| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0005458515283843, |
| "eval_steps": 500, |
| "global_step": 1832, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 0.8506594449281693, |
| "epoch": 0.0054585152838427945, |
| "grad_norm": 6.625, |
| "learning_rate": 1.6363636363636365e-06, |
| "loss": 0.7328, |
| "mean_token_accuracy": 0.8114667266607285, |
| "num_tokens": 7873074.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.8578470677137375, |
| "epoch": 0.010917030567685589, |
| "grad_norm": 3.234375, |
| "learning_rate": 3.454545454545455e-06, |
| "loss": 0.6724, |
| "mean_token_accuracy": 0.8153360992670059, |
| "num_tokens": 15735890.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.868700721859932, |
| "epoch": 0.016375545851528384, |
| "grad_norm": 0.94140625, |
| "learning_rate": 5.272727272727273e-06, |
| "loss": 0.5629, |
| "mean_token_accuracy": 0.8309339731931686, |
| "num_tokens": 23601330.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.8585465878248215, |
| "epoch": 0.021834061135371178, |
| "grad_norm": 0.58984375, |
| "learning_rate": 7.0909090909090916e-06, |
| "loss": 0.5071, |
| "mean_token_accuracy": 0.8447592586278916, |
| "num_tokens": 31458560.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.8470574885606765, |
| "epoch": 0.027292576419213975, |
| "grad_norm": 0.5078125, |
| "learning_rate": 8.90909090909091e-06, |
| "loss": 0.4817, |
| "mean_token_accuracy": 0.8515126377344131, |
| "num_tokens": 39318330.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.8366546362638474, |
| "epoch": 0.03275109170305677, |
| "grad_norm": 0.412109375, |
| "learning_rate": 9.999874978970385e-06, |
| "loss": 0.4536, |
| "mean_token_accuracy": 0.8550278633832932, |
| "num_tokens": 47187690.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.8242797136306763, |
| "epoch": 0.03820960698689956, |
| "grad_norm": 0.5, |
| "learning_rate": 9.998468564187713e-06, |
| "loss": 0.4452, |
| "mean_token_accuracy": 0.8588810175657272, |
| "num_tokens": 55058356.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.8176750153303146, |
| "epoch": 0.043668122270742356, |
| "grad_norm": 0.447265625, |
| "learning_rate": 9.995499899369634e-06, |
| "loss": 0.4375, |
| "mean_token_accuracy": 0.860920637845993, |
| "num_tokens": 62923390.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.8128144711256027, |
| "epoch": 0.04912663755458515, |
| "grad_norm": 1.0078125, |
| "learning_rate": 9.990969912359675e-06, |
| "loss": 0.4483, |
| "mean_token_accuracy": 0.8596585601568222, |
| "num_tokens": 70785326.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.8117900550365448, |
| "epoch": 0.05458515283842795, |
| "grad_norm": 0.486328125, |
| "learning_rate": 9.984880018985966e-06, |
| "loss": 0.4368, |
| "mean_token_accuracy": 0.8614727318286896, |
| "num_tokens": 78646604.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.8099668920040131, |
| "epoch": 0.060043668122270744, |
| "grad_norm": 0.68359375, |
| "learning_rate": 9.977232122618704e-06, |
| "loss": 0.4429, |
| "mean_token_accuracy": 0.8630078643560409, |
| "num_tokens": 86509996.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.8032392680644989, |
| "epoch": 0.06550218340611354, |
| "grad_norm": 0.6015625, |
| "learning_rate": 9.968028613575292e-06, |
| "loss": 0.4483, |
| "mean_token_accuracy": 0.8638610720634461, |
| "num_tokens": 94374220.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.7966970652341843, |
| "epoch": 0.07096069868995633, |
| "grad_norm": 0.546875, |
| "learning_rate": 9.957272368373235e-06, |
| "loss": 0.4306, |
| "mean_token_accuracy": 0.8641012936830521, |
| "num_tokens": 102245070.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.7891126424074173, |
| "epoch": 0.07641921397379912, |
| "grad_norm": 0.65234375, |
| "learning_rate": 9.944966748831104e-06, |
| "loss": 0.4376, |
| "mean_token_accuracy": 0.8643449753522873, |
| "num_tokens": 110114714.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.7812703251838684, |
| "epoch": 0.08187772925764192, |
| "grad_norm": 0.494140625, |
| "learning_rate": 9.931115601017816e-06, |
| "loss": 0.4412, |
| "mean_token_accuracy": 0.8659342557191849, |
| "num_tokens": 117983612.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.7815882682800293, |
| "epoch": 0.08733624454148471, |
| "grad_norm": 0.60546875, |
| "learning_rate": 9.915723254050551e-06, |
| "loss": 0.4264, |
| "mean_token_accuracy": 0.865845575928688, |
| "num_tokens": 125857638.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.7799684792757035, |
| "epoch": 0.0927947598253275, |
| "grad_norm": 0.71875, |
| "learning_rate": 9.898794518741725e-06, |
| "loss": 0.4217, |
| "mean_token_accuracy": 0.8657624512910843, |
| "num_tokens": 133718934.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.7746502578258514, |
| "epoch": 0.0982532751091703, |
| "grad_norm": 0.50390625, |
| "learning_rate": 9.880334686095365e-06, |
| "loss": 0.4375, |
| "mean_token_accuracy": 0.865676325559616, |
| "num_tokens": 141587252.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.7698926359415055, |
| "epoch": 0.1037117903930131, |
| "grad_norm": 0.87890625, |
| "learning_rate": 9.860349525653455e-06, |
| "loss": 0.4142, |
| "mean_token_accuracy": 0.8676840603351593, |
| "num_tokens": 149454258.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.7676965594291687, |
| "epoch": 0.1091703056768559, |
| "grad_norm": 0.75390625, |
| "learning_rate": 9.838845283692665e-06, |
| "loss": 0.4132, |
| "mean_token_accuracy": 0.8689810872077942, |
| "num_tokens": 157314466.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 0.7642738163471222, |
| "epoch": 0.1146288209606987, |
| "grad_norm": 0.7265625, |
| "learning_rate": 9.815828681272127e-06, |
| "loss": 0.4098, |
| "mean_token_accuracy": 0.8706588715314865, |
| "num_tokens": 165182774.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 0.7638502717018127, |
| "epoch": 0.12008733624454149, |
| "grad_norm": 1.484375, |
| "learning_rate": 9.791306912132776e-06, |
| "loss": 0.4081, |
| "mean_token_accuracy": 0.8702643483877182, |
| "num_tokens": 173042008.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 0.7644800752401352, |
| "epoch": 0.12554585152838427, |
| "grad_norm": 1.0390625, |
