{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.75, "eval_steps": 500, "global_step": 3000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "grad_norm": 0.31839632987976074, "learning_rate": 4.5e-06, "loss": 1.2127, "step": 10 }, { "grad_norm": 0.19609376788139343, "learning_rate": 9.5e-06, "loss": 1.1842, "step": 20 }, { "grad_norm": 0.4635807275772095, "learning_rate": 1.45e-05, "loss": 1.1838, "step": 30 }, { "grad_norm": 0.3277273178100586, "learning_rate": 1.9500000000000003e-05, "loss": 1.1629, "step": 40 }, { "grad_norm": 0.40489643812179565, "learning_rate": 2.45e-05, "loss": 1.1264, "step": 50 }, { "grad_norm": 1.2546579837799072, "learning_rate": 2.95e-05, "loss": 1.1117, "step": 60 }, { "grad_norm": 0.3789711594581604, "learning_rate": 3.45e-05, "loss": 1.1066, "step": 70 }, { "grad_norm": 0.3612673878669739, "learning_rate": 3.9500000000000005e-05, "loss": 1.1082, "step": 80 }, { "grad_norm": 0.28633758425712585, "learning_rate": 4.4500000000000004e-05, "loss": 1.1211, "step": 90 }, { "grad_norm": 0.41268351674079895, "learning_rate": 4.9500000000000004e-05, "loss": 1.0998, "step": 100 }, { "grad_norm": 0.2796061933040619, "learning_rate": 5.45e-05, "loss": 1.1131, "step": 110 }, { "grad_norm": 0.3423110544681549, "learning_rate": 5.95e-05, "loss": 1.1004, "step": 120 }, { "grad_norm": 0.33770301938056946, "learning_rate": 6.450000000000001e-05, "loss": 1.0887, "step": 130 }, { "grad_norm": 0.4104395806789398, "learning_rate": 6.95e-05, "loss": 1.1043, "step": 140 }, { "grad_norm": 0.38792213797569275, "learning_rate": 7.450000000000001e-05, "loss": 1.093, "step": 150 }, { "grad_norm": 0.31532591581344604, "learning_rate": 7.950000000000001e-05, "loss": 1.0992, "step": 160 }, { "grad_norm": 0.37639284133911133, "learning_rate": 8.450000000000001e-05, "loss": 1.1033, "step": 170 }, { "grad_norm": 0.4326634407043457, "learning_rate": 8.950000000000001e-05, "loss": 1.0834, "step": 180 }, { "grad_norm": 0.4046025276184082, "learning_rate": 9.449999999999999e-05, "loss": 1.0852, "step": 190 }, { "grad_norm": 0.45471683144569397, "learning_rate": 9.95e-05, "loss": 1.0775, "step": 200 }, { "grad_norm": 0.5478058457374573, "learning_rate": 9.999861593790126e-05, "loss": 1.0781, "step": 210 }, { "grad_norm": 0.3471389412879944, "learning_rate": 9.999383162408304e-05, "loss": 1.0828, "step": 220 }, { "grad_norm": 0.4683222770690918, "learning_rate": 9.998563029828259e-05, "loss": 1.0568, "step": 230 }, { "grad_norm": 0.3368767499923706, "learning_rate": 9.997401252104962e-05, "loss": 1.0364, "step": 240 }, { "grad_norm": 0.425786554813385, "learning_rate": 9.995897908644378e-05, "loss": 1.0061, "step": 250 }, { "grad_norm": 0.38125181198120117, "learning_rate": 9.994053102198034e-05, "loss": 1.0064, "step": 260 }, { "grad_norm": 0.569205105304718, "learning_rate": 9.991866958856003e-05, "loss": 1.0119, "step": 270 }, { "grad_norm": 0.360039621591568, "learning_rate": 9.989339628038276e-05, "loss": 0.9783, "step": 280 }, { "grad_norm": 0.3894808292388916, "learning_rate": 9.98647128248456e-05, "loss": 0.9876, "step": 290 }, { "grad_norm": 0.49482613801956177, "learning_rate": 9.98326211824246e-05, "loss": 0.9774, "step": 300 }, { "grad_norm": 0.43771424889564514, "learning_rate": 9.979712354654091e-05, "loss": 0.9528, "step": 310 }, { "grad_norm": 0.3924391269683838, "learning_rate": 9.975822234341079e-05, "loss": 0.949, "step": 320 }, { "grad_norm": 0.3948723077774048, "learning_rate": 9.97159202318798e-05, "loss": 0.95, "step": 330 }, { "grad_norm": 0.4701744019985199, "learning_rate": 9.967022010324105e-05, "loss": 0.9263, "step": 340 }, { "grad_norm": 0.5202460289001465, "learning_rate": 9.962112508103765e-05, "loss": 0.9409, "step": 350 }, { "grad_norm": 0.4282516837120056, "learning_rate": 9.956863852084914e-05, "loss": 0.9107, "step": 360 }, { "grad_norm": 0.5906583666801453, "learning_rate": 9.951276401006221e-05, "loss": 0.9072, "step": 370 }, { "grad_norm": 0.4856233298778534, "learning_rate": 9.945350536762543e-05, "loss": 