "grad_norm": 2.552131175994873, "learning_rate": 1.1015844820088466e-06, "loss": 0.5134840607643127, "step": 5643 }, { "epoch": 0.7914183551847438, "grad_norm": 6.117297172546387, "learning_rate": 1.1001630969600985e-06, "loss": 0.5569385290145874, "step": 5644 }, { "epoch": 0.7915585781392414, "grad_norm": 4.208003997802734, "learning_rate": 1.0987425161502364e-06, "loss": 0.4690074324607849, "step": 5645 }, { "epoch": 0.791698801093739, "grad_norm": 2.993556499481201, "learning_rate": 1.0973227398722147e-06, "loss": 0.4895402789115906, "step": 5646 }, { "epoch": 0.7918390240482367, "grad_norm": 3.871934652328491, "learning_rate": 1.0959037684188267e-06, "loss": 0.458131343126297, "step": 5647 }, { "epoch": 0.7919792470027344, "grad_norm": 4.857285499572754, "learning_rate": 1.0944856020826977e-06, "loss": 0.5867763161659241, "step": 5648 }, { "epoch": 0.792119469957232, "grad_norm": 6.931204795837402, "learning_rate": 1.0930682411562872e-06, "loss": 0.4611167311668396, "step": 5649 }, { "epoch": 0.7922596929117296, "grad_norm": 2.712252140045166, "learning_rate": 1.0916516859318887e-06, "loss": 0.5137129426002502, "step": 5650 }, { "epoch": 0.7923999158662273, "grad_norm": 4.555152893066406, "learning_rate": 1.0902359367016307e-06, "loss": 0.5359027981758118, "step": 5651 }, { "epoch": 0.7925401388207249, "grad_norm": 7.563233375549316, "learning_rate": 1.0888209937574722e-06, "loss": 0.5668007731437683, "step": 5652 }, { "epoch": 0.7926803617752226, "grad_norm": 7.446235656738281, "learning_rate": 1.0874068573912083e-06, "loss": 0.5471251010894775, "step": 5653 }, { "epoch": 0.7928205847297203, "grad_norm": 2.976409435272217, "learning_rate": 1.0859935278944683e-06, "loss": 0.49558499455451965, "step": 5654 }, { "epoch": 0.792960807684218, "grad_norm": 5.750307083129883, "learning_rate": 1.0845810055587141e-06, "loss": 0.6105446219444275, "step": 5655 }, { "epoch": 0.7931010306387155, "grad_norm": 3.507270574569702, "learning_rate": 1.0831692906752412e-06, "loss": 0.47974613308906555, "step": 5656 }, { "epoch": 0.7932412535932132, "grad_norm": 4.280689716339111, "learning_rate": 1.0817583835351803e-06, "loss": 0.5460109114646912, "step": 5657 }, { "epoch": 0.7933814765477109, "grad_norm": 3.118591070175171, "learning_rate": 1.0803482844294894e-06, "loss": 0.5407853126525879, "step": 5658 }, { "epoch": 0.7935216995022085, "grad_norm": 3.5917787551879883, "learning_rate": 1.0789389936489702e-06, "loss": 0.48255249857902527, "step": 5659 }, { "epoch": 0.7936619224567062, "grad_norm": 2.7563369274139404, "learning_rate": 1.0775305114842471e-06, "loss": 0.5554859638214111, "step": 5660 }, { "epoch": 0.7938021454112039, "grad_norm": 6.99647331237793, "learning_rate": 1.0761228382257849e-06, "loss": 0.5523315668106079, "step": 5661 }, { "epoch": 0.7939423683657014, "grad_norm": 4.301548480987549, "learning_rate": 1.074715974163879e-06, "loss": 0.44821661710739136, "step": 5662 }, { "epoch": 0.7940825913201991, "grad_norm": 4.407712459564209, "learning_rate": 1.0733099195886594e-06, "loss": 0.4259008467197418, "step": 5663 }, { "epoch": 0.7942228142746968, "grad_norm": 2.5108306407928467, "learning_rate": 1.071904674790083e-06, "loss": 0.47252774238586426, "step": 5664 }, { "epoch": 0.7943630372291944, "grad_norm": 7.932316780090332, "learning_rate": 1.0705002400579512e-06, "loss": 0.5002560615539551, "step": 5665 }, { "epoch": 0.7945032601836921, "grad_norm": 3.5532352924346924, "learning_rate": 1.0690966156818871e-06, "loss": 0.46890178322792053, "step": 5666 }, { "epoch": 0.7946434831381898, "grad_norm": 4.348692893981934, "learning_rate": 1.0676938019513533e-06, "loss": 0.5087234973907471, "step": 5667 }, { "epoch": 0.7947837060926873, "grad_norm": 5.315518379211426, "learning_rate": 1.0662917991556426e-06, "loss": 0.393376886844635, "step": 5668 }, { "epoch": 0.794923929047185, "grad_norm": 3.173978090286255, "learning_rate": 1.0648906075838828e-06, "loss": 0.4103110730648041, "step": 5669 }, { "epoch": 0.7950641520016827, "grad_norm": 3.176790952682495, "learning_rate": 1.0634902275250286e-06, "loss": 0.4170130491256714, "step": 5670 }, { "epoch": 0.7952043749561803, "grad_norm": 3.569758892059326, "learning_rate": 1.0620906592678776e-06, "loss": 0.49931252002716064, "step": 5671 }, { "epoch": 0.795344597910678, "grad_norm": 4.167292594909668, "learning_rate": 1.0606919031010494e-06, "loss": 0.46714872121810913, "step": 5672 }, { "epoch": 0.7954848208651756, "grad_norm": 3.1085522174835205, "learning_rate": 1.059293959313002e-06, "loss": 0.44043558835983276, "step": 5673 }, { "epoch": 0.7956250438196732, "grad_norm": 3.4586193561553955, "learning_rate": 1.057896828192025e-06, "loss": 0.5391794443130493, "step": 5674 }, { "epoch": 0.7957652667741709, "grad_norm": 3.233166456222534, "learning_rate": 1.0565005100262393e-06, "loss": 0.42749327421188354, "step": 5675 }, { "epoch": 0.7959054897286686, "grad_norm": 3.478832960128784, "learning_rate": 1.0551050051035995e-06, "loss": 0.47224748134613037, "step": 5676 }, { "epoch": 0.7960457126831663, "grad_norm": 3.5235679149627686, "learning_rate": 1.0537103137118927e-06, "loss": 0.5431873798370361, "step": 5677 }, { "epoch": 0.7961859356376639, "grad_norm": 3.3784432411193848, "learning_rate": 1.0523164361387338e-06, "loss": 0.5818687677383423, "step": 5678 }, { "epoch": 0.7963261585921615, "grad_norm": 3.669964075088501, "learning_rate": 1.0509233726715784e-06, "loss": 0.46289920806884766, "step": 5679 }, { "epoch": 0.7964663815466592, "grad_norm": 4.4696807861328125, "learning_rate": 1.0495311235977056e-06, "loss": 0.4543013572692871, "step": 5680 }, { "epoch": 0.7966066045011568, "grad_norm": 2.8901984691619873, "learning_rate": 1.0481396892042311e-06, "loss": 0.6273643374443054, "step": 5681 }, { "epoch": 0.7967468274556545, "grad_norm": 4.551358222961426, "learning_rate": 1.046749069778102e-06, "loss": 0.5254702568054199, "step": 5682 }, { "epoch": 0.7968870504101522, "grad_norm": 3.9519264698028564, "learning_rate": 1.045359265606098e-06, "loss": 0.5110238194465637, "step": 5683 }, { "epoch": 0.7970272733646498, "grad_norm": 4.055774211883545, "learning_rate": 1.0439702769748261e-06, "loss": 0.5008425712585449, "step": 5684 }, { "epoch": 0.7971674963191474, "grad_norm": 4.43303108215332, "learning_rate": 1.042582104170734e-06, "loss": 0.5812910795211792, "step": 5685 }, { "epoch": 0.7973077192736451, "grad_norm": 4.3639302253723145, "learning_rate": 1.041194747480091e-06, "loss": 0.5210667848587036, "step": 5686 }, { "epoch": 0.7974479422281427, "grad_norm": 3.563199520111084, "learning_rate": 1.0398082071890059e-06, "loss": 0.4990828037261963, "step": 5687 }, { "epoch": 0.7975881651826404, "grad_norm": 3.423027276992798, "learning_rate": 1.0384224835834145e-06, "loss": 0.4042571783065796, "step": 5688 }, { "epoch": 0.7977283881371381, "grad_norm": 3.439558267593384, "learning_rate": 1.037037576949088e-06, "loss": 0.5173017978668213, "step": 5689 }, { "epoch": 0.7978686110916356, "grad_norm": 2.4706685543060303, "learning_rate": 1.0356534875716234e-06, "loss": 0.43622031807899475, "step": 5690 }, { "epoch": 0.7980088340461333, "grad_norm": 4.044893741607666, "learning_rate": 1.0342702157364581e-06, "loss": 0.47303470969200134, "step": 5691 }, { "epoch": 0.798149057000631, "grad_norm": 2.9670698642730713, "learning_rate": 1.0328877617288507e-06, "loss": 0.49020785093307495, "step": 5692 }, { "epoch": 0.7982892799551287, "grad_norm": 2.990525245666504, "learning_rate": 1.0315061258338977e-06, "loss": 0.4867844581604004, "step": 5693 }, { "epoch": 0.7984295029096263, "grad_norm": 3.2001097202301025, "learning_rate": 1.0301253083365253e-06, "loss": 0.5218053460121155, "step": 5694 }, { "epoch": 0.798569725864124, "grad_norm": 3.716290235519409, "learning_rate": 1.0287453095214923e-06, "loss": 0.46048879623413086, "step": 5695 }, { "epoch": 0.7987099488186216, "grad_norm": 5.044041156768799, "learning_rate": 1.0273661296733833e-06, "loss": 0.5276979207992554, "step": 5696 }, { "epoch": 0.7988501717731192, "grad_norm": 4.743199348449707, "learning_rate": 1.0259877690766228e-06, "loss": 0.5411728024482727, "step": 5697 }, { "epoch": 0.7989903947276169, "grad_norm": 9.5782470703125, "learning_rate": 1.0246102280154574e-06, "loss": 0.4904246926307678, "step": 5698 }, { "epoch": 0.7991306176821146, "grad_norm": 2.856027841567993, "learning_rate": 1.0232335067739706e-06, "loss": 0.5332937836647034, "step": 5699 }, { "epoch": 0.7992708406366122, "grad_norm": 3.0783445835113525, "learning_rate": 1.0218576056360751e-06, "loss": 0.5220592021942139, "step": 5700 }, { "epoch": 0.7994110635911099, "grad_norm": 2.929241418838501, "learning_rate": 1.0204825248855132e-06, "loss": 0.5068267583847046, "step": 5701 }, { "epoch": 0.7995512865456075, "grad_norm": 3.338740587234497, "learning_rate": 1.0191082648058604e-06, "loss": 0.5943942070007324, "step": 5702 }, { "epoch": 0.7996915095001051, "grad_norm": 6.985385417938232, "learning_rate": 1.0177348256805226e-06, "loss": 0.5000467300415039, "step": 5703 }, { "epoch": 0.7998317324546028, "grad_norm": 2.835848569869995, "learning_rate": 1.0163622077927315e-06, "loss": 0.4906807243824005, "step": 5704 }, { "epoch": 0.7999719554091005, "grad_norm": 3.056872844696045, "learning_rate": 1.0149904114255587e-06, "loss": 0.513503909111023, "step": 5705 }, { "epoch": 0.8001121783635982, "grad_norm": 4.129247665405273, "learning_rate": 1.0136194368618979e-06, "loss": 0.5341487526893616, "step": 5706 }, { "epoch": 0.8002524013180957, "grad_norm": 2.9561004638671875, "learning_rate": 1.0122492843844766e-06, "loss": 0.44980621337890625, "step": 5707 }, { "epoch": 0.8003926242725934, "grad_norm": 6.730866432189941, "learning_rate": 1.0108799542758535e-06, "loss": 0.5215334892272949, "step": 5708 }, { "epoch": 0.8005328472270911, "grad_norm": 3.2053027153015137, "learning_rate": 1.0095114468184185e-06, "loss": 0.4678722620010376, "step": 5709 }, { "epoch": 0.8006730701815887, "grad_norm": 4.403494834899902, "learning_rate": 1.0081437622943864e-06, "loss": 0.5052769184112549, "step": 5710 }, { "epoch": 0.8008132931360864, "grad_norm": 3.6315412521362305, "learning_rate": 1.0067769009858103e-06, "loss": 0.5302640199661255, "step": 5711 }, { "epoch": 0.8009535160905841, "grad_norm": 3.277771472930908, "learning_rate": 1.0054108631745668e-06, "loss": 0.5221908688545227, "step": 5712 }, { "epoch": 0.8010937390450816, "grad_norm": 3.567652702331543, "learning_rate": 1.004045649142366e-06, "loss": 0.4592962861061096, "step": 5713 }, { "epoch": 0.8012339619995793, "grad_norm": 10.3612060546875, "learning_rate": 1.0026812591707475e-06, "loss": 0.5096999406814575, "step": 5714 }, { "epoch": 0.801374184954077, "grad_norm": 4.3858842849731445, "learning_rate": 1.0013176935410823e-06, "loss": 0.5660616159439087, "step": 5715 }, { "epoch": 0.8015144079085746, "grad_norm": 3.0004444122314453, "learning_rate": 9.99954952534566e-07, "loss": 0.5594584941864014, "step": 5716 }, { "epoch": 0.8016546308630723, "grad_norm": 7.910536289215088, "learning_rate": 9.985930364322333e-07, "loss": 0.5066565275192261, "step": 5717 }, { "epoch": 0.80179485381757, "grad_norm": 3.073329448699951, "learning_rate": 9.972319455149398e-07, "loss": 0.5306826829910278, "step": 5718 }, { "epoch": 0.8019350767720675, "grad_norm": 8.543931007385254, "learning_rate": 9.958716800633761e-07, "loss": 0.5510400533676147, "step": 5719 }, { "epoch": 0.8020752997265652, "grad_norm": 3.0004498958587646, "learning_rate": 9.945122403580608e-07, "loss": 0.5125521421432495, "step": 5720 }, { "epoch": 0.8022155226810629, "grad_norm": 3.710792064666748, "learning_rate": 9.931536266793446e-07, "loss": 0.35200241208076477, "step": 5721 }, { "epoch": 0.8023557456355606, "grad_norm": 4.990890026092529, "learning_rate": 9.917958393074012e-07, "loss": 0.6148022413253784, "step": 5722 }, { "epoch": 0.8024959685900582, "grad_norm": 4.501741886138916, "learning_rate": 9.904388785222446e-07, "loss": 0.5015209913253784, "step": 5723 }, { "epoch": 0.8026361915445559, "grad_norm": 5.122290134429932, "learning_rate": 9.890827446037078e-07, "loss": 0.47283732891082764, "step": 5724 }, { "epoch": 0.8027764144990535, "grad_norm": 4.622465133666992, "learning_rate": 9.87727437831459e-07, "loss": 0.5217185020446777, "step": 5725 }, { "epoch": 0.8029166374535511, "grad_norm": 2.23827862739563, "learning_rate": 9.863729584849945e-07, "loss": 0.48823976516723633, "step": 5726 }, { "epoch": 0.8030568604080488, "grad_norm": 2.642929792404175, "learning_rate": 9.850193068436425e-07, "loss": 0.5512871742248535, "step": 5727 }, { "epoch": 0.8031970833625465, "grad_norm": 5.68960428237915, "learning_rate": 9.836664831865527e-07, "loss": 0.5757427215576172, "step": 5728 }, { "epoch": 0.8033373063170441, "grad_norm": 4.11336088180542, "learning_rate": 9.82314487792716e-07, "loss": 0.4410785138607025, "step": 5729 }, { "epoch": 0.8034775292715417, "grad_norm": 6.2421112060546875, "learning_rate": 9.809633209409392e-07, "loss": 0.48968762159347534, "step": 5730 }, { "epoch": 0.8036177522260394, "grad_norm": 3.295600414276123, "learning_rate": 9.796129829098716e-07, "loss": 0.5922057628631592, "step": 5731 }, { "epoch": 0.803757975180537, "grad_norm": 2.8870692253112793, "learning_rate": 9.782634739779806e-07, "loss": 0.47397381067276, "step": 5732 }, { "epoch": 0.8038981981350347, "grad_norm": 5.965795516967773, "learning_rate": 9.769147944235673e-07, "loss": 0.5685539841651917, "step": 5733 }, { "epoch": 0.8040384210895324, "grad_norm": 4.4657793045043945, "learning_rate": 9.75566944524763e-07, "loss": 0.5912625193595886, "step": 5734 }, { "epoch": 0.80417864404403, "grad_norm": 4.007176399230957, "learning_rate": 9.742199245595269e-07, "loss": 0.45129871368408203, "step": 5735 }, { "epoch": 0.8043188669985276, "grad_norm": 3.465372085571289, "learning_rate": 9.728737348056417e-07, "loss": 0.4485686719417572, "step": 5736 }, { "epoch": 0.8044590899530253, "grad_norm": 3.0342116355895996, "learning_rate": 9.7152837554073e-07, "loss": 0.4817284345626831, "step": 5737 }, { "epoch": 0.804599312907523, "grad_norm": 9.70203685760498, "learning_rate": 9.70183847042233e-07, "loss": 0.48004433512687683, "step": 5738 }, { "epoch": 0.8047395358620206, "grad_norm": 3.381883144378662, "learning_rate": 9.68840149587425e-07, "loss": 0.5052961707115173, "step": 5739 }, { "epoch": 0.8048797588165183, "grad_norm": 3.3669631481170654, "learning_rate": 9.674972834534085e-07, "loss": 0.5373441576957703, "step": 5740 }, { "epoch": 0.805019981771016, "grad_norm": 5.189634323120117, "learning_rate": 9.661552489171156e-07, "loss": 0.45571523904800415, "step": 5741 }, { "epoch": 0.8051602047255135, "grad_norm": 2.72300124168396, "learning_rate": 9.648140462553019e-07, "loss": 0.42847853899002075, "step": 5742 }, { "epoch": 0.8053004276800112, "grad_norm": 3.069897413253784, "learning_rate": 9.634736757445607e-07, "loss": 0.5144776105880737, "step": 5743 }, { "epoch": 0.8054406506345089, "grad_norm": 3.2954845428466797, "learning_rate": 9.62134137661303e-07, "loss": 0.5109180808067322, "step": 5744 }, { "epoch": 0.8055808735890065, "grad_norm": 3.739110231399536, "learning_rate": 9.607954322817764e-07, "loss": 0.514777660369873, "step": 5745 }, { "epoch": 0.8057210965435042, "grad_norm": 4.240675449371338, "learning_rate": 9.594575598820527e-07, "loss": 0.5181026458740234, "step": 5746 }, { "epoch": 0.8058613194980018, "grad_norm": 6.065382957458496, "learning_rate": 9.581205207380345e-07, "loss": 0.43513280153274536, "step": 5747 }, { "epoch": 0.8060015424524994, "grad_norm": 4.094630718231201, "learning_rate": 9.56784315125447e-07, "loss": 0.5736830234527588, "step": 5748 }, { "epoch": 0.8061417654069971, "grad_norm": 4.875075817108154, "learning_rate": 9.554489433198521e-07, "loss": 0.5753277540206909, "step": 5749 }, { "epoch": 0.8062819883614948, "grad_norm": 10.938858032226562, "learning_rate": 9.541144055966328e-07, "loss": 0.45875173807144165, "step": 5750 }, { "epoch": 0.8064222113159925, "grad_norm": 3.359041929244995, "learning_rate": 9.527807022310021e-07, "loss": 0.5094566345214844, "step": 5751 }, { "epoch": 0.8065624342704901, "grad_norm": 4.03774356842041, "learning_rate": 9.514478334980021e-07, "loss": 0.5389789342880249, "step": 5752 }, { "epoch": 0.8067026572249877, "grad_norm": 4.000384330749512, "learning_rate": 9.50115799672503e-07, "loss": 0.5312457084655762, "step": 5753 }, { "epoch": 0.8068428801794854, "grad_norm": 3.218630313873291, "learning_rate": 9.487846010291985e-07, "loss": 0.5164490938186646, "step": 5754 }, { "epoch": 0.806983103133983, "grad_norm": 4.961698055267334, "learning_rate": 9.474542378426171e-07, "loss": 0.4611823856830597, "step": 5755 }, { "epoch": 0.8071233260884807, "grad_norm": 5.699065685272217, "learning_rate": 9.461247103871091e-07, "loss": 0.4845970869064331, "step": 5756 }, { "epoch": 0.8072635490429784, "grad_norm": 4.258228302001953, "learning_rate": 9.447960189368549e-07, "loss": 0.45152828097343445, "step": 5757 }, { "epoch": 0.807403771997476, "grad_norm": 3.3474020957946777, "learning_rate": 9.434681637658622e-07, "loss": 0.4555373191833496, "step": 5758 }, { "epoch": 0.8075439949519736, "grad_norm": 3.082421064376831, "learning_rate": 9.421411451479662e-07, "loss": 0.5124186873435974, "step": 5759 }, { "epoch": 0.8076842179064713, "grad_norm": 3.6178390979766846, "learning_rate": 9.408149633568303e-07, "loss": 0.4729709029197693, "step": 5760 }, { "epoch": 0.8078244408609689, "grad_norm": 3.0470142364501953, "learning_rate": 9.394896186659452e-07, "loss": 0.5171676278114319, "step": 5761 }, { "epoch": 0.8079646638154666, "grad_norm": 2.888819932937622, "learning_rate": 9.38165111348625e-07, "loss": 0.591073751449585, "step": 5762 }, { "epoch": 0.8081048867699643, "grad_norm": 3.0377421379089355, "learning_rate": 9.368414416780191e-07, "loss": 0.514680027961731, "step": 5763 }, { "epoch": 0.8082451097244618, "grad_norm": 7.661496639251709, "learning_rate": 9.355186099270963e-07, "loss": 0.5009703636169434, "step": 5764 }, { "epoch": 0.8083853326789595, "grad_norm": 3.5028793811798096, "learning_rate": 9.341966163686572e-07, "loss": 0.5019195079803467, "step": 5765 }, { "epoch": 0.8085255556334572, "grad_norm": 9.608116149902344, "learning_rate": 9.328754612753277e-07, "loss": 0.5511948466300964, "step": 5766 }, { "epoch": 0.8086657785879549, "grad_norm": 2.8821794986724854, "learning_rate": 9.315551449195631e-07, "loss": 0.5961707234382629, "step": 5767 }, { "epoch": 0.8088060015424525, "grad_norm": 5.157524585723877, "learning_rate": 9.302356675736401e-07, "loss": 0.5540668964385986, "step": 5768 }, { "epoch": 0.8089462244969502, "grad_norm": 4.161945343017578, "learning_rate": 9.289170295096711e-07, "loss": 0.5674068927764893, "step": 5769 }, { "epoch": 0.8090864474514478, "grad_norm": 4.41325044631958, "learning_rate": 9.275992309995863e-07, "loss": 0.5544673204421997, "step": 5770 }, { "epoch": 0.8092266704059454, "grad_norm": 5.756954669952393, "learning_rate": 9.262822723151493e-07, "loss": 0.4635733366012573, "step": 5771 }, { "epoch": 0.8093668933604431, "grad_norm": 2.9624035358428955, "learning_rate": 9.249661537279475e-07, "loss": 0.49230116605758667, "step": 5772 }, { "epoch": 0.8095071163149408, "grad_norm": 5.182456970214844, "learning_rate": 9.236508755093976e-07, "loss": 0.5006545782089233, "step": 5773 }, { "epoch": 0.8096473392694384, "grad_norm": 3.0584805011749268, "learning_rate": 9.22336437930737e-07, "loss": 0.5330756306648254, "step": 5774 }, { "epoch": 0.8097875622239361, "grad_norm": 3.78623366355896, "learning_rate": 9.210228412630385e-07, "loss": 0.43467193841934204, "step": 5775 }, { "epoch": 0.8099277851784337, "grad_norm": 4.125974655151367, "learning_rate": 9.19710085777194e-07, "loss": 0.45098844170570374, "step": 5776 }, { "epoch": 0.8100680081329313, "grad_norm": 3.1431076526641846, "learning_rate": 9.183981717439255e-07, "loss": 0.4840611219406128, "step": 5777 }, { "epoch": 0.810208231087429, "grad_norm": 3.1831374168395996, "learning_rate": 9.17087099433781e-07, "loss": 0.463085800409317, "step": 5778 }, { "epoch": 0.8103484540419267, "grad_norm": 4.189062118530273, "learning_rate": 9.157768691171364e-07, "loss": 0.5238777995109558, "step": 5779 }, { "epoch": 0.8104886769964244, "grad_norm": 4.511083602905273, "learning_rate": 9.144674810641879e-07, "loss": 0.5535401105880737, "step": 5780 }, { "epoch": 0.8106288999509219, "grad_norm": 3.675607204437256, "learning_rate": 9.131589355449671e-07, "loss": 0.37911638617515564, "step": 5781 }, { "epoch": 0.8107691229054196, "grad_norm": 19.759119033813477, "learning_rate": 9.118512328293244e-07, "loss": 0.4455983638763428, "step": 5782 }, { "epoch": 0.8109093458599173, "grad_norm": 3.480304479598999, "learning_rate": 9.105443731869396e-07, "loss": 0.5088881850242615, "step": 5783 }, { "epoch": 0.8110495688144149, "grad_norm": 3.7447104454040527, "learning_rate": 9.092383568873181e-07, "loss": 0.5739526152610779, "step": 5784 }, { "epoch": 0.8111897917689126, "grad_norm": 6.559942722320557, "learning_rate": 9.07933184199793e-07, "loss": 0.5070163011550903, "step": 5785 }, { "epoch": 0.8113300147234103, "grad_norm": 6.803424835205078, "learning_rate": 9.066288553935182e-07, "loss": 0.508262574672699, "step": 5786 }, { "epoch": 0.8114702376779078, "grad_norm": 2.607353925704956, "learning_rate": 9.053253707374821e-07, "loss": 0.5324686765670776, "step": 5787 }, { "epoch": 0.8116104606324055, "grad_norm": 3.3300178050994873, "learning_rate": 9.040227305004894e-07, "loss": 0.5120211839675903, "step": 5788 }, { "epoch": 0.8117506835869032, "grad_norm": 6.819944858551025, "learning_rate": 9.027209349511801e-07, "loss": 0.47023850679397583, "step": 5789 }, { "epoch": 0.8118909065414008, "grad_norm": 4.085634708404541, "learning_rate": 9.014199843580112e-07, "loss": 0.5651723146438599, "step": 5790 }, { "epoch": 0.8120311294958985, "grad_norm": 3.051199436187744, "learning_rate": 9.001198789892718e-07, "loss": 0.47931140661239624, "step": 5791 }, { "epoch": 0.8121713524503962, "grad_norm": 7.125499725341797, "learning_rate": 8.988206191130738e-07, "loss": 0.49611300230026245, "step": 5792 }, { "epoch": 0.8123115754048937, "grad_norm": 4.231937885284424, "learning_rate": 8.97522204997357e-07, "loss": 0.5563002824783325, "step": 5793 }, { "epoch": 0.8124517983593914, "grad_norm": 3.9649996757507324, "learning_rate": 8.962246369098809e-07, "loss": 0.4629974663257599, "step": 5794 }, { "epoch": 0.8125920213138891, "grad_norm": 3.81036639213562, "learning_rate": 8.949279151182405e-07, "loss": 0.48651283979415894, "step": 5795 }, { "epoch": 0.8127322442683867, "grad_norm": 3.3149545192718506, "learning_rate": 8.936320398898468e-07, "loss": 0.4968571960926056, "step": 5796 }, { "epoch": 0.8128724672228844, "grad_norm": 3.5979738235473633, "learning_rate": 8.923370114919406e-07, "loss": 0.4279378652572632, "step": 5797 }, { "epoch": 0.8130126901773821, "grad_norm": 3.565098524093628, "learning_rate": 8.91042830191588e-07, "loss": 0.49432528018951416, "step": 5798 }, { "epoch": 0.8131529131318797, "grad_norm": 4.005277633666992, "learning_rate": 8.897494962556807e-07, "loss": 0.5675826072692871, "step": 5799 }, { "epoch": 0.8132931360863773, "grad_norm": 3.907463550567627, "learning_rate": 8.884570099509315e-07, "loss": 0.43449437618255615, "step": 5800 }, { "epoch": 0.813433359040875, "grad_norm": 4.945826053619385, "learning_rate": 8.871653715438872e-07, "loss": 0.5001936554908752, "step": 5801 }, { "epoch": 0.8135735819953727, "grad_norm": 2.986874580383301, "learning_rate": 8.858745813009095e-07, "loss": 0.44264763593673706, "step": 5802 }, { "epoch": 0.8137138049498703, "grad_norm": 3.1599507331848145, "learning_rate": 8.845846394881918e-07, "loss": 0.36660122871398926, "step": 5803 }, { "epoch": 0.8138540279043679, "grad_norm": 6.626351356506348, "learning_rate": 8.832955463717502e-07, "loss": 0.5145244598388672, "step": 5804 }, { "epoch": 0.8139942508588656, "grad_norm": 6.188109874725342, "learning_rate": 8.820073022174286e-07, "loss": 0.5399333238601685, "step": 5805 }, { "epoch": 0.8141344738133632, "grad_norm": 5.3787031173706055, "learning_rate": 8.807199072908884e-07, "loss": 0.504425585269928, "step": 5806 }, { "epoch": 0.8142746967678609, "grad_norm": 7.386368274688721, "learning_rate": 8.794333618576273e-07, "loss": 0.4728758931159973, "step": 5807 }, { "epoch": 0.8144149197223586, "grad_norm": 3.284217357635498, "learning_rate": 8.781476661829569e-07, "loss": 0.4862024784088135, "step": 5808 }, { "epoch": 0.8145551426768562, "grad_norm": 5.434463024139404, "learning_rate": 8.768628205320195e-07, "loss": 0.4638289511203766, "step": 5809 }, { "epoch": 0.8146953656313538, "grad_norm": 3.3170807361602783, "learning_rate": 8.755788251697805e-07, "loss": 0.410267174243927, "step": 5810 }, { "epoch": 0.8148355885858515, "grad_norm": 4.359637260437012, "learning_rate": 8.74295680361032e-07, "loss": 0.5500190258026123, "step": 5811 }, { "epoch": 0.8149758115403491, "grad_norm": 2.7477564811706543, "learning_rate": 8.730133863703855e-07, "loss": 0.5190468430519104, "step": 5812 }, { "epoch": 0.8151160344948468, "grad_norm": 2.7445082664489746, "learning_rate": 8.71731943462284e-07, "loss": 0.48090076446533203, "step": 5813 }, { "epoch": 0.8152562574493445, "grad_norm": 4.5313262939453125, "learning_rate": 8.704513519009894e-07, "loss": 0.5017322301864624, "step": 5814 }, { "epoch": 0.8153964804038422, "grad_norm": 2.7310338020324707, "learning_rate": 8.691716119505899e-07, "loss": 0.4759320616722107, "step": 5815 }, { "epoch": 0.8155367033583397, "grad_norm": 3.4270026683807373, "learning_rate": 8.67892723874999e-07, "loss": 0.5178266167640686, "step": 5816 }, { "epoch": 0.8156769263128374, "grad_norm": 5.166812419891357, "learning_rate": 8.66614687937955e-07, "loss": 0.5087763071060181, "step": 5817 }, { "epoch": 0.8158171492673351, "grad_norm": 4.055183410644531, "learning_rate": 8.653375044030149e-07, "loss": 0.49566954374313354, "step": 5818 }, { "epoch": 0.8159573722218327, "grad_norm": 6.959184169769287, "learning_rate": 8.640611735335697e-07, "loss": 0.561264157295227, "step": 5819 }, { "epoch": 0.8160975951763304, "grad_norm": 3.5129780769348145, "learning_rate": 8.627856955928243e-07, "loss": 0.49911385774612427, "step": 5820 }, { "epoch": 0.816237818130828, "grad_norm": 4.58638334274292, "learning_rate": 8.615110708438174e-07, "loss": 0.4658457040786743, "step": 5821 }, { "epoch": 0.8163780410853256, "grad_norm": 4.217442989349365, "learning_rate": 8.602372995494024e-07, "loss": 0.5485520958900452, "step": 5822 }, { "epoch": 0.8165182640398233, "grad_norm": 5.068577766418457, "learning_rate": 8.589643819722632e-07, "loss": 0.5414639711380005, "step": 5823 }, { "epoch": 0.816658486994321, "grad_norm": 4.41408109664917, "learning_rate": 8.576923183749053e-07, "loss": 0.560022234916687, "step": 5824 }, { "epoch": 0.8167987099488186, "grad_norm": 2.9816982746124268, "learning_rate": 8.5642110901966e-07, "loss": 0.5085501074790955, "step": 5825 }, { "epoch": 0.8169389329033163, "grad_norm": 14.899410247802734, "learning_rate": 8.551507541686765e-07, "loss": 0.5768952369689941, "step": 5826 }, { "epoch": 0.8170791558578139, "grad_norm": 3.731398344039917, "learning_rate": 8.538812540839381e-07, "loss": 0.44600582122802734, "step": 5827 }, { "epoch": 0.8172193788123115, "grad_norm": 3.2651891708374023, "learning_rate": 8.526126090272408e-07, "loss": 0.4930981695652008, "step": 5828 }, { "epoch": 0.8173596017668092, "grad_norm": 4.915055274963379, "learning_rate": 8.513448192602108e-07, "loss": 0.4934261739253998, "step": 