| "learning_rate": 9.765287640448996e-06, |
| "loss": 0.4065, |
| "mean_token_accuracy": 0.8699748694896698, |
| "num_tokens": 180901588.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 0.7578901439905167, |
| "epoch": 0.13100436681222707, |
| "grad_norm": 0.9453125, |
| "learning_rate": 9.737778998433198e-06, |
| "loss": 0.3974, |
| "mean_token_accuracy": 0.8707681357860565, |
| "num_tokens": 188769044.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 0.7537958860397339, |
| "epoch": 0.13646288209606988, |
| "grad_norm": 0.77734375, |
| "learning_rate": 9.708789583794144e-06, |
| "loss": 0.4011, |
| "mean_token_accuracy": 0.8707371085882187, |
| "num_tokens": 196634434.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 0.7602073311805725, |
| "epoch": 0.14192139737991266, |
| "grad_norm": 0.70703125, |
| "learning_rate": 9.678328457049766e-06, |
| "loss": 0.3991, |
| "mean_token_accuracy": 0.8711989611387253, |
| "num_tokens": 204486562.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 0.7597428560256958, |
| "epoch": 0.14737991266375547, |
| "grad_norm": 0.95703125, |
| "learning_rate": 9.646405138695331e-06, |
| "loss": 0.3997, |
| "mean_token_accuracy": 0.8710573464632034, |
| "num_tokens": 212351956.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 0.7577679485082627, |
| "epoch": 0.15283842794759825, |
| "grad_norm": 2.1875, |
| "learning_rate": 9.613029606227867e-06, |
| "loss": 0.399, |
| "mean_token_accuracy": 0.8701757520437241, |
| "num_tokens": 220205590.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 0.7598035603761673, |
| "epoch": 0.15829694323144106, |
| "grad_norm": 2.78125, |
| "learning_rate": 9.57821229102773e-06, |
| "loss": 0.4217, |
| "mean_token_accuracy": 0.8680002480745316, |
| "num_tokens": 228076474.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 0.7590495645999908, |
| "epoch": 0.16375545851528384, |
| "grad_norm": 2.578125, |
| "learning_rate": 9.541964075098313e-06, |
| "loss": 0.4285, |
| "mean_token_accuracy": 0.8676898956298829, |
| "num_tokens": 235936872.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 0.757094269990921, |
| "epoch": 0.16921397379912664, |
| "grad_norm": 2.359375, |
| "learning_rate": 9.50429628766494e-06, |
| "loss": 0.4185, |
| "mean_token_accuracy": 0.8680381834506988, |
| "num_tokens": 243803792.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 0.7542549550533295, |
| "epoch": 0.17467248908296942, |
| "grad_norm": 3.875, |
| "learning_rate": 9.465220701633953e-06, |
| "loss": 0.4055, |
| "mean_token_accuracy": 0.8681020706892013, |
| "num_tokens": 251674582.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 0.7625361144542694, |
| "epoch": 0.18013100436681223, |
| "grad_norm": 1.5, |
| "learning_rate": 9.424749529913138e-06, |
| "loss": 0.4199, |
| "mean_token_accuracy": 0.8669591844081879, |
| "num_tokens": 259538060.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 0.7554975986480713, |
| "epoch": 0.185589519650655, |
| "grad_norm": 0.68359375, |
| "learning_rate": 9.38289542159464e-06, |
| "loss": 0.4121, |
| "mean_token_accuracy": 0.8684647858142853, |
| "num_tokens": 267404072.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 0.7535371214151383, |
| "epoch": 0.19104803493449782, |
| "grad_norm": 0.8828125, |
| "learning_rate": 9.339671458001543e-06, |
| "loss": 0.3962, |
| "mean_token_accuracy": 0.8698400855064392, |
| "num_tokens": 275270380.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 0.754734218120575, |
| "epoch": 0.1965065502183406, |
| "grad_norm": 0.63671875, |
| "learning_rate": 9.295091148599353e-06, |
| "loss": 0.4112, |
| "mean_token_accuracy": 0.8690466344356537, |
| "num_tokens": 283145890.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 0.7563666641712189, |
| "epoch": 0.2019650655021834, |
| "grad_norm": 0.95703125, |
| "learning_rate": 9.249168426773675e-06, |
| "loss": 0.4091, |
| "mean_token_accuracy": 0.8709859728813172, |
| "num_tokens": 291005988.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 0.7565184265375138, |
| "epoch": 0.2074235807860262, |
| "grad_norm": 0.74609375, |
| "learning_rate": 9.201917645475393e-06, |
| "loss": 0.3981, |
| "mean_token_accuracy": 0.8720056504011154, |
| "num_tokens": 298864526.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 0.760869923233986, |
| "epoch": 0.212882096069869, |
| "grad_norm": 2.3125, |
| "learning_rate": 9.153353572734716e-06, |
| "loss": 0.4139, |
| "mean_token_accuracy": 0.869957122206688, |
| "num_tokens": 306735082.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 0.7582542330026627, |
| "epoch": 0.2183406113537118, |
| "grad_norm": 3.609375, |
| "learning_rate": 9.103491387045495e-06, |
| "loss": 0.4144, |
| "mean_token_accuracy": 0.8715152114629745, |
| "num_tokens": 314604158.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 0.7573513597249985, |
| "epoch": 0.22379912663755458, |
| "grad_norm": 1.6484375, |
| "learning_rate": 9.052346672621246e-06, |
| "loss": 0.4132, |
| "mean_token_accuracy": 0.8716101557016372, |
| "num_tokens": 322465290.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 0.7590894103050232, |
| "epoch": 0.2292576419213974, |
| "grad_norm": 1.90625, |
| "learning_rate": 8.999935414524373e-06, |
| "loss": 0.417, |
| "mean_token_accuracy": 0.8695549905300141, |
| "num_tokens": 330336414.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 0.7527199715375901, |
| "epoch": 0.23471615720524017, |
| "grad_norm": 0.8359375, |
| "learning_rate": 8.9462739936701e-06, |
| "loss": 0.4077, |
| "mean_token_accuracy": 0.8720698267221451, |
| "num_tokens": 338189854.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 0.7517860412597657, |
| "epoch": 0.24017467248908297, |
| "grad_norm": 1.0859375, |
| "learning_rate": 8.891379181706697e-06, |
| "loss": 0.3975, |
| "mean_token_accuracy": 0.8719705253839493, |
| "num_tokens": 346051832.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 0.7506425231695175, |
| "epoch": 0.24563318777292575, |
| "grad_norm": 0.90625, |
| "learning_rate": 8.835268135773561e-06, |
| "loss": 0.4144, |
| "mean_token_accuracy": 0.8714013040065766, |
| "num_tokens": 353923892.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 0.7511818319559097, |