0.9142, "step": 380 }, { "grad_norm": 0.44197753071784973, "learning_rate": 9.939086664378829e-05, "loss": 0.8903, "step": 390 }, { "grad_norm": 0.6055497527122498, "learning_rate": 9.932485211982437e-05, "loss": 0.8942, "step": 400 }, { "grad_norm": 0.5160871744155884, "learning_rate": 9.92554663077387e-05, "loss": 0.8765, "step": 410 }, { "grad_norm": 0.479907751083374, "learning_rate": 9.918271394995935e-05, "loss": 0.8774, "step": 420 }, { "grad_norm": 0.5040944218635559, "learning_rate": 9.910660001901335e-05, "loss": 0.8775, "step": 430 }, { "grad_norm": 0.5206490755081177, "learning_rate": 9.902712971718675e-05, "loss": 0.8647, "step": 440 }, { "grad_norm": 0.44746702909469604, "learning_rate": 9.894430847616915e-05, "loss": 0.8619, "step": 450 }, { "grad_norm": 0.4645554721355438, "learning_rate": 9.885814195668232e-05, "loss": 0.8444, "step": 460 }, { "grad_norm": 0.47834452986717224, "learning_rate": 9.876863604809344e-05, "loss": 0.8333, "step": 470 }, { "grad_norm": 0.43582776188850403, "learning_rate": 9.867579686801245e-05, "loss": 0.8598, "step": 480 }, { "grad_norm": 0.4257030189037323, "learning_rate": 9.8579630761874e-05, "loss": 0.8198, "step": 490 }, { "grad_norm": 0.5325835943222046, "learning_rate": 9.848014430250367e-05, "loss": 0.8271, "step": 500 }, { "grad_norm": 0.46889224648475647, "learning_rate": 9.837734428966885e-05, "loss": 0.8202, "step": 510 }, { "grad_norm": 0.5707681775093079, "learning_rate": 9.827123774961383e-05, "loss": 0.8078, "step": 520 }, { "grad_norm": 0.5601910352706909, "learning_rate": 9.816183193457968e-05, "loss": 0.8296, "step": 530 }, { "grad_norm": 0.6276665925979614, "learning_rate": 9.804913432230856e-05, "loss": 0.8248, "step": 540 }, { "grad_norm": 0.6616746187210083, "learning_rate": 9.793315261553252e-05, "loss": 0.8042, "step": 550 }, { "grad_norm": 0.5051801204681396, "learning_rate": 9.781389474144717e-05, "loss": 0.8047, "step": 560 }, { "grad_norm": 0.45216768980026245, "learning_rate": 9.76913688511698e-05, "loss": 0.8061, "step": 570 }, { "grad_norm": 0.5215824246406555, "learning_rate": 9.756558331918227e-05, "loss": 0.8082, "step": 580 }, { "grad_norm": 0.5071956515312195, "learning_rate": 9.743654674275855e-05, "loss": 0.8092, "step": 590 }, { "grad_norm": 0.4734920263290405, "learning_rate": 9.730426794137727e-05, "loss": 0.7902, "step": 600 }, { "grad_norm": 0.6150533556938171, "learning_rate": 9.716875595611879e-05, "loss": 0.7976, "step": 610 }, { "grad_norm": 0.6230007410049438, "learning_rate": 9.703002004904729e-05, "loss": 0.7894, "step": 620 }, { "grad_norm": 0.47863709926605225, "learning_rate": 9.688806970257773e-05, "loss": 0.7771, "step": 630 }, { "grad_norm": 0.5021641850471497, "learning_rate": 9.674291461882774e-05, "loss": 0.7608, "step": 640 }, { "grad_norm": 0.6127395033836365, "learning_rate": 9.659456471895445e-05, "loss": 0.7793, "step": 650 }, { "grad_norm": 0.5065549612045288, "learning_rate": 9.644303014247648e-05, "loss": 0.7759, "step": 660 }, { "grad_norm": 0.5618578195571899, "learning_rate": 9.628832124658085e-05, "loss": 0.7647, "step": 670 }, { "grad_norm": 0.7806953191757202, "learning_rate": 9.613044860541507e-05, "loss": 0.7829, "step": 680 }, { "grad_norm": 0.48667505383491516, "learning_rate": 9.596942300936445e-05, "loss": 0.7624, "step": 690 }, { "grad_norm": 0.4916687309741974, "learning_rate": 9.580525546431459e-05, "loss": 0.7617, "step": 700 }, { "grad_norm": 0.382213830947876, "learning_rate": 9.563795719089911e-05, "loss": 0.7561, "step": 710 }, { "grad_norm": 0.7185860276222229, "learning_rate": 9.546753962373281e-05, "loss": 0.7619, "step": 720 }, { "grad_norm": 0.48129522800445557, "learning_rate": 9.529401441062997e-05, "loss": 0.773, "step": 730 }, { "grad_norm": 0.5167684555053711, "learning_rate": 9.511739341180842e-05, "loss": 0.7669, "step": 740 }, { "grad_norm": 0.5255888104438782, "learning_rate": 9.493768869907886e-05, "loss": 0.764, "step": 750 }, { "grad_norm": 0.3794105052947998, "learning_rate": 9.475491255501968e-05, "loss": 