5829 }, { "epoch": 0.8174998247213069, "grad_norm": 3.603038787841797, "learning_rate": 8.500778850442976e-07, "loss": 0.49495255947113037, "step": 5830 }, { "epoch": 0.8176400476758046, "grad_norm": 32.20762252807617, "learning_rate": 8.488118066407725e-07, "loss": 0.5317920446395874, "step": 5831 }, { "epoch": 0.8177802706303022, "grad_norm": 6.3540449142456055, "learning_rate": 8.475465843107289e-07, "loss": 0.5507745742797852, "step": 5832 }, { "epoch": 0.8179204935847998, "grad_norm": 2.954434633255005, "learning_rate": 8.462822183150898e-07, "loss": 0.358941912651062, "step": 5833 }, { "epoch": 0.8180607165392975, "grad_norm": 3.6078453063964844, "learning_rate": 8.450187089145939e-07, "loss": 0.41337886452674866, "step": 5834 }, { "epoch": 0.8182009394937951, "grad_norm": 4.799412250518799, "learning_rate": 8.437560563698077e-07, "loss": 0.4589659869670868, "step": 5835 }, { "epoch": 0.8183411624482928, "grad_norm": 5.8915181159973145, "learning_rate": 8.424942609411202e-07, "loss": 0.6329671144485474, "step": 5836 }, { "epoch": 0.8184813854027905, "grad_norm": 4.003087043762207, "learning_rate": 8.412333228887454e-07, "loss": 0.4733150601387024, "step": 5837 }, { "epoch": 0.818621608357288, "grad_norm": 4.417132377624512, "learning_rate": 8.399732424727147e-07, "loss": 0.47036394476890564, "step": 5838 }, { "epoch": 0.8187618313117857, "grad_norm": 4.46934175491333, "learning_rate": 8.387140199528909e-07, "loss": 0.5492590069770813, "step": 5839 }, { "epoch": 0.8189020542662834, "grad_norm": 3.011401653289795, "learning_rate": 8.374556555889524e-07, "loss": 0.5313003063201904, "step": 5840 }, { "epoch": 0.819042277220781, "grad_norm": 4.458736896514893, "learning_rate": 8.361981496404048e-07, "loss": 0.4778260588645935, "step": 5841 }, { "epoch": 0.8191825001752787, "grad_norm": 3.885040283203125, "learning_rate": 8.349415023665763e-07, "loss": 0.43491309881210327, "step": 5842 }, { "epoch": 0.8193227231297764, "grad_norm": 3.7080342769622803, "learning_rate": 8.336857140266175e-07, "loss": 0.4931226968765259, "step": 5843 }, { "epoch": 0.819462946084274, "grad_norm": 3.0994231700897217, "learning_rate": 8.324307848794988e-07, "loss": 0.43043214082717896, "step": 5844 }, { "epoch": 0.8196031690387716, "grad_norm": 2.891594886779785, "learning_rate": 8.311767151840211e-07, "loss": 0.5300012230873108, "step": 5845 }, { "epoch": 0.8197433919932693, "grad_norm": 4.890373706817627, "learning_rate": 8.299235051987997e-07, "loss": 0.5465881824493408, "step": 5846 }, { "epoch": 0.819883614947767, "grad_norm": 3.9884860515594482, "learning_rate": 8.286711551822773e-07, "loss": 0.5278433561325073, "step": 5847 }, { "epoch": 0.8200238379022646, "grad_norm": 2.6111435890197754, "learning_rate": 8.274196653927186e-07, "loss": 0.3884790241718292, "step": 5848 }, { "epoch": 0.8201640608567623, "grad_norm": 4.4121198654174805, "learning_rate": 8.261690360882096e-07, "loss": 0.5169984102249146, "step": 5849 }, { "epoch": 0.8203042838112599, "grad_norm": 3.906156063079834, "learning_rate": 8.249192675266604e-07, "loss": 0.42892277240753174, "step": 5850 }, { "epoch": 0.8204445067657575, "grad_norm": 4.193041801452637, "learning_rate": 8.236703599658041e-07, "loss": 0.4280749559402466, "step": 5851 }, { "epoch": 0.8205847297202552, "grad_norm": 4.039215564727783, "learning_rate": 8.224223136631921e-07, "loss": 0.48548367619514465, "step": 5852 }, { "epoch": 0.8207249526747529, "grad_norm": 2.5588502883911133, "learning_rate": 8.211751288762043e-07, "loss": 0.43088579177856445, "step": 5853 }, { "epoch": 0.8208651756292505, "grad_norm": 3.273756980895996, "learning_rate": 8.199288058620375e-07, "loss": 0.3841194808483124, "step": 5854 }, { "epoch": 0.8210053985837482, "grad_norm": 3.965216875076294, "learning_rate": 8.186833448777137e-07, "loss": 0.34907180070877075, "step": 5855 }, { "epoch": 0.8211456215382458, "grad_norm": 4.259007930755615, "learning_rate": 8.17438746180077e-07, "loss": 0.5041114091873169, "step": 5856 }, { "epoch": 0.8212858444927434, "grad_norm": 4.839386940002441, "learning_rate": 8.161950100257938e-07, "loss": 0.4780023992061615, "step": 5857 }, { "epoch": 0.8214260674472411, "grad_norm": 6.275268077850342, "learning_rate": 8.149521366713486e-07, "loss": 0.5721654295921326, "step": 5858 }, { "epoch": 0.8215662904017388, "grad_norm": 4.229868412017822, "learning_rate": 8.137101263730568e-07, "loss": 0.4641594886779785, "step": 5859 }, { "epoch": 0.8217065133562365, "grad_norm": 9.833662033081055, "learning_rate": 8.124689793870461e-07, "loss": 0.489540159702301, "step": 5860 }, { "epoch": 0.821846736310734, "grad_norm": 3.937781572341919, "learning_rate": 8.112286959692711e-07, "loss": 0.5361095070838928, "step": 5861 }, { "epoch": 0.8219869592652317, "grad_norm": 2.7427151203155518, "learning_rate": 8.09989276375509e-07, "loss": 0.4984699487686157, "step": 5862 }, { "epoch": 0.8221271822197294, "grad_norm": 3.35099196434021, "learning_rate": 8.087507208613582e-07, "loss": 0.5421078205108643, "step": 5863 }, { "epoch": 0.822267405174227, "grad_norm": 2.5523366928100586, "learning_rate": 8.075130296822343e-07, "loss": 0.4672510623931885, "step": 5864 }, { "epoch": 0.8224076281287247, "grad_norm": 10.488831520080566, "learning_rate": 8.062762030933835e-07, "loss": 0.48778653144836426, "step": 5865 }, { "epoch": 0.8225478510832224, "grad_norm": 4.32309103012085, "learning_rate": 8.050402413498648e-07, "loss": 0.4713493585586548, "step": 5866 }, { "epoch": 0.8226880740377199, "grad_norm": 3.7047905921936035, "learning_rate": 8.038051447065653e-07, "loss": 0.5181214809417725, "step": 5867 }, { "epoch": 0.8228282969922176, "grad_norm": 3.8782477378845215, "learning_rate": 8.025709134181902e-07, "loss": 0.44215863943099976, "step": 5868 }, { "epoch": 0.8229685199467153, "grad_norm": 3.4062700271606445, "learning_rate": 8.013375477392682e-07, "loss": 0.5528174638748169, "step": 5869 }, { "epoch": 0.8231087429012129, "grad_norm": 2.8976993560791016, "learning_rate": 8.001050479241463e-07, "loss": 0.4632039964199066, "step": 5870 }, { "epoch": 0.8232489658557106, "grad_norm": 2.9190421104431152, "learning_rate": 7.988734142269983e-07, "loss": 0.6130539774894714, "step": 5871 }, { "epoch": 0.8233891888102083, "grad_norm": 3.4728710651397705, "learning_rate": 7.976426469018145e-07, "loss": 0.4958314895629883, "step": 5872 }, { "epoch": 0.8235294117647058, "grad_norm": 3.4246299266815186, "learning_rate": 7.964127462024079e-07, "loss": 0.41840872168540955, "step": 5873 }, { "epoch": 0.8236696347192035, "grad_norm": 3.766671895980835, "learning_rate": 7.951837123824141e-07, "loss": 0.5226205587387085, "step": 5874 }, { "epoch": 0.8238098576737012, "grad_norm": 3.8615126609802246, "learning_rate": 7.939555456952897e-07, "loss": 0.4745509922504425, "step": 5875 }, { "epoch": 0.8239500806281989, "grad_norm": 4.311433792114258, "learning_rate": 7.927282463943087e-07, "loss": 0.4738467037677765, "step": 5876 }, { "epoch": 0.8240903035826965, "grad_norm": 4.351901054382324, "learning_rate": 7.915018147325742e-07, "loss": 0.4755689203739166, "step": 5877 }, { "epoch": 0.8242305265371941, "grad_norm": 3.99588680267334, "learning_rate": 7.902762509630002e-07, "loss": 0.5103498697280884, "step": 5878 }, { "epoch": 0.8243707494916918, "grad_norm": 3.939070224761963, "learning_rate": 7.890515553383321e-07, "loss": 0.5132961869239807, "step": 5879 }, { "epoch": 0.8245109724461894, "grad_norm": 2.931394577026367, "learning_rate": 7.878277281111274e-07, "loss": 0.5129358768463135, "step": 5880 }, { "epoch": 0.8246511954006871, "grad_norm": 11.761591911315918, "learning_rate": 7.866047695337697e-07, "loss": 0.4343699812889099, "step": 5881 }, { "epoch": 0.8247914183551848, "grad_norm": 5.256741523742676, "learning_rate": 7.853826798584618e-07, "loss": 0.553564190864563, "step": 5882 }, { "epoch": 0.8249316413096824, "grad_norm": 4.095576763153076, "learning_rate": 7.841614593372299e-07, "loss": 0.3960554301738739, "step": 5883 }, { "epoch": 0.82507186426418, "grad_norm": 2.8168790340423584, "learning_rate": 7.829411082219135e-07, "loss": 0.44502681493759155, "step": 5884 }, { "epoch": 0.8252120872186777, "grad_norm": 3.384361982345581, "learning_rate": 7.81721626764183e-07, "loss": 0.42917004227638245, "step": 5885 }, { "epoch": 0.8253523101731753, "grad_norm": 4.078950881958008, "learning_rate": 7.805030152155218e-07, "loss": 0.458207368850708, "step": 5886 }, { "epoch": 0.825492533127673, "grad_norm": 3.168055772781372, "learning_rate": 7.792852738272372e-07, "loss": 0.5211089849472046, "step": 5887 }, { "epoch": 0.8256327560821707, "grad_norm": 4.028746128082275, "learning_rate": 7.78068402850456e-07, "loss": 0.48342204093933105, "step": 5888 }, { "epoch": 0.8257729790366684, "grad_norm": 3.9922218322753906, "learning_rate": 7.768524025361273e-07, "loss": 0.5985658168792725, "step": 5889 }, { "epoch": 0.8259132019911659, "grad_norm": 4.529422760009766, "learning_rate": 7.756372731350159e-07, "loss": 0.5177599191665649, "step": 5890 }, { "epoch": 0.8260534249456636, "grad_norm": 3.693499803543091, "learning_rate": 7.74423014897715e-07, "loss": 0.5225704908370972, "step": 5891 }, { "epoch": 0.8261936479001613, "grad_norm": 2.5241546630859375, "learning_rate": 7.732096280746293e-07, "loss": 0.4443943500518799, "step": 5892 }, { "epoch": 0.8263338708546589, "grad_norm": 3.3435702323913574, "learning_rate": 7.719971129159898e-07, "loss": 0.5271013975143433, "step": 5893 }, { "epoch": 0.8264740938091566, "grad_norm": 3.7331626415252686, "learning_rate": 7.707854696718459e-07, "loss": 0.4658527374267578, "step": 5894 }, { "epoch": 0.8266143167636542, "grad_norm": 3.3804173469543457, "learning_rate": 7.695746985920677e-07, "loss": 0.3805656135082245, "step": 5895 }, { "epoch": 0.8267545397181518, "grad_norm": 2.8748626708984375, "learning_rate": 7.683647999263421e-07, "loss": 0.5335170030593872, "step": 5896 }, { "epoch": 0.8268947626726495, "grad_norm": 3.4221880435943604, "learning_rate": 7.67155773924183e-07, "loss": 0.4899243712425232, "step": 5897 }, { "epoch": 0.8270349856271472, "grad_norm": 3.913001298904419, "learning_rate": 7.659476208349176e-07, "loss": 0.5304555296897888, "step": 5898 }, { "epoch": 0.8271752085816448, "grad_norm": 4.679827690124512, "learning_rate": 7.647403409076959e-07, "loss": 0.5128937363624573, "step": 5899 }, { "epoch": 0.8273154315361425, "grad_norm": 2.8343584537506104, "learning_rate": 7.635339343914883e-07, "loss": 0.46277469396591187, "step": 5900 }, { "epoch": 0.8274556544906401, "grad_norm": 3.7304494380950928, "learning_rate": 7.623284015350851e-07, "loss": 0.5055282115936279, "step": 5901 }, { "epoch": 0.8275958774451377, "grad_norm": 3.4049556255340576, "learning_rate": 7.611237425870927e-07, "loss": 0.5499179363250732, "step": 5902 }, { "epoch": 0.8277361003996354, "grad_norm": 3.155719041824341, "learning_rate": 7.599199577959449e-07, "loss": 0.4725273847579956, "step": 5903 }, { "epoch": 0.8278763233541331, "grad_norm": 2.7991676330566406, "learning_rate": 7.58717047409887e-07, "loss": 0.4689050316810608, "step": 5904 }, { "epoch": 0.8280165463086308, "grad_norm": 8.252909660339355, "learning_rate": 7.575150116769897e-07, "loss": 0.5155631899833679, "step": 5905 }, { "epoch": 0.8281567692631284, "grad_norm": 12.523431777954102, "learning_rate": 7.563138508451401e-07, "loss": 0.5061242580413818, "step": 5906 }, { "epoch": 0.828296992217626, "grad_norm": 8.352473258972168, "learning_rate": 7.551135651620467e-07, "loss": 0.5313688516616821, "step": 5907 }, { "epoch": 0.8284372151721237, "grad_norm": 5.009881496429443, "learning_rate": 7.539141548752366e-07, "loss": 0.5524060726165771, "step": 5908 }, { "epoch": 0.8285774381266213, "grad_norm": 4.718477725982666, "learning_rate": 7.527156202320579e-07, "loss": 0.531682014465332, "step": 5909 }, { "epoch": 0.828717661081119, "grad_norm": 3.7571396827697754, "learning_rate": 7.515179614796736e-07, "loss": 0.5366308689117432, "step": 5910 }, { "epoch": 0.8288578840356167, "grad_norm": 3.329333543777466, "learning_rate": 7.503211788650738e-07, "loss": 0.49414342641830444, "step": 5911 }, { "epoch": 0.8289981069901143, "grad_norm": 4.5624518394470215, "learning_rate": 7.491252726350595e-07, "loss": 0.5001270174980164, "step": 5912 }, { "epoch": 0.8291383299446119, "grad_norm": 2.860375165939331, "learning_rate": 7.479302430362572e-07, "loss": 0.5103741884231567, "step": 5913 }, { "epoch": 0.8292785528991096, "grad_norm": 6.832113742828369, "learning_rate": 7.4673609031511e-07, "loss": 0.4509398937225342, "step": 5914 }, { "epoch": 0.8294187758536072, "grad_norm": 4.728960037231445, "learning_rate": 7.455428147178806e-07, "loss": 0.5460262298583984, "step": 5915 }, { "epoch": 0.8295589988081049, "grad_norm": 3.211026430130005, "learning_rate": 7.44350416490649e-07, "loss": 0.6132277250289917, "step": 5916 }, { "epoch": 0.8296992217626026, "grad_norm": 2.796713352203369, "learning_rate": 7.43158895879319e-07, "loss": 0.4940508306026459, "step": 5917 }, { "epoch": 0.8298394447171001, "grad_norm": 3.165837287902832, "learning_rate": 7.41968253129608e-07, "loss": 0.43433648347854614, "step": 5918 }, { "epoch": 0.8299796676715978, "grad_norm": 7.042505264282227, "learning_rate": 7.407784884870556e-07, "loss": 0.43843311071395874, "step": 5919 }, { "epoch": 0.8301198906260955, "grad_norm": 5.224855422973633, "learning_rate": 7.395896021970195e-07, "loss": 0.41307246685028076, "step": 5920 }, { "epoch": 0.8302601135805932, "grad_norm": 2.697049140930176, "learning_rate": 7.384015945046774e-07, "loss": 0.5681359767913818, "step": 5921 }, { "epoch": 0.8304003365350908, "grad_norm": 3.522915840148926, "learning_rate": 7.372144656550218e-07, "loss": 0.5054333209991455, "step": 5922 }, { "epoch": 0.8305405594895885, "grad_norm": 7.535911560058594, "learning_rate": 7.3602821589287e-07, "loss": 0.4912800192832947, "step": 5923 }, { "epoch": 0.830680782444086, "grad_norm": 6.502521991729736, "learning_rate": 7.348428454628526e-07, "loss": 0.5206750631332397, "step": 5924 }, { "epoch": 0.8308210053985837, "grad_norm": 5.093041896820068, "learning_rate": 7.336583546094217e-07, "loss": 0.4360509514808655, "step": 5925 }, { "epoch": 0.8309612283530814, "grad_norm": 3.3797054290771484, "learning_rate": 7.324747435768481e-07, "loss": 0.43675652146339417, "step": 5926 }, { "epoch": 0.8311014513075791, "grad_norm": 3.163466453552246, "learning_rate": 7.312920126092199e-07, "loss": 0.5486690998077393, "step": 5927 }, { "epoch": 0.8312416742620767, "grad_norm": 2.9998152256011963, "learning_rate": 7.301101619504441e-07, "loss": 0.5152240991592407, "step": 5928 }, { "epoch": 0.8313818972165744, "grad_norm": 2.904226541519165, "learning_rate": 7.289291918442476e-07, "loss": 0.47690078616142273, "step": 5929 }, { "epoch": 0.831522120171072, "grad_norm": 4.532467365264893, "learning_rate": 7.277491025341726e-07, "loss": 0.4599589407444, "step": 5930 }, { "epoch": 0.8316623431255696, "grad_norm": 9.187562942504883, "learning_rate": 7.265698942635829e-07, "loss": 0.48551663756370544, "step": 5931 }, { "epoch": 0.8318025660800673, "grad_norm": 4.4477410316467285, "learning_rate": 7.253915672756579e-07, "loss": 0.44948744773864746, "step": 5932 }, { "epoch": 0.831942789034565, "grad_norm": 2.570741891860962, "learning_rate": 7.24214121813398e-07, "loss": 0.49247032403945923, "step": 5933 }, { "epoch": 0.8320830119890626, "grad_norm": 3.6207823753356934, "learning_rate": 7.230375581196191e-07, "loss": 0.4789878726005554, "step": 5934 }, { "epoch": 0.8322232349435602, "grad_norm": 3.5942344665527344, "learning_rate": 7.218618764369589e-07, "loss": 0.5219608545303345, "step": 5935 }, { "epoch": 0.8323634578980579, "grad_norm": 4.320049285888672, "learning_rate": 7.206870770078667e-07, "loss": 0.46822941303253174, "step": 5936 }, { "epoch": 0.8325036808525555, "grad_norm": 12.332494735717773, "learning_rate": 7.195131600746191e-07, "loss": 0.4578290283679962, "step": 5937 }, { "epoch": 0.8326439038070532, "grad_norm": 3.3473896980285645, "learning_rate": 7.183401258793016e-07, "loss": 0.4443117380142212, "step": 5938 }, { "epoch": 0.8327841267615509, "grad_norm": 18.487573623657227, "learning_rate": 7.171679746638228e-07, "loss": 0.5252812504768372, "step": 5939 }, { "epoch": 0.8329243497160486, "grad_norm": 4.837772369384766, "learning_rate": 7.159967066699086e-07, "loss": 0.46343737840652466, "step": 5940 }, { "epoch": 0.8330645726705461, "grad_norm": 4.599989414215088, "learning_rate": 7.148263221391034e-07, "loss": 0.5360289812088013, "step": 5941 }, { "epoch": 0.8332047956250438, "grad_norm": 3.6735074520111084, "learning_rate": 7.136568213127643e-07, "loss": 0.5690633058547974, "step": 5942 }, { "epoch": 0.8333450185795415, "grad_norm": 6.219583511352539, "learning_rate": 7.124882044320746e-07, "loss": 0.5033608078956604, "step": 5943 }, { "epoch": 0.8334852415340391, "grad_norm": 3.9503326416015625, "learning_rate": 7.113204717380284e-07, "loss": 0.47690412402153015, "step": 5944 }, { "epoch": 0.8336254644885368, "grad_norm": 5.140923023223877, "learning_rate": 7.101536234714401e-07, "loss": 0.5835931301116943, "step": 5945 }, { "epoch": 0.8337656874430345, "grad_norm": 2.6329538822174072, "learning_rate": 7.089876598729417e-07, "loss": 0.5196885466575623, "step": 5946 }, { "epoch": 0.833905910397532, "grad_norm": 3.707181215286255, "learning_rate": 7.07822581182983e-07, "loss": 0.4465870261192322, "step": 5947 }, { "epoch": 0.8340461333520297, "grad_norm": 4.346810340881348, "learning_rate": 7.066583876418304e-07, "loss": 0.4924110174179077, "step": 5948 }, { "epoch": 0.8341863563065274, "grad_norm": 10.592790603637695, "learning_rate": 7.054950794895693e-07, "loss": 0.4721006453037262, "step": 5949 }, { "epoch": 0.834326579261025, "grad_norm": 3.5307886600494385, "learning_rate": 7.043326569660997e-07, "loss": 0.5057017803192139, "step": 5950 }, { "epoch": 0.8344668022155227, "grad_norm": 3.6019999980926514, "learning_rate": 7.031711203111408e-07, "loss": 0.5246058106422424, "step": 5951 }, { "epoch": 0.8346070251700203, "grad_norm": 32.075321197509766, "learning_rate": 7.0201046976423e-07, "loss": 0.45466095209121704, "step": 5952 }, { "epoch": 0.834747248124518, "grad_norm": 3.404721736907959, "learning_rate": 7.008507055647207e-07, "loss": 0.5734758377075195, "step": 5953 }, { "epoch": 0.8348874710790156, "grad_norm": 4.308691501617432, "learning_rate": 6.996918279517839e-07, "loss": 0.49100226163864136, "step": 5954 }, { "epoch": 0.8350276940335133, "grad_norm": 3.6797304153442383, "learning_rate": 6.985338371644085e-07, "loss": 0.4932911694049835, "step": 5955 }, { "epoch": 0.835167916988011, "grad_norm": 7.370316505432129, "learning_rate": 6.973767334413972e-07, "loss": 0.5308588743209839, "step": 5956 }, { "epoch": 0.8353081399425086, "grad_norm": 3.6647696495056152, "learning_rate": 6.962205170213742e-07, "loss": 0.5732541084289551, "step": 5957 }, { "epoch": 0.8354483628970062, "grad_norm": 4.94521951675415, "learning_rate": 6.950651881427784e-07, "loss": 0.4815933406352997, "step": 5958 }, { "epoch": 0.8355885858515039, "grad_norm": 2.4141108989715576, "learning_rate": 6.939107470438656e-07, "loss": 0.49287956953048706, "step": 5959 }, { "epoch": 0.8357288088060015, "grad_norm": 4.943151950836182, "learning_rate": 6.927571939627093e-07, "loss": 0.5598030090332031, "step": 5960 }, { "epoch": 0.8358690317604992, "grad_norm": 2.403999090194702, "learning_rate": 6.916045291371992e-07, "loss": 0.5155785083770752, "step": 5961 }, { "epoch": 0.8360092547149969, "grad_norm": 5.601730823516846, "learning_rate": 6.904527528050436e-07, "loss": 0.5128332376480103, "step": 5962 }, { "epoch": 0.8361494776694945, "grad_norm": 5.074291706085205, "learning_rate": 6.893018652037636e-07, "loss": 0.5204322934150696, "step": 5963 }, { "epoch": 0.8362897006239921, "grad_norm": 3.5766968727111816, "learning_rate": 6.88151866570701e-07, "loss": 0.49065130949020386, "step": 5964 }, { "epoch": 0.8364299235784898, "grad_norm": 4.827025413513184, "learning_rate": 6.870027571430127e-07, "loss": 0.5259977579116821, "step": 5965 }, { "epoch": 0.8365701465329874, "grad_norm": 3.1592133045196533, "learning_rate": 6.858545371576724e-07, "loss": 0.4872305691242218, "step": 5966 }, { "epoch": 0.8367103694874851, "grad_norm": 4.577634334564209, "learning_rate": 6.847072068514699e-07, "loss": 0.44612544775009155, "step": 5967 }, { "epoch": 0.8368505924419828, "grad_norm": 5.759591102600098, "learning_rate": 6.835607664610122e-07, "loss": 0.5691593885421753, "step": 5968 }, { "epoch": 0.8369908153964805, "grad_norm": 7.569307327270508, "learning_rate": 6.824152162227232e-07, "loss": 0.5766527652740479, "step": 5969 }, { "epoch": 0.837131038350978, "grad_norm": 6.904329299926758, "learning_rate": 6.812705563728411e-07, "loss": 0.46780526638031006, "step": 5970 }, { "epoch": 0.8372712613054757, "grad_norm": 3.966256618499756, "learning_rate": 6.801267871474226e-07, "loss": 0.520887017250061, "step": 5971 }, { "epoch": 0.8374114842599734, "grad_norm": 3.3157474994659424, "learning_rate": 6.789839087823397e-07, "loss": 0.5144264698028564, "step": 5972 }, { "epoch": 0.837551707214471, "grad_norm": 3.2210781574249268, "learning_rate": 6.778419215132814e-07, "loss": 0.5418856739997864, "step": 5973 }, { "epoch": 0.8376919301689687, "grad_norm": 4.773917198181152, "learning_rate": 6.767008255757529e-07, "loss": 0.49278223514556885, "step": 5974 }, { "epoch": 0.8378321531234663, "grad_norm": 2.8509304523468018, "learning_rate": 6.755606212050758e-07, "loss": 0.5347970724105835, "step": 5975 }, { "epoch": 0.8379723760779639, "grad_norm": 4.301731109619141, "learning_rate": 6.744213086363854e-07, "loss": 0.5476795434951782, "step": 5976 }, { "epoch": 0.8381125990324616, "grad_norm": 4.049462795257568, "learning_rate": 6.73282888104636e-07, "loss": 0.5656683444976807, "step": 5977 }, { "epoch": 0.8382528219869593, "grad_norm": 4.99293851852417, "learning_rate": 6.721453598445971e-07, "loss": 0.45021551847457886, "step": 5978 }, { "epoch": 0.8383930449414569, "grad_norm": 9.45107364654541, "learning_rate": 6.710087240908536e-07, "loss": 0.40466487407684326, "step": 5979 }, { "epoch": 0.8385332678959546, "grad_norm": 3.792135238647461, "learning_rate": 6.698729810778065e-07, "loss": 0.5309162139892578, "step": 5980 }, { "epoch": 0.8386734908504522, "grad_norm": 3.596222162246704, "learning_rate": 6.68738131039674e-07, "loss": 0.3778146505355835, "step": 5981 }, { "epoch": 0.8388137138049498, "grad_norm": 5.9727463722229, "learning_rate": 6.676041742104894e-07, "loss": 0.5469014644622803, "step": 5982 }, { "epoch": 0.8389539367594475, "grad_norm": 3.314697504043579, "learning_rate": 6.664711108240995e-07, "loss": 0.5462205410003662, "step": 5983 }, { "epoch": 0.8390941597139452, "grad_norm": 4.589282035827637, "learning_rate": 6.653389411141703e-07, "loss": 0.5267593860626221, "step": 5984 }, { "epoch": 0.8392343826684429, "grad_norm": 3.5038001537323, "learning_rate": 6.64207665314181e-07, "loss": 0.5163594484329224, "step": 5985 }, { "epoch": 0.8393746056229405, "grad_norm": 17.379552841186523, "learning_rate": 6.63077283657429e-07, "loss": 0.5172095894813538, "step": 5986 }, { "epoch": 0.8395148285774381, "grad_norm": 3.25984263420105, "learning_rate": 6.619477963770249e-07, "loss": 0.41777703166007996, "step": 5987 }, { "epoch": 0.8396550515319358, "grad_norm": 11.496543884277344, "learning_rate": 6.608192037058964e-07, "loss": 0.5960939526557922, "step": 5988 }, { "epoch": 0.8397952744864334, "grad_norm": 2.6508054733276367, "learning_rate": 6.59691505876785e-07, "loss": 0.4516514539718628, "step": 5989 }, { "epoch": 0.8399354974409311, "grad_norm": 3.1374292373657227, "learning_rate": 6.585647031222492e-07, "loss": 0.4443286061286926, "step": 5990 }, { "epoch": 0.8400757203954288, "grad_norm": 2.3379650115966797, "learning_rate": 6.574387956746625e-07, "loss": 0.5210757255554199, "step": 5991 }, { "epoch": 0.8402159433499263, "grad_norm": 2.9616048336029053, "learning_rate": 6.563137837662142e-07, "loss": 0.5041565299034119, "step": 5992 }, { "epoch": 0.840356166304424, "grad_norm": 3.584850788116455, "learning_rate": 6.551896676289077e-07, "loss": 0.5623985528945923, "step": 5993 }, { "epoch": 0.8404963892589217, "grad_norm": 3.775481700897217, "learning_rate": 6.540664474945641e-07, "loss": 0.5135267376899719, "step": 5994 }, { "epoch": 0.8406366122134193, "grad_norm": 8.79128360748291, "learning_rate": 6.529441235948153e-07, "loss": 0.4575098752975464, "step": 5995 }, { "epoch": 0.840776835167917, "grad_norm": 3.9180142879486084, "learning_rate": 6.51822696161113e-07, "loss": 0.5482797622680664, "step": 5996 }, { "epoch": 0.8409170581224147, "grad_norm": 5.3164215087890625, "learning_rate": 6.507021654247215e-07, "loss": 0.48069852590560913, "step": 5997 }, { "epoch": 0.8410572810769122, "grad_norm": 5.420318126678467, "learning_rate": 6.495825316167204e-07, "loss": 0.5768540501594543, "step": 5998 }, { "epoch": 0.8411975040314099, "grad_norm": 3.0307374000549316, "learning_rate": 6.484637949680062e-07, "loss": 0.42038291692733765, "step": 5999 }, { "epoch": 0.8413377269859076, "grad_norm": 4.608728885650635, "learning_rate": 6.473459557092876e-07, "loss": 0.6185170412063599, "step": 6000 }, { "epoch": 0.8414779499404053, "grad_norm": 6.146535396575928, "learning_rate": 6.462290140710903e-07, "loss": 0.5350656509399414, "step": 6001 }, { "epoch": 0.8416181728949029, "grad_norm": 4.8304572105407715, "learning_rate": 6.451129702837545e-07, "loss": 0.4994102120399475, "step": 6002 }, { "epoch": 0.8417583958494006, "grad_norm": 4.555033206939697, "learning_rate": 6.439978245774336e-07, "loss": 0.5872281789779663, "step": 6003 }, { "epoch": 0.8418986188038982, "grad_norm": 5.142475605010986, "learning_rate": 6.42883577182098e-07, "loss": 0.460292249917984, "step": 6004 }, { "epoch": 0.8420388417583958, "grad_norm": 4.449275016784668, "learning_rate": 6.417702283275313e-07, "loss": 0.49984151124954224, "step": 6005 }, { "epoch": 0.8421790647128935, "grad_norm": 3.2343058586120605, "learning_rate": 6.406577782433332e-07, "loss": 0.49508416652679443, "step": 6006 }, { "epoch": 0.8423192876673912, "grad_norm": 3.3838024139404297, "learning_rate": 6.39546227158917e-07, "loss": 0.475044846534729, "step": 6007 }, { "epoch": 0.8424595106218888, "grad_norm": 4.148469924926758, "learning_rate": 6.384355753035121e-07, "loss": 0.44367098808288574, "step": 6008 }, { "epoch": 0.8425997335763864, "grad_norm": 9.461875915527344, "learning_rate": 6.373258229061585e-07, "loss": 0.5249247550964355, "step": 6009 }, { "epoch": 0.8427399565308841, "grad_norm": 4.032607078552246, "learning_rate": 6.362169701957155e-07, "loss": 0.4348854124546051, "step": 6010 }, { "epoch": 0.8428801794853817, "grad_norm": 3.821446418762207, "learning_rate": 6.351090174008545e-07, "loss": 0.5306451916694641, "step": 6011 }, { "epoch": 0.8430204024398794, "grad_norm": 3.3722691535949707, "learning_rate": 6.340019647500611e-07, "loss": 0.6119763851165771, "step": 6012 }, { "epoch": 0.8431606253943771, "grad_norm": 8.582795143127441, "learning_rate": 6.328958124716367e-07, "loss": 0.5044603943824768, "step": 6013 }, { "epoch": 0.8433008483488748, "grad_norm": 4.205399036407471, "learning_rate": 6.317905607936964e-07, "loss": 0.5369342565536499, "step": 6014 }, { "epoch": 0.8434410713033723, "grad_norm": 4.571974754333496, "learning_rate": 6.306862099441674e-07, "loss": 0.5270997285842896, "step": 6015 }, { "epoch": 0.84358129425787, "grad_norm": 2.6772847175598145, "learning_rate": 6.295827601507947e-07, "loss": 0.4524913430213928, "step": 