| "epoch": 0.25109170305676853, |
| "grad_norm": 0.671875, |
| "learning_rate": 8.777958393138833e-06, |
| "loss": 0.3958, |
| "mean_token_accuracy": 0.8729292124509811, |
| "num_tokens": 361787270.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 0.7484469264745712, |
| "epoch": 0.25655021834061137, |
| "grad_norm": 1.234375, |
| "learning_rate": 8.719467865718192e-06, |
| "loss": 0.4055, |
| "mean_token_accuracy": 0.8726571470499038, |
| "num_tokens": 369659224.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 0.7491981714963913, |
| "epoch": 0.26200873362445415, |
| "grad_norm": 0.9375, |
| "learning_rate": 8.659814834476571e-06, |
| "loss": 0.3889, |
| "mean_token_accuracy": 0.8721846073865891, |
| "num_tokens": 377517650.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 0.745842233300209, |
| "epoch": 0.26746724890829693, |
| "grad_norm": 1.0, |
| "learning_rate": 8.599017943714514e-06, |
| "loss": 0.3995, |
| "mean_token_accuracy": 0.8731576293706894, |
| "num_tokens": 385374510.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 0.7489482790231705, |
| "epoch": 0.27292576419213976, |
| "grad_norm": 0.68359375, |
| "learning_rate": 8.537096195240982e-06, |
| "loss": 0.4032, |
| "mean_token_accuracy": 0.8717446327209473, |
| "num_tokens": 393229928.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 0.7476549535989762, |
| "epoch": 0.27838427947598254, |
| "grad_norm": 2.046875, |
| "learning_rate": 8.47406894243441e-06, |
| "loss": 0.4009, |
| "mean_token_accuracy": 0.8734071612358093, |
| "num_tokens": 401092592.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 0.751323652267456, |
| "epoch": 0.2838427947598253, |
| "grad_norm": 1.0, |
| "learning_rate": 8.40995588419391e-06, |
| "loss": 0.3989, |
| "mean_token_accuracy": 0.8721231341361999, |
| "num_tokens": 408948350.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 0.7470169544219971, |
| "epoch": 0.2893013100436681, |
| "grad_norm": 1.8046875, |
| "learning_rate": 8.344777058782442e-06, |
| "loss": 0.3981, |
| "mean_token_accuracy": 0.8728294968605042, |
| "num_tokens": 416816292.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 0.7452338933944702, |
| "epoch": 0.29475982532751094, |
| "grad_norm": 1.1171875, |
| "learning_rate": 8.278552837563957e-06, |
| "loss": 0.3889, |
| "mean_token_accuracy": 0.8725773304700851, |
| "num_tokens": 424683528.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 0.7451816380023957, |
| "epoch": 0.3002183406113537, |
| "grad_norm": 2.28125, |
| "learning_rate": 8.211303918636403e-06, |
| "loss": 0.4006, |
| "mean_token_accuracy": 0.8727004051208496, |
| "num_tokens": 432547452.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 0.7443063974380493, |
| "epoch": 0.3056768558951965, |
| "grad_norm": 0.84765625, |
| "learning_rate": 8.143051320362632e-06, |
| "loss": 0.3947, |
| "mean_token_accuracy": 0.8734056413173675, |
| "num_tokens": 440414732.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 0.7448951125144958, |
| "epoch": 0.3111353711790393, |
| "grad_norm": 1.5390625, |
| "learning_rate": 8.07381637480119e-06, |
| "loss": 0.3892, |
| "mean_token_accuracy": 0.8715481579303741, |
| "num_tokens": 448281138.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 0.7429590493440628, |
| "epoch": 0.3165938864628821, |
| "grad_norm": 2.734375, |
| "learning_rate": 8.003620721039089e-06, |
| "loss": 0.3999, |
| "mean_token_accuracy": 0.8723650634288788, |
| "num_tokens": 456150890.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 0.7418043345212937, |
| "epoch": 0.3220524017467249, |
| "grad_norm": 0.7890625, |
| "learning_rate": 7.932486298428582e-06, |
| "loss": 0.3906, |
| "mean_token_accuracy": 0.8723206043243408, |
| "num_tokens": 464017298.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 0.7461079835891724, |
| "epoch": 0.32751091703056767, |
| "grad_norm": 1.5390625, |
| "learning_rate": 7.860435339730123e-06, |
| "loss": 0.4117, |
| "mean_token_accuracy": 0.8710065305233001, |
| "num_tokens": 471883034.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 0.742401072382927, |
| "epoch": 0.3329694323144105, |
| "grad_norm": 1.34375, |
| "learning_rate": 7.787490364163622e-06, |
| "loss": 0.3828, |
| "mean_token_accuracy": 0.8727285087108612, |
| "num_tokens": 479752180.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 0.7451883584260941, |
| "epoch": 0.3384279475982533, |
| "grad_norm": 1.046875, |
| "learning_rate": 7.71367417037014e-06, |
| "loss": 0.3981, |
| "mean_token_accuracy": 0.8712346762418747, |
| "num_tokens": 487618472.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 0.742529284954071, |
| "epoch": 0.34388646288209607, |
| "grad_norm": 0.828125, |
| "learning_rate": 7.639009829286281e-06, |
| "loss": 0.3989, |
| "mean_token_accuracy": 0.8732034027576446, |
| "num_tokens": 495485140.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 0.7405054122209549, |
| "epoch": 0.34934497816593885, |
| "grad_norm": 0.65234375, |
| "learning_rate": 7.5635206769334715e-06, |
| "loss": 0.3937, |
| "mean_token_accuracy": 0.8724321722984314, |
| "num_tokens": 503352820.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 0.7433331936597825, |
| "epoch": 0.3548034934497817, |
| "grad_norm": 7.96875, |
| "learning_rate": 7.487230307124377e-06, |
| "loss": 0.4174, |
| "mean_token_accuracy": 0.8709851861000061, |
| "num_tokens": 511216636.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 0.7436719715595246, |
| "epoch": 0.36026200873362446, |
| "grad_norm": 4.375, |
| "learning_rate": 7.41016256408877e-06, |
| "loss": 0.4096, |
| "mean_token_accuracy": 0.870672419667244, |
| "num_tokens": 519092300.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 0.7409616202116013, |
| "epoch": 0.36572052401746724, |
| "grad_norm": 3.9375, |
| "learning_rate": 7.3323415350211035e-06, |
| "loss": 0.4065, |
| "mean_token_accuracy": 0.871986648440361, |
| "num_tokens": 526956202.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 0.7405611276626587, |
| "epoch": 0.37117903930131, |
| "grad_norm": 1.078125, |
| "learning_rate": 7.253791542552171e-06, |
| "loss": 0.4048, |
| "mean_token_accuracy": 0.8718220502138138, |
| "num_tokens": 534825720.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 0.7422936409711838, |