0.7532, "step": 760 }, { "grad_norm": 0.4577208459377289, "learning_rate": 9.456907747213748e-05, "loss": 0.7512, "step": 770 }, { "grad_norm": 0.47813680768013, "learning_rate": 9.438019615201336e-05, "loss": 0.7653, "step": 780 }, { "grad_norm": 0.48698732256889343, "learning_rate": 9.418828150443469e-05, "loss": 0.7354, "step": 790 }, { "grad_norm": 0.48488903045654297, "learning_rate": 9.399334664651262e-05, "loss": 0.7649, "step": 800 }, { "grad_norm": 0.46380874514579773, "learning_rate": 9.379540490178581e-05, "loss": 0.7617, "step": 810 }, { "grad_norm": 0.48268088698387146, "learning_rate": 9.359446979930955e-05, "loss": 0.7466, "step": 820 }, { "grad_norm": 0.5104127526283264, "learning_rate": 9.33905550727312e-05, "loss": 0.7389, "step": 830 }, { "grad_norm": 0.4325626790523529, "learning_rate": 9.318367465935142e-05, "loss": 0.7414, "step": 840 }, { "grad_norm": 0.45519083738327026, "learning_rate": 9.29738426991717e-05, "loss": 0.7517, "step": 850 }, { "grad_norm": 0.5354924201965332, "learning_rate": 9.276107353392774e-05, "loss": 0.7427, "step": 860 }, { "grad_norm": 0.5575360655784607, "learning_rate": 9.254538170610938e-05, "loss": 0.7515, "step": 870 }, { "grad_norm": 0.5105330944061279, "learning_rate": 9.232678195796654e-05, "loss": 0.722, "step": 880 }, { "grad_norm": 0.5286569595336914, "learning_rate": 9.210528923050164e-05, "loss": 0.7215, "step": 890 }, { "grad_norm": 0.46469196677207947, "learning_rate": 9.188091866244834e-05, "loss": 0.72, "step": 900 }, { "grad_norm": 0.43992435932159424, "learning_rate": 9.165368558923695e-05, "loss": 0.7195, "step": 910 }, { "grad_norm": 0.4441291391849518, "learning_rate": 9.142360554194618e-05, "loss": 0.7272, "step": 920 }, { "grad_norm": 0.5133683085441589, "learning_rate": 9.119069424624163e-05, "loss": 0.7142, "step": 930 }, { "grad_norm": 0.5577358603477478, "learning_rate": 9.0954967621301e-05, "loss": 0.7095, "step": 940 }, { "grad_norm": 0.621738076210022, "learning_rate": 9.071644177872594e-05, "loss": 0.7276, "step": 950 }, { "grad_norm": 0.4756941497325897, "learning_rate": 9.047513302144095e-05, "loss": 0.7196, "step": 960 }, { "grad_norm": 0.3742871582508087, "learning_rate": 9.023105784257906e-05, "loss": 0.7159, "step": 970 }, { "grad_norm": 0.43546372652053833, "learning_rate": 8.998423292435454e-05, "loss": 0.7127, "step": 980 }, { "grad_norm": 0.5410100817680359, "learning_rate": 8.973467513692265e-05, "loss": 0.7089, "step": 990 }, { "grad_norm": 0.5081359148025513, "learning_rate": 8.94824015372267e-05, "loss": 0.6982, "step": 1000 }, { "grad_norm": 0.49883362650871277, "learning_rate": 8.922742936783207e-05, "loss": 0.7099, "step": 1010 }, { "grad_norm": 0.5988953709602356, "learning_rate": 8.896977605574788e-05, "loss": 0.7041, "step": 1020 }, { "grad_norm": 0.648632824420929, "learning_rate": 8.870945921123576e-05, "loss": 0.7184, "step": 1030 }, { "grad_norm": 0.4201085865497589, "learning_rate": 8.844649662660624e-05, "loss": 0.7186, "step": 1040 }, { "grad_norm": 0.5427833199501038, "learning_rate": 8.818090627500266e-05, "loss": 0.7271, "step": 1050 }, { "grad_norm": 0.5188281536102295, "learning_rate": 8.791270630917275e-05, "loss": 0.7092, "step": 1060 }, { "grad_norm": 0.6617937684059143, "learning_rate": 8.764191506022795e-05, "loss": 0.7114, "step": 1070 }, { "grad_norm": 0.5660023093223572, "learning_rate": 8.736855103639037e-05, "loss": 0.6944, "step": 1080 }, { "grad_norm": 0.45464205741882324, "learning_rate": 8.709263292172794e-05, "loss": 0.7176, "step": 1090 }, { "grad_norm": 0.44230857491493225, "learning_rate": 8.681417957487729e-05, "loss": 0.7053, "step": 1100 }, { "grad_norm": 0.5209611654281616, "learning_rate": 8.653321002775478e-05, "loss": 0.7061, "step": 1110 }, { "grad_norm": 0.5073080658912659, "learning_rate": 8.624974348425574e-05, "loss": 0.7162, "step": 1120 }, { "grad_norm": 0.5269641280174255, "learning_rate": 8.596379931894188e-05, "loss": 0.7059, "step": 1130 }, { "grad_norm": 0.45516136288642883, "learning_rate": 8.567539707571703e-05, "loss": 