6016 }, { "epoch": 0.8437215172123677, "grad_norm": 6.335851669311523, "learning_rate": 6.284802116411348e-07, "loss": 0.5942035913467407, "step": 6017 }, { "epoch": 0.8438617401668653, "grad_norm": 5.146488666534424, "learning_rate": 6.273785646425607e-07, "loss": 0.5139443874359131, "step": 6018 }, { "epoch": 0.844001963121363, "grad_norm": 5.002234935760498, "learning_rate": 6.262778193822566e-07, "loss": 0.5512716770172119, "step": 6019 }, { "epoch": 0.8441421860758607, "grad_norm": 7.558016777038574, "learning_rate": 6.251779760872245e-07, "loss": 0.5115269422531128, "step": 6020 }, { "epoch": 0.8442824090303582, "grad_norm": 3.7386302947998047, "learning_rate": 6.240790349842746e-07, "loss": 0.4614346921443939, "step": 6021 }, { "epoch": 0.8444226319848559, "grad_norm": 4.066388130187988, "learning_rate": 6.229809963000389e-07, "loss": 0.4609043002128601, "step": 6022 }, { "epoch": 0.8445628549393536, "grad_norm": 3.594405174255371, "learning_rate": 6.218838602609556e-07, "loss": 0.5487974882125854, "step": 6023 }, { "epoch": 0.8447030778938512, "grad_norm": 4.0231404304504395, "learning_rate": 6.207876270932817e-07, "loss": 0.4563594460487366, "step": 6024 }, { "epoch": 0.8448433008483489, "grad_norm": 4.204634189605713, "learning_rate": 6.196922970230862e-07, "loss": 0.46862542629241943, "step": 6025 }, { "epoch": 0.8449835238028466, "grad_norm": 3.573631525039673, "learning_rate": 6.185978702762524e-07, "loss": 0.4552021920681, "step": 6026 }, { "epoch": 0.8451237467573441, "grad_norm": 3.643481731414795, "learning_rate": 6.175043470784764e-07, "loss": 0.5417330265045166, "step": 6027 }, { "epoch": 0.8452639697118418, "grad_norm": 2.719011068344116, "learning_rate": 6.164117276552705e-07, "loss": 0.5134601593017578, "step": 6028 }, { "epoch": 0.8454041926663395, "grad_norm": 3.2145066261291504, "learning_rate": 6.153200122319558e-07, "loss": 0.46639809012413025, "step": 6029 }, { "epoch": 0.8455444156208372, "grad_norm": 4.5833001136779785, "learning_rate": 6.14229201033672e-07, "loss": 0.4791615605354309, "step": 6030 }, { "epoch": 0.8456846385753348, "grad_norm": 3.371305227279663, "learning_rate": 6.131392942853692e-07, "loss": 0.46201056241989136, "step": 6031 }, { "epoch": 0.8458248615298324, "grad_norm": 6.335750102996826, "learning_rate": 6.120502922118132e-07, "loss": 0.5184293985366821, "step": 6032 }, { "epoch": 0.84596508448433, "grad_norm": 5.543509006500244, "learning_rate": 6.10962195037581e-07, "loss": 0.48935163021087646, "step": 6033 }, { "epoch": 0.8461053074388277, "grad_norm": 6.903641700744629, "learning_rate": 6.098750029870653e-07, "loss": 0.4915942847728729, "step": 6034 }, { "epoch": 0.8462455303933254, "grad_norm": 4.459780216217041, "learning_rate": 6.087887162844691e-07, "loss": 0.4348471760749817, "step": 6035 }, { "epoch": 0.8463857533478231, "grad_norm": 3.0184402465820312, "learning_rate": 6.077033351538114e-07, "loss": 0.44648635387420654, "step": 6036 }, { "epoch": 0.8465259763023207, "grad_norm": 3.5866196155548096, "learning_rate": 6.066188598189233e-07, "loss": 0.4834877550601959, "step": 6037 }, { "epoch": 0.8466661992568183, "grad_norm": 4.025976657867432, "learning_rate": 6.055352905034501e-07, "loss": 0.49270322918891907, "step": 6038 }, { "epoch": 0.846806422211316, "grad_norm": 3.493560791015625, "learning_rate": 6.044526274308482e-07, "loss": 0.41499996185302734, "step": 6039 }, { "epoch": 0.8469466451658136, "grad_norm": 3.175711154937744, "learning_rate": 6.033708708243912e-07, "loss": 0.5561112761497498, "step": 6040 }, { "epoch": 0.8470868681203113, "grad_norm": 3.1529176235198975, "learning_rate": 6.02290020907158e-07, "loss": 0.48844102025032043, "step": 6041 }, { "epoch": 0.847227091074809, "grad_norm": 3.041566848754883, "learning_rate": 6.012100779020513e-07, "loss": 0.4618963599205017, "step": 6042 }, { "epoch": 0.8473673140293067, "grad_norm": 3.151679515838623, "learning_rate": 6.001310420317769e-07, "loss": 0.513701856136322, "step": 6043 }, { "epoch": 0.8475075369838042, "grad_norm": 7.8387579917907715, "learning_rate": 5.990529135188583e-07, "loss": 0.4784315526485443, "step": 6044 }, { "epoch": 0.8476477599383019, "grad_norm": 4.441922187805176, "learning_rate": 5.979756925856323e-07, "loss": 0.5337022542953491, "step": 6045 }, { "epoch": 0.8477879828927996, "grad_norm": 2.7601113319396973, "learning_rate": 5.968993794542477e-07, "loss": 0.6155603528022766, "step": 6046 }, { "epoch": 0.8479282058472972, "grad_norm": 3.678837299346924, "learning_rate": 5.958239743466626e-07, "loss": 0.4281916618347168, "step": 6047 }, { "epoch": 0.8480684288017949, "grad_norm": 2.9632747173309326, "learning_rate": 5.947494774846552e-07, "loss": 0.42763352394104004, "step": 6048 }, { "epoch": 0.8482086517562925, "grad_norm": 3.8981544971466064, "learning_rate": 5.936758890898098e-07, "loss": 0.5345702171325684, "step": 6049 }, { "epoch": 0.8483488747107901, "grad_norm": 3.740712881088257, "learning_rate": 5.926032093835265e-07, "loss": 0.4629342555999756, "step": 6050 }, { "epoch": 0.8484890976652878, "grad_norm": 10.970778465270996, "learning_rate": 5.915314385870169e-07, "loss": 0.5446549654006958, "step": 6051 }, { "epoch": 0.8486293206197855, "grad_norm": 3.3942456245422363, "learning_rate": 5.904605769213068e-07, "loss": 0.4069250822067261, "step": 6052 }, { "epoch": 0.8487695435742831, "grad_norm": 4.789662837982178, "learning_rate": 5.893906246072306e-07, "loss": 0.5457303524017334, "step": 6053 }, { "epoch": 0.8489097665287808, "grad_norm": 5.974961280822754, "learning_rate": 5.883215818654414e-07, "loss": 0.5034723281860352, "step": 6054 }, { "epoch": 0.8490499894832784, "grad_norm": 3.164987802505493, "learning_rate": 5.872534489163989e-07, "loss": 0.5315748453140259, "step": 6055 }, { "epoch": 0.849190212437776, "grad_norm": 3.178011178970337, "learning_rate": 5.861862259803774e-07, "loss": 0.5460142493247986, "step": 6056 }, { "epoch": 0.8493304353922737, "grad_norm": 5.222911357879639, "learning_rate": 5.851199132774638e-07, "loss": 0.5644906163215637, "step": 6057 }, { "epoch": 0.8494706583467714, "grad_norm": 5.391061305999756, "learning_rate": 5.840545110275581e-07, "loss": 0.5432374477386475, "step": 6058 }, { "epoch": 0.849610881301269, "grad_norm": 3.657891273498535, "learning_rate": 5.829900194503701e-07, "loss": 0.5025343298912048, "step": 6059 }, { "epoch": 0.8497511042557667, "grad_norm": 3.0401105880737305, "learning_rate": 5.819264387654255e-07, "loss": 0.5069263577461243, "step": 6060 }, { "epoch": 0.8498913272102643, "grad_norm": 3.2493064403533936, "learning_rate": 5.80863769192056e-07, "loss": 0.5040997266769409, "step": 6061 }, { "epoch": 0.850031550164762, "grad_norm": 4.2004523277282715, "learning_rate": 5.798020109494134e-07, "loss": 0.5506185293197632, "step": 6062 }, { "epoch": 0.8501717731192596, "grad_norm": 6.330861568450928, "learning_rate": 5.78741164256455e-07, "loss": 0.411601722240448, "step": 6063 }, { "epoch": 0.8503119960737573, "grad_norm": 10.788196563720703, "learning_rate": 5.776812293319528e-07, "loss": 0.45973849296569824, "step": 6064 }, { "epoch": 0.850452219028255, "grad_norm": 3.3715925216674805, "learning_rate": 5.76622206394491e-07, "loss": 0.4869237542152405, "step": 6065 }, { "epoch": 0.8505924419827525, "grad_norm": 3.7867846488952637, "learning_rate": 5.755640956624659e-07, "loss": 0.5094268918037415, "step": 6066 }, { "epoch": 0.8507326649372502, "grad_norm": 3.0932464599609375, "learning_rate": 5.745068973540824e-07, "loss": 0.491904079914093, "step": 6067 }, { "epoch": 0.8508728878917479, "grad_norm": 5.202266693115234, "learning_rate": 5.734506116873639e-07, "loss": 0.561369776725769, "step": 6068 }, { "epoch": 0.8510131108462455, "grad_norm": 3.2562644481658936, "learning_rate": 5.723952388801385e-07, "loss": 0.5190184116363525, "step": 6069 }, { "epoch": 0.8511533338007432, "grad_norm": 3.235247850418091, "learning_rate": 5.713407791500497e-07, "loss": 0.5105820894241333, "step": 6070 }, { "epoch": 0.8512935567552409, "grad_norm": 3.1796929836273193, "learning_rate": 5.702872327145526e-07, "loss": 0.47585374116897583, "step": 6071 }, { "epoch": 0.8514337797097384, "grad_norm": 3.4758262634277344, "learning_rate": 5.692345997909138e-07, "loss": 0.5195116996765137, "step": 6072 }, { "epoch": 0.8515740026642361, "grad_norm": 5.231656551361084, "learning_rate": 5.681828805962092e-07, "loss": 0.47856032848358154, "step": 6073 }, { "epoch": 0.8517142256187338, "grad_norm": 4.337890625, "learning_rate": 5.671320753473314e-07, "loss": 0.4114651381969452, "step": 6074 }, { "epoch": 0.8518544485732314, "grad_norm": 5.335511207580566, "learning_rate": 5.660821842609792e-07, "loss": 0.5078638195991516, "step": 6075 }, { "epoch": 0.8519946715277291, "grad_norm": 4.082079887390137, "learning_rate": 5.650332075536652e-07, "loss": 0.5587594509124756, "step": 6076 }, { "epoch": 0.8521348944822268, "grad_norm": 22.19207000732422, "learning_rate": 5.639851454417133e-07, "loss": 0.5323141813278198, "step": 6077 }, { "epoch": 0.8522751174367243, "grad_norm": 4.943235397338867, "learning_rate": 5.629379981412602e-07, "loss": 0.5295834541320801, "step": 6078 }, { "epoch": 0.852415340391222, "grad_norm": 4.204049110412598, "learning_rate": 5.618917658682499e-07, "loss": 0.5361879467964172, "step": 6079 }, { "epoch": 0.8525555633457197, "grad_norm": 2.8747634887695312, "learning_rate": 5.608464488384435e-07, "loss": 0.5417553186416626, "step": 6080 }, { "epoch": 0.8526957863002174, "grad_norm": 4.869547367095947, "learning_rate": 5.598020472674071e-07, "loss": 0.4518100321292877, "step": 6081 }, { "epoch": 0.852836009254715, "grad_norm": 9.30168628692627, "learning_rate": 5.587585613705227e-07, "loss": 0.45363932847976685, "step": 6082 }, { "epoch": 0.8529762322092127, "grad_norm": 5.506342887878418, "learning_rate": 5.577159913629821e-07, "loss": 0.4927392601966858, "step": 6083 }, { "epoch": 0.8531164551637103, "grad_norm": 3.188300609588623, "learning_rate": 5.566743374597866e-07, "loss": 0.5217576622962952, "step": 6084 }, { "epoch": 0.8532566781182079, "grad_norm": 3.7804946899414062, "learning_rate": 5.556335998757512e-07, "loss": 0.5133460164070129, "step": 6085 }, { "epoch": 0.8533969010727056, "grad_norm": 5.020493507385254, "learning_rate": 5.545937788255018e-07, "loss": 0.48002761602401733, "step": 6086 }, { "epoch": 0.8535371240272033, "grad_norm": 3.7228341102600098, "learning_rate": 5.535548745234698e-07, "loss": 0.5775730609893799, "step": 6087 }, { "epoch": 0.853677346981701, "grad_norm": 4.5164008140563965, "learning_rate": 5.525168871839076e-07, "loss": 0.47093647718429565, "step": 6088 }, { "epoch": 0.8538175699361985, "grad_norm": 3.586122751235962, "learning_rate": 5.514798170208685e-07, "loss": 0.6392295360565186, "step": 6089 }, { "epoch": 0.8539577928906962, "grad_norm": 3.455939292907715, "learning_rate": 5.504436642482225e-07, "loss": 0.4112502336502075, "step": 6090 }, { "epoch": 0.8540980158451938, "grad_norm": 3.1398398876190186, "learning_rate": 5.494084290796487e-07, "loss": 0.48183608055114746, "step": 6091 }, { "epoch": 0.8542382387996915, "grad_norm": 4.261809825897217, "learning_rate": 5.483741117286384e-07, "loss": 0.554736852645874, "step": 6092 }, { "epoch": 0.8543784617541892, "grad_norm": 4.5838165283203125, "learning_rate": 5.473407124084895e-07, "loss": 0.48229557275772095, "step": 6093 }, { "epoch": 0.8545186847086869, "grad_norm": 4.187001705169678, "learning_rate": 5.46308231332317e-07, "loss": 0.5692620277404785, "step": 6094 }, { "epoch": 0.8546589076631844, "grad_norm": 3.693671226501465, "learning_rate": 5.452766687130407e-07, "loss": 0.5780977606773376, "step": 6095 }, { "epoch": 0.8547991306176821, "grad_norm": 5.2050018310546875, "learning_rate": 5.442460247633935e-07, "loss": 0.5658141374588013, "step": 6096 }, { "epoch": 0.8549393535721798, "grad_norm": 5.861263751983643, "learning_rate": 5.432162996959183e-07, "loss": 0.5634242296218872, "step": 6097 }, { "epoch": 0.8550795765266774, "grad_norm": 4.087706565856934, "learning_rate": 5.42187493722971e-07, "loss": 0.44726455211639404, "step": 6098 }, { "epoch": 0.8552197994811751, "grad_norm": 12.572776794433594, "learning_rate": 5.411596070567127e-07, "loss": 0.5541310906410217, "step": 6099 }, { "epoch": 0.8553600224356728, "grad_norm": 4.737624645233154, "learning_rate": 5.401326399091211e-07, "loss": 0.4887765645980835, "step": 6100 }, { "epoch": 0.8555002453901703, "grad_norm": 5.37550163269043, "learning_rate": 5.391065924919786e-07, "loss": 0.32557111978530884, "step": 6101 }, { "epoch": 0.855640468344668, "grad_norm": 5.530886173248291, "learning_rate": 5.380814650168815e-07, "loss": 0.4416327178478241, "step": 6102 }, { "epoch": 0.8557806912991657, "grad_norm": 4.17859411239624, "learning_rate": 5.370572576952359e-07, "loss": 0.4519381523132324, "step": 6103 }, { "epoch": 0.8559209142536633, "grad_norm": 2.7738094329833984, "learning_rate": 5.360339707382578e-07, "loss": 0.5121080875396729, "step": 6104 }, { "epoch": 0.856061137208161, "grad_norm": 3.0884740352630615, "learning_rate": 5.350116043569708e-07, "loss": 0.4794786870479584, "step": 6105 }, { "epoch": 0.8562013601626586, "grad_norm": 4.984045028686523, "learning_rate": 5.339901587622154e-07, "loss": 0.4749660789966583, "step": 6106 }, { "epoch": 0.8563415831171562, "grad_norm": 8.419073104858398, "learning_rate": 5.32969634164634e-07, "loss": 0.5398589372634888, "step": 6107 }, { "epoch": 0.8564818060716539, "grad_norm": 3.7715890407562256, "learning_rate": 5.31950030774685e-07, "loss": 0.5534454584121704, "step": 6108 }, { "epoch": 0.8566220290261516, "grad_norm": 4.84243106842041, "learning_rate": 5.309313488026336e-07, "loss": 0.45708683133125305, "step": 6109 }, { "epoch": 0.8567622519806493, "grad_norm": 6.110823631286621, "learning_rate": 5.299135884585582e-07, "loss": 0.4443765878677368, "step": 6110 }, { "epoch": 0.8569024749351469, "grad_norm": 6.40153169631958, "learning_rate": 5.288967499523418e-07, "loss": 0.4349692761898041, "step": 6111 }, { "epoch": 0.8570426978896445, "grad_norm": 3.703591823577881, "learning_rate": 5.278808334936847e-07, "loss": 0.48623448610305786, "step": 6112 }, { "epoch": 0.8571829208441422, "grad_norm": 3.087911367416382, "learning_rate": 5.2686583929209e-07, "loss": 0.5367450714111328, "step": 6113 }, { "epoch": 0.8573231437986398, "grad_norm": 3.720700263977051, "learning_rate": 5.258517675568742e-07, "loss": 0.4228687584400177, "step": 6114 }, { "epoch": 0.8574633667531375, "grad_norm": 3.4644792079925537, "learning_rate": 5.248386184971632e-07, "loss": 0.4996946454048157, "step": 6115 }, { "epoch": 0.8576035897076352, "grad_norm": 5.176329612731934, "learning_rate": 5.238263923218928e-07, "loss": 0.45662420988082886, "step": 6116 }, { "epoch": 0.8577438126621328, "grad_norm": 2.237504720687866, "learning_rate": 5.228150892398076e-07, "loss": 0.5448564291000366, "step": 6117 }, { "epoch": 0.8578840356166304, "grad_norm": 3.62772274017334, "learning_rate": 5.21804709459463e-07, "loss": 0.6019477844238281, "step": 6118 }, { "epoch": 0.8580242585711281, "grad_norm": 2.9647860527038574, "learning_rate": 5.207952531892208e-07, "loss": 0.5242617130279541, "step": 6119 }, { "epoch": 0.8581644815256257, "grad_norm": 4.584299564361572, "learning_rate": 5.197867206372587e-07, "loss": 0.562610924243927, "step": 6120 }, { "epoch": 0.8583047044801234, "grad_norm": 3.5597383975982666, "learning_rate": 5.187791120115565e-07, "loss": 0.4381536841392517, "step": 6121 }, { "epoch": 0.8584449274346211, "grad_norm": 4.110355377197266, "learning_rate": 5.177724275199092e-07, "loss": 0.4316568076610565, "step": 6122 }, { "epoch": 0.8585851503891186, "grad_norm": 5.147919654846191, "learning_rate": 5.167666673699179e-07, "loss": 0.5046255588531494, "step": 6123 }, { "epoch": 0.8587253733436163, "grad_norm": 5.229735851287842, "learning_rate": 5.157618317689955e-07, "loss": 0.5255545377731323, "step": 6124 }, { "epoch": 0.858865596298114, "grad_norm": 7.095446586608887, "learning_rate": 5.147579209243602e-07, "loss": 0.44860219955444336, "step": 6125 }, { "epoch": 0.8590058192526117, "grad_norm": 3.129851818084717, "learning_rate": 5.137549350430465e-07, "loss": 0.4868948757648468, "step": 6126 }, { "epoch": 0.8591460422071093, "grad_norm": 2.986868143081665, "learning_rate": 5.127528743318899e-07, "loss": 0.49893009662628174, "step": 6127 }, { "epoch": 0.859286265161607, "grad_norm": 3.333935499191284, "learning_rate": 5.117517389975407e-07, "loss": 0.512389600276947, "step": 6128 }, { "epoch": 0.8594264881161046, "grad_norm": 3.273777961730957, "learning_rate": 5.107515292464571e-07, "loss": 0.5284743309020996, "step": 6129 }, { "epoch": 0.8595667110706022, "grad_norm": 6.075028419494629, "learning_rate": 5.097522452849063e-07, "loss": 0.4382099509239197, "step": 6130 }, { "epoch": 0.8597069340250999, "grad_norm": 4.400467872619629, "learning_rate": 5.087538873189618e-07, "loss": 0.4878127872943878, "step": 6131 }, { "epoch": 0.8598471569795976, "grad_norm": 3.823761463165283, "learning_rate": 5.077564555545128e-07, "loss": 0.4584558308124542, "step": 6132 }, { "epoch": 0.8599873799340952, "grad_norm": 2.873786449432373, "learning_rate": 5.067599501972503e-07, "loss": 0.5687689185142517, "step": 6133 }, { "epoch": 0.8601276028885929, "grad_norm": 5.793558597564697, "learning_rate": 5.057643714526784e-07, "loss": 0.5272310376167297, "step": 6134 }, { "epoch": 0.8602678258430905, "grad_norm": 6.364016056060791, "learning_rate": 5.047697195261081e-07, "loss": 0.6245299577713013, "step": 6135 }, { "epoch": 0.8604080487975881, "grad_norm": 3.3288302421569824, "learning_rate": 5.037759946226628e-07, "loss": 0.6217705011367798, "step": 6136 }, { "epoch": 0.8605482717520858, "grad_norm": 7.190315246582031, "learning_rate": 5.027831969472685e-07, "loss": 0.5397258996963501, "step": 6137 }, { "epoch": 0.8606884947065835, "grad_norm": 4.195319652557373, "learning_rate": 5.01791326704667e-07, "loss": 0.480267196893692, "step": 6138 }, { "epoch": 0.8608287176610812, "grad_norm": 4.835942268371582, "learning_rate": 5.008003840994036e-07, "loss": 0.5469614863395691, "step": 6139 }, { "epoch": 0.8609689406155787, "grad_norm": 4.634002208709717, "learning_rate": 4.998103693358342e-07, "loss": 0.5402122735977173, "step": 6140 }, { "epoch": 0.8611091635700764, "grad_norm": 4.961989879608154, "learning_rate": 4.988212826181238e-07, "loss": 0.570580780506134, "step": 6141 }, { "epoch": 0.8612493865245741, "grad_norm": 4.661580562591553, "learning_rate": 4.978331241502465e-07, "loss": 0.49881064891815186, "step": 6142 }, { "epoch": 0.8613896094790717, "grad_norm": 22.19768714904785, "learning_rate": 4.968458941359811e-07, "loss": 0.4895189106464386, "step": 6143 }, { "epoch": 0.8615298324335694, "grad_norm": 4.744365692138672, "learning_rate": 4.958595927789212e-07, "loss": 0.4855647683143616, "step": 6144 }, { "epoch": 0.8616700553880671, "grad_norm": 3.1192195415496826, "learning_rate": 4.948742202824625e-07, "loss": 0.5651423931121826, "step": 6145 }, { "epoch": 0.8618102783425646, "grad_norm": 4.132171154022217, "learning_rate": 4.938897768498158e-07, "loss": 0.5624023079872131, "step": 6146 }, { "epoch": 0.8619505012970623, "grad_norm": 4.740688323974609, "learning_rate": 4.929062626839936e-07, "loss": 0.45918959379196167, "step": 6147 }, { "epoch": 0.86209072425156, "grad_norm": 3.7468321323394775, "learning_rate": 4.919236779878205e-07, "loss": 0.6142987012863159, "step": 6148 }, { "epoch": 0.8622309472060576, "grad_norm": 3.371502637863159, "learning_rate": 4.909420229639294e-07, "loss": 0.42076820135116577, "step": 6149 }, { "epoch": 0.8623711701605553, "grad_norm": 3.7761690616607666, "learning_rate": 4.899612978147622e-07, "loss": 0.4759458005428314, "step": 6150 }, { "epoch": 0.862511393115053, "grad_norm": 3.7782270908355713, "learning_rate": 4.889815027425637e-07, "loss": 0.5257951617240906, "step": 6151 }, { "epoch": 0.8626516160695505, "grad_norm": 2.80558705329895, "learning_rate": 4.880026379493951e-07, "loss": 0.4627722501754761, "step": 6152 }, { "epoch": 0.8627918390240482, "grad_norm": 4.937188148498535, "learning_rate": 4.87024703637119e-07, "loss": 0.5278668403625488, "step": 6153 }, { "epoch": 0.8629320619785459, "grad_norm": 9.414649963378906, "learning_rate": 4.860477000074093e-07, "loss": 0.47466158866882324, "step": 6154 }, { "epoch": 0.8630722849330436, "grad_norm": 4.0392560958862305, "learning_rate": 4.850716272617473e-07, "loss": 0.4872925877571106, "step": 6155 }, { "epoch": 0.8632125078875412, "grad_norm": 3.268385171890259, "learning_rate": 4.840964856014236e-07, "loss": 0.5344682335853577, "step": 6156 }, { "epoch": 0.8633527308420389, "grad_norm": 23.242774963378906, "learning_rate": 4.831222752275322e-07, "loss": 0.46450185775756836, "step": 6157 }, { "epoch": 0.8634929537965365, "grad_norm": 6.027032375335693, "learning_rate": 4.821489963409825e-07, "loss": 0.4702167510986328, "step": 6158 }, { "epoch": 0.8636331767510341, "grad_norm": 3.9268457889556885, "learning_rate": 4.811766491424852e-07, "loss": 0.6016159057617188, "step": 6159 }, { "epoch": 0.8637733997055318, "grad_norm": 4.726380348205566, "learning_rate": 4.802052338325619e-07, "loss": 0.5623700618743896, "step": 6160 }, { "epoch": 0.8639136226600295, "grad_norm": 4.5140604972839355, "learning_rate": 4.792347506115419e-07, "loss": 0.5127232074737549, "step": 6161 }, { "epoch": 0.8640538456145271, "grad_norm": 6.314579486846924, "learning_rate": 4.782651996795617e-07, "loss": 0.5141472220420837, "step": 6162 }, { "epoch": 0.8641940685690247, "grad_norm": 8.816179275512695, "learning_rate": 4.772965812365643e-07, "loss": 0.5353741645812988, "step": 6163 }, { "epoch": 0.8643342915235224, "grad_norm": 4.948485851287842, "learning_rate": 4.763288954823042e-07, "loss": 0.5515885353088379, "step": 6164 }, { "epoch": 0.86447451447802, "grad_norm": 2.695988178253174, "learning_rate": 4.7536214261633964e-07, "loss": 0.49391263723373413, "step": 6165 }, { "epoch": 0.8646147374325177, "grad_norm": 4.853061199188232, "learning_rate": 4.7439632283803826e-07, "loss": 0.4752282500267029, "step": 6166 }, { "epoch": 0.8647549603870154, "grad_norm": 2.4917855262756348, "learning_rate": 4.7343143634657475e-07, "loss": 0.5233514904975891, "step": 6167 }, { "epoch": 0.864895183341513, "grad_norm": 3.995392322540283, "learning_rate": 4.7246748334093317e-07, "loss": 0.4828329086303711, "step": 6168 }, { "epoch": 0.8650354062960106, "grad_norm": 4.680375576019287, "learning_rate": 4.7150446401990014e-07, "loss": 0.5049529075622559, "step": 6169 }, { "epoch": 0.8651756292505083, "grad_norm": 3.368821620941162, "learning_rate": 4.705423785820773e-07, "loss": 0.42786112427711487, "step": 6170 }, { "epoch": 0.865315852205006, "grad_norm": 6.108922481536865, "learning_rate": 4.6958122722586595e-07, "loss": 0.5547919869422913, "step": 6171 }, { "epoch": 0.8654560751595036, "grad_norm": 7.032618522644043, "learning_rate": 4.686210101494804e-07, "loss": 0.5486111640930176, "step": 6172 }, { "epoch": 0.8655962981140013, "grad_norm": 5.277344703674316, "learning_rate": 4.676617275509393e-07, "loss": 0.5889949202537537, "step": 6173 }, { "epoch": 0.865736521068499, "grad_norm": 4.440482139587402, "learning_rate": 4.667033796280696e-07, "loss": 0.5126322507858276, "step": 6174 }, { "epoch": 0.8658767440229965, "grad_norm": 2.858509063720703, "learning_rate": 4.657459665785058e-07, "loss": 0.3813086450099945, "step": 6175 }, { "epoch": 0.8660169669774942, "grad_norm": 3.9926462173461914, "learning_rate": 4.6478948859968955e-07, "loss": 0.5497701168060303, "step": 6176 }, { "epoch": 0.8661571899319919, "grad_norm": 4.249154090881348, "learning_rate": 4.638339458888663e-07, "loss": 0.5694629549980164, "step": 6177 }, { "epoch": 0.8662974128864895, "grad_norm": 2.8672096729278564, "learning_rate": 4.628793386430963e-07, "loss": 0.5849848985671997, "step": 6178 }, { "epoch": 0.8664376358409872, "grad_norm": 14.312941551208496, "learning_rate": 4.619256670592392e-07, "loss": 0.45496779680252075, "step": 6179 }, { "epoch": 0.8665778587954848, "grad_norm": 5.34425163269043, "learning_rate": 4.6097293133396505e-07, "loss": 0.5044119358062744, "step": 6180 }, { "epoch": 0.8667180817499824, "grad_norm": 5.392059803009033, "learning_rate": 4.600211316637504e-07, "loss": 0.6125530004501343, "step": 6181 }, { "epoch": 0.8668583047044801, "grad_norm": 2.9999008178710938, "learning_rate": 4.590702682448811e-07, "loss": 0.4980255365371704, "step": 6182 }, { "epoch": 0.8669985276589778, "grad_norm": 3.137176036834717, "learning_rate": 4.581203412734436e-07, "loss": 0.45679378509521484, "step": 6183 }, { "epoch": 0.8671387506134755, "grad_norm": 4.006549835205078, "learning_rate": 4.5717135094534016e-07, "loss": 0.5314128398895264, "step": 6184 }, { "epoch": 0.8672789735679731, "grad_norm": 4.113144397735596, "learning_rate": 4.562232974562714e-07, "loss": 0.5180879235267639, "step": 6185 }, { "epoch": 0.8674191965224707, "grad_norm": 4.369700908660889, "learning_rate": 4.5527618100174976e-07, "loss": 0.4891033470630646, "step": 6186 }, { "epoch": 0.8675594194769684, "grad_norm": 3.4892661571502686, "learning_rate": 4.543300017770935e-07, "loss": 0.39322909712791443, "step": 6187 }, { "epoch": 0.867699642431466, "grad_norm": 4.078638076782227, "learning_rate": 4.533847599774277e-07, "loss": 0.47069016098976135, "step": 6188 }, { "epoch": 0.8678398653859637, "grad_norm": 3.5549912452697754, "learning_rate": 4.524404557976808e-07, "loss": 0.4976484775543213, "step": 6189 }, { "epoch": 0.8679800883404614, "grad_norm": 3.644702672958374, "learning_rate": 4.5149708943259483e-07, "loss": 0.45337486267089844, "step": 6190 }, { "epoch": 0.868120311294959, "grad_norm": 4.985726833343506, "learning_rate": 4.5055466107671084e-07, "loss": 0.4666650891304016, "step": 6191 }, { "epoch": 0.8682605342494566, "grad_norm": 3.249546766281128, "learning_rate": 4.4961317092438174e-07, "loss": 0.4836929142475128, "step": 6192 }, { "epoch": 0.8684007572039543, "grad_norm": 4.591796875, "learning_rate": 4.486726191697649e-07, "loss": 0.45104819536209106, "step": 6193 }, { "epoch": 0.8685409801584519, "grad_norm": 3.3294713497161865, "learning_rate": 4.477330060068247e-07, "loss": 0.5608555674552917, "step": 6194 }, { "epoch": 0.8686812031129496, "grad_norm": 3.2659707069396973, "learning_rate": 4.4679433162932937e-07, "loss": 0.4209635853767395, "step": 6195 }, { "epoch": 0.8688214260674473, "grad_norm": 3.985828399658203, "learning_rate": 4.458565962308592e-07, "loss": 0.5708413124084473, "step": 6196 }, { "epoch": 0.8689616490219448, "grad_norm": 7.866321563720703, "learning_rate": 4.4491980000479554e-07, "loss": 0.5012202858924866, "step": 6197 }, { "epoch": 0.8691018719764425, "grad_norm": 5.912465572357178, "learning_rate": 4.439839431443277e-07, "loss": 0.5060169696807861, "step": 6198 }, { "epoch": 0.8692420949309402, "grad_norm": 4.221380710601807, "learning_rate": 4.4304902584245245e-07, "loss": 0.5716583728790283, "step": 6199 }, { "epoch": 0.8693823178854378, "grad_norm": 4.337264060974121, "learning_rate": 4.421150482919728e-07, "loss": 0.49778079986572266, "step": 6200 }, { "epoch": 0.8695225408399355, "grad_norm": 6.136110782623291, "learning_rate": 4.4118201068549415e-07, "loss": 0.4645495116710663, "step": 6201 }, { "epoch": 0.8696627637944332, "grad_norm": 3.2882397174835205, "learning_rate": 4.402499132154348e-07, "loss": 0.4701688885688782, "step": 6202 }, { "epoch": 0.8698029867489308, "grad_norm": 3.844143867492676, "learning_rate": 4.3931875607401086e-07, "loss": 0.4945991635322571, "step": 