| "epoch": 0.37663755458515286, |
| "grad_norm": 2.6875, |
| "learning_rate": 7.1745371371471695e-06, |
| "loss": 0.4162, |
| "mean_token_accuracy": 0.870332533121109, |
| "num_tokens": 542689774.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 0.7440266788005829, |
| "epoch": 0.38209606986899564, |
| "grad_norm": 1.125, |
| "learning_rate": 7.094603089432554e-06, |
| "loss": 0.4026, |
| "mean_token_accuracy": 0.8710634887218476, |
| "num_tokens": 550546898.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 0.7456912964582443, |
| "epoch": 0.3875545851528384, |
| "grad_norm": 2.578125, |
| "learning_rate": 7.014014382454081e-06, |
| "loss": 0.4013, |
| "mean_token_accuracy": 0.869822895526886, |
| "num_tokens": 558414626.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 0.7425404369831086, |
| "epoch": 0.3930131004366812, |
| "grad_norm": 2.859375, |
| "learning_rate": 6.932796203868477e-06, |
| "loss": 0.3988, |
| "mean_token_accuracy": 0.8730183124542237, |
| "num_tokens": 566274998.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 0.7412711918354035, |
| "epoch": 0.39847161572052403, |
| "grad_norm": 0.87109375, |
| "learning_rate": 6.850973938071128e-06, |
| "loss": 0.3962, |
| "mean_token_accuracy": 0.8734320014715194, |
| "num_tokens": 574133032.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 0.7430791050195694, |
| "epoch": 0.4039301310043668, |
| "grad_norm": 2.46875, |
| "learning_rate": 6.7685731582623084e-06, |
| "loss": 0.4118, |
| "mean_token_accuracy": 0.8718510061502457, |
| "num_tokens": 582002578.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 0.744779172539711, |
| "epoch": 0.4093886462882096, |
| "grad_norm": 1.5390625, |
| "learning_rate": 6.685619618454372e-06, |
| "loss": 0.4077, |
| "mean_token_accuracy": 0.8716625690460205, |
| "num_tokens": 589865234.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 0.7440292358398437, |
| "epoch": 0.4148471615720524, |
| "grad_norm": 1.28125, |
| "learning_rate": 6.602139245422458e-06, |
| "loss": 0.4022, |
| "mean_token_accuracy": 0.8723435640335083, |
| "num_tokens": 597730534.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 0.7423117280006408, |
| "epoch": 0.4203056768558952, |
| "grad_norm": 2.71875, |
| "learning_rate": 6.518158130601188e-06, |
| "loss": 0.3945, |
| "mean_token_accuracy": 0.8720312714576721, |
| "num_tokens": 605595694.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 0.7398325890302658, |
| "epoch": 0.425764192139738, |
| "grad_norm": 0.8671875, |
| "learning_rate": 6.433702521929882e-06, |
| "loss": 0.4023, |
| "mean_token_accuracy": 0.874044144153595, |
| "num_tokens": 613453782.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 0.7427696764469147, |
| "epoch": 0.43122270742358076, |
| "grad_norm": 0.83984375, |
| "learning_rate": 6.348798815648904e-06, |
| "loss": 0.4091, |
| "mean_token_accuracy": 0.8732124745845795, |
| "num_tokens": 621320520.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 0.7425595790147781, |
| "epoch": 0.4366812227074236, |
| "grad_norm": 0.67578125, |
| "learning_rate": 6.2634735480496035e-06, |
| "loss": 0.3911, |
| "mean_token_accuracy": 0.8732421159744262, |
| "num_tokens": 629189244.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 0.7432102680206298, |
| "epoch": 0.4421397379912664, |
| "grad_norm": 1.03125, |
| "learning_rate": 6.177753387180528e-06, |
| "loss": 0.4079, |
| "mean_token_accuracy": 0.8715735673904419, |
| "num_tokens": 637061832.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 0.7431057959794998, |
| "epoch": 0.44759825327510916, |
| "grad_norm": 0.98828125, |
| "learning_rate": 6.091665124512433e-06, |
| "loss": 0.4053, |
| "mean_token_accuracy": 0.8730859875679016, |
| "num_tokens": 644924166.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 0.7412999778985977, |
| "epoch": 0.45305676855895194, |
| "grad_norm": 2.046875, |
| "learning_rate": 6.0052356665647195e-06, |
| "loss": 0.3975, |
| "mean_token_accuracy": 0.8744613200426101, |
| "num_tokens": 652790794.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 0.7394814968109131, |
| "epoch": 0.4585152838427948, |
| "grad_norm": 0.875, |
| "learning_rate": 5.918492026495918e-06, |
| "loss": 0.4016, |
| "mean_token_accuracy": 0.8731278359889985, |
| "num_tokens": 660662846.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 0.7431211411952973, |
| "epoch": 0.46397379912663755, |
| "grad_norm": 1.0078125, |
| "learning_rate": 5.831461315660843e-06, |
| "loss": 0.4068, |
| "mean_token_accuracy": 0.8717893481254577, |
| "num_tokens": 668537662.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 0.7419637799263, |
| "epoch": 0.46943231441048033, |
| "grad_norm": 1.7734375, |
| "learning_rate": 5.744170735137053e-06, |
| "loss": 0.405, |
| "mean_token_accuracy": 0.8728329062461853, |
| "num_tokens": 676404470.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 0.7394852250814438, |
| "epoch": 0.47489082969432317, |
| "grad_norm": 0.90625, |
| "learning_rate": 5.6566475672232665e-06, |
| "loss": 0.3971, |
| "mean_token_accuracy": 0.874018257856369, |
| "num_tokens": 684267358.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 0.7418612122535706, |
| "epoch": 0.48034934497816595, |
| "grad_norm": 1.4765625, |
| "learning_rate": 5.568919166912403e-06, |
| "loss": 0.3945, |
| "mean_token_accuracy": 0.8733464300632476, |
| "num_tokens": 692133098.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 0.743475404381752, |
| "epoch": 0.48580786026200873, |
| "grad_norm": 0.62109375, |
| "learning_rate": 5.481012953341891e-06, |
| "loss": 0.4053, |
| "mean_token_accuracy": 0.872043314576149, |
| "num_tokens": 699998766.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 0.7418242216110229, |
| "epoch": 0.4912663755458515, |
| "grad_norm": 0.90625, |
| "learning_rate": 5.392956401223933e-06, |
| "loss": 0.4069, |
| "mean_token_accuracy": 0.8733739018440246, |
| "num_tokens": 707860696.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 0.7420300841331482, |
| "epoch": 0.49672489082969434, |
| "grad_norm": 1.40625, |
| "learning_rate": 5.304777032258407e-06, |
| "loss": 0.393, |
| "mean_token_accuracy": 0.8732639759778976, |