0.7021, "step": 1140 }, { "grad_norm": 0.4557558298110962, "learning_rate": 8.538455646649146e-05, "loss": 0.6988, "step": 1150 }, { "grad_norm": 0.5678983926773071, "learning_rate": 8.509129736983446e-05, "loss": 0.7003, "step": 1160 }, { "grad_norm": 0.5725619196891785, "learning_rate": 8.479563982961571e-05, "loss": 0.7027, "step": 1170 }, { "grad_norm": 0.46510183811187744, "learning_rate": 8.449760405363539e-05, "loss": 0.7054, "step": 1180 }, { "grad_norm": 0.5408710241317749, "learning_rate": 8.419721041224287e-05, "loss": 0.6948, "step": 1190 }, { "grad_norm": 0.46410325169563293, "learning_rate": 8.389447943694451e-05, "loss": 0.7045, "step": 1200 }, { "grad_norm": 0.5080893039703369, "learning_rate": 8.358943181900032e-05, "loss": 0.6939, "step": 1210 }, { "grad_norm": 0.5485800504684448, "learning_rate": 8.328208840800981e-05, "loss": 0.695, "step": 1220 }, { "grad_norm": 0.5217918157577515, "learning_rate": 8.297247021048686e-05, "loss": 0.7029, "step": 1230 }, { "grad_norm": 0.5817974209785461, "learning_rate": 8.266059838842396e-05, "loss": 0.7023, "step": 1240 }, { "grad_norm": 0.4946444034576416, "learning_rate": 8.23464942578459e-05, "loss": 0.6997, "step": 1250 }, { "grad_norm": 0.5017271041870117, "learning_rate": 8.203017928735277e-05, "loss": 0.7013, "step": 1260 }, { "grad_norm": 0.4506302773952484, "learning_rate": 8.17116750966526e-05, "loss": 0.6914, "step": 1270 }, { "grad_norm": 0.5228651762008667, "learning_rate": 8.139100345508377e-05, "loss": 0.7048, "step": 1280 }, { "grad_norm": 0.47274133563041687, "learning_rate": 8.106818628012697e-05, "loss": 0.6809, "step": 1290 }, { "grad_norm": 0.47493863105773926, "learning_rate": 8.074324563590736e-05, "loss": 0.693, "step": 1300 }, { "grad_norm": 0.5628791451454163, "learning_rate": 8.041620373168628e-05, "loss": 0.7053, "step": 1310 }, { "grad_norm": 0.5795761942863464, "learning_rate": 8.008708292034349e-05, "loss": 0.7127, "step": 1320 }, { "grad_norm": 0.46782001852989197, "learning_rate": 7.975590569684925e-05, "loss": 0.6882, "step": 1330 }, { "grad_norm": 0.45206907391548157, "learning_rate": 7.942269469672687e-05, "loss": 0.6894, "step": 1340 }, { "grad_norm": 0.5340469479560852, "learning_rate": 7.908747269450558e-05, "loss": 0.6839, "step": 1350 }, { "grad_norm": 0.6080896854400635, "learning_rate": 7.875026260216393e-05, "loss": 0.6956, "step": 1360 }, { "grad_norm": 0.5087507367134094, "learning_rate": 7.841108746756382e-05, "loss": 0.6895, "step": 1370 }, { "grad_norm": 0.4710014760494232, "learning_rate": 7.806997047287516e-05, "loss": 0.6839, "step": 1380 }, { "grad_norm": 0.5395244359970093, "learning_rate": 7.772693493299138e-05, "loss": 0.6944, "step": 1390 }, { "grad_norm": 0.5339425206184387, "learning_rate": 7.7382004293936e-05, "loss": 0.6979, "step": 1400 }, { "grad_norm": 0.4487476348876953, "learning_rate": 7.703520213126e-05, "loss": 0.6793, "step": 1410 }, { "grad_norm": 0.5018513798713684, "learning_rate": 7.66865521484305e-05, "loss": 0.7039, "step": 1420 }, { "grad_norm": 0.497934490442276, "learning_rate": 7.633607817521074e-05, "loss": 0.6904, "step": 1430 }, { "grad_norm": 0.5556654334068298, "learning_rate": 7.598380416603119e-05, "loss": 0.6821, "step": 1440 }, { "grad_norm": 0.5551984906196594, "learning_rate": 7.562975419835247e-05, "loss": 0.682, "step": 1450 }, { "grad_norm": 0.5837743878364563, "learning_rate": 7.527395247101956e-05, "loss": 0.6929, "step": 1460 }, { "grad_norm": 0.504239022731781, "learning_rate": 7.491642330260789e-05, "loss": 0.6718, "step": 1470 }, { "grad_norm": 0.4760385751724243, "learning_rate": 7.45571911297612e-05, "loss": 0.6712, "step": 1480 }, { "grad_norm": 0.4641706347465515, "learning_rate": 7.419628050552131e-05, "loss": 0.6831, "step": 1490 }, { "grad_norm": 0.5901619791984558, "learning_rate": 7.383371609764999e-05, "loss": 0.6675, "step": 1500 }, { "grad_norm": 0.5062085390090942, "learning_rate": 7.346952268694288e-05, "loss": 0.6798, "step": 1510 }, { "grad_norm": 0.49795156717300415, "learning_rate": 