6203 }, { "epoch": 0.8699432097034284, "grad_norm": 5.004286289215088, "learning_rate": 4.383885394532539e-07, "loss": 0.5045117139816284, "step": 6204 }, { "epoch": 0.8700834326579261, "grad_norm": 3.1561968326568604, "learning_rate": 4.3745926354499315e-07, "loss": 0.436651349067688, "step": 6205 }, { "epoch": 0.8702236556124238, "grad_norm": 3.364365577697754, "learning_rate": 4.3653092854086864e-07, "loss": 0.4754066467285156, "step": 6206 }, { "epoch": 0.8703638785669214, "grad_norm": 4.6823930740356445, "learning_rate": 4.356035346323245e-07, "loss": 0.5348535180091858, "step": 6207 }, { "epoch": 0.8705041015214191, "grad_norm": 3.249521017074585, "learning_rate": 4.346770820106133e-07, "loss": 0.49652597308158875, "step": 6208 }, { "epoch": 0.8706443244759167, "grad_norm": 5.08164119720459, "learning_rate": 4.337515708667878e-07, "loss": 0.540960431098938, "step": 6209 }, { "epoch": 0.8707845474304143, "grad_norm": 4.727184772491455, "learning_rate": 4.3282700139171406e-07, "loss": 0.517547607421875, "step": 6210 }, { "epoch": 0.870924770384912, "grad_norm": 3.585969924926758, "learning_rate": 4.3190337377605863e-07, "loss": 0.5008244514465332, "step": 6211 }, { "epoch": 0.8710649933394097, "grad_norm": 5.64485502243042, "learning_rate": 4.3098068821029517e-07, "loss": 0.49840718507766724, "step": 6212 }, { "epoch": 0.8712052162939073, "grad_norm": 3.7190771102905273, "learning_rate": 4.300589448847037e-07, "loss": 0.4817824363708496, "step": 6213 }, { "epoch": 0.871345439248405, "grad_norm": 3.7441093921661377, "learning_rate": 4.2913814398936993e-07, "loss": 0.519174337387085, "step": 6214 }, { "epoch": 0.8714856622029026, "grad_norm": 3.1138863563537598, "learning_rate": 4.282182857141831e-07, "loss": 0.4702731668949127, "step": 6215 }, { "epoch": 0.8716258851574002, "grad_norm": 5.174038410186768, "learning_rate": 4.2729937024884315e-07, "loss": 0.5206326246261597, "step": 6216 }, { "epoch": 0.8717661081118979, "grad_norm": 3.336731433868408, "learning_rate": 4.263813977828496e-07, "loss": 0.4263184368610382, "step": 6217 }, { "epoch": 0.8719063310663956, "grad_norm": 4.452002048492432, "learning_rate": 4.2546436850551044e-07, "loss": 0.5065233707427979, "step": 6218 }, { "epoch": 0.8720465540208933, "grad_norm": 3.8937549591064453, "learning_rate": 4.245482826059394e-07, "loss": 0.38229620456695557, "step": 6219 }, { "epoch": 0.8721867769753908, "grad_norm": 4.86118745803833, "learning_rate": 4.236331402730559e-07, "loss": 0.6014640927314758, "step": 6220 }, { "epoch": 0.8723269999298885, "grad_norm": 3.648245096206665, "learning_rate": 4.2271894169558127e-07, "loss": 0.5556396245956421, "step": 6221 }, { "epoch": 0.8724672228843862, "grad_norm": 3.3949363231658936, "learning_rate": 4.218056870620485e-07, "loss": 0.4837261736392975, "step": 6222 }, { "epoch": 0.8726074458388838, "grad_norm": 3.5386388301849365, "learning_rate": 4.208933765607898e-07, "loss": 0.5021528005599976, "step": 6223 }, { "epoch": 0.8727476687933815, "grad_norm": 3.267667531967163, "learning_rate": 4.199820103799457e-07, "loss": 0.4992366433143616, "step": 6224 }, { "epoch": 0.8728878917478792, "grad_norm": 3.001965284347534, "learning_rate": 4.1907158870746256e-07, "loss": 0.4418685734272003, "step": 6225 }, { "epoch": 0.8730281147023767, "grad_norm": 4.217376708984375, "learning_rate": 4.181621117310908e-07, "loss": 0.501887321472168, "step": 6226 }, { "epoch": 0.8731683376568744, "grad_norm": 3.1698620319366455, "learning_rate": 4.1725357963838366e-07, "loss": 0.545934796333313, "step": 6227 }, { "epoch": 0.8733085606113721, "grad_norm": 4.0339436531066895, "learning_rate": 4.163459926167057e-07, "loss": 0.6331784129142761, "step": 6228 }, { "epoch": 0.8734487835658697, "grad_norm": 10.9097261428833, "learning_rate": 4.154393508532206e-07, "loss": 0.5746479034423828, "step": 6229 }, { "epoch": 0.8735890065203674, "grad_norm": 3.1161510944366455, "learning_rate": 4.145336545348999e-07, "loss": 0.49587100744247437, "step": 6230 }, { "epoch": 0.8737292294748651, "grad_norm": 2.971090316772461, "learning_rate": 4.136289038485197e-07, "loss": 0.5145991444587708, "step": 6231 }, { "epoch": 0.8738694524293626, "grad_norm": 3.1745848655700684, "learning_rate": 4.1272509898066083e-07, "loss": 0.4737186133861542, "step": 6232 }, { "epoch": 0.8740096753838603, "grad_norm": 6.695793151855469, "learning_rate": 4.1182224011770964e-07, "loss": 0.43988358974456787, "step": 6233 }, { "epoch": 0.874149898338358, "grad_norm": 2.906381368637085, "learning_rate": 4.1092032744585787e-07, "loss": 0.5352190732955933, "step": 6234 }, { "epoch": 0.8742901212928557, "grad_norm": 3.4749810695648193, "learning_rate": 4.100193611510983e-07, "loss": 0.5320730209350586, "step": 6235 }, { "epoch": 0.8744303442473533, "grad_norm": 3.7775304317474365, "learning_rate": 4.091193414192357e-07, "loss": 0.46173518896102905, "step": 6236 }, { "epoch": 0.8745705672018509, "grad_norm": 3.3994908332824707, "learning_rate": 4.082202684358727e-07, "loss": 0.4711923599243164, "step": 6237 }, { "epoch": 0.8747107901563486, "grad_norm": 3.4530067443847656, "learning_rate": 4.073221423864199e-07, "loss": 0.4884164333343506, "step": 6238 }, { "epoch": 0.8748510131108462, "grad_norm": 3.135263681411743, "learning_rate": 4.0642496345609295e-07, "loss": 0.43810468912124634, "step": 6239 }, { "epoch": 0.8749912360653439, "grad_norm": 4.621537685394287, "learning_rate": 4.0552873182991114e-07, "loss": 0.5761824250221252, "step": 6240 }, { "epoch": 0.8751314590198416, "grad_norm": 3.801389217376709, "learning_rate": 4.046334476926972e-07, "loss": 0.49086081981658936, "step": 6241 }, { "epoch": 0.8752716819743392, "grad_norm": 3.3008294105529785, "learning_rate": 4.037391112290828e-07, "loss": 0.4935500919818878, "step": 6242 }, { "epoch": 0.8754119049288368, "grad_norm": 2.803039312362671, "learning_rate": 4.028457226234994e-07, "loss": 0.5290677547454834, "step": 6243 }, { "epoch": 0.8755521278833345, "grad_norm": 4.070984840393066, "learning_rate": 4.0195328206018515e-07, "loss": 0.641440749168396, "step": 6244 }, { "epoch": 0.8756923508378321, "grad_norm": 6.2046074867248535, "learning_rate": 4.010617897231822e-07, "loss": 0.544421374797821, "step": 6245 }, { "epoch": 0.8758325737923298, "grad_norm": 4.89216947555542, "learning_rate": 4.0017124579633917e-07, "loss": 0.490679532289505, "step": 6246 }, { "epoch": 0.8759727967468275, "grad_norm": 3.5929176807403564, "learning_rate": 3.99281650463304e-07, "loss": 0.4830724895000458, "step": 6247 }, { "epoch": 0.8761130197013252, "grad_norm": 3.621598243713379, "learning_rate": 3.9839300390753677e-07, "loss": 0.5578638911247253, "step": 6248 }, { "epoch": 0.8762532426558227, "grad_norm": 7.731222152709961, "learning_rate": 3.9750530631229357e-07, "loss": 0.5092662572860718, "step": 6249 }, { "epoch": 0.8763934656103204, "grad_norm": 11.595685005187988, "learning_rate": 3.9661855786064076e-07, "loss": 0.4929966628551483, "step": 6250 }, { "epoch": 0.8765336885648181, "grad_norm": 3.8654825687408447, "learning_rate": 3.957327587354459e-07, "loss": 0.5699561834335327, "step": 6251 }, { "epoch": 0.8766739115193157, "grad_norm": 5.24092960357666, "learning_rate": 3.9484790911938353e-07, "loss": 0.5901668071746826, "step": 6252 }, { "epoch": 0.8768141344738134, "grad_norm": 3.736661434173584, "learning_rate": 3.939640091949276e-07, "loss": 0.45215097069740295, "step": 6253 }, { "epoch": 0.876954357428311, "grad_norm": 4.0930705070495605, "learning_rate": 3.9308105914436237e-07, "loss": 0.43884724378585815, "step": 6254 }, { "epoch": 0.8770945803828086, "grad_norm": 16.540250778198242, "learning_rate": 3.921990591497715e-07, "loss": 0.4521584212779999, "step": 6255 }, { "epoch": 0.8772348033373063, "grad_norm": 4.131829261779785, "learning_rate": 3.913180093930441e-07, "loss": 0.6159782409667969, "step": 6256 }, { "epoch": 0.877375026291804, "grad_norm": 3.585191011428833, "learning_rate": 3.904379100558742e-07, "loss": 0.5433588027954102, "step": 6257 }, { "epoch": 0.8775152492463016, "grad_norm": 3.8538947105407715, "learning_rate": 3.8955876131975934e-07, "loss": 0.523387610912323, "step": 6258 }, { "epoch": 0.8776554722007993, "grad_norm": 4.345365524291992, "learning_rate": 3.886805633659996e-07, "loss": 0.5384384393692017, "step": 6259 }, { "epoch": 0.8777956951552969, "grad_norm": 3.0585179328918457, "learning_rate": 3.8780331637570223e-07, "loss": 0.4612129330635071, "step": 6260 }, { "epoch": 0.8779359181097945, "grad_norm": 2.972074508666992, "learning_rate": 3.8692702052977313e-07, "loss": 0.3965420126914978, "step": 6261 }, { "epoch": 0.8780761410642922, "grad_norm": 3.014146089553833, "learning_rate": 3.8605167600892946e-07, "loss": 0.5840620398521423, "step": 6262 }, { "epoch": 0.8782163640187899, "grad_norm": 9.519797325134277, "learning_rate": 3.8517728299368564e-07, "loss": 0.49463745951652527, "step": 6263 }, { "epoch": 0.8783565869732876, "grad_norm": 3.8093276023864746, "learning_rate": 3.8430384166436185e-07, "loss": 0.42299339175224304, "step": 6264 }, { "epoch": 0.8784968099277852, "grad_norm": 5.483515739440918, "learning_rate": 3.834313522010835e-07, "loss": 0.5047587752342224, "step": 6265 }, { "epoch": 0.8786370328822828, "grad_norm": 4.241987705230713, "learning_rate": 3.8255981478377893e-07, "loss": 0.36334332823753357, "step": 6266 }, { "epoch": 0.8787772558367805, "grad_norm": 3.364457607269287, "learning_rate": 3.81689229592177e-07, "loss": 0.44073349237442017, "step": 6267 }, { "epoch": 0.8789174787912781, "grad_norm": 3.502164602279663, "learning_rate": 3.808195968058176e-07, "loss": 0.4413871765136719, "step": 6268 }, { "epoch": 0.8790577017457758, "grad_norm": 3.244274854660034, "learning_rate": 3.7995091660403603e-07, "loss": 0.4278065264225006, "step": 6269 }, { "epoch": 0.8791979247002735, "grad_norm": 10.438868522644043, "learning_rate": 3.7908318916597574e-07, "loss": 0.5640962719917297, "step": 6270 }, { "epoch": 0.8793381476547711, "grad_norm": 3.949042797088623, "learning_rate": 3.78216414670583e-07, "loss": 0.47685056924819946, "step": 6271 }, { "epoch": 0.8794783706092687, "grad_norm": 3.5959572792053223, "learning_rate": 3.773505932966082e-07, "loss": 0.5539879202842712, "step": 6272 }, { "epoch": 0.8796185935637664, "grad_norm": 3.4470064640045166, "learning_rate": 3.7648572522260175e-07, "loss": 0.48281988501548767, "step": 6273 }, { "epoch": 0.879758816518264, "grad_norm": 5.369194984436035, "learning_rate": 3.756218106269227e-07, "loss": 0.405731737613678, "step": 6274 }, { "epoch": 0.8798990394727617, "grad_norm": 3.324153184890747, "learning_rate": 3.7475884968772856e-07, "loss": 0.4741559624671936, "step": 6275 }, { "epoch": 0.8800392624272594, "grad_norm": 5.068419933319092, "learning_rate": 3.738968425829836e-07, "loss": 0.44152969121932983, "step": 6276 }, { "epoch": 0.8801794853817569, "grad_norm": 4.96820592880249, "learning_rate": 3.730357894904535e-07, "loss": 0.5001162886619568, "step": 6277 }, { "epoch": 0.8803197083362546, "grad_norm": 3.3920931816101074, "learning_rate": 3.7217569058770944e-07, "loss": 0.453571617603302, "step": 6278 }, { "epoch": 0.8804599312907523, "grad_norm": 3.7639667987823486, "learning_rate": 3.713165460521206e-07, "loss": 0.5262458920478821, "step": 6279 }, { "epoch": 0.88060015424525, "grad_norm": 4.192340850830078, "learning_rate": 3.7045835606086764e-07, "loss": 0.33819490671157837, "step": 6280 }, { "epoch": 0.8807403771997476, "grad_norm": 4.7011847496032715, "learning_rate": 3.6960112079092613e-07, "loss": 0.4907991588115692, "step": 6281 }, { "epoch": 0.8808806001542453, "grad_norm": 6.885136127471924, "learning_rate": 3.687448404190791e-07, "loss": 0.5161405205726624, "step": 6282 }, { "epoch": 0.8810208231087429, "grad_norm": 3.1072890758514404, "learning_rate": 3.6788951512191306e-07, "loss": 0.5114532709121704, "step": 6283 }, { "epoch": 0.8811610460632405, "grad_norm": 3.5764408111572266, "learning_rate": 3.6703514507581586e-07, "loss": 0.5880341529846191, "step": 6284 }, { "epoch": 0.8813012690177382, "grad_norm": 4.202634811401367, "learning_rate": 3.66181730456977e-07, "loss": 0.4553258419036865, "step": 6285 }, { "epoch": 0.8814414919722359, "grad_norm": 3.5234262943267822, "learning_rate": 3.6532927144139475e-07, "loss": 0.4598923325538635, "step": 6286 }, { "epoch": 0.8815817149267335, "grad_norm": 2.99609112739563, "learning_rate": 3.6447776820486227e-07, "loss": 0.49121904373168945, "step": 6287 }, { "epoch": 0.8817219378812312, "grad_norm": 3.207470178604126, "learning_rate": 3.6362722092298243e-07, "loss": 0.6123430132865906, "step": 6288 }, { "epoch": 0.8818621608357288, "grad_norm": 8.301007270812988, "learning_rate": 3.627776297711566e-07, "loss": 0.46634018421173096, "step": 6289 }, { "epoch": 0.8820023837902264, "grad_norm": 5.707313060760498, "learning_rate": 3.619289949245919e-07, "loss": 0.48311740159988403, "step": 6290 }, { "epoch": 0.8821426067447241, "grad_norm": 3.430060863494873, "learning_rate": 3.6108131655829605e-07, "loss": 0.49607419967651367, "step": 6291 }, { "epoch": 0.8822828296992218, "grad_norm": 2.382871150970459, "learning_rate": 3.60234594847082e-07, "loss": 0.4271370768547058, "step": 6292 }, { "epoch": 0.8824230526537195, "grad_norm": 5.882759094238281, "learning_rate": 3.593888299655612e-07, "loss": 0.503017246723175, "step": 6293 }, { "epoch": 0.882563275608217, "grad_norm": 3.019299030303955, "learning_rate": 3.585440220881531e-07, "loss": 0.48494595289230347, "step": 6294 }, { "epoch": 0.8827034985627147, "grad_norm": 2.943922519683838, "learning_rate": 3.5770017138907544e-07, "loss": 0.4956873953342438, "step": 6295 }, { "epoch": 0.8828437215172124, "grad_norm": 3.710536003112793, "learning_rate": 3.568572780423507e-07, "loss": 0.5397679805755615, "step": 6296 }, { "epoch": 0.88298394447171, "grad_norm": 7.207403659820557, "learning_rate": 3.560153422218032e-07, "loss": 0.48275163769721985, "step": 6297 }, { "epoch": 0.8831241674262077, "grad_norm": 5.731988430023193, "learning_rate": 3.5517436410106185e-07, "loss": 0.5284103751182556, "step": 6298 }, { "epoch": 0.8832643903807054, "grad_norm": 3.395639181137085, "learning_rate": 3.5433434385355293e-07, "loss": 0.5470658540725708, "step": 6299 }, { "epoch": 0.8834046133352029, "grad_norm": 4.523375988006592, "learning_rate": 3.534952816525122e-07, "loss": 0.5010764002799988, "step": 6300 }, { "epoch": 0.8835448362897006, "grad_norm": 4.884759426116943, "learning_rate": 3.526571776709714e-07, "loss": 0.5601965188980103, "step": 6301 }, { "epoch": 0.8836850592441983, "grad_norm": 2.454686164855957, "learning_rate": 3.5182003208176885e-07, "loss": 0.44748422503471375, "step": 6302 }, { "epoch": 0.8838252821986959, "grad_norm": 3.7920117378234863, "learning_rate": 3.5098384505754314e-07, "loss": 0.4058155417442322, "step": 6303 }, { "epoch": 0.8839655051531936, "grad_norm": 4.0583815574646, "learning_rate": 3.501486167707374e-07, "loss": 0.551499605178833, "step": 6304 }, { "epoch": 0.8841057281076913, "grad_norm": 4.835405349731445, "learning_rate": 3.493143473935928e-07, "loss": 0.3985919952392578, "step": 6305 }, { "epoch": 0.8842459510621888, "grad_norm": 3.2670156955718994, "learning_rate": 3.4848103709815837e-07, "loss": 0.4182354211807251, "step": 6306 }, { "epoch": 0.8843861740166865, "grad_norm": 4.775146961212158, "learning_rate": 3.4764868605628e-07, "loss": 0.39464300870895386, "step": 6307 }, { "epoch": 0.8845263969711842, "grad_norm": 3.252504348754883, "learning_rate": 3.4681729443960974e-07, "loss": 0.4038257300853729, "step": 6308 }, { "epoch": 0.8846666199256819, "grad_norm": 2.974752187728882, "learning_rate": 3.459868624196e-07, "loss": 0.41149038076400757, "step": 6309 }, { "epoch": 0.8848068428801795, "grad_norm": 2.7129933834075928, "learning_rate": 3.451573901675054e-07, "loss": 0.40805140137672424, "step": 6310 }, { "epoch": 0.8849470658346771, "grad_norm": 4.455323219299316, "learning_rate": 3.443288778543824e-07, "loss": 0.574429988861084, "step": 6311 }, { "epoch": 0.8850872887891748, "grad_norm": 2.5459060668945312, "learning_rate": 3.4350132565109164e-07, "loss": 0.5102808475494385, "step": 6312 }, { "epoch": 0.8852275117436724, "grad_norm": 4.312536716461182, "learning_rate": 3.4267473372829153e-07, "loss": 0.40759527683258057, "step": 6313 }, { "epoch": 0.8853677346981701, "grad_norm": 3.7940967082977295, "learning_rate": 3.418491022564463e-07, "loss": 0.5342624187469482, "step": 6314 }, { "epoch": 0.8855079576526678, "grad_norm": 4.528714656829834, "learning_rate": 3.410244314058203e-07, "loss": 0.524437427520752, "step": 6315 }, { "epoch": 0.8856481806071654, "grad_norm": 3.0161757469177246, "learning_rate": 3.4020072134648085e-07, "loss": 0.4283076524734497, "step": 6316 }, { "epoch": 0.885788403561663, "grad_norm": 3.419625997543335, "learning_rate": 3.393779722482959e-07, "loss": 0.4590426981449127, "step": 6317 }, { "epoch": 0.8859286265161607, "grad_norm": 3.8786826133728027, "learning_rate": 3.3855618428093707e-07, "loss": 0.5612515211105347, "step": 6318 }, { "epoch": 0.8860688494706583, "grad_norm": 2.3139681816101074, "learning_rate": 3.377353576138742e-07, "loss": 0.36168694496154785, "step": 6319 }, { "epoch": 0.886209072425156, "grad_norm": 3.263310194015503, "learning_rate": 3.369154924163831e-07, "loss": 0.47737038135528564, "step": 6320 }, { "epoch": 0.8863492953796537, "grad_norm": 7.252425670623779, "learning_rate": 3.360965888575385e-07, "loss": 0.4402734041213989, "step": 6321 }, { "epoch": 0.8864895183341513, "grad_norm": 3.944840669631958, "learning_rate": 3.35278647106218e-07, "loss": 0.49586111307144165, "step": 6322 }, { "epoch": 0.8866297412886489, "grad_norm": 4.530950546264648, "learning_rate": 3.3446166733110074e-07, "loss": 0.490642249584198, "step": 6323 }, { "epoch": 0.8867699642431466, "grad_norm": 4.808738708496094, "learning_rate": 3.336456497006685e-07, "loss": 0.42808640003204346, "step": 6324 }, { "epoch": 0.8869101871976443, "grad_norm": 3.7167892456054688, "learning_rate": 3.3283059438320054e-07, "loss": 0.3945884704589844, "step": 6325 }, { "epoch": 0.8870504101521419, "grad_norm": 3.7535626888275146, "learning_rate": 3.3201650154678353e-07, "loss": 0.4876222312450409, "step": 6326 }, { "epoch": 0.8871906331066396, "grad_norm": 5.857436180114746, "learning_rate": 3.3120337135930105e-07, "loss": 0.491840124130249, "step": 6327 }, { "epoch": 0.8873308560611373, "grad_norm": 5.044559001922607, "learning_rate": 3.303912039884399e-07, "loss": 0.5119888782501221, "step": 6328 }, { "epoch": 0.8874710790156348, "grad_norm": 3.6271698474884033, "learning_rate": 3.2957999960168907e-07, "loss": 0.5617128610610962, "step": 6329 }, { "epoch": 0.8876113019701325, "grad_norm": 4.142279624938965, "learning_rate": 3.2876975836633796e-07, "loss": 0.4664498567581177, "step": 6330 }, { "epoch": 0.8877515249246302, "grad_norm": 3.317103147506714, "learning_rate": 3.279604804494768e-07, "loss": 0.44235146045684814, "step": 6331 }, { "epoch": 0.8878917478791278, "grad_norm": 6.973483085632324, "learning_rate": 3.271521660179994e-07, "loss": 0.522323489189148, "step": 6332 }, { "epoch": 0.8880319708336255, "grad_norm": 7.133228778839111, "learning_rate": 3.263448152385973e-07, "loss": 0.5262758135795593, "step": 6333 }, { "epoch": 0.8881721937881231, "grad_norm": 6.038126468658447, "learning_rate": 3.2553842827776683e-07, "loss": 0.5186618566513062, "step": 6334 }, { "epoch": 0.8883124167426207, "grad_norm": 7.211801528930664, "learning_rate": 3.2473300530180384e-07, "loss": 0.47101855278015137, "step": 6335 }, { "epoch": 0.8884526396971184, "grad_norm": 8.878159523010254, "learning_rate": 3.2392854647680494e-07, "loss": 0.4323374032974243, "step": 6336 }, { "epoch": 0.8885928626516161, "grad_norm": 3.587824821472168, "learning_rate": 3.2312505196866963e-07, "loss": 0.41961669921875, "step": 6337 }, { "epoch": 0.8887330856061137, "grad_norm": 17.016342163085938, "learning_rate": 3.223225219430981e-07, "loss": 0.502328634262085, "step": 6338 }, { "epoch": 0.8888733085606114, "grad_norm": 10.245205879211426, "learning_rate": 3.215209565655891e-07, "loss": 0.5904932618141174, "step": 6339 }, { "epoch": 0.889013531515109, "grad_norm": 3.84475040435791, "learning_rate": 3.2072035600144546e-07, "loss": 0.4858267903327942, "step": 6340 }, { "epoch": 0.8891537544696066, "grad_norm": 4.201672554016113, "learning_rate": 3.199207204157706e-07, "loss": 0.5788991451263428, "step": 6341 }, { "epoch": 0.8892939774241043, "grad_norm": 3.8114733695983887, "learning_rate": 3.1912204997346705e-07, "loss": 0.5482731461524963, "step": 6342 }, { "epoch": 0.889434200378602, "grad_norm": 2.859968423843384, "learning_rate": 3.1832434483924034e-07, "loss": 0.47695285081863403, "step": 6343 }, { "epoch": 0.8895744233330997, "grad_norm": 2.9976303577423096, "learning_rate": 3.175276051775972e-07, "loss": 0.5554389953613281, "step": 6344 }, { "epoch": 0.8897146462875973, "grad_norm": 5.6379265785217285, "learning_rate": 3.1673183115284225e-07, "loss": 0.6129797697067261, "step": 6345 }, { "epoch": 0.8898548692420949, "grad_norm": 5.1078314781188965, "learning_rate": 3.1593702292908424e-07, "loss": 0.3783196210861206, "step": 6346 }, { "epoch": 0.8899950921965926, "grad_norm": 3.4873969554901123, "learning_rate": 3.1514318067023043e-07, "loss": 0.4743191599845886, "step": 6347 }, { "epoch": 0.8901353151510902, "grad_norm": 4.310131549835205, "learning_rate": 3.143503045399915e-07, "loss": 0.4747859537601471, "step": 6348 }, { "epoch": 0.8902755381055879, "grad_norm": 3.2021634578704834, "learning_rate": 3.135583947018761e-07, "loss": 0.4188064932823181, "step": 6349 }, { "epoch": 0.8904157610600856, "grad_norm": 3.664354085922241, "learning_rate": 3.127674513191953e-07, "loss": 0.41199588775634766, "step": 6350 }, { "epoch": 0.8905559840145831, "grad_norm": 3.1679325103759766, "learning_rate": 3.1197747455506023e-07, "loss": 0.4724361300468445, "step": 6351 }, { "epoch": 0.8906962069690808, "grad_norm": 10.30709171295166, "learning_rate": 3.1118846457238337e-07, "loss": 0.5406294465065002, "step": 6352 }, { "epoch": 0.8908364299235785, "grad_norm": 3.7546193599700928, "learning_rate": 3.104004215338763e-07, "loss": 0.5026737451553345, "step": 6353 }, { "epoch": 0.8909766528780761, "grad_norm": 3.786402463912964, "learning_rate": 3.096133456020528e-07, "loss": 0.4475786089897156, "step": 6354 }, { "epoch": 0.8911168758325738, "grad_norm": 8.46565055847168, "learning_rate": 3.088272369392265e-07, "loss": 0.4540424942970276, "step": 6355 }, { "epoch": 0.8912570987870715, "grad_norm": 3.3865957260131836, "learning_rate": 3.080420957075114e-07, "loss": 0.4328194856643677, "step": 6356 }, { "epoch": 0.891397321741569, "grad_norm": 2.9638512134552, "learning_rate": 3.072579220688232e-07, "loss": 0.44252482056617737, "step": 6357 }, { "epoch": 0.8915375446960667, "grad_norm": 4.002925872802734, "learning_rate": 3.0647471618487635e-07, "loss": 0.5142244100570679, "step": 6358 }, { "epoch": 0.8916777676505644, "grad_norm": 4.721743106842041, "learning_rate": 3.0569247821718663e-07, "loss": 0.4248015880584717, "step": 6359 }, { "epoch": 0.8918179906050621, "grad_norm": 4.716409206390381, "learning_rate": 3.049112083270694e-07, "loss": 0.48596665263175964, "step": 6360 }, { "epoch": 0.8919582135595597, "grad_norm": 4.161472797393799, "learning_rate": 3.041309066756415e-07, "loss": 0.5112884044647217, "step": 6361 }, { "epoch": 0.8920984365140574, "grad_norm": 4.443430423736572, "learning_rate": 3.0335157342382015e-07, "loss": 0.5499827861785889, "step": 6362 }, { "epoch": 0.892238659468555, "grad_norm": 3.8637819290161133, "learning_rate": 3.025732087323219e-07, "loss": 0.5843981504440308, "step": 6363 }, { "epoch": 0.8923788824230526, "grad_norm": 3.6007497310638428, "learning_rate": 3.017958127616649e-07, "loss": 0.5316433906555176, "step": 6364 }, { "epoch": 0.8925191053775503, "grad_norm": 4.8482184410095215, "learning_rate": 3.010193856721655e-07, "loss": 0.4524117410182953, "step": 6365 }, { "epoch": 0.892659328332048, "grad_norm": 2.7642064094543457, "learning_rate": 3.0024392762394104e-07, "loss": 0.5735940933227539, "step": 6366 }, { "epoch": 0.8927995512865456, "grad_norm": 3.368631362915039, "learning_rate": 2.9946943877691037e-07, "loss": 0.5997990965843201, "step": 6367 }, { "epoch": 0.8929397742410432, "grad_norm": 4.0343499183654785, "learning_rate": 2.9869591929079124e-07, "loss": 0.44391149282455444, "step": 6368 }, { "epoch": 0.8930799971955409, "grad_norm": 10.895891189575195, "learning_rate": 2.9792336932510104e-07, "loss": 0.5316097736358643, "step": 6369 }, { "epoch": 0.8932202201500385, "grad_norm": 7.412517547607422, "learning_rate": 2.97151789039159e-07, "loss": 0.47067368030548096, "step": 6370 }, { "epoch": 0.8933604431045362, "grad_norm": 4.474780082702637, "learning_rate": 2.963811785920834e-07, "loss": 0.4211066961288452, "step": 6371 }, { "epoch": 0.8935006660590339, "grad_norm": 3.757434368133545, "learning_rate": 2.9561153814279097e-07, "loss": 0.5336971282958984, "step": 6372 }, { "epoch": 0.8936408890135316, "grad_norm": 4.166934013366699, "learning_rate": 2.9484286785000093e-07, "loss": 0.5148067474365234, "step": 6373 }, { "epoch": 0.8937811119680291, "grad_norm": 3.9343254566192627, "learning_rate": 2.940751678722303e-07, "loss": 0.6140024662017822, "step": 6374 }, { "epoch": 0.8939213349225268, "grad_norm": 6.139981269836426, "learning_rate": 2.9330843836779867e-07, "loss": 0.5343812704086304, "step": 6375 }, { "epoch": 0.8940615578770245, "grad_norm": 6.165988445281982, "learning_rate": 2.9254267949482217e-07, "loss": 0.5510526299476624, "step": 6376 }, { "epoch": 0.8942017808315221, "grad_norm": 3.8324782848358154, "learning_rate": 2.9177789141122016e-07, "loss": 0.4888492822647095, "step": 6377 }, { "epoch": 0.8943420037860198, "grad_norm": 2.567937135696411, "learning_rate": 2.9101407427470863e-07, "loss": 0.4396015405654907, "step": 6378 }, { "epoch": 0.8944822267405175, "grad_norm": 3.56432843208313, "learning_rate": 2.9025122824280496e-07, "loss": 0.46375763416290283, "step": 6379 }, { "epoch": 0.894622449695015, "grad_norm": 3.142287254333496, "learning_rate": 2.8948935347282657e-07, "loss": 0.5691022872924805, "step": 6380 }, { "epoch": 0.8947626726495127, "grad_norm": 4.0236616134643555, "learning_rate": 2.887284501218901e-07, "loss": 0.4704663157463074, "step": 6381 }, { "epoch": 0.8949028956040104, "grad_norm": 3.4972784519195557, "learning_rate": 2.8796851834691164e-07, "loss": 0.5126334428787231, "step": 6382 }, { "epoch": 0.895043118558508, "grad_norm": 3.5280063152313232, "learning_rate": 2.8720955830460753e-07, "loss": 0.5337185859680176, "step": 6383 }, { "epoch": 0.8951833415130057, "grad_norm": 4.028863430023193, "learning_rate": 2.864515701514925e-07, "loss": 0.5977660417556763, "step": 6384 }, { "epoch": 0.8953235644675034, "grad_norm": 3.9105632305145264, "learning_rate": 2.8569455404388326e-07, "loss": 0.5066303610801697, "step": 6385 }, { "epoch": 0.895463787422001, "grad_norm": 4.207047462463379, "learning_rate": 2.8493851013789263e-07, "loss": 0.48561516404151917, "step": 6386 }, { "epoch": 0.8956040103764986, "grad_norm": 3.448890209197998, "learning_rate": 2.8418343858943596e-07, "loss": 0.4403822720050812, "step": 6387 }, { "epoch": 0.8957442333309963, "grad_norm": 4.1047186851501465, "learning_rate": 2.8342933955422644e-07, "loss": 0.5208213329315186, "step": 6388 }, { "epoch": 0.895884456285494, "grad_norm": 4.768404483795166, "learning_rate": 2.8267621318777695e-07, "loss": 0.5017185807228088, "step": 6389 }, { "epoch": 0.8960246792399916, "grad_norm": 