| "num_tokens": 715726050.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 0.7410448163747787, |
| "epoch": 0.5021834061135371, |
| "grad_norm": 0.91015625, |
| "learning_rate": 5.21650240653107e-06, |
| "loss": 0.4004, |
| "mean_token_accuracy": 0.8743464261293411, |
| "num_tokens": 723597802.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 0.7398734450340271, |
| "epoch": 0.50764192139738, |
| "grad_norm": 1.25, |
| "learning_rate": 5.128160113899775e-06, |
| "loss": 0.3923, |
| "mean_token_accuracy": 0.8746407985687256, |
| "num_tokens": 731470234.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 0.7414282083511352, |
| "epoch": 0.5131004366812227, |
| "grad_norm": 3.0, |
| "learning_rate": 5.0397777653713775e-06, |
| "loss": 0.3814, |
| "mean_token_accuracy": 0.874212983250618, |
| "num_tokens": 739340274.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 0.7401980370283127, |
| "epoch": 0.5185589519650655, |
| "grad_norm": 1.3828125, |
| "learning_rate": 4.951382984472033e-06, |
| "loss": 0.3949, |
| "mean_token_accuracy": 0.8753201216459274, |
| "num_tokens": 747205480.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 0.7414378315210343, |
| "epoch": 0.5240174672489083, |
| "grad_norm": 1.1015625, |
| "learning_rate": 4.86300339861358e-06, |
| "loss": 0.3825, |
| "mean_token_accuracy": 0.8729045927524567, |
| "num_tokens": 755074202.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 0.7381639093160629, |
| "epoch": 0.5294759825327511, |
| "grad_norm": 0.6875, |
| "learning_rate": 4.774666630458711e-06, |
| "loss": 0.3976, |
| "mean_token_accuracy": 0.875198820233345, |
| "num_tokens": 762934560.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 0.7392808586359024, |
| "epoch": 0.5349344978165939, |
| "grad_norm": 1.1640625, |
| "learning_rate": 4.686400289287634e-06, |
| "loss": 0.3904, |
| "mean_token_accuracy": 0.8743301123380661, |
| "num_tokens": 770791148.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 0.739506584405899, |
| "epoch": 0.5403930131004366, |
| "grad_norm": 0.90234375, |
| "learning_rate": 4.598231962368897e-06, |
| "loss": 0.3959, |
| "mean_token_accuracy": 0.8746915906667709, |
| "num_tokens": 778655538.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 0.737652936577797, |
| "epoch": 0.5458515283842795, |
| "grad_norm": 1.109375, |
| "learning_rate": 4.510189206337115e-06, |
| "loss": 0.3862, |
| "mean_token_accuracy": 0.8748303711414337, |
| "num_tokens": 786523130.0, |
| "step": 1000 |
| }, |
| { |
| "entropy": 0.7382937103509903, |
| "epoch": 0.5513100436681223, |
| "grad_norm": 0.62890625, |
| "learning_rate": 4.422299538580254e-06, |
| "loss": 0.3806, |
| "mean_token_accuracy": 0.8751903176307678, |
| "num_tokens": 794381750.0, |
| "step": 1010 |
| }, |
| { |
| "entropy": 0.7428804397583008, |
| "epoch": 0.5567685589519651, |
| "grad_norm": 1.8359375, |
| "learning_rate": 4.3345904286391935e-06, |
| "loss": 0.394, |
| "mean_token_accuracy": 0.8731270760297776, |
| "num_tokens": 802240156.0, |
| "step": 1020 |
| }, |
| { |
| "entropy": 0.7401430517435074, |
| "epoch": 0.5622270742358079, |
| "grad_norm": 1.703125, |
| "learning_rate": 4.247089289622243e-06, |
| "loss": 0.3917, |
| "mean_token_accuracy": 0.8754486054182052, |
| "num_tokens": 810102422.0, |
| "step": 1030 |
| }, |
| { |
| "entropy": 0.7402924805879593, |
| "epoch": 0.5676855895196506, |
| "grad_norm": 0.7421875, |
| "learning_rate": 4.159823469637281e-06, |
| "loss": 0.38, |
| "mean_token_accuracy": 0.875374722480774, |
| "num_tokens": 817969112.0, |
| "step": 1040 |
| }, |
| { |
| "entropy": 0.7410555720329285, |
| "epoch": 0.5731441048034934, |
| "grad_norm": 0.8203125, |
| "learning_rate": 4.072820243244226e-06, |
| "loss": 0.395, |
| "mean_token_accuracy": 0.8747154682874679, |
| "num_tokens": 825833002.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 0.7426031261682511, |
| "epoch": 0.5786026200873362, |
| "grad_norm": 0.73046875, |
| "learning_rate": 3.986106802930491e-06, |
| "loss": 0.3981, |
| "mean_token_accuracy": 0.8738587260246277, |
| "num_tokens": 833690626.0, |
| "step": 1060 |
| }, |
| { |
| "entropy": 0.7397441834211349, |
| "epoch": 0.584061135371179, |
| "grad_norm": 1.171875, |
| "learning_rate": 3.8997102506120845e-06, |
| "loss": 0.3851, |
| "mean_token_accuracy": 0.8763326793909073, |
| "num_tokens": 841557350.0, |
| "step": 1070 |
| }, |
| { |
| "entropy": 0.7419826507568359, |
| "epoch": 0.5895196506550219, |
| "grad_norm": 0.72265625, |
| "learning_rate": 3.8136575891630253e-06, |
| "loss": 0.3837, |
| "mean_token_accuracy": 0.8744709640741348, |
| "num_tokens": 849428364.0, |
| "step": 1080 |
| }, |
| { |
| "entropy": 0.7412165403366089, |
| "epoch": 0.5949781659388647, |
| "grad_norm": 0.93359375, |
| "learning_rate": 3.727975713975706e-06, |
| "loss": 0.3882, |
| "mean_token_accuracy": 0.8752618104219436, |
| "num_tokens": 857296112.0, |
| "step": 1090 |
| }, |
| { |
| "entropy": 0.7414689183235168, |
| "epoch": 0.6004366812227074, |
| "grad_norm": 0.8046875, |
| "learning_rate": 3.6426914045548528e-06, |
| "loss": 0.3952, |
| "mean_token_accuracy": 0.8748543292284012, |
| "num_tokens": 865156004.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 0.7438260167837143, |
| "epoch": 0.6058951965065502, |
| "grad_norm": 0.96875, |
| "learning_rate": 3.5578313161477096e-06, |
| "loss": 0.3846, |
| "mean_token_accuracy": 0.8741238504648209, |
| "num_tokens": 873013806.0, |
| "step": 1110 |
| }, |
| { |
| "entropy": 0.7430766463279724, |
| "epoch": 0.611353711790393, |
| "grad_norm": 0.6640625, |
| "learning_rate": 3.473421971413047e-06, |
| "loss": 0.3854, |
| "mean_token_accuracy": 0.8744657546281814, |
| "num_tokens": 880878266.0, |
| "step": 1120 |
| }, |
| { |
| "entropy": 0.7424992769956589, |
| "epoch": 0.6168122270742358, |
| "grad_norm": 1.265625, |
| "learning_rate": 3.38948975213163e-06, |
| "loss": 0.3791, |
| "mean_token_accuracy": 0.8751037955284119, |
| "num_tokens": 888749520.0, |
| "step": 1130 |
| }, |
| { |
| "entropy": 0.7424061298370361, |
| "epoch": 0.6222707423580786, |
| "grad_norm": 1.3671875, |
| "learning_rate": 3.306060890960692e-06, |
| "loss": 0.3896, |
| "mean_token_accuracy": 0.8747448861598969, |
| "num_tokens": 896613382.0, |
| "step": 1140 |
| }, |
| { |