7.310372516553585e-05, "loss": 0.68, "step": 1520 }, { "grad_norm": 0.4773595929145813, "learning_rate": 7.273634853520356e-05, "loss": 0.6758, "step": 1530 }, { "grad_norm": 0.5229724645614624, "learning_rate": 7.236741790565072e-05, "loss": 0.687, "step": 1540 }, { "grad_norm": 0.4959690570831299, "learning_rate": 7.199695849279576e-05, "loss": 0.6939, "step": 1550 }, { "grad_norm": 0.4881291687488556, "learning_rate": 7.162499561704747e-05, "loss": 0.6905, "step": 1560 }, { "grad_norm": 0.48054420948028564, "learning_rate": 7.125155470157429e-05, "loss": 0.6672, "step": 1570 }, { "grad_norm": 0.47718197107315063, "learning_rate": 7.087666127056675e-05, "loss": 0.6745, "step": 1580 }, { "grad_norm": 0.39660972356796265, "learning_rate": 7.050034094749286e-05, "loss": 0.6731, "step": 1590 }, { "grad_norm": 0.4159504771232605, "learning_rate": 7.012261945334683e-05, "loss": 0.6727, "step": 1600 }, { "grad_norm": 0.5238457322120667, "learning_rate": 6.974352260489103e-05, "loss": 0.6777, "step": 1610 }, { "grad_norm": 0.5296777486801147, "learning_rate": 6.936307631289148e-05, "loss": 0.6842, "step": 1620 }, { "grad_norm": 0.5169921517372131, "learning_rate": 6.898130658034685e-05, "loss": 0.6722, "step": 1630 }, { "grad_norm": 0.46622392535209656, "learning_rate": 6.859823950071127e-05, "loss": 0.6768, "step": 1640 }, { "grad_norm": 0.4715481698513031, "learning_rate": 6.821390125611078e-05, "loss": 0.6875, "step": 1650 }, { "grad_norm": 0.4542713761329651, "learning_rate": 6.782831811555385e-05, "loss": 0.6647, "step": 1660 }, { "grad_norm": 0.4589802324771881, "learning_rate": 6.744151643313597e-05, "loss": 0.6769, "step": 1670 }, { "grad_norm": 0.46197426319122314, "learning_rate": 6.705352264623828e-05, "loss": 0.6818, "step": 1680 }, { "grad_norm": 0.4620882570743561, "learning_rate": 6.666436327372078e-05, "loss": 0.6723, "step": 1690 }, { "grad_norm": 0.4430062174797058, "learning_rate": 6.62740649141096e-05, "loss": 0.6743, "step": 1700 }, { "grad_norm": 0.49391141533851624, "learning_rate": 6.588265424377919e-05, "loss": 0.6687, "step": 1710 }, { "grad_norm": 0.46312108635902405, "learning_rate": 6.549015801512895e-05, "loss": 0.6715, "step": 1720 }, { "grad_norm": 0.5987693071365356, "learning_rate": 6.509660305475468e-05, "loss": 0.6784, "step": 1730 }, { "grad_norm": 0.5958335995674133, "learning_rate": 6.47020162616152e-05, "loss": 0.6722, "step": 1740 }, { "grad_norm": 0.47428029775619507, "learning_rate": 6.430642460519365e-05, "loss": 0.6666, "step": 1750 }, { "grad_norm": 0.5168448090553284, "learning_rate": 6.390985512365426e-05, "loss": 0.6717, "step": 1760 }, { "grad_norm": 0.5116503238677979, "learning_rate": 6.351233492199431e-05, "loss": 0.6729, "step": 1770 }, { "grad_norm": 0.44382596015930176, "learning_rate": 6.311389117019155e-05, "loss": 0.6729, "step": 1780 }, { "grad_norm": 0.493990421295166, "learning_rate": 6.271455110134713e-05, "loss": 0.67, "step": 1790 }, { "grad_norm": 0.4669109880924225, "learning_rate": 6.231434200982428e-05, "loss": 0.6675, "step": 1800 }, { "grad_norm": 0.5045506954193115, "learning_rate": 6.191329124938285e-05, "loss": 0.6669, "step": 1810 }, { "grad_norm": 0.44471701979637146, "learning_rate": 6.15114262313095e-05, "loss": 0.6674, "step": 1820 }, { "grad_norm": 0.4768633246421814, "learning_rate": 6.110877442254444e-05, "loss": 0.6627, "step": 1830 }, { "grad_norm": 0.44661039113998413, "learning_rate": 6.0705363343803946e-05, "loss": 0.6601, "step": 1840 }, { "grad_norm": 0.3572286367416382, "learning_rate": 6.030122056769934e-05, "loss": 0.6664, "step": 1850 }, { "grad_norm": 0.5288762450218201, "learning_rate": 5.989637371685257e-05, "loss": 0.6776, "step": 1860 }, { "grad_norm": 0.5009581446647644, "learning_rate": 5.949085046200808e-05, "loss": 0.6725, "step": 1870 }, { "grad_norm": 0.44043007493019104, "learning_rate": 5.908467852014169e-05, "loss": 0.6632, "step": 1880 }, { "grad_norm": 0.4002927243709564, "learning_rate": 5.867788565256607e-05, "loss": 0.6646, "step": 