4.160044193267822, "learning_rate": 2.819240596454009e-07, "loss": 0.4508909583091736, "step": 6390 }, { "epoch": 0.8961649021944892, "grad_norm": 6.157525062561035, "learning_rate": 2.8117287908220993e-07, "loss": 0.5497045516967773, "step": 6391 }, { "epoch": 0.8963051251489869, "grad_norm": 2.807050943374634, "learning_rate": 2.80422671653115e-07, "loss": 0.34922486543655396, "step": 6392 }, { "epoch": 0.8964453481034845, "grad_norm": 3.397242307662964, "learning_rate": 2.796734375128263e-07, "loss": 0.5807775259017944, "step": 6393 }, { "epoch": 0.8965855710579822, "grad_norm": 3.5927507877349854, "learning_rate": 2.789251768158541e-07, "loss": 0.5174795985221863, "step": 6394 }, { "epoch": 0.8967257940124799, "grad_norm": 5.69230318069458, "learning_rate": 2.781778897165077e-07, "loss": 0.5258055925369263, "step": 6395 }, { "epoch": 0.8968660169669775, "grad_norm": 3.8924169540405273, "learning_rate": 2.7743157636889504e-07, "loss": 0.56321120262146, "step": 6396 }, { "epoch": 0.8970062399214751, "grad_norm": 2.8873870372772217, "learning_rate": 2.766862369269252e-07, "loss": 0.5169029235839844, "step": 6397 }, { "epoch": 0.8971464628759728, "grad_norm": 4.869393348693848, "learning_rate": 2.7594187154430187e-07, "loss": 0.48741382360458374, "step": 6398 }, { "epoch": 0.8972866858304704, "grad_norm": 4.379576683044434, "learning_rate": 2.751984803745333e-07, "loss": 0.504843533039093, "step": 6399 }, { "epoch": 0.8974269087849681, "grad_norm": 5.206376552581787, "learning_rate": 2.744560635709231e-07, "loss": 0.5115541219711304, "step": 6400 }, { "epoch": 0.8975671317394658, "grad_norm": 3.005748987197876, "learning_rate": 2.73714621286576e-07, "loss": 0.5383385419845581, "step": 6401 }, { "epoch": 0.8977073546939635, "grad_norm": 3.3952863216400146, "learning_rate": 2.7297415367439405e-07, "loss": 0.45350104570388794, "step": 6402 }, { "epoch": 0.897847577648461, "grad_norm": 4.069650650024414, "learning_rate": 2.7223466088708126e-07, "loss": 0.516359806060791, "step": 6403 }, { "epoch": 0.8979878006029587, "grad_norm": 4.392079830169678, "learning_rate": 2.714961430771357e-07, "loss": 0.508870005607605, "step": 6404 }, { "epoch": 0.8981280235574564, "grad_norm": 21.204347610473633, "learning_rate": 2.7075860039685984e-07, "loss": 0.5295894145965576, "step": 6405 }, { "epoch": 0.898268246511954, "grad_norm": 4.153314113616943, "learning_rate": 2.7002203299835103e-07, "loss": 0.453036904335022, "step": 6406 }, { "epoch": 0.8984084694664517, "grad_norm": 3.9501266479492188, "learning_rate": 2.692864410335072e-07, "loss": 0.49011096358299255, "step": 6407 }, { "epoch": 0.8985486924209493, "grad_norm": 3.9240469932556152, "learning_rate": 2.6855182465402474e-07, "loss": 0.4152948260307312, "step": 6408 }, { "epoch": 0.8986889153754469, "grad_norm": 8.518176078796387, "learning_rate": 2.678181840113997e-07, "loss": 0.43971380591392517, "step": 6409 }, { "epoch": 0.8988291383299446, "grad_norm": 6.851307392120361, "learning_rate": 2.670855192569255e-07, "loss": 0.4572938084602356, "step": 6410 }, { "epoch": 0.8989693612844423, "grad_norm": 2.9066715240478516, "learning_rate": 2.663538305416957e-07, "loss": 0.5535341501235962, "step": 6411 }, { "epoch": 0.8991095842389399, "grad_norm": 11.182611465454102, "learning_rate": 2.656231180166008e-07, "loss": 0.4913599491119385, "step": 6412 }, { "epoch": 0.8992498071934376, "grad_norm": 3.1598503589630127, "learning_rate": 2.648933818323313e-07, "loss": 0.4802544116973877, "step": 6413 }, { "epoch": 0.8993900301479352, "grad_norm": 3.391913890838623, "learning_rate": 2.6416462213937677e-07, "loss": 0.4765380918979645, "step": 6414 }, { "epoch": 0.8995302531024328, "grad_norm": 3.2480387687683105, "learning_rate": 2.634368390880243e-07, "loss": 0.46914032101631165, "step": 6415 }, { "epoch": 0.8996704760569305, "grad_norm": 3.0138070583343506, "learning_rate": 2.627100328283605e-07, "loss": 0.5394332408905029, "step": 6416 }, { "epoch": 0.8998106990114282, "grad_norm": 2.868457555770874, "learning_rate": 2.6198420351026987e-07, "loss": 0.48176395893096924, "step": 6417 }, { "epoch": 0.8999509219659259, "grad_norm": 9.075613975524902, "learning_rate": 2.6125935128343493e-07, "loss": 0.524145245552063, "step": 6418 }, { "epoch": 0.9000911449204235, "grad_norm": 3.0954151153564453, "learning_rate": 2.6053547629733776e-07, "loss": 0.5188779234886169, "step": 6419 }, { "epoch": 0.9002313678749211, "grad_norm": 8.281558990478516, "learning_rate": 2.59812578701259e-07, "loss": 0.5399119853973389, "step": 6420 }, { "epoch": 0.9003715908294188, "grad_norm": 5.1493120193481445, "learning_rate": 2.5909065864427706e-07, "loss": 0.46475523710250854, "step": 6421 }, { "epoch": 0.9005118137839164, "grad_norm": 5.681302547454834, "learning_rate": 2.5836971627526853e-07, "loss": 0.49961942434310913, "step": 6422 }, { "epoch": 0.9006520367384141, "grad_norm": 9.642638206481934, "learning_rate": 2.576497517429105e-07, "loss": 0.556611955165863, "step": 6423 }, { "epoch": 0.9007922596929118, "grad_norm": 6.834743976593018, "learning_rate": 2.5693076519567375e-07, "loss": 0.5139497518539429, "step": 6424 }, { "epoch": 0.9009324826474093, "grad_norm": 10.360334396362305, "learning_rate": 2.562127567818329e-07, "loss": 0.4106442630290985, "step": 6425 }, { "epoch": 0.901072705601907, "grad_norm": 4.7941060066223145, "learning_rate": 2.554957266494573e-07, "loss": 0.4979260265827179, "step": 6426 }, { "epoch": 0.9012129285564047, "grad_norm": 6.311246395111084, "learning_rate": 2.54779674946416e-07, "loss": 0.5633423328399658, "step": 6427 }, { "epoch": 0.9013531515109023, "grad_norm": 3.245985269546509, "learning_rate": 2.540646018203757e-07, "loss": 0.5168198347091675, "step": 6428 }, { "epoch": 0.9014933744654, "grad_norm": 3.8202412128448486, "learning_rate": 2.5335050741880143e-07, "loss": 0.46194761991500854, "step": 6429 }, { "epoch": 0.9016335974198977, "grad_norm": 3.2243752479553223, "learning_rate": 2.526373918889552e-07, "loss": 0.46773189306259155, "step": 6430 }, { "epoch": 0.9017738203743952, "grad_norm": 3.7129831314086914, "learning_rate": 2.5192525537790115e-07, "loss": 0.4243502616882324, "step": 6431 }, { "epoch": 0.9019140433288929, "grad_norm": 3.7104079723358154, "learning_rate": 2.512140980324962e-07, "loss": 0.5113905072212219, "step": 6432 }, { "epoch": 0.9020542662833906, "grad_norm": 3.0205576419830322, "learning_rate": 2.505039199993986e-07, "loss": 0.523698091506958, "step": 6433 }, { "epoch": 0.9021944892378883, "grad_norm": 5.960275650024414, "learning_rate": 2.49794721425064e-07, "loss": 0.5580571889877319, "step": 6434 }, { "epoch": 0.9023347121923859, "grad_norm": 5.476459980010986, "learning_rate": 2.490865024557465e-07, "loss": 0.5107141733169556, "step": 6435 }, { "epoch": 0.9024749351468836, "grad_norm": 5.216886520385742, "learning_rate": 2.4837926323749595e-07, "loss": 0.48893386125564575, "step": 6436 }, { "epoch": 0.9026151581013812, "grad_norm": 4.382233142852783, "learning_rate": 2.476730039161646e-07, "loss": 0.5833481550216675, "step": 6437 }, { "epoch": 0.9027553810558788, "grad_norm": 7.6974663734436035, "learning_rate": 2.469677246373975e-07, "loss": 0.4766559302806854, "step": 6438 }, { "epoch": 0.9028956040103765, "grad_norm": 2.8514552116394043, "learning_rate": 2.462634255466406e-07, "loss": 0.5408880114555359, "step": 6439 }, { "epoch": 0.9030358269648742, "grad_norm": 7.646645545959473, "learning_rate": 2.4556010678913777e-07, "loss": 0.4909723997116089, "step": 6440 }, { "epoch": 0.9031760499193718, "grad_norm": 3.1639885902404785, "learning_rate": 2.44857768509929e-07, "loss": 0.46879714727401733, "step": 6441 }, { "epoch": 0.9033162728738694, "grad_norm": 6.140766143798828, "learning_rate": 2.441564108538541e-07, "loss": 0.44686761498451233, "step": 6442 }, { "epoch": 0.9034564958283671, "grad_norm": 3.845618486404419, "learning_rate": 2.434560339655495e-07, "loss": 0.5053866505622864, "step": 6443 }, { "epoch": 0.9035967187828647, "grad_norm": 3.793048143386841, "learning_rate": 2.4275663798944805e-07, "loss": 0.49745240807533264, "step": 6444 }, { "epoch": 0.9037369417373624, "grad_norm": 3.684835195541382, "learning_rate": 2.4205822306978376e-07, "loss": 0.4542698264122009, "step": 6445 }, { "epoch": 0.9038771646918601, "grad_norm": 3.8358726501464844, "learning_rate": 2.413607893505854e-07, "loss": 0.556151270866394, "step": 6446 }, { "epoch": 0.9040173876463578, "grad_norm": 4.541685581207275, "learning_rate": 2.4066433697568057e-07, "loss": 0.48060035705566406, "step": 6447 }, { "epoch": 0.9041576106008553, "grad_norm": 3.0634219646453857, "learning_rate": 2.3996886608869394e-07, "loss": 0.5613493919372559, "step": 6448 }, { "epoch": 0.904297833555353, "grad_norm": 4.567008018493652, "learning_rate": 2.392743768330491e-07, "loss": 0.5648361444473267, "step": 6449 }, { "epoch": 0.9044380565098507, "grad_norm": 3.397984504699707, "learning_rate": 2.3858086935196425e-07, "loss": 0.4024297595024109, "step": 6450 }, { "epoch": 0.9045782794643483, "grad_norm": 3.58627986907959, "learning_rate": 2.3788834378845937e-07, "loss": 0.4322476387023926, "step": 6451 }, { "epoch": 0.904718502418846, "grad_norm": 3.9873945713043213, "learning_rate": 2.3719680028534808e-07, "loss": 0.42698314785957336, "step": 6452 }, { "epoch": 0.9048587253733437, "grad_norm": 10.706025123596191, "learning_rate": 2.365062389852435e-07, "loss": 0.5217586755752563, "step": 6453 }, { "epoch": 0.9049989483278412, "grad_norm": 6.093356132507324, "learning_rate": 2.3581666003055614e-07, "loss": 0.4398765563964844, "step": 6454 }, { "epoch": 0.9051391712823389, "grad_norm": 2.5368082523345947, "learning_rate": 2.3512806356349394e-07, "loss": 0.48959267139434814, "step": 6455 }, { "epoch": 0.9052793942368366, "grad_norm": 3.9762115478515625, "learning_rate": 2.344404497260594e-07, "loss": 0.41227155923843384, "step": 6456 }, { "epoch": 0.9054196171913342, "grad_norm": 3.7974209785461426, "learning_rate": 2.3375381866005799e-07, "loss": 0.5530972480773926, "step": 6457 }, { "epoch": 0.9055598401458319, "grad_norm": 3.953970193862915, "learning_rate": 2.3306817050708696e-07, "loss": 0.5381544828414917, "step": 6458 }, { "epoch": 0.9057000631003296, "grad_norm": 2.788188934326172, "learning_rate": 2.3238350540854437e-07, "loss": 0.5627260208129883, "step": 6459 }, { "epoch": 0.9058402860548271, "grad_norm": 3.497359275817871, "learning_rate": 2.3169982350562391e-07, "loss": 0.4895835518836975, "step": 6460 }, { "epoch": 0.9059805090093248, "grad_norm": 20.90129280090332, "learning_rate": 2.310171249393184e-07, "loss": 0.5615236759185791, "step": 6461 }, { "epoch": 0.9061207319638225, "grad_norm": 5.949379920959473, "learning_rate": 2.3033540985041346e-07, "loss": 0.41764673590660095, "step": 6462 }, { "epoch": 0.9062609549183201, "grad_norm": 3.7305550575256348, "learning_rate": 2.296546783794984e-07, "loss": 0.506677508354187, "step": 6463 }, { "epoch": 0.9064011778728178, "grad_norm": 2.7146379947662354, "learning_rate": 2.2897493066695364e-07, "loss": 0.4719267189502716, "step": 6464 }, { "epoch": 0.9065414008273154, "grad_norm": 3.0445287227630615, "learning_rate": 2.2829616685296098e-07, "loss": 0.46313560009002686, "step": 6465 }, { "epoch": 0.906681623781813, "grad_norm": 3.6701550483703613, "learning_rate": 2.2761838707749618e-07, "loss": 0.5493425130844116, "step": 6466 }, { "epoch": 0.9068218467363107, "grad_norm": 4.01767110824585, "learning_rate": 2.2694159148033467e-07, "loss": 0.5084078907966614, "step": 6467 }, { "epoch": 0.9069620696908084, "grad_norm": 3.659886121749878, "learning_rate": 2.262657802010465e-07, "loss": 0.42044076323509216, "step": 6468 }, { "epoch": 0.9071022926453061, "grad_norm": 2.860818386077881, "learning_rate": 2.2559095337900183e-07, "loss": 0.4425997734069824, "step": 6469 }, { "epoch": 0.9072425155998037, "grad_norm": 3.2733569145202637, "learning_rate": 2.249171111533638e-07, "loss": 0.5205758810043335, "step": 6470 }, { "epoch": 0.9073827385543013, "grad_norm": 6.397177696228027, "learning_rate": 2.2424425366309678e-07, "loss": 0.5366122722625732, "step": 6471 }, { "epoch": 0.907522961508799, "grad_norm": 3.555163621902466, "learning_rate": 2.2357238104695868e-07, "loss": 0.43204668164253235, "step": 6472 }, { "epoch": 0.9076631844632966, "grad_norm": 3.065704345703125, "learning_rate": 2.2290149344350532e-07, "loss": 0.4532129466533661, "step": 6473 }, { "epoch": 0.9078034074177943, "grad_norm": 8.622529029846191, "learning_rate": 2.2223159099109048e-07, "loss": 0.49641138315200806, "step": 6474 }, { "epoch": 0.907943630372292, "grad_norm": 3.8838305473327637, "learning_rate": 2.2156267382786424e-07, "loss": 0.4311753511428833, "step": 6475 }, { "epoch": 0.9080838533267896, "grad_norm": 2.6774845123291016, "learning_rate": 2.2089474209177063e-07, "loss": 0.4748929738998413, "step": 6476 }, { "epoch": 0.9082240762812872, "grad_norm": 5.279290676116943, "learning_rate": 2.2022779592055676e-07, "loss": 0.4344980716705322, "step": 6477 }, { "epoch": 0.9083642992357849, "grad_norm": 2.4138638973236084, "learning_rate": 2.1956183545176037e-07, "loss": 0.3738149404525757, "step": 6478 }, { "epoch": 0.9085045221902825, "grad_norm": 4.654057025909424, "learning_rate": 2.1889686082271876e-07, "loss": 0.5238021612167358, "step": 6479 }, { "epoch": 0.9086447451447802, "grad_norm": 4.67538595199585, "learning_rate": 2.1823287217056565e-07, "loss": 0.49833452701568604, "step": 6480 }, { "epoch": 0.9087849680992779, "grad_norm": 3.901698350906372, "learning_rate": 2.1756986963223205e-07, "loss": 0.4703795611858368, "step": 6481 }, { "epoch": 0.9089251910537754, "grad_norm": 4.694812297821045, "learning_rate": 2.1690785334444187e-07, "loss": 0.4257599115371704, "step": 6482 }, { "epoch": 0.9090654140082731, "grad_norm": 4.424495697021484, "learning_rate": 2.1624682344372261e-07, "loss": 0.5014468431472778, "step": 6483 }, { "epoch": 0.9092056369627708, "grad_norm": 2.792539358139038, "learning_rate": 2.1558678006639132e-07, "loss": 0.4287847876548767, "step": 6484 }, { "epoch": 0.9093458599172685, "grad_norm": 3.2841291427612305, "learning_rate": 2.1492772334856582e-07, "loss": 0.475796639919281, "step": 6485 }, { "epoch": 0.9094860828717661, "grad_norm": 2.438552141189575, "learning_rate": 2.1426965342615902e-07, "loss": 0.5464831590652466, "step": 6486 }, { "epoch": 0.9096263058262638, "grad_norm": 4.011698246002197, "learning_rate": 2.1361257043488127e-07, "loss": 0.445245623588562, "step": 6487 }, { "epoch": 0.9097665287807614, "grad_norm": 2.972764253616333, "learning_rate": 2.1295647451023694e-07, "loss": 0.5392571687698364, "step": 6488 }, { "epoch": 0.909906751735259, "grad_norm": 3.669750213623047, "learning_rate": 2.1230136578753057e-07, "loss": 0.5357089042663574, "step": 6489 }, { "epoch": 0.9100469746897567, "grad_norm": 3.4399752616882324, "learning_rate": 2.116472444018597e-07, "loss": 0.39039933681488037, "step": 6490 }, { "epoch": 0.9101871976442544, "grad_norm": 5.376026630401611, "learning_rate": 2.109941104881197e-07, "loss": 0.5501754879951477, "step": 6491 }, { "epoch": 0.910327420598752, "grad_norm": 5.18295431137085, "learning_rate": 2.103419641810034e-07, "loss": 0.47342008352279663, "step": 6492 }, { "epoch": 0.9104676435532497, "grad_norm": 3.0969903469085693, "learning_rate": 2.0969080561499823e-07, "loss": 0.43676239252090454, "step": 6493 }, { "epoch": 0.9106078665077473, "grad_norm": 3.1724116802215576, "learning_rate": 2.090406349243873e-07, "loss": 0.517497718334198, "step": 6494 }, { "epoch": 0.910748089462245, "grad_norm": 2.9252028465270996, "learning_rate": 2.0839145224325397e-07, "loss": 0.48350226879119873, "step": 6495 }, { "epoch": 0.9108883124167426, "grad_norm": 3.4038515090942383, "learning_rate": 2.0774325770547277e-07, "loss": 0.4656262993812561, "step": 6496 }, { "epoch": 0.9110285353712403, "grad_norm": 5.212020397186279, "learning_rate": 2.0709605144471733e-07, "loss": 0.49029022455215454, "step": 6497 }, { "epoch": 0.911168758325738, "grad_norm": 5.033134460449219, "learning_rate": 2.0644983359445702e-07, "loss": 0.5789562463760376, "step": 6498 }, { "epoch": 0.9113089812802355, "grad_norm": 4.35667085647583, "learning_rate": 2.05804604287958e-07, "loss": 0.5545712113380432, "step": 6499 }, { "epoch": 0.9114492042347332, "grad_norm": 4.111931800842285, "learning_rate": 2.0516036365828106e-07, "loss": 0.4380730986595154, "step": 6500 }, { "epoch": 0.9115894271892309, "grad_norm": 4.754739284515381, "learning_rate": 2.0451711183828438e-07, "loss": 0.4091135263442993, "step": 6501 }, { "epoch": 0.9117296501437285, "grad_norm": 4.198370933532715, "learning_rate": 2.038748489606207e-07, "loss": 0.5532406568527222, "step": 6502 }, { "epoch": 0.9118698730982262, "grad_norm": 3.2110321521759033, "learning_rate": 2.0323357515774189e-07, "loss": 0.39024800062179565, "step": 6503 }, { "epoch": 0.9120100960527239, "grad_norm": 3.7774605751037598, "learning_rate": 2.0259329056189157e-07, "loss": 0.5195188522338867, "step": 6504 }, { "epoch": 0.9121503190072214, "grad_norm": 3.100834846496582, "learning_rate": 2.0195399530511306e-07, "loss": 0.46187660098075867, "step": 6505 }, { "epoch": 0.9122905419617191, "grad_norm": 3.241974353790283, "learning_rate": 2.0131568951924362e-07, "loss": 0.49046680331230164, "step": 6506 }, { "epoch": 0.9124307649162168, "grad_norm": 3.374173402786255, "learning_rate": 2.00678373335918e-07, "loss": 0.4671938419342041, "step": 6507 }, { "epoch": 0.9125709878707144, "grad_norm": 4.101308345794678, "learning_rate": 2.0004204688656325e-07, "loss": 0.4851452708244324, "step": 6508 }, { "epoch": 0.9127112108252121, "grad_norm": 7.305972099304199, "learning_rate": 1.9940671030240888e-07, "loss": 0.5363845825195312, "step": 6509 }, { "epoch": 0.9128514337797098, "grad_norm": 4.732419967651367, "learning_rate": 1.987723637144734e-07, "loss": 0.3680363893508911, "step": 6510 }, { "epoch": 0.9129916567342073, "grad_norm": 3.6546437740325928, "learning_rate": 1.9813900725357493e-07, "loss": 0.5361485481262207, "step": 6511 }, { "epoch": 0.913131879688705, "grad_norm": 4.258800983428955, "learning_rate": 1.975066410503268e-07, "loss": 0.5366368889808655, "step": 6512 }, { "epoch": 0.9132721026432027, "grad_norm": 4.466535568237305, "learning_rate": 1.9687526523513855e-07, "loss": 0.5741611123085022, "step": 6513 }, { "epoch": 0.9134123255977004, "grad_norm": 3.8365209102630615, "learning_rate": 1.9624487993821274e-07, "loss": 0.4581945836544037, "step": 6514 }, { "epoch": 0.913552548552198, "grad_norm": 3.6772677898406982, "learning_rate": 1.9561548528955253e-07, "loss": 0.46171119809150696, "step": 6515 }, { "epoch": 0.9136927715066957, "grad_norm": 3.253145217895508, "learning_rate": 1.9498708141895195e-07, "loss": 0.47437137365341187, "step": 6516 }, { "epoch": 0.9138329944611933, "grad_norm": 4.171911239624023, "learning_rate": 1.9435966845600396e-07, "loss": 0.5042953491210938, "step": 6517 }, { "epoch": 0.9139732174156909, "grad_norm": 11.025880813598633, "learning_rate": 1.9373324653009505e-07, "loss": 0.4458000659942627, "step": 6518 }, { "epoch": 0.9141134403701886, "grad_norm": 15.730589866638184, "learning_rate": 1.9310781577040971e-07, "loss": 0.4944759011268616, "step": 6519 }, { "epoch": 0.9142536633246863, "grad_norm": 3.1134634017944336, "learning_rate": 1.9248337630592416e-07, "loss": 0.45405149459838867, "step": 6520 }, { "epoch": 0.9143938862791839, "grad_norm": 6.1330695152282715, "learning_rate": 1.9185992826541545e-07, "loss": 0.5510032773017883, "step": 6521 }, { "epoch": 0.9145341092336815, "grad_norm": 3.3903648853302, "learning_rate": 1.9123747177745178e-07, "loss": 0.4519807994365692, "step": 6522 }, { "epoch": 0.9146743321881792, "grad_norm": 3.2955877780914307, "learning_rate": 1.9061600697039828e-07, "loss": 0.5210970044136047, "step": 6523 }, { "epoch": 0.9148145551426768, "grad_norm": 4.9787068367004395, "learning_rate": 1.8999553397241633e-07, "loss": 0.4738457500934601, "step": 6524 }, { "epoch": 0.9149547780971745, "grad_norm": 4.78665018081665, "learning_rate": 1.8937605291146245e-07, "loss": 0.5154866576194763, "step": 6525 }, { "epoch": 0.9150950010516722, "grad_norm": 6.031578063964844, "learning_rate": 1.887575639152872e-07, "loss": 0.4586801528930664, "step": 6526 }, { "epoch": 0.9152352240061699, "grad_norm": 9.199455261230469, "learning_rate": 1.8814006711143917e-07, "loss": 0.4196861982345581, "step": 6527 }, { "epoch": 0.9153754469606674, "grad_norm": 5.789379119873047, "learning_rate": 1.8752356262725869e-07, "loss": 0.5669254064559937, "step": 6528 }, { "epoch": 0.9155156699151651, "grad_norm": 4.940304279327393, "learning_rate": 1.869080505898868e-07, "loss": 0.48086756467819214, "step": 6529 }, { "epoch": 0.9156558928696628, "grad_norm": 3.1831047534942627, "learning_rate": 1.862935311262537e-07, "loss": 0.4537739157676697, "step": 6530 }, { "epoch": 0.9157961158241604, "grad_norm": 3.3920693397521973, "learning_rate": 1.8568000436308964e-07, "loss": 0.5394070148468018, "step": 6531 }, { "epoch": 0.9159363387786581, "grad_norm": 4.427249431610107, "learning_rate": 1.850674704269173e-07, "loss": 0.4679955542087555, "step": 6532 }, { "epoch": 0.9160765617331558, "grad_norm": 5.127667427062988, "learning_rate": 1.8445592944405676e-07, "loss": 0.46633386611938477, "step": 6533 }, { "epoch": 0.9162167846876533, "grad_norm": 206.18092346191406, "learning_rate": 1.8384538154062105e-07, "loss": 0.5156704187393188, "step": 6534 }, { "epoch": 0.916357007642151, "grad_norm": 5.238541603088379, "learning_rate": 1.8323582684252106e-07, "loss": 0.5855374336242676, "step": 6535 }, { "epoch": 0.9164972305966487, "grad_norm": 3.050014019012451, "learning_rate": 1.8262726547546018e-07, "loss": 0.49667492508888245, "step": 6536 }, { "epoch": 0.9166374535511463, "grad_norm": 3.3264882564544678, "learning_rate": 1.8201969756493855e-07, "loss": 0.5580578446388245, "step": 6537 }, { "epoch": 0.916777676505644, "grad_norm": 3.7096972465515137, "learning_rate": 1.814131232362515e-07, "loss": 0.4635372757911682, "step": 6538 }, { "epoch": 0.9169178994601416, "grad_norm": 3.560670852661133, "learning_rate": 1.8080754261448952e-07, "loss": 0.4583066701889038, "step": 6539 }, { "epoch": 0.9170581224146392, "grad_norm": 4.796631813049316, "learning_rate": 1.802029558245355e-07, "loss": 0.582756757736206, "step": 6540 }, { "epoch": 0.9171983453691369, "grad_norm": 4.4578657150268555, "learning_rate": 1.795993629910725e-07, "loss": 0.49642500281333923, "step": 6541 }, { "epoch": 0.9173385683236346, "grad_norm": 5.180263519287109, "learning_rate": 1.7899676423857314e-07, "loss": 0.5268181562423706, "step": 6542 }, { "epoch": 0.9174787912781323, "grad_norm": 4.1975626945495605, "learning_rate": 1.7839515969130917e-07, "loss": 0.43343573808670044, "step": 6543 }, { "epoch": 0.9176190142326299, "grad_norm": 3.635056495666504, "learning_rate": 1.7779454947334463e-07, "loss": 0.5231281518936157, "step": 6544 }, { "epoch": 0.9177592371871275, "grad_norm": 4.184784412384033, "learning_rate": 1.7719493370854157e-07, "loss": 0.5689061880111694, "step": 6545 }, { "epoch": 0.9178994601416252, "grad_norm": 3.0106606483459473, "learning_rate": 1.7659631252055164e-07, "loss": 0.48732179403305054, "step": 6546 }, { "epoch": 0.9180396830961228, "grad_norm": 3.6992528438568115, "learning_rate": 1.7599868603282834e-07, "loss": 0.4179764986038208, "step": 6547 }, { "epoch": 0.9181799060506205, "grad_norm": 3.7120373249053955, "learning_rate": 1.7540205436861414e-07, "loss": 0.5106438398361206, "step": 6548 }, { "epoch": 0.9183201290051182, "grad_norm": 3.6936912536621094, "learning_rate": 1.7480641765094896e-07, "loss": 0.4393734037876129, "step": 6549 }, { "epoch": 0.9184603519596158, "grad_norm": 4.396049499511719, "learning_rate": 1.7421177600266792e-07, "loss": 0.5627527236938477, "step": 6550 }, { "epoch": 0.9186005749141134, "grad_norm": 2.7033417224884033, "learning_rate": 1.7361812954640013e-07, "loss": 0.44486603140830994, "step": 6551 }, { "epoch": 0.9187407978686111, "grad_norm": 3.957735776901245, "learning_rate": 1.7302547840456818e-07, "loss": 0.4146135449409485, "step": 6552 }, { "epoch": 0.9188810208231087, "grad_norm": 13.208252906799316, "learning_rate": 1.7243382269939324e-07, "loss": 0.5102630853652954, "step": 6553 }, { "epoch": 0.9190212437776064, "grad_norm": 3.6974947452545166, "learning_rate": 1.7184316255288714e-07, "loss": 0.546593427658081, "step": 6554 }, { "epoch": 0.9191614667321041, "grad_norm": 4.286349296569824, "learning_rate": 1.7125349808685742e-07, "loss": 0.4431439936161041, "step": 6555 }, { "epoch": 0.9193016896866016, "grad_norm": 3.9475488662719727, "learning_rate": 1.7066482942290853e-07, "loss": 0.44038307666778564, "step": 6556 }, { "epoch": 0.9194419126410993, "grad_norm": 23.019556045532227, "learning_rate": 1.7007715668243664e-07, "loss": 0.4255867898464203, "step": 6557 }, { "epoch": 0.919582135595597, "grad_norm": 3.445169687271118, "learning_rate": 1.694904799866348e-07, "loss": 0.4157713055610657, "step": 6558 }, { "epoch": 0.9197223585500947, "grad_norm": 3.356719493865967, "learning_rate": 1.6890479945648964e-07, "loss": 0.4197017550468445, "step": 6559 }, { "epoch": 0.9198625815045923, "grad_norm": 5.631300449371338, "learning_rate": 1.683201152127806e-07, "loss": 0.5129579305648804, "step": 6560 }, { "epoch": 0.92000280445909, "grad_norm": 4.185061931610107, "learning_rate": 1.6773642737608565e-07, "loss": 0.5555629134178162, "step": 6561 }, { "epoch": 0.9201430274135876, "grad_norm": 12.086515426635742, "learning_rate": 1.6715373606677355e-07, "loss": 0.43943318724632263, "step": 6562 }, { "epoch": 0.9202832503680852, "grad_norm": 4.0598225593566895, "learning_rate": 1.6657204140501037e-07, "loss": 0.5268769264221191, "step": 6563 }, { "epoch": 0.9204234733225829, "grad_norm": 5.412821292877197, "learning_rate": 1.6599134351075409e-07, "loss": 0.43315693736076355, "step": 6564 }, { "epoch": 0.9205636962770806, "grad_norm": 3.19281005859375, "learning_rate": 1.6541164250375995e-07, "loss": 0.5770294666290283, "step": 6565 }, { "epoch": 0.9207039192315782, "grad_norm": 3.423623561859131, "learning_rate": 1.6483293850357352e-07, "loss": 0.5307299494743347, "step": 6566 }, { "epoch": 0.9208441421860759, "grad_norm": 4.154082775115967, "learning_rate": 1.6425523162954038e-07, "loss": 0.48986703157424927, "step": 6567 }, { "epoch": 0.9209843651405735, "grad_norm": 4.847164630889893, "learning_rate": 1.636785220007947e-07, "loss": 0.469061017036438, "step": 6568 }, { "epoch": 0.9211245880950711, "grad_norm": 2.7996675968170166, "learning_rate": 1.6310280973626967e-07, "loss": 0.35780930519104004, "step": 6569 }, { "epoch": 0.9212648110495688, "grad_norm": 11.182826042175293, "learning_rate": 1.6252809495468925e-07, "loss": 0.5331989526748657, "step": 6570 }, { "epoch": 0.9214050340040665, "grad_norm": 2.7180070877075195, "learning_rate": 1.6195437777457522e-07, "loss": 0.4020475149154663, "step": 6571 }, { "epoch": 0.9215452569585642, "grad_norm": 5.032795429229736, "learning_rate": 1.6138165831423857e-07, "loss": 0.5074608325958252, "step": 6572 }, { "epoch": 0.9216854799130618, "grad_norm": 2.9958722591400146, "learning_rate": 1.6080993669179145e-07, "loss": 0.4153211712837219, "step": 6573 }, { "epoch": 0.9218257028675594, "grad_norm": 3.1464900970458984, "learning_rate": 1.6023921302513347e-07, "loss": 0.4455384910106659, "step": 6574 }, { "epoch": 0.921965925822057, "grad_norm": 4.7689385414123535, "learning_rate": 1.5966948743196265e-07, "loss": 0.42284008860588074, "step": 6575 }, { "epoch": 