| "entropy": 0.7466125965118409, |
| "epoch": 0.6277292576419214, |
| "grad_norm": 1.3359375, |
| "learning_rate": 3.223161463235035e-06, |
| "loss": 0.3862, |
| "mean_token_accuracy": 0.8735823392868042, |
| "num_tokens": 904473860.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 0.7452135056257247, |
| "epoch": 0.6331877729257642, |
| "grad_norm": 0.64453125, |
| "learning_rate": 3.1408173788173015e-06, |
| "loss": 0.3979, |
| "mean_token_accuracy": 0.8739745587110519, |
| "num_tokens": 912345842.0, |
| "step": 1160 |
| }, |
| { |
| "entropy": 0.7459590375423432, |
| "epoch": 0.638646288209607, |
| "grad_norm": 0.74609375, |
| "learning_rate": 3.059054373999942e-06, |
| "loss": 0.398, |
| "mean_token_accuracy": 0.8739953517913819, |
| "num_tokens": 920213660.0, |
| "step": 1170 |
| }, |
| { |
| "entropy": 0.7454611182212829, |
| "epoch": 0.6441048034934498, |
| "grad_norm": 0.7890625, |
| "learning_rate": 2.9778980034614635e-06, |
| "loss": 0.3969, |
| "mean_token_accuracy": 0.8728385120630264, |
| "num_tokens": 928074534.0, |
| "step": 1180 |
| }, |
| { |
| "entropy": 0.7428855746984482, |
| "epoch": 0.6495633187772926, |
| "grad_norm": 1.7109375, |
| "learning_rate": 2.8973736322794134e-06, |
| "loss": 0.3808, |
| "mean_token_accuracy": 0.8749400556087494, |
| "num_tokens": 935930082.0, |
| "step": 1190 |
| }, |
| { |
| "entropy": 0.7424870818853379, |
| "epoch": 0.6550218340611353, |
| "grad_norm": 0.90625, |
| "learning_rate": 2.8175064280026344e-06, |
| "loss": 0.3979, |
| "mean_token_accuracy": 0.8748441934585571, |
| "num_tokens": 943801142.0, |
| "step": 1200 |
| }, |
| { |
| "entropy": 0.7410305082798004, |
| "epoch": 0.6604803493449781, |
| "grad_norm": 0.87890625, |
| "learning_rate": 2.738321352785254e-06, |
| "loss": 0.3828, |
| "mean_token_accuracy": 0.8764384746551513, |
| "num_tokens": 951668790.0, |
| "step": 1210 |
| }, |
| { |
| "entropy": 0.7426535874605179, |
| "epoch": 0.665938864628821, |
| "grad_norm": 0.9375, |
| "learning_rate": 2.659843155584874e-06, |
| "loss": 0.3956, |
| "mean_token_accuracy": 0.8743496358394622, |
| "num_tokens": 959533058.0, |
| "step": 1220 |
| }, |
| { |
| "entropy": 0.7412624359130859, |
| "epoch": 0.6713973799126638, |
| "grad_norm": 0.7109375, |
| "learning_rate": 2.5820963644273867e-06, |
| "loss": 0.3846, |
| "mean_token_accuracy": 0.8750651776790619, |
| "num_tokens": 967391844.0, |
| "step": 1230 |
| }, |
| { |
| "entropy": 0.7417336344718933, |
| "epoch": 0.6768558951965066, |
| "grad_norm": 0.6953125, |
| "learning_rate": 2.5051052787408415e-06, |
| "loss": 0.4046, |
| "mean_token_accuracy": 0.8743031829595566, |
| "num_tokens": 975262708.0, |
| "step": 1240 |
| }, |
| { |
| "entropy": 0.7430081754922867, |
| "epoch": 0.6823144104803494, |
| "grad_norm": 0.89453125, |
| "learning_rate": 2.4288939617607632e-06, |
| "loss": 0.3763, |
| "mean_token_accuracy": 0.873823493719101, |
| "num_tokens": 983128708.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 0.7428836464881897, |
| "epoch": 0.6877729257641921, |
| "grad_norm": 0.6328125, |
| "learning_rate": 2.353486233009301e-06, |
| "loss": 0.3944, |
| "mean_token_accuracy": 0.8746105074882508, |
| "num_tokens": 990985896.0, |
| "step": 1260 |
| }, |
| { |
| "entropy": 0.7428994864225388, |
| "epoch": 0.6932314410480349, |
| "grad_norm": 1.390625, |
| "learning_rate": 2.27890566085052e-06, |
| "loss": 0.3913, |
| "mean_token_accuracy": 0.8748791068792343, |
| "num_tokens": 998843880.0, |
| "step": 1270 |
| }, |
| { |
| "entropy": 0.7413315206766129, |
| "epoch": 0.6986899563318777, |
| "grad_norm": 0.69140625, |
| "learning_rate": 2.205175555124228e-06, |
| "loss": 0.3863, |
| "mean_token_accuracy": 0.87540702521801, |
| "num_tokens": 1006713580.0, |
| "step": 1280 |
| }, |
| { |
| "entropy": 0.741332420706749, |
| "epoch": 0.7041484716157205, |
| "grad_norm": 0.984375, |
| "learning_rate": 2.1323189598605687e-06, |
| "loss": 0.3813, |
| "mean_token_accuracy": 0.8754213988780976, |
| "num_tokens": 1014581600.0, |
| "step": 1290 |
| }, |
| { |
| "entropy": 0.7419189482927322, |
| "epoch": 0.7096069868995634, |
| "grad_norm": 1.1015625, |
| "learning_rate": 2.0603586460777215e-06, |
| "loss": 0.3827, |
| "mean_token_accuracy": 0.8748749196529388, |
| "num_tokens": 1022449292.0, |
| "step": 1300 |
| }, |
| { |
| "entropy": 0.7426786899566651, |
| "epoch": 0.7150655021834061, |
| "grad_norm": 1.2578125, |
| "learning_rate": 1.989317104664907e-06, |
| "loss": 0.3986, |
| "mean_token_accuracy": 0.8742215305566787, |
| "num_tokens": 1030306366.0, |
| "step": 1310 |
| }, |
| { |
| "entropy": 0.7427356332540512, |
| "epoch": 0.7205240174672489, |
| "grad_norm": 0.90234375, |
| "learning_rate": 1.9192165393529584e-06, |
| "loss": 0.3891, |
| "mean_token_accuracy": 0.8744012355804444, |
| "num_tokens": 1038174306.0, |
| "step": 1320 |
| }, |
| { |
| "entropy": 0.7432858228683472, |
| "epoch": 0.7259825327510917, |
| "grad_norm": 1.1015625, |
| "learning_rate": 1.8500788597746444e-06, |
| "loss": 0.3955, |
| "mean_token_accuracy": 0.8737243920564651, |
| "num_tokens": 1046038572.0, |
| "step": 1330 |
| }, |
| { |
| "entropy": 0.7421870291233063, |
| "epoch": 0.7314410480349345, |
| "grad_norm": 0.6875, |
| "learning_rate": 1.7819256746169051e-06, |
| "loss": 0.3833, |
| "mean_token_accuracy": 0.8757769674062729, |
| "num_tokens": 1053903468.0, |
| "step": 1340 |
| }, |
| { |
| "entropy": 0.7417985558509826, |
| "epoch": 0.7368995633187773, |
| "grad_norm": 0.87109375, |
| "learning_rate": 1.7147782848671412e-06, |
| "loss": 0.3833, |
| "mean_token_accuracy": 0.8752977877855301, |
| "num_tokens": 1061776998.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 0.7430289268493653, |
| "epoch": 0.74235807860262, |
| "grad_norm": 0.9609375, |
| "learning_rate": 1.648657677155691e-06, |
| "loss": 0.3851, |
| "mean_token_accuracy": 0.8745603919029236, |
| "num_tokens": 1069637602.0, |
| "step": 1360 |
| }, |
| { |
| "entropy": 0.7432134211063385, |
| "epoch": 0.7478165938864629, |
| "grad_norm": 0.6796875, |
| "learning_rate": 1.5835845171965464e-06, |
| "loss": 0.3931, |
| "mean_token_accuracy": 0.8747707784175873, |
| "num_tokens": 1077501978.0, |
| "step": 1370 |
| }, |
| { |
| "entropy": 0.742434960603714, |
| "epoch": 0.7532751091703057, |