1890 }, { "grad_norm": 0.49478879570961, "learning_rate": 5.827049966303335e-05, "loss": 0.6567, "step": 1900 }, { "grad_norm": 0.4791210889816284, "learning_rate": 5.786254839583478e-05, "loss": 0.6634, "step": 1910 }, { "grad_norm": 0.5025086998939514, "learning_rate": 5.745405973389757e-05, "loss": 0.6534, "step": 1920 }, { "grad_norm": 0.4516906142234802, "learning_rate": 5.7045061596879134e-05, "loss": 0.6736, "step": 1930 }, { "grad_norm": 0.4860899746417999, "learning_rate": 5.6635581939258855e-05, "loss": 0.658, "step": 1940 }, { "grad_norm": 0.514963686466217, "learning_rate": 5.622564874842742e-05, "loss": 0.6562, "step": 1950 }, { "grad_norm": 0.48472991585731506, "learning_rate": 5.5815290042773836e-05, "loss": 0.6619, "step": 1960 }, { "grad_norm": 0.5486400723457336, "learning_rate": 5.540453386977058e-05, "loss": 0.651, "step": 1970 }, { "grad_norm": 0.5085767507553101, "learning_rate": 5.4993408304056425e-05, "loss": 0.6531, "step": 1980 }, { "grad_norm": 0.5380701422691345, "learning_rate": 5.458194144551768e-05, "loss": 0.6554, "step": 1990 }, { "grad_norm": 0.48443129658699036, "learning_rate": 5.417016141736756e-05, "loss": 0.6568, "step": 2000 }, { "grad_norm": 0.500551164150238, "learning_rate": 5.375809636422399e-05, "loss": 0.65, "step": 2010 }, { "grad_norm": 0.45972248911857605, "learning_rate": 5.334577445018599e-05, "loss": 0.6526, "step": 2020 }, { "grad_norm": 0.48264095187187195, "learning_rate": 5.293322385690867e-05, "loss": 0.6528, "step": 2030 }, { "grad_norm": 0.5277835726737976, "learning_rate": 5.252047278167709e-05, "loss": 0.6554, "step": 2040 }, { "grad_norm": 0.5141885280609131, "learning_rate": 5.210754943547893e-05, "loss": 0.6401, "step": 2050 }, { "grad_norm": 0.5499096512794495, "learning_rate": 5.169448204107643e-05, "loss": 0.6523, "step": 2060 }, { "grad_norm": 0.4706327021121979, "learning_rate": 5.128129883107729e-05, "loss": 0.6457, "step": 2070 }, { "grad_norm": 0.5084936618804932, "learning_rate": 5.086802804600505e-05, "loss": 0.6563, "step": 2080 }, { "grad_norm": 0.5018666386604309, "learning_rate": 5.045469793236892e-05, "loss": 0.6661, "step": 2090 }, { "grad_norm": 0.5113282203674316, "learning_rate": 5.00413367407331e-05, "loss": 0.6594, "step": 2100 }, { "grad_norm": 0.5432279109954834, "learning_rate": 4.9627972723785964e-05, "loss": 0.6575, "step": 2110 }, { "grad_norm": 0.43599316477775574, "learning_rate": 4.921463413440898e-05, "loss": 0.6635, "step": 2120 }, { "grad_norm": 0.5157215595245361, "learning_rate": 4.8801349223745654e-05, "loss": 0.6621, "step": 2130 }, { "grad_norm": 0.5271717309951782, "learning_rate": 4.838814623927067e-05, "loss": 0.6507, "step": 2140 }, { "grad_norm": 0.6172201037406921, "learning_rate": 4.797505342285912e-05, "loss": 0.658, "step": 2150 }, { "grad_norm": 0.5685967206954956, "learning_rate": 4.756209900885628e-05, "loss": 0.6563, "step": 2160 }, { "grad_norm": 0.5275602340698242, "learning_rate": 4.714931122214781e-05, "loss": 0.6453, "step": 2170 }, { "grad_norm": 0.4504585266113281, "learning_rate": 4.673671827623058e-05, "loss": 0.6433, "step": 2180 }, { "grad_norm": 0.5779574513435364, "learning_rate": 4.632434837128443e-05, "loss": 0.6324, "step": 2190 }, { "grad_norm": 0.5458188652992249, "learning_rate": 4.591222969224453e-05, "loss": 0.6315, "step": 2200 }, { "grad_norm": 0.4926324784755707, "learning_rate": 4.550039040687518e-05, "loss": 0.6461, "step": 2210 }, { "grad_norm": 0.495878666639328, "learning_rate": 4.508885866384446e-05, "loss": 0.6547, "step": 2220 }, { "grad_norm": 0.48175400495529175, "learning_rate": 4.4677662590800355e-05, "loss": 0.6362, "step": 2230 }, { "grad_norm": 0.5608018040657043, "learning_rate": 4.426683029244825e-05, "loss": 0.6301, "step": 2240 }, { "grad_norm": 0.5170360803604126, "learning_rate": 4.385638984863e-05, "loss": 0.6295, "step": 2250 }, { "grad_norm": 0.4240834712982178, "learning_rate": 4.3446369312404745e-05, "loss": 0.6451, "step": 2260 }, { "grad_norm": 0.5210784673690796, "learning_rate": 