0.9221061487765547, "grad_norm": 5.739182949066162, "learning_rate": 1.591007600297695e-07, "loss": 0.6211773157119751, "step": 6576 }, { "epoch": 0.9222463717310524, "grad_norm": 4.513568878173828, "learning_rate": 1.585330309358396e-07, "loss": 0.44584158062934875, "step": 6577 }, { "epoch": 0.9223865946855501, "grad_norm": 4.348278999328613, "learning_rate": 1.5796630026725102e-07, "loss": 0.5501066446304321, "step": 6578 }, { "epoch": 0.9225268176400476, "grad_norm": 3.062105894088745, "learning_rate": 1.5740056814087912e-07, "loss": 0.45085451006889343, "step": 6579 }, { "epoch": 0.9226670405945453, "grad_norm": 3.708059549331665, "learning_rate": 1.5683583467338947e-07, "loss": 0.5122017860412598, "step": 6580 }, { "epoch": 0.922807263549043, "grad_norm": 4.0897932052612305, "learning_rate": 1.5627209998124394e-07, "loss": 0.46727490425109863, "step": 6581 }, { "epoch": 0.9229474865035406, "grad_norm": 10.336079597473145, "learning_rate": 1.5570936418069836e-07, "loss": 0.44510746002197266, "step": 6582 }, { "epoch": 0.9230877094580383, "grad_norm": 4.028283596038818, "learning_rate": 1.551476273878022e-07, "loss": 0.4981389343738556, "step": 6583 }, { "epoch": 0.923227932412536, "grad_norm": 3.1901118755340576, "learning_rate": 1.5458688971839776e-07, "loss": 0.5022615194320679, "step": 6584 }, { "epoch": 0.9233681553670335, "grad_norm": 3.460038423538208, "learning_rate": 1.5402715128812474e-07, "loss": 0.4738561809062958, "step": 6585 }, { "epoch": 0.9235083783215312, "grad_norm": 5.308485984802246, "learning_rate": 1.5346841221241248e-07, "loss": 0.49145543575286865, "step": 6586 }, { "epoch": 0.9236486012760289, "grad_norm": 4.516809463500977, "learning_rate": 1.5291067260648661e-07, "loss": 0.4443165063858032, "step": 6587 }, { "epoch": 0.9237888242305266, "grad_norm": 3.58364200592041, "learning_rate": 1.523539325853668e-07, "loss": 0.6174654960632324, "step": 6588 }, { "epoch": 0.9239290471850242, "grad_norm": 4.056895732879639, "learning_rate": 1.5179819226386561e-07, "loss": 0.5307915210723877, "step": 6589 }, { "epoch": 0.9240692701395219, "grad_norm": 4.880468368530273, "learning_rate": 1.5124345175659028e-07, "loss": 0.4788006842136383, "step": 6590 }, { "epoch": 0.9242094930940195, "grad_norm": 4.527062892913818, "learning_rate": 1.5068971117794208e-07, "loss": 0.4671030640602112, "step": 6591 }, { "epoch": 0.9243497160485171, "grad_norm": 3.079456090927124, "learning_rate": 1.5013697064211298e-07, "loss": 0.4715634882450104, "step": 6592 }, { "epoch": 0.9244899390030148, "grad_norm": 15.956510543823242, "learning_rate": 1.4958523026309456e-07, "loss": 0.5410653352737427, "step": 6593 }, { "epoch": 0.9246301619575125, "grad_norm": 4.0662031173706055, "learning_rate": 1.4903449015466587e-07, "loss": 0.5298868417739868, "step": 6594 }, { "epoch": 0.9247703849120101, "grad_norm": 4.4373555183410645, "learning_rate": 1.4848475043040377e-07, "loss": 0.5180261135101318, "step": 6595 }, { "epoch": 0.9249106078665077, "grad_norm": 4.9448370933532715, "learning_rate": 1.4793601120367817e-07, "loss": 0.3598032593727112, "step": 6596 }, { "epoch": 0.9250508308210054, "grad_norm": 4.1397705078125, "learning_rate": 1.4738827258765187e-07, "loss": 0.49334055185317993, "step": 6597 }, { "epoch": 0.925191053775503, "grad_norm": 3.8829774856567383, "learning_rate": 1.4684153469528008e-07, "loss": 0.5154731273651123, "step": 6598 }, { "epoch": 0.9253312767300007, "grad_norm": 4.729805946350098, "learning_rate": 1.4629579763931533e-07, "loss": 0.495788037776947, "step": 6599 }, { "epoch": 0.9254714996844984, "grad_norm": 4.649932861328125, "learning_rate": 1.4575106153230044e-07, "loss": 0.4444567561149597, "step": 6600 }, { "epoch": 0.925611722638996, "grad_norm": 4.002816677093506, "learning_rate": 1.452073264865722e-07, "loss": 0.46217018365859985, "step": 6601 }, { "epoch": 0.9257519455934936, "grad_norm": 5.483064651489258, "learning_rate": 1.4466459261426314e-07, "loss": 0.5774502754211426, "step": 6602 }, { "epoch": 0.9258921685479913, "grad_norm": 5.463901042938232, "learning_rate": 1.441228600272976e-07, "loss": 0.6235504746437073, "step": 6603 }, { "epoch": 0.926032391502489, "grad_norm": 3.4690511226654053, "learning_rate": 1.4358212883739232e-07, "loss": 0.5067235231399536, "step": 6604 }, { "epoch": 0.9261726144569866, "grad_norm": 7.3165788650512695, "learning_rate": 1.4304239915606088e-07, "loss": 0.49992650747299194, "step": 6605 }, { "epoch": 0.9263128374114843, "grad_norm": 6.746048450469971, "learning_rate": 1.425036710946065e-07, "loss": 0.48372572660446167, "step": 6606 }, { "epoch": 0.926453060365982, "grad_norm": 7.425688743591309, "learning_rate": 1.4196594476412917e-07, "loss": 0.4730786979198456, "step": 6607 }, { "epoch": 0.9265932833204795, "grad_norm": 8.036542892456055, "learning_rate": 1.4142922027551964e-07, "loss": 0.5719169974327087, "step": 6608 }, { "epoch": 0.9267335062749772, "grad_norm": 5.17649507522583, "learning_rate": 1.4089349773946436e-07, "loss": 0.4545862376689911, "step": 6609 }, { "epoch": 0.9268737292294749, "grad_norm": 3.572538375854492, "learning_rate": 1.4035877726644054e-07, "loss": 0.3952884078025818, "step": 6610 }, { "epoch": 0.9270139521839725, "grad_norm": 4.397035598754883, "learning_rate": 1.3982505896672217e-07, "loss": 0.4627529978752136, "step": 6611 }, { "epoch": 0.9271541751384702, "grad_norm": 4.0407538414001465, "learning_rate": 1.3929234295037287e-07, "loss": 0.5543367266654968, "step": 6612 }, { "epoch": 0.9272943980929678, "grad_norm": 2.567780017852783, "learning_rate": 1.3876062932725198e-07, "loss": 0.43978774547576904, "step": 6613 }, { "epoch": 0.9274346210474654, "grad_norm": 4.792719841003418, "learning_rate": 1.3822991820701182e-07, "loss": 0.4930151104927063, "step": 6614 }, { "epoch": 0.9275748440019631, "grad_norm": 4.312706470489502, "learning_rate": 1.377002096990976e-07, "loss": 0.44738495349884033, "step": 6615 }, { "epoch": 0.9277150669564608, "grad_norm": 21.751426696777344, "learning_rate": 1.371715039127469e-07, "loss": 0.5076283812522888, "step": 6616 }, { "epoch": 0.9278552899109584, "grad_norm": 5.712543964385986, "learning_rate": 1.366438009569926e-07, "loss": 0.532865047454834, "step": 6617 }, { "epoch": 0.9279955128654561, "grad_norm": 3.339108943939209, "learning_rate": 1.3611710094065756e-07, "loss": 0.4279215335845947, "step": 6618 }, { "epoch": 0.9281357358199537, "grad_norm": 4.702699184417725, "learning_rate": 1.3559140397236271e-07, "loss": 0.45821964740753174, "step": 6619 }, { "epoch": 0.9282759587744513, "grad_norm": 2.952014446258545, "learning_rate": 1.3506671016051685e-07, "loss": 0.5145565271377563, "step": 6620 }, { "epoch": 0.928416181728949, "grad_norm": 5.1218791007995605, "learning_rate": 1.345430196133257e-07, "loss": 0.5025187134742737, "step": 6621 }, { "epoch": 0.9285564046834467, "grad_norm": 3.2992303371429443, "learning_rate": 1.3402033243878564e-07, "loss": 0.5621842741966248, "step": 6622 }, { "epoch": 0.9286966276379444, "grad_norm": 2.840080499649048, "learning_rate": 1.3349864874468875e-07, "loss": 0.5112437009811401, "step": 6623 }, { "epoch": 0.928836850592442, "grad_norm": 6.931813716888428, "learning_rate": 1.3297796863861568e-07, "loss": 0.4622855484485626, "step": 6624 }, { "epoch": 0.9289770735469396, "grad_norm": 3.1635963916778564, "learning_rate": 1.324582922279466e-07, "loss": 0.42935171723365784, "step": 6625 }, { "epoch": 0.9291172965014373, "grad_norm": 2.463245391845703, "learning_rate": 1.3193961961984857e-07, "loss": 0.41402190923690796, "step": 6626 }, { "epoch": 0.9292575194559349, "grad_norm": 3.2136993408203125, "learning_rate": 1.3142195092128497e-07, "loss": 0.5386649966239929, "step": 6627 }, { "epoch": 0.9293977424104326, "grad_norm": 4.25710391998291, "learning_rate": 1.3090528623901144e-07, "loss": 0.4983500838279724, "step": 6628 }, { "epoch": 0.9295379653649303, "grad_norm": 3.673877239227295, "learning_rate": 1.3038962567957669e-07, "loss": 0.4259940981864929, "step": 6629 }, { "epoch": 0.929678188319428, "grad_norm": 5.3824872970581055, "learning_rate": 1.298749693493212e-07, "loss": 0.42764464020729065, "step": 6630 }, { "epoch": 0.9298184112739255, "grad_norm": 4.218553066253662, "learning_rate": 1.2936131735438061e-07, "loss": 0.5413248538970947, "step": 6631 }, { "epoch": 0.9299586342284232, "grad_norm": 6.175479412078857, "learning_rate": 1.2884866980068133e-07, "loss": 0.4201742708683014, "step": 6632 }, { "epoch": 0.9300988571829208, "grad_norm": 4.944520473480225, "learning_rate": 1.2833702679394376e-07, "loss": 0.4515761733055115, "step": 6633 }, { "epoch": 0.9302390801374185, "grad_norm": 4.482059478759766, "learning_rate": 1.278263884396802e-07, "loss": 0.581857442855835, "step": 6634 }, { "epoch": 0.9303793030919162, "grad_norm": 8.280807495117188, "learning_rate": 1.2731675484319804e-07, "loss": 0.526099443435669, "step": 6635 }, { "epoch": 0.9305195260464137, "grad_norm": 3.647294521331787, "learning_rate": 1.2680812610959327e-07, "loss": 0.5435647964477539, "step": 6636 }, { "epoch": 0.9306597490009114, "grad_norm": 6.86469841003418, "learning_rate": 1.2630050234375967e-07, "loss": 0.4617874324321747, "step": 6637 }, { "epoch": 0.9307999719554091, "grad_norm": 6.069308280944824, "learning_rate": 1.2579388365038027e-07, "loss": 0.5156941413879395, "step": 6638 }, { "epoch": 0.9309401949099068, "grad_norm": 2.9799606800079346, "learning_rate": 1.2528827013393142e-07, "loss": 0.4921755790710449, "step": 6639 }, { "epoch": 0.9310804178644044, "grad_norm": 2.974668264389038, "learning_rate": 1.2478366189868306e-07, "loss": 0.44733208417892456, "step": 6640 }, { "epoch": 0.9312206408189021, "grad_norm": 3.7589058876037598, "learning_rate": 1.2428005904869757e-07, "loss": 0.4613626301288605, "step": 6641 }, { "epoch": 0.9313608637733997, "grad_norm": 5.125380516052246, "learning_rate": 1.23777461687829e-07, "loss": 0.4285014271736145, "step": 6642 }, { "epoch": 0.9315010867278973, "grad_norm": 4.12538480758667, "learning_rate": 1.2327586991972674e-07, "loss": 0.4443069398403168, "step": 6643 }, { "epoch": 0.931641309682395, "grad_norm": 3.8719425201416016, "learning_rate": 1.2277528384782856e-07, "loss": 0.4895140826702118, "step": 6644 }, { "epoch": 0.9317815326368927, "grad_norm": 3.471693754196167, "learning_rate": 1.2227570357536855e-07, "loss": 0.4034040868282318, "step": 6645 }, { "epoch": 0.9319217555913903, "grad_norm": 4.075011253356934, "learning_rate": 1.2177712920537154e-07, "loss": 0.548351526260376, "step": 6646 }, { "epoch": 0.932061978545888, "grad_norm": 3.8705060482025146, "learning_rate": 1.2127956084065585e-07, "loss": 0.5234445929527283, "step": 6647 }, { "epoch": 0.9322022015003856, "grad_norm": 2.584468364715576, "learning_rate": 1.2078299858383103e-07, "loss": 0.4101872444152832, "step": 6648 }, { "epoch": 0.9323424244548832, "grad_norm": 4.794949531555176, "learning_rate": 1.2028744253730184e-07, "loss": 0.40298277139663696, "step": 6649 }, { "epoch": 0.9324826474093809, "grad_norm": 2.9204626083374023, "learning_rate": 1.19792892803261e-07, "loss": 0.5883734226226807, "step": 6650 }, { "epoch": 0.9326228703638786, "grad_norm": 3.2103967666625977, "learning_rate": 1.192993494836986e-07, "loss": 0.49111437797546387, "step": 6651 }, { "epoch": 0.9327630933183763, "grad_norm": 4.346634864807129, "learning_rate": 1.188068126803943e-07, "loss": 0.5513768196105957, "step": 6652 }, { "epoch": 0.9329033162728738, "grad_norm": 6.200963497161865, "learning_rate": 1.1831528249492019e-07, "loss": 0.5171458721160889, "step": 6653 }, { "epoch": 0.9330435392273715, "grad_norm": 4.422163963317871, "learning_rate": 1.1782475902864243e-07, "loss": 0.491942822933197, "step": 6654 }, { "epoch": 0.9331837621818692, "grad_norm": 5.670274257659912, "learning_rate": 1.1733524238271843e-07, "loss": 0.42572689056396484, "step": 6655 }, { "epoch": 0.9333239851363668, "grad_norm": 3.1835172176361084, "learning_rate": 1.1684673265809687e-07, "loss": 0.6039832830429077, "step": 6656 }, { "epoch": 0.9334642080908645, "grad_norm": 2.4784717559814453, "learning_rate": 1.1635922995552218e-07, "loss": 0.394634485244751, "step": 6657 }, { "epoch": 0.9336044310453622, "grad_norm": 4.327437877655029, "learning_rate": 1.1587273437552726e-07, "loss": 0.40400248765945435, "step": 6658 }, { "epoch": 0.9337446539998597, "grad_norm": 3.5939533710479736, "learning_rate": 1.153872460184402e-07, "loss": 0.36976391077041626, "step": 6659 }, { "epoch": 0.9338848769543574, "grad_norm": 4.519238471984863, "learning_rate": 1.1490276498437924e-07, "loss": 0.39820924401283264, "step": 6660 }, { "epoch": 0.9340250999088551, "grad_norm": 3.4765636920928955, "learning_rate": 1.1441929137325669e-07, "loss": 0.6222891807556152, "step": 6661 }, { "epoch": 0.9341653228633527, "grad_norm": 3.1374895572662354, "learning_rate": 1.1393682528477501e-07, "loss": 0.47168871760368347, "step": 6662 }, { "epoch": 0.9343055458178504, "grad_norm": 5.2392096519470215, "learning_rate": 1.1345536681843183e-07, "loss": 0.4105359613895416, "step": 6663 }, { "epoch": 0.9344457687723481, "grad_norm": 4.0422515869140625, "learning_rate": 1.129749160735144e-07, "loss": 0.526939868927002, "step": 6664 }, { "epoch": 0.9345859917268456, "grad_norm": 4.707797527313232, "learning_rate": 1.1249547314910292e-07, "loss": 0.5008038878440857, "step": 6665 }, { "epoch": 0.9347262146813433, "grad_norm": 3.66251802444458, "learning_rate": 1.120170381440705e-07, "loss": 0.5028330087661743, "step": 6666 }, { "epoch": 0.934866437635841, "grad_norm": 3.699373483657837, "learning_rate": 1.1153961115708157e-07, "loss": 0.601658821105957, "step": 6667 }, { "epoch": 0.9350066605903387, "grad_norm": 7.672122955322266, "learning_rate": 1.1106319228659179e-07, "loss": 0.4379594326019287, "step": 6668 }, { "epoch": 0.9351468835448363, "grad_norm": 4.0513811111450195, "learning_rate": 1.1058778163085204e-07, "loss": 0.5787304043769836, "step": 6669 }, { "epoch": 0.9352871064993339, "grad_norm": 3.6733787059783936, "learning_rate": 1.1011337928790167e-07, "loss": 0.5091578960418701, "step": 6670 }, { "epoch": 0.9354273294538316, "grad_norm": 3.073925733566284, "learning_rate": 1.0963998535557407e-07, "loss": 0.5160921812057495, "step": 6671 }, { "epoch": 0.9355675524083292, "grad_norm": 4.5466766357421875, "learning_rate": 1.0916759993149507e-07, "loss": 0.5288118124008179, "step": 6672 }, { "epoch": 0.9357077753628269, "grad_norm": 6.087284088134766, "learning_rate": 1.0869622311308059e-07, "loss": 0.4781099557876587, "step": 6673 }, { "epoch": 0.9358479983173246, "grad_norm": 6.6118621826171875, "learning_rate": 1.0822585499754068e-07, "loss": 0.5485419034957886, "step": 6674 }, { "epoch": 0.9359882212718222, "grad_norm": 3.5935139656066895, "learning_rate": 1.0775649568187662e-07, "loss": 0.512155294418335, "step": 6675 }, { "epoch": 0.9361284442263198, "grad_norm": 3.406430959701538, "learning_rate": 1.0728814526287935e-07, "loss": 0.42921939492225647, "step": 6676 }, { "epoch": 0.9362686671808175, "grad_norm": 3.1255011558532715, "learning_rate": 1.0682080383713656e-07, "loss": 0.42192569375038147, "step": 6677 }, { "epoch": 0.9364088901353151, "grad_norm": 31.23439598083496, "learning_rate": 1.0635447150102396e-07, "loss": 0.5256422162055969, "step": 6678 }, { "epoch": 0.9365491130898128, "grad_norm": 5.184985160827637, "learning_rate": 1.0588914835070962e-07, "loss": 0.5664788484573364, "step": 6679 }, { "epoch": 0.9366893360443105, "grad_norm": 3.54248309135437, "learning_rate": 1.0542483448215512e-07, "loss": 0.526331901550293, "step": 6680 }, { "epoch": 0.9368295589988082, "grad_norm": 3.3937010765075684, "learning_rate": 1.0496152999111276e-07, "loss": 0.5337750911712646, "step": 6681 }, { "epoch": 0.9369697819533057, "grad_norm": 5.897461414337158, "learning_rate": 1.0449923497312664e-07, "loss": 0.5039955377578735, "step": 6682 }, { "epoch": 0.9371100049078034, "grad_norm": 2.539247989654541, "learning_rate": 1.0403794952353385e-07, "loss": 0.40468430519104004, "step": 6683 }, { "epoch": 0.937250227862301, "grad_norm": 4.355393409729004, "learning_rate": 1.0357767373746108e-07, "loss": 0.5068204402923584, "step": 6684 }, { "epoch": 0.9373904508167987, "grad_norm": 3.8376011848449707, "learning_rate": 1.0311840770982906e-07, "loss": 0.5622605681419373, "step": 6685 }, { "epoch": 0.9375306737712964, "grad_norm": 3.4155330657958984, "learning_rate": 1.0266015153534925e-07, "loss": 0.44538840651512146, "step": 6686 }, { "epoch": 0.9376708967257941, "grad_norm": 5.082574844360352, "learning_rate": 1.0220290530852495e-07, "loss": 0.4705128073692322, "step": 6687 }, { "epoch": 0.9378111196802916, "grad_norm": 5.020482063293457, "learning_rate": 1.0174666912365017e-07, "loss": 0.5624330043792725, "step": 6688 }, { "epoch": 0.9379513426347893, "grad_norm": 2.944395065307617, "learning_rate": 1.0129144307481353e-07, "loss": 0.4213770031929016, "step": 6689 }, { "epoch": 0.938091565589287, "grad_norm": 3.576474905014038, "learning_rate": 1.0083722725589218e-07, "loss": 0.5352160930633545, "step": 6690 }, { "epoch": 0.9382317885437846, "grad_norm": 6.036546230316162, "learning_rate": 1.0038402176055561e-07, "loss": 0.5380736589431763, "step": 6691 }, { "epoch": 0.9383720114982823, "grad_norm": 3.3281097412109375, "learning_rate": 9.993182668226687e-08, "loss": 0.4577438533306122, "step": 6692 }, { "epoch": 0.9385122344527799, "grad_norm": 3.834587335586548, "learning_rate": 9.94806421142791e-08, "loss": 0.46192795038223267, "step": 6693 }, { "epoch": 0.9386524574072775, "grad_norm": 2.9255998134613037, "learning_rate": 9.903046814963624e-08, "loss": 0.4253678321838379, "step": 6694 }, { "epoch": 0.9387926803617752, "grad_norm": 4.852125644683838, "learning_rate": 9.858130488117623e-08, "loss": 0.46632856130599976, "step": 6695 }, { "epoch": 0.9389329033162729, "grad_norm": 3.7223258018493652, "learning_rate": 9.81331524015261e-08, "loss": 0.485087513923645, "step": 6696 }, { "epoch": 0.9390731262707706, "grad_norm": 3.023178815841675, "learning_rate": 9.768601080310581e-08, "loss": 0.4958670735359192, "step": 6697 }, { "epoch": 0.9392133492252682, "grad_norm": 6.449380397796631, "learning_rate": 9.723988017812713e-08, "loss": 0.43372511863708496, "step": 6698 }, { "epoch": 0.9393535721797658, "grad_norm": 3.6100471019744873, "learning_rate": 9.679476061859206e-08, "loss": 0.49867355823516846, "step": 6699 }, { "epoch": 0.9394937951342635, "grad_norm": 4.866650104522705, "learning_rate": 9.635065221629491e-08, "loss": 0.49291080236434937, "step": 6700 }, { "epoch": 0.9396340180887611, "grad_norm": 4.936594009399414, "learning_rate": 9.59075550628219e-08, "loss": 0.4406236708164215, "step": 6701 }, { "epoch": 0.9397742410432588, "grad_norm": 3.2599825859069824, "learning_rate": 9.546546924954992e-08, "loss": 0.5252838730812073, "step": 6702 }, { "epoch": 0.9399144639977565, "grad_norm": 4.369500160217285, "learning_rate": 9.502439486764714e-08, "loss": 0.4802742302417755, "step": 6703 }, { "epoch": 0.9400546869522541, "grad_norm": 3.8422963619232178, "learning_rate": 9.45843320080736e-08, "loss": 0.5909746289253235, "step": 6704 }, { "epoch": 0.9401949099067517, "grad_norm": 2.943052053451538, "learning_rate": 9.414528076158114e-08, "loss": 0.4585094153881073, "step": 6705 }, { "epoch": 0.9403351328612494, "grad_norm": 4.231261730194092, "learning_rate": 9.370724121871233e-08, "loss": 0.47979193925857544, "step": 6706 }, { "epoch": 0.940475355815747, "grad_norm": 3.5442724227905273, "learning_rate": 9.327021346980214e-08, "loss": 0.4761849343776703, "step": 6707 }, { "epoch": 0.9406155787702447, "grad_norm": 3.0685977935791016, "learning_rate": 9.283419760497404e-08, "loss": 0.37568044662475586, "step": 6708 }, { "epoch": 0.9407558017247424, "grad_norm": 2.7115530967712402, "learning_rate": 9.239919371414718e-08, "loss": 0.4562106728553772, "step": 6709 }, { "epoch": 0.9408960246792399, "grad_norm": 4.482102870941162, "learning_rate": 9.196520188702762e-08, "loss": 0.5668232440948486, "step": 6710 }, { "epoch": 0.9410362476337376, "grad_norm": 2.8507509231567383, "learning_rate": 9.153222221311653e-08, "loss": 0.4841950237751007, "step": 6711 }, { "epoch": 0.9411764705882353, "grad_norm": 4.5656208992004395, "learning_rate": 9.110025478170304e-08, "loss": 0.5175672769546509, "step": 6712 }, { "epoch": 0.941316693542733, "grad_norm": 4.926710605621338, "learning_rate": 9.066929968187033e-08, "loss": 0.5168806910514832, "step": 6713 }, { "epoch": 0.9414569164972306, "grad_norm": 3.1805641651153564, "learning_rate": 9.02393570024912e-08, "loss": 0.47672006487846375, "step": 6714 }, { "epoch": 0.9415971394517283, "grad_norm": 2.6261327266693115, "learning_rate": 8.981042683222974e-08, "loss": 0.4122730493545532, "step": 6715 }, { "epoch": 0.9417373624062259, "grad_norm": 3.8901286125183105, "learning_rate": 8.938250925954183e-08, "loss": 0.4838349223136902, "step": 6716 }, { "epoch": 0.9418775853607235, "grad_norm": 3.522550344467163, "learning_rate": 8.895560437267358e-08, "loss": 0.46583229303359985, "step": 6717 }, { "epoch": 0.9420178083152212, "grad_norm": 3.3369882106781006, "learning_rate": 8.8529712259664e-08, "loss": 0.4976871907711029, "step": 6718 }, { "epoch": 0.9421580312697189, "grad_norm": 5.194134712219238, "learning_rate": 8.810483300834117e-08, "loss": 0.4904468357563019, "step": 6719 }, { "epoch": 0.9422982542242165, "grad_norm": 5.008084774017334, "learning_rate": 8.768096670632553e-08, "loss": 0.5054634809494019, "step": 6720 }, { "epoch": 0.9424384771787142, "grad_norm": 2.61655592918396, "learning_rate": 8.725811344102885e-08, "loss": 0.49705010652542114, "step": 6721 }, { "epoch": 0.9425787001332118, "grad_norm": 3.8159704208374023, "learning_rate": 8.683627329965305e-08, "loss": 0.5328267812728882, "step": 6722 }, { "epoch": 0.9427189230877094, "grad_norm": 3.6332786083221436, "learning_rate": 8.641544636919186e-08, "loss": 0.45060935616493225, "step": 6723 }, { "epoch": 0.9428591460422071, "grad_norm": 4.863574981689453, "learning_rate": 8.599563273642918e-08, "loss": 0.5044992566108704, "step": 6724 }, { "epoch": 0.9429993689967048, "grad_norm": 3.3905413150787354, "learning_rate": 8.557683248794079e-08, "loss": 0.5301456451416016, "step": 6725 }, { "epoch": 0.9431395919512024, "grad_norm": 3.9414212703704834, "learning_rate": 8.51590457100937e-08, "loss": 0.4527585208415985, "step": 6726 }, { "epoch": 0.9432798149057, "grad_norm": 6.30441427230835, "learning_rate": 8.474227248904565e-08, "loss": 0.4935207962989807, "step": 6727 }, { "epoch": 0.9434200378601977, "grad_norm": 3.025573968887329, "learning_rate": 8.4326512910744e-08, "loss": 0.5312299728393555, "step": 6728 }, { "epoch": 0.9435602608146954, "grad_norm": 4.238125324249268, "learning_rate": 8.391176706092907e-08, "loss": 0.6048150062561035, "step": 6729 }, { "epoch": 0.943700483769193, "grad_norm": 3.2026615142822266, "learning_rate": 8.349803502513131e-08, "loss": 0.5447614192962646, "step": 6730 }, { "epoch": 0.9438407067236907, "grad_norm": 2.695451259613037, "learning_rate": 8.308531688867138e-08, "loss": 0.560965895652771, "step": 6731 }, { "epoch": 0.9439809296781884, "grad_norm": 3.2573251724243164, "learning_rate": 8.26736127366623e-08, "loss": 0.4577239155769348, "step": 6732 }, { "epoch": 0.9441211526326859, "grad_norm": 5.700080871582031, "learning_rate": 8.226292265400726e-08, "loss": 0.3974899351596832, "step": 6733 }, { "epoch": 0.9442613755871836, "grad_norm": 4.6464996337890625, "learning_rate": 8.185324672539963e-08, "loss": 0.40668219327926636, "step": 6734 }, { "epoch": 0.9444015985416813, "grad_norm": 3.690880298614502, "learning_rate": 8.144458503532515e-08, "loss": 0.4743529260158539, "step": 6735 }, { "epoch": 0.9445418214961789, "grad_norm": 6.681997776031494, "learning_rate": 8.10369376680592e-08, "loss": 0.5836194157600403, "step": 6736 }, { "epoch": 0.9446820444506766, "grad_norm": 3.500396966934204, "learning_rate": 8.063030470766786e-08, "loss": 0.504029393196106, "step": 6737 }, { "epoch": 0.9448222674051743, "grad_norm": 3.108381748199463, "learning_rate": 8.022468623800905e-08, "loss": 0.4792996644973755, "step": 6738 }, { "epoch": 0.9449624903596718, "grad_norm": 3.650362014770508, "learning_rate": 7.982008234273031e-08, "loss": 0.523494303226471, "step": 6739 }, { "epoch": 0.9451027133141695, "grad_norm": 4.353604793548584, "learning_rate": 7.941649310527155e-08, "loss": 0.5591269731521606, "step": 6740 }, { "epoch": 0.9452429362686672, "grad_norm": 3.178600549697876, "learning_rate": 7.901391860886176e-08, "loss": 0.5087417960166931, "step": 6741 }, { "epoch": 0.9453831592231648, "grad_norm": 7.662815570831299, "learning_rate": 7.861235893652174e-08, "loss": 0.5015906095504761, "step": 6742 }, { "epoch": 0.9455233821776625, "grad_norm": 8.410927772521973, "learning_rate": 7.821181417106194e-08, "loss": 0.4437536299228668, "step": 6743 }, { "epoch": 0.9456636051321602, "grad_norm": 3.33976674079895, "learning_rate": 7.781228439508459e-08, "loss": 0.4147428274154663, "step": 6744 }, { "epoch": 0.9458038280866577, "grad_norm": 2.69058895111084, "learning_rate": 7.741376969098268e-08, "loss": 0.5232632160186768, "step": 6745 }, { "epoch": 0.9459440510411554, "grad_norm": 3.6665825843811035, "learning_rate": 7.701627014093882e-08, "loss": 0.4890992045402527, "step": 6746 }, { "epoch": 0.9460842739956531, "grad_norm": 4.658398628234863, "learning_rate": 7.661978582692687e-08, "loss": 0.445631206035614, "step": 6747 }, { "epoch": 0.9462244969501508, "grad_norm": 41.95500564575195, "learning_rate": 7.62243168307114e-08, "loss": 0.44363003969192505, "step": 6748 }, { "epoch": 0.9463647199046484, "grad_norm": 5.415390491485596, "learning_rate": 7.582986323384777e-08, "loss": 0.5569084882736206, "step": 6749 }, { "epoch": 0.946504942859146, "grad_norm": 5.181396484375, "learning_rate": 7.54364251176809e-08, "loss": 0.5216388702392578, "step": 6750 }, { "epoch": 0.9466451658136437, "grad_norm": 3.951007127761841, "learning_rate": 7.50440025633481e-08, "loss": 0.5131596326828003, "step": 6751 }, { "epoch": 0.9467853887681413, "grad_norm": 5.05630350112915, "learning_rate": 7.465259565177573e-08, "loss": 0.44271814823150635, "step": 6752 }, { "epoch": 0.946925611722639, "grad_norm": 4.392708778381348, "learning_rate": 7.426220446368037e-08, "loss": 0.45423728227615356, "step": 6753 }, { "epoch": 0.9470658346771367, "grad_norm": 3.9357359409332275, "learning_rate": 7.387282907957205e-08, "loss": 0.5882298946380615, "step": 6754 }, { "epoch": 0.9472060576316343, "grad_norm": 5.408178806304932, "learning_rate": 7.348446957974653e-08, "loss": 0.4851563572883606, "step": 6755 }, { "epoch": 0.9473462805861319, "grad_norm": 3.2530441284179688, "learning_rate": 7.309712604429476e-08, "loss": 0.43707016110420227, "step": 6756 }, { "epoch": 0.9474865035406296, "grad_norm": 4.34001350402832, "learning_rate": 7.271079855309559e-08, "loss": 0.4656713306903839, "step": 6757 }, { "epoch": 0.9476267264951272, "grad_norm": 4.243765354156494, "learning_rate": 7.232548718581866e-08, "loss": 0.5263950228691101, "step": 6758 }, { "epoch": 0.9477669494496249, "grad_norm": 2.891005039215088, "learning_rate": 7.194119202192429e-08, "loss": 0.4642214775085449, "step": 6759 }, { "epoch": 0.9479071724041226, "grad_norm": 4.6320390701293945, "learning_rate": 7.155791314066407e-08, "loss": 0.5363730192184448, "step": 6760 }, { "epoch": 0.9480473953586203, "grad_norm": 3.923649311065674, "learning_rate": 7.117565062107812e-08, "loss": 0.42512476444244385, "step": 6761 }, { "epoch": 0.9481876183131178, "grad_norm": 3.831380605697632, "learning_rate": 