| "grad_norm": 1.1796875, |
| "learning_rate": 1.5195791433283702e-06, |
| "loss": 0.3796, |
| "mean_token_accuracy": 0.8753932148218155, |
| "num_tokens": 1085366906.0, |
| "step": 1380 |
| }, |
| { |
| "entropy": 0.7430311769247055, |
| "epoch": 0.7587336244541485, |
| "grad_norm": 1.3125, |
| "learning_rate": 1.4566615601578326e-06, |
| "loss": 0.3884, |
| "mean_token_accuracy": 0.8746572107076644, |
| "num_tokens": 1093230380.0, |
| "step": 1390 |
| }, |
| { |
| "entropy": 0.7433284431695938, |
| "epoch": 0.7641921397379913, |
| "grad_norm": 0.671875, |
| "learning_rate": 1.3948514323072654e-06, |
| "loss": 0.3886, |
| "mean_token_accuracy": 0.8729349434375763, |
| "num_tokens": 1101095000.0, |
| "step": 1400 |
| }, |
| { |
| "entropy": 0.7436177790164947, |
| "epoch": 0.769650655021834, |
| "grad_norm": 0.76171875, |
| "learning_rate": 1.3341680782685574e-06, |
| "loss": 0.3918, |
| "mean_token_accuracy": 0.8735940039157868, |
| "num_tokens": 1108962808.0, |
| "step": 1410 |
| }, |
| { |
| "entropy": 0.7442159414291382, |
| "epoch": 0.7751091703056768, |
| "grad_norm": 0.828125, |
| "learning_rate": 1.2746304643652485e-06, |
| "loss": 0.4007, |
| "mean_token_accuracy": 0.873666587471962, |
| "num_tokens": 1116829358.0, |
| "step": 1420 |
| }, |
| { |
| "entropy": 0.7438120782375336, |
| "epoch": 0.7805676855895196, |
| "grad_norm": 0.71875, |
| "learning_rate": 1.2162571988246834e-06, |
| "loss": 0.3976, |
| "mean_token_accuracy": 0.8736205577850342, |
| "num_tokens": 1124693428.0, |
| "step": 1430 |
| }, |
| { |
| "entropy": 0.7424930274486542, |
| "epoch": 0.7860262008733624, |
| "grad_norm": 0.78125, |
| "learning_rate": 1.1590665259620993e-06, |
| "loss": 0.3842, |
| "mean_token_accuracy": 0.8745506823062896, |
| "num_tokens": 1132557916.0, |
| "step": 1440 |
| }, |
| { |
| "entropy": 0.7446203082799911, |
| "epoch": 0.7914847161572053, |
| "grad_norm": 0.84375, |
| "learning_rate": 1.1030763204784251e-06, |
| "loss": 0.3917, |
| "mean_token_accuracy": 0.8729688644409179, |
| "num_tokens": 1140430412.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 0.7433162957429886, |
| "epoch": 0.7969432314410481, |
| "grad_norm": 0.46484375, |
| "learning_rate": 1.0483040818736318e-06, |
| "loss": 0.3803, |
| "mean_token_accuracy": 0.8738045871257782, |
| "num_tokens": 1148291328.0, |
| "step": 1460 |
| }, |
| { |
| "entropy": 0.7410401582717896, |
| "epoch": 0.8024017467248908, |
| "grad_norm": 1.40625, |
| "learning_rate": 9.947669289773393e-07, |
| "loss": 0.3838, |
| "mean_token_accuracy": 0.8753872156143189, |
| "num_tokens": 1156167482.0, |
| "step": 1470 |
| }, |
| { |
| "entropy": 0.742080283164978, |
| "epoch": 0.8078602620087336, |
| "grad_norm": 0.75390625, |
| "learning_rate": 9.424815945983917e-07, |
| "loss": 0.3867, |
| "mean_token_accuracy": 0.8751390099525451, |
| "num_tokens": 1164025554.0, |
| "step": 1480 |
| }, |
| { |
| "entropy": 0.7427247047424317, |
| "epoch": 0.8133187772925764, |
| "grad_norm": 0.6015625, |
| "learning_rate": 8.914644202950972e-07, |
| "loss": 0.3832, |
| "mean_token_accuracy": 0.8736295759677887, |
| "num_tokens": 1171898796.0, |
| "step": 1490 |
| }, |
| { |
| "entropy": 0.7434464186429978, |
| "epoch": 0.8187772925764192, |
| "grad_norm": 0.671875, |
| "learning_rate": 8.417313512677372e-07, |
| "loss": 0.3763, |
| "mean_token_accuracy": 0.8743604719638824, |
| "num_tokens": 1179763240.0, |
| "step": 1500 |
| }, |
| { |
| "entropy": 0.7422494500875473, |
| "epoch": 0.824235807860262, |
| "grad_norm": 0.68359375, |
| "learning_rate": 7.932979313749667e-07, |
| "loss": 0.3842, |
| "mean_token_accuracy": 0.8736101686954498, |
| "num_tokens": 1187625898.0, |
| "step": 1510 |
| }, |
| { |
| "entropy": 0.7422716528177261, |
| "epoch": 0.8296943231441049, |
| "grad_norm": 1.0546875, |
| "learning_rate": 7.461792982756443e-07, |
| "loss": 0.3958, |
| "mean_token_accuracy": 0.8738951504230499, |
| "num_tokens": 1195493530.0, |
| "step": 1520 |
| }, |
| { |
| "entropy": 0.7435609191656113, |
| "epoch": 0.8351528384279476, |
| "grad_norm": 0.61328125, |
| "learning_rate": 7.003901786976225e-07, |
| "loss": 0.38, |
| "mean_token_accuracy": 0.8739309489727021, |
| "num_tokens": 1203353814.0, |
| "step": 1530 |
| }, |
| { |
| "entropy": 0.7422756880521775, |
| "epoch": 0.8406113537117904, |
| "grad_norm": 0.74609375, |
| "learning_rate": 6.559448838349735e-07, |
| "loss": 0.3851, |
| "mean_token_accuracy": 0.8749569296836853, |
| "num_tokens": 1211227998.0, |
| "step": 1540 |
| }, |
| { |
| "entropy": 0.7427633851766586, |
| "epoch": 0.8460698689956332, |
| "grad_norm": 0.8125, |
| "learning_rate": 6.128573048750847e-07, |
| "loss": 0.3856, |
| "mean_token_accuracy": 0.8736144304275513, |
| "num_tokens": 1219091732.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 0.7434135794639587, |
| "epoch": 0.851528384279476, |
| "grad_norm": 0.58984375, |
| "learning_rate": 5.711409086570274e-07, |
| "loss": 0.3886, |
| "mean_token_accuracy": 0.8741229772567749, |
| "num_tokens": 1226953726.0, |
| "step": 1560 |
| }, |
| { |
| "entropy": 0.7427491456270218, |
| "epoch": 0.8569868995633187, |
| "grad_norm": 1.171875, |
| "learning_rate": 5.308087334625511e-07, |
| "loss": 0.3911, |
| "mean_token_accuracy": 0.8744769752025604, |
| "num_tokens": 1234815036.0, |
| "step": 1570 |
| }, |
| { |
| "entropy": 0.7418983399868011, |
| "epoch": 0.8624454148471615, |
| "grad_norm": 0.609375, |
| "learning_rate": 4.918733849410323e-07, |
| "loss": 0.3802, |
| "mean_token_accuracy": 0.8741312026977539, |
| "num_tokens": 1242684150.0, |
| "step": 1580 |
| }, |
| { |
| "entropy": 0.7432045787572861, |
| "epoch": 0.8679039301310044, |
| "grad_norm": 0.77734375, |
| "learning_rate": 4.543470321696236e-07, |
| "loss": 0.3889, |
| "mean_token_accuracy": 0.8745778888463974, |
| "num_tokens": 1250549962.0, |
| "step": 1590 |
| }, |
| { |
| "entropy": 0.74481041431427, |
| "epoch": 0.8733624454148472, |
| "grad_norm": 0.6953125, |
| "learning_rate": 4.1824140384986503e-07, |
| "loss": 0.3886, |
| "mean_token_accuracy": 0.8733837962150574, |
| "num_tokens": 1258406108.0, |
| "step": 1600 |
| }, |
| { |
| "entropy": 0.7427057713270188, |
| "epoch": 0.87882096069869, |
| "grad_norm": 0.74609375, |
| "learning_rate": 3.8356778464192614e-07, |