4.3036796708131474e-05, "loss": 0.6609, "step": 2270 }, { "grad_norm": 0.49699047207832336, "learning_rate": 4.262770002955363e-05, "loss": 0.65, "step": 2280 }, { "grad_norm": 0.5782934427261353, "learning_rate": 4.221910723788578e-05, "loss": 0.6389, "step": 2290 }, { "grad_norm": 0.537568986415863, "learning_rate": 4.1811046259902474e-05, "loss": 0.6498, "step": 2300 }, { "grad_norm": 0.5546226501464844, "learning_rate": 4.140354498602952e-05, "loss": 0.6278, "step": 2310 }, { "grad_norm": 0.5449338555335999, "learning_rate": 4.099663126843769e-05, "loss": 0.6412, "step": 2320 }, { "grad_norm": 0.47158190608024597, "learning_rate": 4.059033291913902e-05, "loss": 0.6245, "step": 2330 }, { "grad_norm": 0.4968015253543854, "learning_rate": 4.0184677708086014e-05, "loss": 0.6351, "step": 2340 }, { "grad_norm": 0.5768001079559326, "learning_rate": 3.977969336127348e-05, "loss": 0.6199, "step": 2350 }, { "grad_norm": 0.5403270125389099, "learning_rate": 3.937540755884357e-05, "loss": 0.6196, "step": 2360 }, { "grad_norm": 0.5366491675376892, "learning_rate": 3.897184793319384e-05, "loss": 0.6335, "step": 2370 }, { "grad_norm": 0.59100341796875, "learning_rate": 3.856904206708863e-05, "loss": 0.626, "step": 2380 }, { "grad_norm": 0.5830090641975403, "learning_rate": 3.8167017491773847e-05, "loss": 0.6129, "step": 2390 }, { "grad_norm": 0.551158607006073, "learning_rate": 3.776580168509516e-05, "loss": 0.6326, "step": 2400 }, { "grad_norm": 0.6444660425186157, "learning_rate": 3.736542206962e-05, "loss": 0.6334, "step": 2410 }, { "grad_norm": 0.5306467413902283, "learning_rate": 3.696590601076326e-05, "loss": 0.6127, "step": 2420 }, { "grad_norm": 0.557221531867981, "learning_rate": 3.656728081491686e-05, "loss": 0.6015, "step": 2430 }, { "grad_norm": 0.5166459083557129, "learning_rate": 3.6169573727583405e-05, "loss": 0.6108, "step": 2440 }, { "grad_norm": 0.601004421710968, "learning_rate": 3.5772811931514036e-05, "loss": 0.609, "step": 2450 }, { "grad_norm": 0.5955168604850769, "learning_rate": 3.5377022544850505e-05, "loss": 0.5829, "step": 2460 }, { "grad_norm": 0.7004075050354004, "learning_rate": 3.498223261927158e-05, "loss": 0.6138, "step": 2470 }, { "grad_norm": 0.7036697864532471, "learning_rate": 3.4588469138144295e-05, "loss": 0.5839, "step": 2480 }, { "grad_norm": 0.7682510614395142, "learning_rate": 3.419575901467952e-05, "loss": 0.5833, "step": 2490 }, { "grad_norm": 0.627487301826477, "learning_rate": 3.380412909009254e-05, "loss": 0.5898, "step": 2500 }, { "grad_norm": 0.8526833653450012, "learning_rate": 3.3413606131768475e-05, "loss": 0.5891, "step": 2510 }, { "grad_norm": 0.6904925107955933, "learning_rate": 3.302421683143279e-05, "loss": 0.5835, "step": 2520 }, { "grad_norm": 0.6932260990142822, "learning_rate": 3.2635987803326896e-05, "loss": 0.5705, "step": 2530 }, { "grad_norm": 0.7479665279388428, "learning_rate": 3.224894558238918e-05, "loss": 0.5594, "step": 2540 }, { "grad_norm": 0.7718488574028015, "learning_rate": 3.18631166224413e-05, "loss": 0.5739, "step": 2550 }, { "grad_norm": 0.6979143619537354, "learning_rate": 3.147852729438017e-05, "loss": 0.5642, "step": 2560 }, { "grad_norm": 0.7248340845108032, "learning_rate": 3.109520388437548e-05, "loss": 0.5722, "step": 2570 }, { "grad_norm": 0.6221643686294556, "learning_rate": 3.0713172592073116e-05, "loss": 0.5494, "step": 2580 }, { "grad_norm": 0.6455109715461731, "learning_rate": 3.0332459528804457e-05, "loss": 0.5576, "step": 2590 }, { "grad_norm": 0.9877533316612244, "learning_rate": 2.9953090715801634e-05, "loss": 0.5429, "step": 2600 }, { "grad_norm": 0.7915239930152893, "learning_rate": 2.9575092082419086e-05, "loss": 0.5507, "step": 2610 }, { "grad_norm": 0.7198984622955322, "learning_rate": 2.9198489464361288e-05, "loss": 0.5413, "step": 2620 }, { "grad_norm": 0.6209663152694702, "learning_rate": 2.8823308601916948e-05, "loss": 0.5279, "step": 2630 }, { "grad_norm": 0.6671990752220154, "learning_rate": 2.8449575138199613e-05, "loss": 0.5459, "step": 2640 }, { "grad_norm": 