7.079440454199837e-08, "loss": 0.43561506271362305, "step": 6762 }, { "epoch": 0.9483278412676155, "grad_norm": 4.717105865478516, "learning_rate": 7.041417498204695e-08, "loss": 0.4814426302909851, "step": 6763 }, { "epoch": 0.9484680642221132, "grad_norm": 2.93677020072937, "learning_rate": 7.003496201963612e-08, "loss": 0.49031105637550354, "step": 6764 }, { "epoch": 0.9486082871766108, "grad_norm": 9.429290771484375, "learning_rate": 6.965676573296886e-08, "loss": 0.5173500776290894, "step": 6765 }, { "epoch": 0.9487485101311085, "grad_norm": 2.175638198852539, "learning_rate": 6.927958620003783e-08, "loss": 0.4163549840450287, "step": 6766 }, { "epoch": 0.9488887330856061, "grad_norm": 5.229108810424805, "learning_rate": 6.890342349862744e-08, "loss": 0.5097619891166687, "step": 6767 }, { "epoch": 0.9490289560401037, "grad_norm": 4.949207782745361, "learning_rate": 6.852827770630954e-08, "loss": 0.532860279083252, "step": 6768 }, { "epoch": 0.9491691789946014, "grad_norm": 3.620723009109497, "learning_rate": 6.815414890044946e-08, "loss": 0.38466739654541016, "step": 6769 }, { "epoch": 0.9493094019490991, "grad_norm": 5.548761367797852, "learning_rate": 6.778103715820106e-08, "loss": 0.43756920099258423, "step": 6770 }, { "epoch": 0.9494496249035967, "grad_norm": 2.832883834838867, "learning_rate": 6.740894255650887e-08, "loss": 0.5191283226013184, "step": 6771 }, { "epoch": 0.9495898478580944, "grad_norm": 3.3473989963531494, "learning_rate": 6.703786517210708e-08, "loss": 0.4710230529308319, "step": 6772 }, { "epoch": 0.949730070812592, "grad_norm": 3.3632876873016357, "learning_rate": 6.666780508152171e-08, "loss": 0.5434761047363281, "step": 6773 }, { "epoch": 0.9498702937670896, "grad_norm": 3.799257278442383, "learning_rate": 6.629876236106725e-08, "loss": 0.32367005944252014, "step": 6774 }, { "epoch": 0.9500105167215873, "grad_norm": 4.007659435272217, "learning_rate": 6.593073708684894e-08, "loss": 0.5151004195213318, "step": 6775 }, { "epoch": 0.950150739676085, "grad_norm": 2.3968989849090576, "learning_rate": 6.556372933476273e-08, "loss": 0.39848196506500244, "step": 6776 }, { "epoch": 0.9502909626305827, "grad_norm": 6.34404993057251, "learning_rate": 6.519773918049422e-08, "loss": 0.5023632049560547, "step": 6777 }, { "epoch": 0.9504311855850803, "grad_norm": 4.201510429382324, "learning_rate": 6.48327666995191e-08, "loss": 0.5435914993286133, "step": 6778 }, { "epoch": 0.9505714085395779, "grad_norm": 3.6631267070770264, "learning_rate": 6.44688119671033e-08, "loss": 0.45477020740509033, "step": 6779 }, { "epoch": 0.9507116314940756, "grad_norm": 16.49472999572754, "learning_rate": 6.410587505830346e-08, "loss": 0.5201307535171509, "step": 6780 }, { "epoch": 0.9508518544485732, "grad_norm": 6.891530513763428, "learning_rate": 6.374395604796469e-08, "loss": 0.4805988669395447, "step": 6781 }, { "epoch": 0.9509920774030709, "grad_norm": 3.211937665939331, "learning_rate": 6.33830550107245e-08, "loss": 0.5018019676208496, "step": 6782 }, { "epoch": 0.9511323003575686, "grad_norm": 5.169919490814209, "learning_rate": 6.302317202100839e-08, "loss": 0.4778946042060852, "step": 6783 }, { "epoch": 0.9512725233120661, "grad_norm": 3.6858203411102295, "learning_rate": 6.266430715303363e-08, "loss": 0.43480876088142395, "step": 6784 }, { "epoch": 0.9514127462665638, "grad_norm": 5.045166015625, "learning_rate": 6.230646048080546e-08, "loss": 0.4301249384880066, "step": 6785 }, { "epoch": 0.9515529692210615, "grad_norm": 4.367793560028076, "learning_rate": 6.19496320781221e-08, "loss": 0.5053211450576782, "step": 6786 }, { "epoch": 0.9516931921755591, "grad_norm": 2.729010581970215, "learning_rate": 6.1593822018568e-08, "loss": 0.476375937461853, "step": 6787 }, { "epoch": 0.9518334151300568, "grad_norm": 3.7177045345306396, "learning_rate": 6.12390303755206e-08, "loss": 0.3863213360309601, "step": 6788 }, { "epoch": 0.9519736380845545, "grad_norm": 2.9207651615142822, "learning_rate": 6.088525722214688e-08, "loss": 0.4395144581794739, "step": 6789 }, { "epoch": 0.952113861039052, "grad_norm": 2.797997236251831, "learning_rate": 6.053250263140242e-08, "loss": 0.5369513034820557, "step": 6790 }, { "epoch": 0.9522540839935497, "grad_norm": 3.1632142066955566, "learning_rate": 6.018076667603346e-08, "loss": 0.5439740419387817, "step": 6791 }, { "epoch": 0.9523943069480474, "grad_norm": 3.8534677028656006, "learning_rate": 5.98300494285775e-08, "loss": 0.5028524994850159, "step": 6792 }, { "epoch": 0.9525345299025451, "grad_norm": 4.6305365562438965, "learning_rate": 5.948035096135951e-08, "loss": 0.5366537570953369, "step": 6793 }, { "epoch": 0.9526747528570427, "grad_norm": 5.711101055145264, "learning_rate": 5.9131671346496225e-08, "loss": 0.4525984525680542, "step": 6794 }, { "epoch": 0.9528149758115404, "grad_norm": 8.578597068786621, "learning_rate": 5.878401065589345e-08, "loss": 0.4062616229057312, "step": 6795 }, { "epoch": 0.952955198766038, "grad_norm": 7.9603352546691895, "learning_rate": 5.843736896124719e-08, "loss": 0.4411182999610901, "step": 6796 }, { "epoch": 0.9530954217205356, "grad_norm": 3.401705265045166, "learning_rate": 5.8091746334043576e-08, "loss": 0.558505117893219, "step": 6797 }, { "epoch": 0.9532356446750333, "grad_norm": 3.8481922149658203, "learning_rate": 5.774714284555727e-08, "loss": 0.5664606094360352, "step": 6798 }, { "epoch": 0.953375867629531, "grad_norm": 3.786691427230835, "learning_rate": 5.7403558566853646e-08, "loss": 0.5133238434791565, "step": 6799 }, { "epoch": 0.9535160905840286, "grad_norm": 3.5318315029144287, "learning_rate": 5.706099356878936e-08, "loss": 0.4842100739479065, "step": 6800 }, { "epoch": 0.9536563135385262, "grad_norm": 4.641214370727539, "learning_rate": 5.671944792200845e-08, "loss": 0.5345771312713623, "step": 6801 }, { "epoch": 0.9537965364930239, "grad_norm": 4.37357234954834, "learning_rate": 5.6378921696945144e-08, "loss": 0.47262078523635864, "step": 6802 }, { "epoch": 0.9539367594475215, "grad_norm": 6.231270790100098, "learning_rate": 5.603941496382492e-08, "loss": 0.5255985856056213, "step": 6803 }, { "epoch": 0.9540769824020192, "grad_norm": 7.208160400390625, "learning_rate": 5.570092779266234e-08, "loss": 0.5319086313247681, "step": 6804 }, { "epoch": 0.9542172053565169, "grad_norm": 2.968463659286499, "learning_rate": 5.536346025326045e-08, "loss": 0.4154321849346161, "step": 6805 }, { "epoch": 0.9543574283110146, "grad_norm": 2.8336265087127686, "learning_rate": 5.502701241521413e-08, "loss": 0.33485889434814453, "step": 6806 }, { "epoch": 0.9544976512655121, "grad_norm": 4.7355217933654785, "learning_rate": 5.469158434790622e-08, "loss": 0.5722538232803345, "step": 6807 }, { "epoch": 0.9546378742200098, "grad_norm": 5.015691757202148, "learning_rate": 5.435717612051028e-08, "loss": 0.5520492196083069, "step": 6808 }, { "epoch": 0.9547780971745075, "grad_norm": 4.672919750213623, "learning_rate": 5.4023787801988916e-08, "loss": 0.49042558670043945, "step": 6809 }, { "epoch": 0.9549183201290051, "grad_norm": 3.5907392501831055, "learning_rate": 5.3691419461094904e-08, "loss": 0.5053659081459045, "step": 6810 }, { "epoch": 0.9550585430835028, "grad_norm": 5.341287612915039, "learning_rate": 5.3360071166370653e-08, "loss": 0.5343413352966309, "step": 6811 }, { "epoch": 0.9551987660380005, "grad_norm": 16.51247215270996, "learning_rate": 5.30297429861476e-08, "loss": 0.5123958587646484, "step": 6812 }, { "epoch": 0.955338988992498, "grad_norm": 3.7731504440307617, "learning_rate": 5.270043498854738e-08, "loss": 0.6056094169616699, "step": 6813 }, { "epoch": 0.9554792119469957, "grad_norm": 4.830306529998779, "learning_rate": 5.2372147241481766e-08, "loss": 0.5416485071182251, "step": 6814 }, { "epoch": 0.9556194349014934, "grad_norm": 9.25625991821289, "learning_rate": 5.2044879812650495e-08, "loss": 0.4766702651977539, "step": 6815 }, { "epoch": 0.955759657855991, "grad_norm": 4.054047107696533, "learning_rate": 5.171863276954458e-08, "loss": 0.46964746713638306, "step": 6816 }, { "epoch": 0.9558998808104887, "grad_norm": 4.1294684410095215, "learning_rate": 5.139340617944355e-08, "loss": 0.45963054895401, "step": 6817 }, { "epoch": 0.9560401037649864, "grad_norm": 3.728012800216675, "learning_rate": 5.106920010941707e-08, "loss": 0.5219224691390991, "step": 6818 }, { "epoch": 0.9561803267194839, "grad_norm": 5.096053600311279, "learning_rate": 5.074601462632389e-08, "loss": 0.486418753862381, "step": 6819 }, { "epoch": 0.9563205496739816, "grad_norm": 2.8331804275512695, "learning_rate": 5.0423849796812917e-08, "loss": 0.492492139339447, "step": 6820 }, { "epoch": 0.9564607726284793, "grad_norm": 3.546708583831787, "learning_rate": 5.0102705687321005e-08, "loss": 0.4633045792579651, "step": 6821 }, { "epoch": 0.956600995582977, "grad_norm": 8.474648475646973, "learning_rate": 4.97825823640774e-08, "loss": 0.5332913398742676, "step": 6822 }, { "epoch": 0.9567412185374746, "grad_norm": 4.580708980560303, "learning_rate": 4.946347989309819e-08, "loss": 0.5412535667419434, "step": 6823 }, { "epoch": 0.9568814414919722, "grad_norm": 6.242432117462158, "learning_rate": 4.914539834018961e-08, "loss": 0.48999273777008057, "step": 6824 }, { "epoch": 0.9570216644464699, "grad_norm": 3.659485340118408, "learning_rate": 4.8828337770948084e-08, "loss": 0.3793187737464905, "step": 6825 }, { "epoch": 0.9571618874009675, "grad_norm": 4.92431640625, "learning_rate": 4.851229825075965e-08, "loss": 0.458099901676178, "step": 6826 }, { "epoch": 0.9573021103554652, "grad_norm": 3.5439019203186035, "learning_rate": 4.819727984479716e-08, "loss": 0.4721416234970093, "step": 6827 }, { "epoch": 0.9574423333099629, "grad_norm": 9.301725387573242, "learning_rate": 4.788328261802755e-08, "loss": 0.505505383014679, "step": 6828 }, { "epoch": 0.9575825562644605, "grad_norm": 3.364112615585327, "learning_rate": 4.757030663520235e-08, "loss": 0.5354289412498474, "step": 6829 }, { "epoch": 0.9577227792189581, "grad_norm": 4.683002948760986, "learning_rate": 4.725835196086548e-08, "loss": 0.4568362236022949, "step": 6830 }, { "epoch": 0.9578630021734558, "grad_norm": 2.8820319175720215, "learning_rate": 4.6947418659349376e-08, "loss": 0.44435518980026245, "step": 6831 }, { "epoch": 0.9580032251279534, "grad_norm": 3.8133277893066406, "learning_rate": 4.6637506794776075e-08, "loss": 0.5566501617431641, "step": 6832 }, { "epoch": 0.9581434480824511, "grad_norm": 3.1382458209991455, "learning_rate": 4.632861643105557e-08, "loss": 0.5094060301780701, "step": 6833 }, { "epoch": 0.9582836710369488, "grad_norm": 3.010126829147339, "learning_rate": 4.602074763189024e-08, "loss": 0.5256474614143372, "step": 6834 }, { "epoch": 0.9584238939914465, "grad_norm": 3.703352928161621, "learning_rate": 4.571390046076818e-08, "loss": 0.5447753667831421, "step": 6835 }, { "epoch": 0.958564116945944, "grad_norm": 2.735600233078003, "learning_rate": 4.540807498096988e-08, "loss": 0.4836867153644562, "step": 6836 }, { "epoch": 0.9587043399004417, "grad_norm": 4.343998432159424, "learning_rate": 4.510327125556324e-08, "loss": 0.4377157986164093, "step": 6837 }, { "epoch": 0.9588445628549394, "grad_norm": 6.785863399505615, "learning_rate": 4.47994893474063e-08, "loss": 0.4525579512119293, "step": 6838 }, { "epoch": 0.958984785809437, "grad_norm": 4.265939235687256, "learning_rate": 4.449672931914506e-08, "loss": 0.4916689395904541, "step": 6839 }, { "epoch": 0.9591250087639347, "grad_norm": 3.4597134590148926, "learning_rate": 4.4194991233217353e-08, "loss": 0.5292965769767761, "step": 6840 }, { "epoch": 0.9592652317184323, "grad_norm": 2.7150397300720215, "learning_rate": 4.3894275151847855e-08, "loss": 0.46113115549087524, "step": 6841 }, { "epoch": 0.9594054546729299, "grad_norm": 5.3067450523376465, "learning_rate": 4.3594581137051396e-08, "loss": 0.585527777671814, "step": 6842 }, { "epoch": 0.9595456776274276, "grad_norm": 3.620945692062378, "learning_rate": 4.3295909250631874e-08, "loss": 0.48821157217025757, "step": 6843 }, { "epoch": 0.9596859005819253, "grad_norm": 3.395998001098633, "learning_rate": 4.2998259554183355e-08, "loss": 0.45460033416748047, "step": 6844 }, { "epoch": 0.9598261235364229, "grad_norm": 4.284814834594727, "learning_rate": 4.2701632109087285e-08, "loss": 0.4671725630760193, "step": 6845 }, { "epoch": 0.9599663464909206, "grad_norm": 3.430332660675049, "learning_rate": 4.2406026976515854e-08, "loss": 0.47953978180885315, "step": 6846 }, { "epoch": 0.9601065694454182, "grad_norm": 7.821562767028809, "learning_rate": 4.211144421742919e-08, "loss": 0.45599913597106934, "step": 6847 }, { "epoch": 0.9602467923999158, "grad_norm": 3.7519078254699707, "learning_rate": 4.1817883892578124e-08, "loss": 0.6098675727844238, "step": 6848 }, { "epoch": 0.9603870153544135, "grad_norm": 5.090197563171387, "learning_rate": 4.1525346062500914e-08, "loss": 0.5694113373756409, "step": 6849 }, { "epoch": 0.9605272383089112, "grad_norm": 4.259760856628418, "learning_rate": 4.1233830787526516e-08, "loss": 0.5087373852729797, "step": 6850 }, { "epoch": 0.9606674612634089, "grad_norm": 3.891181468963623, "learning_rate": 4.094333812777185e-08, "loss": 0.42402541637420654, "step": 6851 }, { "epoch": 0.9608076842179065, "grad_norm": 3.5182785987854004, "learning_rate": 4.065386814314398e-08, "loss": 0.4190545678138733, "step": 6852 }, { "epoch": 0.9609479071724041, "grad_norm": 3.982131242752075, "learning_rate": 4.036542089333739e-08, "loss": 0.43954992294311523, "step": 6853 }, { "epoch": 0.9610881301269018, "grad_norm": 4.108159065246582, "learning_rate": 4.007799643783783e-08, "loss": 0.6635360717773438, "step": 6854 }, { "epoch": 0.9612283530813994, "grad_norm": 2.7286317348480225, "learning_rate": 3.979159483591843e-08, "loss": 0.4478684365749359, "step": 6855 }, { "epoch": 0.9613685760358971, "grad_norm": 5.387564659118652, "learning_rate": 3.950621614664196e-08, "loss": 0.5136961340904236, "step": 6856 }, { "epoch": 0.9615087989903948, "grad_norm": 3.6515555381774902, "learning_rate": 3.922186042886078e-08, "loss": 0.5007206797599792, "step": 6857 }, { "epoch": 0.9616490219448923, "grad_norm": 4.8703484535217285, "learning_rate": 3.893852774121576e-08, "loss": 0.6069878935813904, "step": 6858 }, { "epoch": 0.96178924489939, "grad_norm": 3.5927951335906982, "learning_rate": 3.865621814213627e-08, "loss": 0.49254751205444336, "step": 6859 }, { "epoch": 0.9619294678538877, "grad_norm": 3.046942949295044, "learning_rate": 3.8374931689841856e-08, "loss": 0.5628843307495117, "step": 6860 }, { "epoch": 0.9620696908083853, "grad_norm": 3.7469654083251953, "learning_rate": 3.809466844233944e-08, "loss": 0.5744143128395081, "step": 6861 }, { "epoch": 0.962209913762883, "grad_norm": 5.198047637939453, "learning_rate": 3.781542845742725e-08, "loss": 0.4773283004760742, "step": 6862 }, { "epoch": 0.9623501367173807, "grad_norm": 3.7521347999572754, "learning_rate": 3.753721179269032e-08, "loss": 0.5115818977355957, "step": 6863 }, { "epoch": 0.9624903596718782, "grad_norm": 2.9870831966400146, "learning_rate": 3.726001850550442e-08, "loss": 0.565445065498352, "step": 6864 }, { "epoch": 0.9626305826263759, "grad_norm": 3.744138717651367, "learning_rate": 3.698384865303162e-08, "loss": 0.5303007364273071, "step": 6865 }, { "epoch": 0.9627708055808736, "grad_norm": 6.027413368225098, "learning_rate": 3.6708702292226895e-08, "loss": 0.474165141582489, "step": 6866 }, { "epoch": 0.9629110285353712, "grad_norm": 3.16483473777771, "learning_rate": 3.6434579479830423e-08, "loss": 0.5358745455741882, "step": 6867 }, { "epoch": 0.9630512514898689, "grad_norm": 6.032349109649658, "learning_rate": 3.6161480272373095e-08, "loss": 0.43805229663848877, "step": 6868 }, { "epoch": 0.9631914744443666, "grad_norm": 2.7154252529144287, "learning_rate": 3.588940472617486e-08, "loss": 0.38719990849494934, "step": 6869 }, { "epoch": 0.9633316973988642, "grad_norm": 6.016224384307861, "learning_rate": 3.5618352897344165e-08, "loss": 0.42274239659309387, "step": 6870 }, { "epoch": 0.9634719203533618, "grad_norm": 2.7120158672332764, "learning_rate": 3.534832484177797e-08, "loss": 0.4726073145866394, "step": 6871 }, { "epoch": 0.9636121433078595, "grad_norm": 2.255384683609009, "learning_rate": 3.5079320615162835e-08, "loss": 0.4669667184352875, "step": 6872 }, { "epoch": 0.9637523662623572, "grad_norm": 4.7229390144348145, "learning_rate": 3.4811340272973284e-08, "loss": 0.4836791753768921, "step": 6873 }, { "epoch": 0.9638925892168548, "grad_norm": 4.392395973205566, "learning_rate": 3.454438387047343e-08, "loss": 0.49301597476005554, "step": 6874 }, { "epoch": 0.9640328121713525, "grad_norm": 6.817976474761963, "learning_rate": 3.4278451462715913e-08, "loss": 0.6306959986686707, "step": 6875 }, { "epoch": 0.9641730351258501, "grad_norm": 3.0660009384155273, "learning_rate": 3.4013543104543525e-08, "loss": 0.35935401916503906, "step": 6876 }, { "epoch": 0.9643132580803477, "grad_norm": 4.452619552612305, "learning_rate": 3.374965885058423e-08, "loss": 0.5013530850410461, "step": 6877 }, { "epoch": 0.9644534810348454, "grad_norm": 4.790187358856201, "learning_rate": 3.348679875525951e-08, "loss": 0.5312634706497192, "step": 6878 }, { "epoch": 0.9645937039893431, "grad_norm": 4.114894866943359, "learning_rate": 3.3224962872776544e-08, "loss": 0.5188139081001282, "step": 6879 }, { "epoch": 0.9647339269438407, "grad_norm": 3.4613466262817383, "learning_rate": 3.2964151257131597e-08, "loss": 0.391924113035202, "step": 6880 }, { "epoch": 0.9648741498983383, "grad_norm": 4.797677516937256, "learning_rate": 3.270436396211052e-08, "loss": 0.4025723338127136, "step": 6881 }, { "epoch": 0.965014372852836, "grad_norm": 4.24549674987793, "learning_rate": 3.2445601041288244e-08, "loss": 0.5007058382034302, "step": 6882 }, { "epoch": 0.9651545958073336, "grad_norm": 4.666280746459961, "learning_rate": 3.218786254802708e-08, "loss": 0.48129576444625854, "step": 6883 }, { "epoch": 0.9652948187618313, "grad_norm": 4.156304836273193, "learning_rate": 3.193114853547896e-08, "loss": 0.4221552610397339, "step": 6884 }, { "epoch": 0.965435041716329, "grad_norm": 3.2111730575561523, "learning_rate": 3.167545905658431e-08, "loss": 0.49785271286964417, "step": 6885 }, { "epoch": 0.9655752646708267, "grad_norm": 3.9989514350891113, "learning_rate": 3.1420794164073175e-08, "loss": 0.4727584421634674, "step": 6886 }, { "epoch": 0.9657154876253242, "grad_norm": 3.7739381790161133, "learning_rate": 3.116715391046243e-08, "loss": 0.4748827815055847, "step": 6887 }, { "epoch": 0.9658557105798219, "grad_norm": 3.561185836791992, "learning_rate": 3.0914538348059133e-08, "loss": 0.5098675489425659, "step": 6888 }, { "epoch": 0.9659959335343196, "grad_norm": 4.792469501495361, "learning_rate": 3.0662947528958266e-08, "loss": 0.3988746106624603, "step": 6889 }, { "epoch": 0.9661361564888172, "grad_norm": 3.178603410720825, "learning_rate": 3.0412381505044997e-08, "loss": 0.5872601866722107, "step": 6890 }, { "epoch": 0.9662763794433149, "grad_norm": 3.399329900741577, "learning_rate": 3.0162840327990214e-08, "loss": 0.48808449506759644, "step": 6891 }, { "epoch": 0.9664166023978126, "grad_norm": 5.4339375495910645, "learning_rate": 2.9914324049257206e-08, "loss": 0.5425524115562439, "step": 6892 }, { "epoch": 0.9665568253523101, "grad_norm": 5.243915557861328, "learning_rate": 2.966683272009441e-08, "loss": 0.5398074388504028, "step": 6893 }, { "epoch": 0.9666970483068078, "grad_norm": 3.761759042739868, "learning_rate": 2.9420366391541e-08, "loss": 0.4405481815338135, "step": 6894 }, { "epoch": 0.9668372712613055, "grad_norm": 6.462145805358887, "learning_rate": 2.9174925114423547e-08, "loss": 0.43979114294052124, "step": 6895 }, { "epoch": 0.9669774942158031, "grad_norm": 3.0264644622802734, "learning_rate": 2.8930508939359335e-08, "loss": 0.46386122703552246, "step": 6896 }, { "epoch": 0.9671177171703008, "grad_norm": 3.5774941444396973, "learning_rate": 2.8687117916750828e-08, "loss": 0.5604634284973145, "step": 6897 }, { "epoch": 0.9672579401247984, "grad_norm": 3.195225238800049, "learning_rate": 2.844475209679287e-08, "loss": 0.528176486492157, "step": 6898 }, { "epoch": 0.967398163079296, "grad_norm": 3.6226844787597656, "learning_rate": 2.820341152946604e-08, "loss": 0.419750452041626, "step": 6899 }, { "epoch": 0.9675383860337937, "grad_norm": 2.6605498790740967, "learning_rate": 2.7963096264540524e-08, "loss": 0.4529294967651367, "step": 6900 }, { "epoch": 0.9676786089882914, "grad_norm": 4.973453044891357, "learning_rate": 2.7723806351575012e-08, "loss": 0.5153623819351196, "step": 6901 }, { "epoch": 0.9678188319427891, "grad_norm": 3.572364568710327, "learning_rate": 2.748554183991725e-08, "loss": 0.5283204317092896, "step": 6902 }, { "epoch": 0.9679590548972867, "grad_norm": 3.6856114864349365, "learning_rate": 2.724830277870183e-08, "loss": 0.501023530960083, "step": 6903 }, { "epoch": 0.9680992778517843, "grad_norm": 2.766636848449707, "learning_rate": 2.7012089216855164e-08, "loss": 0.5185884833335876, "step": 6904 }, { "epoch": 0.968239500806282, "grad_norm": 3.5278265476226807, "learning_rate": 2.677690120308829e-08, "loss": 0.47449159622192383, "step": 6905 }, { "epoch": 0.9683797237607796, "grad_norm": 2.9729413986206055, "learning_rate": 2.6542738785902967e-08, "loss": 0.5305837988853455, "step": 6906 }, { "epoch": 0.9685199467152773, "grad_norm": 4.433371543884277, "learning_rate": 2.6309602013589453e-08, "loss": 0.5060468316078186, "step": 6907 }, { "epoch": 0.968660169669775, "grad_norm": 3.155902624130249, "learning_rate": 2.6077490934225956e-08, "loss": 0.6088829040527344, "step": 6908 }, { "epoch": 0.9688003926242726, "grad_norm": 2.963160753250122, "learning_rate": 2.5846405595678635e-08, "loss": 0.5255131721496582, "step": 6909 }, { "epoch": 0.9689406155787702, "grad_norm": 5.4099202156066895, "learning_rate": 2.5616346045604367e-08, "loss": 0.3756476938724518, "step": 6910 }, { "epoch": 0.9690808385332679, "grad_norm": 3.294496774673462, "learning_rate": 2.5387312331444645e-08, "loss": 0.5047805309295654, "step": 6911 }, { "epoch": 0.9692210614877655, "grad_norm": 4.032608509063721, "learning_rate": 2.5159304500433357e-08, "loss": 0.4559618830680847, "step": 6912 }, { "epoch": 0.9693612844422632, "grad_norm": 3.4905192852020264, "learning_rate": 2.4932322599590663e-08, "loss": 0.5567033886909485, "step": 6913 }, { "epoch": 0.9695015073967609, "grad_norm": 5.134452819824219, "learning_rate": 2.4706366675725792e-08, "loss": 0.43547025322914124, "step": 6914 }, { "epoch": 0.9696417303512584, "grad_norm": 3.4251351356506348, "learning_rate": 2.4481436775435353e-08, "loss": 0.45437899231910706, "step": 6915 }, { "epoch": 0.9697819533057561, "grad_norm": 4.353879451751709, "learning_rate": 2.4257532945106688e-08, "loss": 0.47204238176345825, "step": 6916 }, { "epoch": 0.9699221762602538, "grad_norm": 3.200758695602417, "learning_rate": 2.4034655230912308e-08, "loss": 0.4631630778312683, "step": 6917 }, { "epoch": 0.9700623992147515, "grad_norm": 2.8262081146240234, "learning_rate": 2.3812803678816555e-08, "loss": 0.534365713596344, "step": 6918 }, { "epoch": 0.9702026221692491, "grad_norm": 4.7179460525512695, "learning_rate": 2.3591978334568945e-08, "loss": 0.48271816968917847, "step": 6919 }, { "epoch": 0.9703428451237468, "grad_norm": 2.7694754600524902, "learning_rate": 2.337217924371027e-08, "loss": 0.3749126195907593, "step": 6920 }, { "epoch": 0.9704830680782444, "grad_norm": 5.251498222351074, "learning_rate": 2.3153406451567607e-08, "loss": 0.46302151679992676, "step": 6921 }, { "epoch": 0.970623291032742, "grad_norm": 3.0423848628997803, "learning_rate": 2.2935660003257644e-08, "loss": 0.4267139434814453, "step": 6922 }, { "epoch": 0.9707635139872397, "grad_norm": 4.945920467376709, "learning_rate": 2.2718939943683903e-08, "loss": 0.5236279964447021, "step": 6923 }, { "epoch": 0.9709037369417374, "grad_norm": 3.3338265419006348, "learning_rate": 2.2503246317540084e-08, "loss": 0.5370104908943176, "step": 6924 }, { "epoch": 0.971043959896235, "grad_norm": 2.832479953765869, "learning_rate": 2.2288579169307268e-08, "loss": 0.44857048988342285, "step": 6925 }, { "epoch": 0.9711841828507327, "grad_norm": 4.055529594421387, "learning_rate": 2.2074938543253932e-08, "loss": 0.37515926361083984, "step": 6926 }, { "epoch": 0.9713244058052303, "grad_norm": 3.7282357215881348, "learning_rate": 2.186232448343928e-08, "loss": 0.5278527140617371, "step": 6927 }, { "epoch": 0.9714646287597279, "grad_norm": 3.7818379402160645, "learning_rate": 2.1650737033708237e-08, "loss": 0.5301807522773743, "step": 6928 }, { "epoch": 0.9716048517142256, "grad_norm": 5.049676418304443, "learning_rate": 2.1440176237695344e-08, "loss": 0.4316985607147217, "step": 6929 }, { "epoch": 0.9717450746687233, "grad_norm": 3.7755014896392822, "learning_rate": 2.12306421388242e-08, "loss": 0.6402297019958496, "step": 6930 }, { "epoch": 0.971885297623221, "grad_norm": 4.049496650695801, "learning_rate": 2.1022134780304682e-08, "loss": 0.4675329327583313, "step": 6931 }, { "epoch": 0.9720255205777186, "grad_norm": 3.8587872982025146, "learning_rate": 2.081465420513573e-08, "loss": 0.4124658703804016, "step": 6932 }, { "epoch": 0.9721657435322162, "grad_norm": 4.070671081542969, "learning_rate": 2.0608200456105897e-08, "loss": 0.41604548692703247, "step": 6933 }, { "epoch": 0.9723059664867139, "grad_norm": 4.129211902618408, "learning_rate": 2.0402773575790013e-08, "loss": 0.482951819896698, "step": 6934 }, { "epoch": 0.9724461894412115, "grad_norm": 3.1846868991851807, "learning_rate": 2.019837360655197e-08, "loss": 0.4782305657863617, "step": 6935 }, { "epoch": 0.9725864123957092, "grad_norm": 6.584560871124268, "learning_rate": 1.9995000590544156e-08, "loss": 0.45747989416122437, "step": 6936 }, { "epoch": 0.9727266353502069, "grad_norm": 3.268845319747925, "learning_rate": 1.9792654569706915e-08, "loss": 0.4660401940345764, "step": 6937 }, { "epoch": 0.9728668583047044, "grad_norm": 3.783618927001953, "learning_rate": 1.959133558576909e-08, "loss": 0.5003327131271362, "step": 6938 }, { "epoch": 0.9730070812592021, "grad_norm": 2.7923362255096436, "learning_rate": 1.9391043680246358e-08, "loss": 0.47308477759361267, "step": 6939 }, { "epoch": 0.9731473042136998, "grad_norm": 6.911540508270264, "learning_rate": 1.9191778894445123e-08, "loss": 0.49774593114852905, "step": 6940 }, { "epoch": 0.9732875271681974, "grad_norm": 3.2048540115356445, "learning_rate": 1.8993541269457516e-08, "loss": 0.482883095741272, "step": 6941 }, { "epoch": 0.9734277501226951, "grad_norm": 6.548345565795898, "learning_rate": 1.879633084616528e-08, "loss": 0.5156548023223877, "step": 6942 }, { "epoch": 0.9735679730771928, "grad_norm": 4.1398844718933105, "learning_rate": 1.860014766523699e-08, "loss": 0.47528040409088135, "step": 6943 }, { "epoch": 0.9737081960316903, "grad_norm": 3.591486692428589, "learning_rate": 1.84049917671314e-08, "loss": 0.46327507495880127, "step": 6944 }, { "epoch": 0.973848418986188, "grad_norm": 5.370471000671387, "learning_rate": 1.8210863192094085e-08, "loss": 0.5264064073562622, "step": 6945 }, { "epoch": 0.9739886419406857, "grad_norm": 3.465566396713257, "learning_rate": 1.8017761980158587e-08, "loss": 0.5142987966537476, "step": 6946 }, { "epoch": 0.9741288648951834, "grad_norm": 3.7548177242279053, "learning_rate": 1.7825688171146938e-08, "loss": 0.5299339294433594, "step": 6947 }, { "epoch": 0.974269087849681, "grad_norm": 4.217898845672607, "learning_rate": 1.7634641804669673e-08, "loss": 0.5340462923049927, "step": 6948 }, { "epoch": 0.9744093108041787, "grad_norm": 2.4739830493927, "learning_rate": 1.744462292012472e-08, "loss": 0.5010097026824951, "step": 6949 }, { "epoch": 0.9745495337586763, "grad_norm": 3.1756691932678223, "learning_rate": 1.725563155669907e-08, "loss": 0.5038886070251465, "step": 6950 }, { "epoch": 0.9746897567131739, "grad_norm": 3.090909004211426, "learning_rate": 1.7067667753366546e-08, "loss": 0.4970949590206146, "step": 6951 }, { "epoch": 0.9748299796676716, "grad_norm": 3.8668551445007324, "learning_rate": 1.6880731548889474e-08, "loss": 0.4524810314178467, "step": 6952 }, { "epoch": 0.9749702026221693, "grad_norm": 3.4769604206085205, "learning_rate": 1.6694822981819792e-08, "loss": 0.46901735663414, "step": 6953 }, { "epoch": 0.9751104255766669, "grad_norm": 5.1371684074401855, "learning_rate": 1.6509942090495725e-08, "loss": 0.5519708395004272, "step": 6954 }, { "epoch": 0.9752506485311645, "grad_norm": 3.6507835388183594, "learning_rate": 1.632608891304288e-08, "loss": 0.4444270730018616, "step": 6955 }, { "epoch": 0.9753908714856622, "grad_norm": 20.71015739440918, "learning_rate": 1.6143263487378158e-08, "loss": 0.46108168363571167, "step": 6956 }, { "epoch": 0.9755310944401598, "grad_norm": 68.50418090820312, "learning_rate": 1.596146585120306e-08, "loss": 0.44370585680007935, "step": 6957 }, { "epoch": 0.9756713173946575, "grad_norm": 3.4742116928100586, "learning_rate": 1.578069604200927e-08, "loss": 0.5026458501815796, "step": 6958 }, { "epoch": 0.9758115403491552, "grad_norm": 4.6336774826049805, "learning_rate": 1.5600954097075293e-08, "loss": 0.43325430154800415, "step": 6959 }, { "epoch": 0.9759517633036529, "grad_norm": 3.7771005630493164, "learning_rate": 1.5422240053468708e-08, "loss": 0.4629908502101898, "step": 6960 }, { "epoch": 0.9760919862581504, "grad_norm": 3.7281196117401123, "learning_rate": 1.5244553948043917e-08, "loss": 0.4496552348136902, "step": 6961 }, { "epoch": 0.9762322092126481, "grad_norm": 4.246340751647949, "learning_rate": 1.5067895817444944e-08, "loss": 0.4813506007194519, "step": 6962 }, { "epoch": 0.9763724321671458, "grad_norm": 4.917055130004883, "learning_rate": 1.4892265698102093e-08, "loss": 0.5793432593345642, "step": 6963 }, { "epoch": 0.9765126551216434, "grad_norm": 4.193134784698486, "learning_rate": 1.4717663626234723e-08, "loss": 0.477347731590271, "step": 6964 }, { "epoch": 0.9766528780761411, "grad_norm": 3.2893614768981934, "learning_rate": 1.4544089637850145e-08, "loss": 0.5292370319366455, "step": 6965 }, { "epoch": 0.9767931010306388, "grad_norm": 5.914944648742676, "learning_rate": 1.4371543768743612e-08, "loss": 0.5232148170471191, "step": 6966 }, { "epoch": 0.9769333239851363, "grad_norm": 3.0938000679016113, "learning_rate": 1.4200026054496664e-08, "loss": 0.47246935963630676, "step": 6967 }, { "epoch": 0.977073546939634, "grad_norm": 15.484689712524414, "learning_rate": 1.4029536530482668e-08, "loss": 0.46686697006225586, "step": 6968 }, { "epoch": 0.9772137698941317, "grad_norm": 3.7310428619384766, "learning_rate": 1.3860075231858504e-08, "loss": 0.43905842304229736, "step": 6969 }, { "epoch": 0.9773539928486293, "grad_norm": 5.605560302734375, "learning_rate": 1.369164219357233e-08, "loss": 0.5594035387039185, "step": 6970 }, { "epoch": 0.977494215803127, "grad_norm": 3.318152666091919, "learning_rate": 1.3524237450358579e-08, "loss": 0.4352760910987854, "step": 6971 }, { "epoch": 0.9776344387576246, "grad_norm": 4.55572509765625, "learning_rate": 1.3357861036740195e-08, "loss": 0.5172879695892334, "step": 6972 }, { "epoch": 0.9777746617121222, "grad_norm": 7.67323112487793, "learning_rate": 1.319251298702806e-08, "loss": 0.5175172090530396, "step": 6973 }, { "epoch": 0.9779148846666199, "grad_norm": 5.5621337890625, "learning_rate": 1.3028193335321015e-08, "loss": 0.3732137978076935, "step": 6974 }, { "epoch": 0.9780551076211176, "grad_norm": 2.941453695297241, "learning_rate": 1.286490211550473e-08, "loss": 0.4983517527580261, "step": 6975 }, { "epoch": 0.9781953305756153, "grad_norm": 5.33626651763916, "learning_rate": 1.2702639361255043e-08, "loss": 0.5406942367553711, "step": 6976 }, { "epoch": 0.9783355535301129, "grad_norm": 3.117129325866699, "learning_rate": 1.2541405106033521e-08, "loss": 0.5655613541603088, "step": 6977 }, { "epoch": 0.9784757764846105, "grad_norm": 4.470315933227539, "learning_rate": 1.2381199383090791e-08, "loss": 0.537522554397583, "step": 6978 }, { "epoch": 0.9786159994391082, "grad_norm": 2.888781785964966, "learning_rate": 1.2222022225464868e-08, "loss": 0.4874977469444275, "step": 6979 }, { "epoch": 0.9787562223936058, "grad_norm": 2.8441948890686035, "learning_rate": 1.2063873665982273e-08, "loss": 0.47413507103919983, "step": 6980 }, { "epoch": 0.9788964453481035, "grad_norm": 3.5532712936401367, "learning_rate": 1.190675373725636e-08, "loss": 0.518770158290863, "step": 6981 }, { "epoch": 0.9790366683026012, "grad_norm": 2.913830518722534, "learning_rate": 1.1750662471689544e-08, "loss": 0.5558143854141235, "step": 6982 }, { "epoch": 0.9791768912570988, "grad_norm": 4.6752519607543945, "learning_rate": 1.1595599901471632e-08, "loss": 0.5291550755500793, "step": 6983 }, { "epoch": 0.9793171142115964, "grad_norm": 4.634284973144531, "learning_rate": 1.1441566058579268e-08, "loss": 0.5500937104225159, "step": 6984 }, { "epoch": 0.9794573371660941, "grad_norm": 3.4299354553222656, "learning_rate": 1.1288560974778706e-08, "loss": 0.4651952087879181, "step": 6985 }, { "epoch": 0.9795975601205917, "grad_norm": 7.061094284057617, "learning_rate": 1.1136584681623596e-08, "loss": 0.5740068554878235, "step": 6986 }, { "epoch": 0.9797377830750894, "grad_norm": 94.48650360107422, "learning_rate": 1.098563721045387e-08, "loss": 0.5182435512542725, "step": 6987 }, { "epoch": 0.9798780060295871, "grad_norm": 3.8840997219085693, "learning_rate": 1.0835718592399625e-08, "loss": 0.35718220472335815, "step": 6988 }, { "epoch": 0.9800182289840847, "grad_norm": 3.9814696311950684, "learning_rate": 1.0686828858376685e-08, "loss": 0.5345021486282349, "step": 6989 }, { "epoch": 0.9801584519385823, "grad_norm": 4.19553279876709, "learning_rate": 1.0538968039090492e-08, "loss": 0.4082028865814209, "step": 6990 }, { "epoch": 0.98029867489308, "grad_norm": 5.142977714538574, "learning_rate": 1.0392136165032763e-08, "loss": 0.500320553779602, "step": 6991 }, { "epoch": 0.9804388978475777, "grad_norm": 9.083763122558594, "learning_rate": 1.0246333266483722e-08, "loss": 0.5482412576675415, "step": 6992 }, { "epoch": 0.9805791208020753, "grad_norm": 6.06606912612915, "learning_rate": 1.0101559373512094e-08, "loss": 0.4738859534263611, "step": 6993 }, { "epoch": 0.980719343756573, "grad_norm": 3.6668288707733154, "learning_rate": 9.957814515972885e-09, "loss": 0.33690494298934937, "step": 6994 }, { "epoch": 0.9808595667110706, "grad_norm": 2.9861466884613037, "learning_rate": 9.815098723510719e-09, "loss": 0.4692199230194092, "step": 6995 }, { "epoch": 0.9809997896655682, "grad_norm": 6.307127952575684, "learning_rate": 9.67341202555594e-09, "loss": 0.4831730127334595, "step": 6996 }, { "epoch": 0.9811400126200659, "grad_norm": 3.966702699661255, "learning_rate": 9.532754451327953e-09, "loss": 0.5493277311325073, "step": 6997 }, { "epoch": 0.9812802355745636, "grad_norm": 3.2732834815979004, "learning_rate": 9.393126029834109e-09, "loss": 0.4569019079208374, "step": 6998 }, { "epoch": 0.9814204585290612, "grad_norm": 3.862361192703247, "learning_rate": 9.254526789868601e-09, "loss": 0.48203644156455994, "step": 6999 }, { "epoch": 0.9815606814835589, "grad_norm": 5.537235736846924, "learning_rate": 9.116956760014117e-09, "loss": 0.49831974506378174, "step": 7000 }, { "epoch": 0.9817009044380565, "grad_norm": 4.623417854309082, "learning_rate": 8.980415968640743e-09, "loss": 0.46496275067329407, "step": 7001 }, { "epoch": 0.9818411273925541, "grad_norm": 3.5615949630737305, "learning_rate": 8.84490444390651e-09, "loss": 0.5718339681625366, "step": 7002 }, { "epoch": 0.9819813503470518, "grad_norm": 8.43185806274414, "learning_rate": 8.710422213757397e-09, "loss": 0.41792234778404236, "step": 7003 }, { "epoch": 0.9821215733015495, "grad_norm": 3.5111422538757324, "learning_rate": 8.576969305926774e-09, "loss": 0.466348797082901, "step": 7004 }, { "epoch": 0.9822617962560471, "grad_norm": 4.671680450439453, "learning_rate": 8.444545747934851e-09, "loss": 0.4433354139328003, "step": 7005 }, { "epoch": 0.9824020192105448, "grad_norm": 2.560351610183716, "learning_rate": 8.313151567092004e-09, "loss": 0.4911808669567108, "step": 7006 }, { "epoch": 0.9825422421650424, "grad_norm": 4.136348724365234, "learning_rate": 8.182786790493224e-09, "loss": 0.5273933410644531, "step": 7007 }, { "epoch": 0.98268246511954, "grad_norm": 4.722623348236084, "learning_rate": 8.053451445024785e-09, "loss": 0.45370712876319885, "step": 7008 }, { "epoch": 0.9828226880740377, "grad_norm": 5.1187238693237305, "learning_rate": 7.925145557356462e-09, "loss": 0.5424070358276367, "step": 7009 }, { "epoch": 0.9829629110285354, "grad_norm": 7.247821807861328, "learning_rate": 7.797869153949867e-09, "loss": 0.46846529841423035, "step": 7010 }, { "epoch": 0.9831031339830331, "grad_norm": 58.614990234375, "learning_rate": 7.671622261051226e-09, "loss": 0.5170347094535828, "step": 7011 }, { "epoch": 0.9832433569375306, "grad_norm": 4.109353065490723, "learning_rate": 7.546404904696381e-09, "loss": 0.5434017181396484, "step": 7012 }, { "epoch": 0.9833835798920283, "grad_norm": 3.8607118129730225, "learning_rate": 7.422217110707453e-09, "loss": 0.5075194835662842, "step": 7013 }, { "epoch": 0.983523802846526, "grad_norm": 3.422628164291382, "learning_rate": 7.299058904695622e-09, "loss": 0.5347572565078735, "step": 7014 }, { "epoch": 0.9836640258010236, "grad_norm": 3.3238649368286133, "learning_rate": 7.17693031205835e-09, "loss": 0.4945088028907776, "step": 7015 }, { "epoch": 0.9838042487555213, "grad_norm": 3.4509952068328857, "learning_rate": 7.055831357981602e-09, "loss": 0.5430070161819458, "step": 7016 }, { "epoch": 0.983944471710019, "grad_norm": 3.4949147701263428, "learning_rate": 6.935762067439289e-09, "loss": 0.45764461159706116, "step": 7017 }, { "epoch": 0.9840846946645165, "grad_norm": 3.7316088676452637, "learning_rate": 6.81672246519216e-09, "loss": 0.54860919713974, "step": 7018 }, { "epoch": 0.9842249176190142, "grad_norm": 4.1135687828063965, "learning_rate": 6.698712575789468e-09, "loss": 0.4400228261947632, "step": 7019 }, { "epoch": 0.9843651405735119, "grad_norm": 6.075937271118164, "learning_rate": 6.581732423566744e-09, "loss": 0.5052804946899414, "step": 7020 }, { "epoch": 0.9845053635280095, "grad_norm": 3.1481690406799316, "learning_rate": 6.465782032649137e-09, "loss": 0.5229392051696777, "step": 7021 }, { "epoch": 0.9846455864825072, "grad_norm": 3.151642322540283, "learning_rate": 6.350861426947519e-09, "loss": 0.49645671248435974, "step": 7022 }, { "epoch": 0.9847858094370049, "grad_norm": 4.00504207611084, "learning_rate": 6.2369706301618204e-09, "loss": 0.47696155309677124, "step": 7023 }, { "epoch": 0.9849260323915024, "grad_norm": 4.467617511749268, "learning_rate": 6.12410966577881e-09, "loss": 0.5543171763420105, "step": 7024 }, { "epoch": 0.9850662553460001, "grad_norm": 7.030697345733643, "learning_rate": 6.012278557072648e-09, "loss": 0.5840026140213013, "step": 7025 }, { "epoch": 0.9852064783004978, "grad_norm": 4.087917804718018, "learning_rate": 5.9014773271065525e-09, "loss": 0.5495997071266174, "step": 7026 }, { "epoch": 0.9853467012549955, "grad_norm": 4.259969234466553, "learning_rate": 5.791705998729469e-09, "loss": 0.485393226146698, "step": 7027 }, { "epoch": 0.9854869242094931, "grad_norm": 3.531754493713379, "learning_rate": 5.682964594579398e-09, "loss": 0.5687962174415588, "step": 7028 }, { "epoch": 0.9856271471639907, "grad_norm": 3.790555000305176, "learning_rate": 5.5752531370811825e-09, "loss": 0.5427722334861755, "step": 7029 }, { "epoch": 0.9857673701184884, "grad_norm": 4.367465972900391, "learning_rate": 5.468571648447052e-09, "loss": 0.507989764213562, "step": 7030 }, { "epoch": 0.985907593072986, "grad_norm": 3.8118746280670166, "learning_rate": 5.362920150678297e-09, "loss": 0.361017107963562, "step": 7031 }, { "epoch": 0.9860478160274837, "grad_norm": 3.1690564155578613, "learning_rate": 5.258298665561934e-09, "loss": 0.5996038913726807, "step": 7032 }, { "epoch": 0.9861880389819814, "grad_norm": 2.9956490993499756, "learning_rate": 5.1547072146734824e-09, "loss": 0.5052468180656433, "step": 7033 }, { "epoch": 0.986328261936479, "grad_norm": 3.1806607246398926, "learning_rate": 5.0521458193758535e-09, "loss": 0.4967566728591919, "step": 7034 }, { "epoch": 0.9864684848909766, "grad_norm": 6.064853668212891, "learning_rate": 4.950614500820461e-09, "loss": 0.5941884517669678, "step": 7035 }, { "epoch": 0.9866087078454743, "grad_norm": 6.465209484100342, "learning_rate": 4.850113279944446e-09, "loss": 0.48797813057899475, "step": 7036 }, { "epoch": 0.986748930799972, "grad_norm": 2.601358652114868, "learning_rate": 4.750642177474007e-09, "loss": 0.4927372932434082, "step": 7037 }, { "epoch": 0.9868891537544696, "grad_norm": 3.093158483505249, "learning_rate": 4.652201213922736e-09, "loss": 0.5782419443130493, "step": 7038 }, { "epoch": 0.9870293767089673, "grad_norm": 7.410717010498047, "learning_rate": 4.5547904095910586e-09, "loss": 0.441010057926178, "step": 7039 }, { "epoch": 0.987169599663465, "grad_norm": 8.091596603393555, "learning_rate": 4.4584097845673526e-09, "loss": 0.5605856776237488, "step": 7040 }, { "epoch": 0.9873098226179625, "grad_norm": 3.9051990509033203, "learning_rate": 4.363059358727939e-09, "loss": 0.4864389896392822, "step": 7041 }, { "epoch": 0.9874500455724602, "grad_norm": 4.846956253051758, "learning_rate": 4.268739151735979e-09, "loss": 0.4694893956184387, "step": 7042 }, { "epoch": 0.9875902685269579, "grad_norm": 5.197719573974609, "learning_rate": 4.175449183043134e-09, "loss": 0.5946613550186157, "step": 7043 }, { "epoch": 0.9877304914814555, "grad_norm": 4.357798099517822, "learning_rate": 4.08318947188735e-09, "loss": 0.5667786598205566, "step": 7044 }, { "epoch": 0.9878707144359532, "grad_norm": 3.728200912475586, "learning_rate": 3.991960037294518e-09, "loss": 0.4729151725769043, "step": 7045 }, { "epoch": 0.9880109373904509, "grad_norm": 3.06598162651062, "learning_rate": 3.9017608980795876e-09, "loss": 0.45881909132003784, "step": 7046 }, { "epoch": 0.9881511603449484, "grad_norm": 4.191188812255859, "learning_rate": 3.81259207284268e-09, "loss": 0.5134598016738892, "step": 7047 }, { "epoch": 0.9882913832994461, "grad_norm": 3.587801456451416, "learning_rate": 3.7244535799724203e-09, "loss": 0.5622541904449463, "step": 7048 }, { "epoch": 0.9884316062539438, "grad_norm": 3.986344337463379, "learning_rate": 3.6373454376459337e-09, "loss": 0.49269843101501465, "step": 7049 }, { "epoch": 0.9885718292084414, "grad_norm": 3.398500680923462, "learning_rate": 3.5512676638260745e-09, "loss": 0.5298171639442444, "step": 7050 }, { "epoch": 0.9887120521629391, "grad_norm": 4.941451549530029, "learning_rate": 3.4662202762647535e-09, "loss": 0.4029807448387146, "step": 7051 }, { "epoch": 0.9888522751174367, "grad_norm": 4.254795074462891, "learning_rate": 3.3822032925007185e-09, "loss": 0.6260508894920349, "step": 7052 }, { "epoch": 0.9889924980719343, "grad_norm": 4.5481109619140625, "learning_rate": 3.2992167298601108e-09, "loss": 0.6127663850784302, "step": 7053 }, { "epoch": 0.989132721026432, "grad_norm": 3.8529462814331055, "learning_rate": 3.2172606054564625e-09, "loss": 0.6252793073654175, "step": 7054 }, { "epoch": 0.9892729439809297, "grad_norm": 5.988460063934326, "learning_rate": 3.1363349361918095e-09, "loss": 0.4366728663444519, "step": 7055 }, { "epoch": 0.9894131669354274, "grad_norm": 5.058331489562988, "learning_rate": 3.0564397387539135e-09, "loss": 0.4583549499511719, "step": 7056 }, { "epoch": 0.989553389889925, "grad_norm": 3.697164535522461, "learning_rate": 2.977575029619595e-09, "loss": 0.4416784644126892, "step": 7057 }, { "epoch": 0.9896936128444226, "grad_norm": 4.375686168670654, "learning_rate": 2.8997408250530657e-09, "loss": 0.4921589195728302, "step": 7058 }, { "epoch": 0.9898338357989203, "grad_norm": 3.998993158340454, "learning_rate": 2.82293714110482e-09, "loss": 0.37049463391304016, "step": 7059 }, { "epoch": 0.9899740587534179, "grad_norm": 4.737581729888916, "learning_rate": 2.74716399361441e-09, "loss": 0.46118056774139404, "step": 7060 }, { "epoch": 0.9901142817079156, "grad_norm": 3.989661455154419, "learning_rate": 2.6724213982071143e-09, "loss": 0.33089232444763184, "step": 7061 }, { "epoch": 0.9902545046624133, "grad_norm": 3.969783306121826, "learning_rate": 2.59870937029727e-09, "loss": 0.5150891542434692, "step": 7062 }, { "epoch": 0.9903947276169109, "grad_norm": 2.677950620651245, "learning_rate": 2.52602792508605e-09, "loss": 0.4964337646961212, "step": 7063 }, { "epoch": 0.9905349505714085, "grad_norm": 5.46086311340332, "learning_rate": 2.454377077561465e-09, "loss": 0.5777947902679443, "step": 7064 }, { "epoch": 0.9906751735259062, "grad_norm": 4.568802356719971, "learning_rate": 2.383756842500584e-09, "loss": 0.48418909311294556, "step": 7065 }, { "epoch": 0.9908153964804038, "grad_norm": 2.6904537677764893, "learning_rate": 2.3141672344662024e-09, "loss": 0.5105115175247192, "step": 7066 }, { "epoch": 0.9909556194349015, "grad_norm": 4.175483703613281, "learning_rate": 2.245608267809618e-09, "loss": 0.38319361209869385, "step": 7067 }, { "epoch": 0.9910958423893992, "grad_norm": 3.5131871700286865, "learning_rate": 2.178079956668966e-09, "loss": 0.4984518885612488, "step": 7068 }, { "epoch": 0.9912360653438967, "grad_norm": 3.492751359939575, "learning_rate": 2.1115823149708836e-09, "loss": 0.5156593322753906, "step": 7069 }, { "epoch": 0.9913762882983944, "grad_norm": 4.700314521789551, "learning_rate": 2.046115356428846e-09, "loss": 0.5407376885414124, "step": 7070 }, { "epoch": 0.9915165112528921, "grad_norm": 17.82343101501465, "learning_rate": 1.98167909454261e-09, "loss": 0.4858160614967346, "step": 7071 }, { "epoch": 0.9916567342073898, "grad_norm": 3.313621759414673, "learning_rate": 1.9182735426015454e-09, "loss": 0.5417055487632751, "step": 7072 }, { "epoch": 0.9917969571618874, "grad_norm": 2.8709702491760254, "learning_rate": 1.8558987136801931e-09, "loss": 0.4317436218261719, "step": 7073 }, { "epoch": 0.9919371801163851, "grad_norm": 3.381411552429199, "learning_rate": 1.7945546206432629e-09, "loss": 0.5186681747436523, "step": 7074 }, { "epoch": 0.9920774030708827, "grad_norm": 6.161316394805908, "learning_rate": 1.7342412761400807e-09, "loss": 0.555695652961731, "step": 7075 }, { "epoch": 0.9922176260253803, "grad_norm": 2.766960620880127, "learning_rate": 1.6749586926095852e-09, "loss": 0.4713144600391388, "step": 7076 }, { "epoch": 0.992357848979878, "grad_norm": 5.292446613311768, "learning_rate": 1.616706882276442e-09, "loss": 0.5864259600639343, "step": 7077 }, { "epoch": 0.9924980719343757, "grad_norm": 4.982076644897461, "learning_rate": 1.5594858571543747e-09, "loss": 0.4716126620769501, "step": 7078 }, { "epoch": 0.9926382948888733, "grad_norm": 4.649347305297852, "learning_rate": 1.5032956290428335e-09, "loss": 0.5150991678237915, "step": 7079 }, { "epoch": 0.992778517843371, "grad_norm": 3.4146101474761963, "learning_rate": 1.4481362095303264e-09, "loss": 0.47972631454467773, "step": 7080 }, { "epoch": 0.9929187407978686, "grad_norm": 6.113639831542969, "learning_rate": 1.3940076099921984e-09, "loss": 0.5195252895355225, "step": 7081 }, { "epoch": 0.9930589637523662, "grad_norm": 3.106297731399536, "learning_rate": 1.3409098415900767e-09, "loss": 0.4602455794811249, "step": 7082 }, { "epoch": 0.9931991867068639, "grad_norm": 3.39815092086792, "learning_rate": 1.2888429152740912e-09, "loss": 0.5205271244049072, "step": 7083 }, { "epoch": 0.9933394096613616, "grad_norm": 3.4119977951049805, "learning_rate": 1.2378068417828737e-09, "loss": 0.568879246711731, "step": 7084 }, { "epoch": 0.9934796326158593, "grad_norm": 4.297319412231445, "learning_rate": 1.1878016316402286e-09, "loss": 0.5839649438858032, "step": 7085 }, { "epoch": 0.9936198555703568, "grad_norm": 23.861698150634766, "learning_rate": 1.1388272951584623e-09, "loss": 0.5036071538925171, "step": 7086 }, { "epoch": 0.9937600785248545, "grad_norm": 5.888838768005371, "learning_rate": 1.0908838424378287e-09, "loss": 0.4812625050544739, "step": 7087 }, { "epoch": 0.9939003014793522, "grad_norm": 3.6896719932556152, "learning_rate": 1.043971283364864e-09, "loss": 0.5644697546958923, "step": 7088 }, { "epoch": 0.9940405244338498, "grad_norm": 4.710498332977295, "learning_rate": 9.980896276140517e-10, "loss": 0.5324850082397461, "step": 7089 }, { "epoch": 0.9941807473883475, "grad_norm": 8.260242462158203, "learning_rate": 9.532388846478225e-10, "loss": 0.44426101446151733, "step": 7090 }, { "epoch": 0.9943209703428452, "grad_norm": 6.175504684448242, "learning_rate": 9.094190637148892e-10, "loss": 0.4898422062397003, "step": 7091 }, { "epoch": 0.9944611932973427, "grad_norm": 4.887430667877197, "learning_rate": 8.666301738519123e-10, "loss": 0.4941239058971405, "step": 7092 }, { "epoch": 0.9946014162518404, "grad_norm": 2.780773162841797, "learning_rate": 8.248722238834994e-10, "loss": 0.4584958553314209, "step": 7093 }, { "epoch": 0.9947416392063381, "grad_norm": 4.6813788414001465, "learning_rate": 7.841452224210954e-10, "loss": 0.49533313512802124, "step": 7094 }, { "epoch": 0.9948818621608357, "grad_norm": 4.2443437576293945, "learning_rate": 7.444491778629825e-10, "loss": 0.4855805039405823, "step": 7095 }, { "epoch": 0.9950220851153334, "grad_norm": 6.347696304321289, "learning_rate": 7.0578409839539e-10, "loss": 0.451069712638855, "step": 7096 }, { "epoch": 0.9951623080698311, "grad_norm": 3.803884267807007, "learning_rate": 6.681499919930501e-10, "loss": 0.5871946811676025, "step": 7097 }, { "epoch": 0.9953025310243286, "grad_norm": 5.324495792388916, "learning_rate": 6.315468664158664e-10, "loss": 0.5243570804595947, "step": 7098 }, { "epoch": 0.9954427539788263, "grad_norm": 3.2314791679382324, "learning_rate": 5.959747292128004e-10, "loss": 0.44809114933013916, "step": 7099 }, { "epoch": 0.995582976933324, "grad_norm": 4.541907787322998, "learning_rate": 5.614335877196509e-10, "loss": 0.48110485076904297, "step": 7100 }, { "epoch": 0.9957231998878217, "grad_norm": 4.978224277496338, "learning_rate": 5.279234490596086e-10, "loss": 0.4862392246723175, "step": 7101 }, { "epoch": 0.9958634228423193, "grad_norm": 2.781277894973755, "learning_rate": 4.954443201432568e-10, "loss": 0.5126190781593323, "step": 7102 }, { "epoch": 0.996003645796817, "grad_norm": 3.3553192615509033, "learning_rate": 4.63996207668016e-10, "loss": 0.466628760099411, "step": 7103 }, { "epoch": 0.9961438687513146, "grad_norm": 4.904669761657715, "learning_rate": 4.335791181203641e-10, "loss": 0.44562163949012756, "step": 7104 }, { "epoch": 0.9962840917058122, "grad_norm": 3.3630120754241943, "learning_rate": 4.041930577719511e-10, "loss": 0.4607432186603546, "step": 7105 }, { "epoch": 0.9964243146603099, "grad_norm": 3.82898211479187, "learning_rate": 3.7583803268348426e-10, "loss": 0.4353354573249817, "step": 7106 }, { "epoch": 0.9965645376148076, "grad_norm": 6.2102155685424805, "learning_rate": 3.4851404870195336e-10, "loss": 0.40086013078689575, "step": 7107 }, { "epoch": 0.9967047605693052, "grad_norm": 4.823862552642822, "learning_rate": 3.222211114628504e-10, "loss": 0.46908891201019287, "step": 7108 }, { "epoch": 0.9968449835238028, "grad_norm": 4.170313835144043, "learning_rate": 2.969592263885046e-10, "loss": 0.44246554374694824, "step": 7109 }, { "epoch": 0.9969852064783005, "grad_norm": 9.754981994628906, "learning_rate": 2.727283986875273e-10, "loss": 0.47990477085113525, "step": 7110 }, { "epoch": 0.9971254294327981, "grad_norm": 5.249129295349121, "learning_rate": 2.495286333575875e-10, "loss": 0.4796043932437897, "step": 7111 }, { "epoch": 0.9972656523872958, "grad_norm": 4.572911739349365, "learning_rate": 2.273599351826361e-10, "loss": 0.5580001473426819, "step": 7112 }, { "epoch": 0.9974058753417935, "grad_norm": 3.054412841796875, "learning_rate": 2.062223087351267e-10, "loss": 0.469429075717926, "step": 7113 }, { "epoch": 0.9975460982962912, "grad_norm": 3.5024194717407227, "learning_rate": 1.861157583732398e-10, "loss": 0.4818953573703766, "step": 7114 }, { "epoch": 0.9976863212507887, "grad_norm": 3.5726966857910156, "learning_rate": 1.6704028824421348e-10, "loss": 0.4830567240715027, "step": 7115 }, { "epoch": 0.9978265442052864, "grad_norm": 4.209657192230225, "learning_rate": 1.489959022810128e-10, "loss": 0.5035165548324585, "step": 7116 }, { "epoch": 0.997966767159784, "grad_norm": 4.230338096618652, "learning_rate": 1.3198260420566044e-10, "loss": 0.4765794277191162, "step": 7117 }, { "epoch": 0.9981069901142817, "grad_norm": 3.485731601715088, "learning_rate": 1.160003975264612e-10, "loss": 0.5966200828552246, "step": 7118 }, { "epoch": 0.9982472130687794, "grad_norm": 3.0648300647735596, "learning_rate": 1.0104928553855698e-10, "loss": 0.4029024839401245, "step": 7119 }, { "epoch": 0.9983874360232771, "grad_norm": 8.534547805786133, "learning_rate": 8.712927132670245e-11, "loss": 0.5137718319892883, "step": 7120 }, { "epoch": 0.9985276589777746, "grad_norm": 6.918546676635742, "learning_rate": 7.424035776026905e-11, "loss": 0.547723114490509, "step": 7121 }, { "epoch": 0.9986678819322723, "grad_norm": 3.6001195907592773, "learning_rate": 6.23825474976858e-11, "loss": 0.5487658381462097, "step": 7122 }, { "epoch": 0.99880810488677, "grad_norm": 4.010841369628906, "learning_rate": 5.15558429842189e-11, "loss": 0.3486000597476959, "step": 7123 }, { "epoch": 0.9989483278412676, "grad_norm": 3.7277462482452393, "learning_rate": 4.1760246453081963e-11, "loss": 0.4874245822429657, "step": 7124 }, { "epoch": 0.9990885507957653, "grad_norm": 3.2917287349700928, "learning_rate": 3.2995759923215574e-11, "loss": 0.46669766306877136, "step": 7125 }, { "epoch": 0.9992287737502629, "grad_norm": 3.262174367904663, "learning_rate": 2.5262385203728147e-11, "loss": 0.3994342088699341, "step": 7126 }, { "epoch": 0.9993689967047605, "grad_norm": 4.418114185333252, "learning_rate": 1.8560123887789718e-11, "loss": 0.4731462895870209, "step": 7127 }, { "epoch": 0.9995092196592582, "grad_norm": 4.058036804199219, "learning_rate": 1.2888977358738176e-11, "loss": 0.5246137976646423, "step": 7128 }, { "epoch": 0.9996494426137559, "grad_norm": 4.973879814147949, "learning_rate": 8.248946785638367e-12, "loss": 0.5133951902389526, "step": 7129 }, { "epoch": 0.9997896655682535, "grad_norm": 2.350848913192749, "learning_rate": 4.64003312494743e-12, "loss": 0.5039857029914856, "step": 7130 }, { "epoch": 0.9999298885227512, "grad_norm": 4.443264007568359, "learning_rate": 2.0622371216250105e-12, "loss": 0.469647079706192, "step": 7131 }, { "epoch": 1.0, "grad_norm": 17.92053985595703, "learning_rate": 5.155593069128273e-13, "loss": 0.5106716752052307, "step": 7132 }, { "epoch": 1.0, "step": 7132, "total_flos": 8.15562965182715e+19, "train_loss": 0.5490085107686475, "train_runtime": 368539.957, "train_samples_per_second": 2.477, "train_steps_per_second": 0.019 } ], "logging_steps": 1.0, "max_steps": 7132, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 8.15562965182715e+19, "train_batch_size": 4, "trial_name": null, "trial_params": null }