| "loss": 0.4, |
| "mean_token_accuracy": 0.8739647537469863, |
| "num_tokens": 1266273152.0, |
| "step": 1610 |
| }, |
| { |
| "entropy": 0.744545865058899, |
| "epoch": 0.8842794759825328, |
| "grad_norm": 0.6328125, |
| "learning_rate": 3.5033701163763757e-07, |
| "loss": 0.3923, |
| "mean_token_accuracy": 0.8734740257263184, |
| "num_tokens": 1274139484.0, |
| "step": 1620 |
| }, |
| { |
| "entropy": 0.7441187381744385, |
| "epoch": 0.8897379912663755, |
| "grad_norm": 0.71875, |
| "learning_rate": 3.1855947097339914e-07, |
| "loss": 0.3999, |
| "mean_token_accuracy": 0.873001080751419, |
| "num_tokens": 1282008842.0, |
| "step": 1630 |
| }, |
| { |
| "entropy": 0.7436953485012054, |
| "epoch": 0.8951965065502183, |
| "grad_norm": 0.76171875, |
| "learning_rate": 2.882450945840409e-07, |
| "loss": 0.3941, |
| "mean_token_accuracy": 0.8738514393568039, |
| "num_tokens": 1289875314.0, |
| "step": 1640 |
| }, |
| { |
| "entropy": 0.7423629492521286, |
| "epoch": 0.9006550218340611, |
| "grad_norm": 0.73046875, |
| "learning_rate": 2.5940335709863816e-07, |
| "loss": 0.386, |
| "mean_token_accuracy": 0.8746936202049256, |
| "num_tokens": 1297748728.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 0.7432297259569168, |
| "epoch": 0.9061135371179039, |
| "grad_norm": 0.7421875, |
| "learning_rate": 2.3204327287925542e-07, |
| "loss": 0.3879, |
| "mean_token_accuracy": 0.8750167161226272, |
| "num_tokens": 1305609784.0, |
| "step": 1660 |
| }, |
| { |
| "entropy": 0.7419020563364029, |
| "epoch": 0.9115720524017468, |
| "grad_norm": 0.765625, |
| "learning_rate": 2.0617339320354646e-07, |
| "loss": 0.3903, |
| "mean_token_accuracy": 0.8754764199256897, |
| "num_tokens": 1313475844.0, |
| "step": 1670 |
| }, |
| { |
| "entropy": 0.7424279659986496, |
| "epoch": 0.9170305676855895, |
| "grad_norm": 0.84375, |
| "learning_rate": 1.81801803592091e-07, |
| "loss": 0.3878, |
| "mean_token_accuracy": 0.8746344208717346, |
| "num_tokens": 1321340470.0, |
| "step": 1680 |
| }, |
| { |
| "entropy": 0.7409710973501206, |
| "epoch": 0.9224890829694323, |
| "grad_norm": 0.6796875, |
| "learning_rate": 1.5893612128129843e-07, |
| "loss": 0.3846, |
| "mean_token_accuracy": 0.8754217594861984, |
| "num_tokens": 1329199550.0, |
| "step": 1690 |
| }, |
| { |
| "entropy": 0.7412744700908661, |
| "epoch": 0.9279475982532751, |
| "grad_norm": 0.62890625, |
| "learning_rate": 1.3758349284267058e-07, |
| "loss": 0.3893, |
| "mean_token_accuracy": 0.8758824586868286, |
| "num_tokens": 1337064502.0, |
| "step": 1700 |
| }, |
| { |
| "entropy": 0.7443627923727035, |
| "epoch": 0.9334061135371179, |
| "grad_norm": 0.70703125, |
| "learning_rate": 1.1775059194917504e-07, |
| "loss": 0.387, |
| "mean_token_accuracy": 0.8735955387353898, |
| "num_tokens": 1344931426.0, |
| "step": 1710 |
| }, |
| { |
| "entropy": 0.7438138067722321, |
| "epoch": 0.9388646288209607, |
| "grad_norm": 0.6953125, |
| "learning_rate": 9.944361728941532e-08, |
| "loss": 0.3972, |
| "mean_token_accuracy": 0.8743302762508393, |
| "num_tokens": 1352791680.0, |
| "step": 1720 |
| }, |
| { |
| "entropy": 0.7403326630592346, |
| "epoch": 0.9443231441048034, |
| "grad_norm": 0.90625, |
| "learning_rate": 8.266829063025672e-08, |
| "loss": 0.3928, |
| "mean_token_accuracy": 0.8761739164590836, |
| "num_tokens": 1360659130.0, |
| "step": 1730 |
| }, |
| { |
| "entropy": 0.7423051565885543, |
| "epoch": 0.9497816593886463, |
| "grad_norm": 0.6875, |
| "learning_rate": 6.742985502851407e-08, |
| "loss": 0.3916, |
| "mean_token_accuracy": 0.8752289861440659, |
| "num_tokens": 1368518210.0, |
| "step": 1740 |
| }, |
| { |
| "entropy": 0.742406964302063, |
| "epoch": 0.9552401746724891, |
| "grad_norm": 0.765625, |
| "learning_rate": 5.373307319225529e-08, |
| "loss": 0.3908, |
| "mean_token_accuracy": 0.8748453021049499, |
| "num_tokens": 1376390268.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 0.743376687169075, |
| "epoch": 0.9606986899563319, |
| "grad_norm": 0.8828125, |
| "learning_rate": 4.158222599223827e-08, |
| "loss": 0.3842, |
| "mean_token_accuracy": 0.874573078751564, |
| "num_tokens": 1384261402.0, |
| "step": 1760 |
| }, |
| { |
| "entropy": 0.7422017276287078, |
| "epoch": 0.9661572052401747, |
| "grad_norm": 0.61328125, |
| "learning_rate": 3.098111112394164e-08, |
| "loss": 0.3949, |
| "mean_token_accuracy": 0.8753235667943955, |
| "num_tokens": 1392125720.0, |
| "step": 1770 |
| }, |
| { |
| "entropy": 0.7448121666908264, |
| "epoch": 0.9716157205240175, |
| "grad_norm": 0.56640625, |
| "learning_rate": 2.193304192061263e-08, |
| "loss": 0.3952, |
| "mean_token_accuracy": 0.8734730213880539, |
| "num_tokens": 1399984364.0, |
| "step": 1780 |
| }, |
| { |
| "entropy": 0.743220853805542, |
| "epoch": 0.9770742358078602, |
| "grad_norm": 0.54296875, |
| "learning_rate": 1.44408463176976e-08, |
| "loss": 0.3863, |
| "mean_token_accuracy": 0.8741205990314483, |
| "num_tokens": 1407851382.0, |
| "step": 1790 |
| }, |
| { |
| "entropy": 0.7465447574853897, |
| "epoch": 0.982532751091703, |
| "grad_norm": 0.85546875, |
| "learning_rate": 8.506865968985756e-09, |
| "loss": 0.3951, |
| "mean_token_accuracy": 0.8725526750087738, |
| "num_tokens": 1415715356.0, |
| "step": 1800 |
| }, |
| { |
| "entropy": 0.7446548283100128, |
| "epoch": 0.9879912663755459, |
| "grad_norm": 0.578125, |
| "learning_rate": 4.1329555147301416e-09, |
| "loss": 0.3898, |
| "mean_token_accuracy": 0.8753064006567002, |
| "num_tokens": 1423565254.0, |
| "step": 1810 |
| }, |
| { |
| "entropy": 0.7455879837274552, |
| "epoch": 0.9934497816593887, |
| "grad_norm": 0.67578125, |
| "learning_rate": 1.3204820019924181e-09, |
| "loss": 0.4045, |
| "mean_token_accuracy": 0.8725648373365402, |
| "num_tokens": 1431437384.0, |
| "step": 1820 |
| }, |
| { |
| "entropy": 0.7449402421712875, |
| "epoch": 0.9989082969432315, |
| "grad_norm": 0.63671875, |
| "learning_rate": 7.03244573768691e-11, |
| "loss": 0.3904, |
| "mean_token_accuracy": 0.8746490359306336, |
| "num_tokens": 1439301400.0, |
| "step": 1830 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 1832, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.794652359511507e+19, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