0.7317913770675659, "learning_rate": 2.807731461739509e-05, "loss": 0.5154, "step": 2650 }, { "grad_norm": 0.7610775232315063, "learning_rate": 2.7706552483015485e-05, "loss": 0.5226, "step": 2660 }, { "grad_norm": 0.781760573387146, "learning_rate": 2.733731407616018e-05, "loss": 0.4998, "step": 2670 }, { "grad_norm": 0.8036126494407654, "learning_rate": 2.6969624633783806e-05, "loss": 0.515, "step": 2680 }, { "grad_norm": 0.9693417549133301, "learning_rate": 2.660350928697134e-05, "loss": 0.5162, "step": 2690 }, { "grad_norm": 0.7961346507072449, "learning_rate": 2.6238993059220395e-05, "loss": 0.517, "step": 2700 }, { "grad_norm": 0.7805870771408081, "learning_rate": 2.5876100864730933e-05, "loss": 0.4988, "step": 2710 }, { "grad_norm": 0.7758889198303223, "learning_rate": 2.5514857506702405e-05, "loss": 0.5037, "step": 2720 }, { "grad_norm": 0.737293541431427, "learning_rate": 2.5155287675638474e-05, "loss": 0.4796, "step": 2730 }, { "grad_norm": 0.8677336573600769, "learning_rate": 2.4797415947659457e-05, "loss": 0.4858, "step": 2740 }, { "grad_norm": 0.8488855361938477, "learning_rate": 2.4441266782822588e-05, "loss": 0.4781, "step": 2750 }, { "grad_norm": 0.746828556060791, "learning_rate": 2.4086864523450183e-05, "loss": 0.4737, "step": 2760 }, { "grad_norm": 0.8593442440032959, "learning_rate": 2.3734233392465903e-05, "loss": 0.4832, "step": 2770 }, { "grad_norm": 0.737777590751648, "learning_rate": 2.3383397491739145e-05, "loss": 0.4797, "step": 2780 }, { "grad_norm": 0.7161794304847717, "learning_rate": 2.3034380800437678e-05, "loss": 0.4545, "step": 2790 }, { "grad_norm": 0.8545267581939697, "learning_rate": 2.2687207173388743e-05, "loss": 0.4664, "step": 2800 }, { "grad_norm": 0.7654674649238586, "learning_rate": 2.234190033944858e-05, "loss": 0.4647, "step": 2810 }, { "grad_norm": 0.8628227710723877, "learning_rate": 2.1998483899880596e-05, "loss": 0.4588, "step": 2820 }, { "grad_norm": 0.9096059799194336, "learning_rate": 2.1656981326742266e-05, "loss": 0.4431, "step": 2830 }, { "grad_norm": 0.8760948181152344, "learning_rate": 2.1317415961280824e-05, "loss": 0.4565, "step": 2840 }, { "grad_norm": 0.8818371295928955, "learning_rate": 2.097981101233794e-05, "loss": 0.4248, "step": 2850 }, { "grad_norm": 0.9236174821853638, "learning_rate": 2.0644189554763417e-05, "loss": 0.4139, "step": 2860 }, { "grad_norm": 0.8099502921104431, "learning_rate": 2.0310574527838072e-05, "loss": 0.4365, "step": 2870 }, { "grad_norm": 0.9216195344924927, "learning_rate": 1.9978988733705807e-05, "loss": 0.4367, "step": 2880 }, { "grad_norm": 0.8922995328903198, "learning_rate": 1.9649454835815202e-05, "loss": 0.4581, "step": 2890 }, { "grad_norm": 0.8256015181541443, "learning_rate": 1.932199535737045e-05, "loss": 0.4173, "step": 2900 }, { "grad_norm": 0.9429636001586914, "learning_rate": 1.8996632679791914e-05, "loss": 0.4392, "step": 2910 }, { "grad_norm": 1.0027697086334229, "learning_rate": 1.8673389041186418e-05, "loss": 0.3899, "step": 2920 }, { "grad_norm": 0.9124972820281982, "learning_rate": 1.8352286534827274e-05, "loss": 0.4113, "step": 2930 }, { "grad_norm": 0.8158929944038391, "learning_rate": 1.803334710764426e-05, "loss": 0.4008, "step": 2940 }, { "grad_norm": 0.9610748291015625, "learning_rate": 1.7716592558723556e-05, "loss": 0.392, "step": 2950 }, { "grad_norm": 0.9714084267616272, "learning_rate": 1.7402044537817824e-05, "loss": 0.3887, "step": 2960 }, { "grad_norm": 0.9433429837226868, "learning_rate": 1.7089724543866465e-05, "loss": 0.3764, "step": 2970 }, { "grad_norm": 0.8527407050132751, "learning_rate": 1.6779653923526188e-05, "loss": 0.3971, "step": 2980 }, { "grad_norm": 0.9382534027099609, "learning_rate": 1.6471853869712023e-05, "loss": 0.3891, "step": 2990 }, { "grad_norm": 0.8641057014465332, "learning_rate": 1.6166345420148787e-05, "loss": 0.388, "step": 3000 } ], "logging_steps": 10, "max_steps": 4000, "num_input_tokens_seen": 0, "num_train_epochs": 9223372036854775807, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }