| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 3030, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0049517207229512255, | |
| "grad_norm": 4.494762897491455, | |
| "learning_rate": 5.263157894736843e-07, | |
| "loss": 1.0863, | |
| "mean_token_accuracy": 0.7343291759490966, | |
| "num_tokens": 10417883.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009903441445902451, | |
| "grad_norm": 3.2665634155273438, | |
| "learning_rate": 1.1842105263157894e-06, | |
| "loss": 1.076, | |
| "mean_token_accuracy": 0.7338468879461288, | |
| "num_tokens": 20806975.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014855162168853677, | |
| "grad_norm": 1.024572491645813, | |
| "learning_rate": 1.8421052631578948e-06, | |
| "loss": 1.0287, | |
| "mean_token_accuracy": 0.7371937811374665, | |
| "num_tokens": 31224276.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.019806882891804902, | |
| "grad_norm": 1.0827839374542236, | |
| "learning_rate": 2.5e-06, | |
| "loss": 0.994, | |
| "mean_token_accuracy": 0.7427578687667846, | |
| "num_tokens": 41600322.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02475860361475613, | |
| "grad_norm": 0.7391007542610168, | |
| "learning_rate": 3.157894736842105e-06, | |
| "loss": 0.9706, | |
| "mean_token_accuracy": 0.7464866191148758, | |
| "num_tokens": 51996625.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029710324337707355, | |
| "grad_norm": 0.4652908146381378, | |
| "learning_rate": 3.815789473684211e-06, | |
| "loss": 0.9541, | |
| "mean_token_accuracy": 0.7493666768074035, | |
| "num_tokens": 62376576.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03466204506065858, | |
| "grad_norm": 0.3708527982234955, | |
| "learning_rate": 4.473684210526316e-06, | |
| "loss": 0.9459, | |
| "mean_token_accuracy": 0.7504437863826752, | |
| "num_tokens": 72739525.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.039613765783609804, | |
| "grad_norm": 0.3008730709552765, | |
| "learning_rate": 5.131578947368422e-06, | |
| "loss": 0.9541, | |
| "mean_token_accuracy": 0.7509326428174973, | |
| "num_tokens": 83158379.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04456548650656103, | |
| "grad_norm": 12.92960262298584, | |
| "learning_rate": 5.789473684210527e-06, | |
| "loss": 0.9527, | |
| "mean_token_accuracy": 0.7486720085144043, | |
| "num_tokens": 93561279.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04951720722951226, | |
| "grad_norm": 0.2265157252550125, | |
| "learning_rate": 6.447368421052632e-06, | |
| "loss": 0.9215, | |
| "mean_token_accuracy": 0.7535740584135056, | |
| "num_tokens": 103975900.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05446892795246348, | |
| "grad_norm": 0.22998610138893127, | |
| "learning_rate": 7.1052631578947375e-06, | |
| "loss": 0.9193, | |
| "mean_token_accuracy": 0.7536993026733398, | |
| "num_tokens": 114358295.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05942064867541471, | |
| "grad_norm": 0.20382240414619446, | |
| "learning_rate": 7.763157894736843e-06, | |
| "loss": 0.8993, | |
| "mean_token_accuracy": 0.758358484506607, | |
| "num_tokens": 124741874.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06437236939836594, | |
| "grad_norm": 0.20741654932498932, | |
| "learning_rate": 8.421052631578948e-06, | |
| "loss": 0.8847, | |
| "mean_token_accuracy": 0.7618912905454636, | |
| "num_tokens": 135125198.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06932409012131716, | |
| "grad_norm": 0.19601891934871674, | |
| "learning_rate": 9.078947368421054e-06, | |
| "loss": 0.8754, | |
| "mean_token_accuracy": 0.7635368853807449, | |
| "num_tokens": 145516638.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07427581084426839, | |
| "grad_norm": 0.1902785450220108, | |
| "learning_rate": 9.736842105263159e-06, | |
| "loss": 0.8702, | |
| "mean_token_accuracy": 0.7641876369714737, | |
| "num_tokens": 155902199.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07922753156721961, | |
| "grad_norm": 0.21357858180999756, | |
| "learning_rate": 1.0394736842105264e-05, | |
| "loss": 0.8855, | |
| "mean_token_accuracy": 0.7601119011640549, | |
| "num_tokens": 166260992.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08417925229017083, | |
| "grad_norm": 0.21855609118938446, | |
| "learning_rate": 1.105263157894737e-05, | |
| "loss": 0.8808, | |
| "mean_token_accuracy": 0.7608364224433899, | |
| "num_tokens": 176655378.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.08913097301312206, | |
| "grad_norm": 0.22869279980659485, | |
| "learning_rate": 1.1710526315789475e-05, | |
| "loss": 0.8838, | |
| "mean_token_accuracy": 0.7606816172599793, | |
| "num_tokens": 187049412.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09408269373607328, | |
| "grad_norm": 0.21363244950771332, | |
| "learning_rate": 1.236842105263158e-05, | |
| "loss": 0.8668, | |
| "mean_token_accuracy": 0.7635636687278747, | |
| "num_tokens": 197428098.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.09903441445902451, | |
| "grad_norm": 0.2309870570898056, | |
| "learning_rate": 1.3026315789473684e-05, | |
| "loss": 0.8568, | |
| "mean_token_accuracy": 0.7659854501485824, | |
| "num_tokens": 207818677.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10398613518197573, | |
| "grad_norm": 0.23947252333164215, | |
| "learning_rate": 1.3684210526315791e-05, | |
| "loss": 0.8636, | |
| "mean_token_accuracy": 0.7642275482416153, | |
| "num_tokens": 218213873.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.10893785590492697, | |
| "grad_norm": 0.247147336602211, | |
| "learning_rate": 1.4342105263157895e-05, | |
| "loss": 0.8585, | |
| "mean_token_accuracy": 0.7652702659368515, | |
| "num_tokens": 228635598.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11388957662787819, | |
| "grad_norm": 0.2094859629869461, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 0.8672, | |
| "mean_token_accuracy": 0.7633111596107482, | |
| "num_tokens": 239063783.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.11884129735082942, | |
| "grad_norm": 0.33069688081741333, | |
| "learning_rate": 1.5657894736842107e-05, | |
| "loss": 0.8528, | |
| "mean_token_accuracy": 0.7691669374704361, | |
| "num_tokens": 249470214.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12379301807378064, | |
| "grad_norm": 0.2780938446521759, | |
| "learning_rate": 1.6315789473684213e-05, | |
| "loss": 0.8464, | |
| "mean_token_accuracy": 0.7677050292491913, | |
| "num_tokens": 259887336.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.12874473879673187, | |
| "grad_norm": 0.22850839793682098, | |
| "learning_rate": 1.6973684210526318e-05, | |
| "loss": 0.8364, | |
| "mean_token_accuracy": 0.7698385208845139, | |
| "num_tokens": 270284999.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1336964595196831, | |
| "grad_norm": 0.2590622305870056, | |
| "learning_rate": 1.763157894736842e-05, | |
| "loss": 0.8543, | |
| "mean_token_accuracy": 0.764978775382042, | |
| "num_tokens": 280680904.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.1386481802426343, | |
| "grad_norm": 0.21655666828155518, | |
| "learning_rate": 1.828947368421053e-05, | |
| "loss": 0.8441, | |
| "mean_token_accuracy": 0.7674482077360153, | |
| "num_tokens": 291077727.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14359990096558553, | |
| "grad_norm": 0.27917516231536865, | |
| "learning_rate": 1.894736842105263e-05, | |
| "loss": 0.8314, | |
| "mean_token_accuracy": 0.7709874927997589, | |
| "num_tokens": 301498523.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.14855162168853678, | |
| "grad_norm": 0.2864488661289215, | |
| "learning_rate": 1.960526315789474e-05, | |
| "loss": 0.8347, | |
| "mean_token_accuracy": 0.769895127415657, | |
| "num_tokens": 311908148.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.153503342411488, | |
| "grad_norm": 0.24762648344039917, | |
| "learning_rate": 1.9999982126514483e-05, | |
| "loss": 0.8387, | |
| "mean_token_accuracy": 0.7687274873256683, | |
| "num_tokens": 322322809.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.15845506313443922, | |
| "grad_norm": 0.23356765508651733, | |
| "learning_rate": 1.9999781050780763e-05, | |
| "loss": 0.8111, | |
| "mean_token_accuracy": 0.7753471970558167, | |
| "num_tokens": 332741557.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16340678385739044, | |
| "grad_norm": 0.22937612235546112, | |
| "learning_rate": 1.999935656346626e-05, | |
| "loss": 0.8395, | |
| "mean_token_accuracy": 0.7681750059127808, | |
| "num_tokens": 343139709.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.16835850458034166, | |
| "grad_norm": 0.23504067957401276, | |
| "learning_rate": 1.999870867721605e-05, | |
| "loss": 0.8159, | |
| "mean_token_accuracy": 0.7737643718719482, | |
| "num_tokens": 353571629.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1733102253032929, | |
| "grad_norm": 0.2992646396160126, | |
| "learning_rate": 1.9997837411330073e-05, | |
| "loss": 0.8384, | |
| "mean_token_accuracy": 0.7703067153692246, | |
| "num_tokens": 363981542.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.17826194602624412, | |
| "grad_norm": 0.2727688252925873, | |
| "learning_rate": 1.999674279176254e-05, | |
| "loss": 0.8161, | |
| "mean_token_accuracy": 0.7731374055147171, | |
| "num_tokens": 374352478.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.18321366674919534, | |
| "grad_norm": 0.3550196886062622, | |
| "learning_rate": 1.9995424851121163e-05, | |
| "loss": 0.8287, | |
| "mean_token_accuracy": 0.7716741412878036, | |
| "num_tokens": 384752657.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.18816538747214656, | |
| "grad_norm": 0.2896004319190979, | |
| "learning_rate": 1.999388362866618e-05, | |
| "loss": 0.8149, | |
| "mean_token_accuracy": 0.7733279794454575, | |
| "num_tokens": 395152658.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1931171081950978, | |
| "grad_norm": 0.26007845997810364, | |
| "learning_rate": 1.9992119170309188e-05, | |
| "loss": 0.8236, | |
| "mean_token_accuracy": 0.7709115266799926, | |
| "num_tokens": 405574496.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.19806882891804903, | |
| "grad_norm": 0.2737730145454407, | |
| "learning_rate": 1.9990131528611783e-05, | |
| "loss": 0.8064, | |
| "mean_token_accuracy": 0.7754090011119843, | |
| "num_tokens": 415954581.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.20302054964100025, | |
| "grad_norm": 0.2782779037952423, | |
| "learning_rate": 1.9987920762783978e-05, | |
| "loss": 0.8066, | |
| "mean_token_accuracy": 0.7754531413316726, | |
| "num_tokens": 426347583.0, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.20797227036395147, | |
| "grad_norm": 0.2829101085662842, | |
| "learning_rate": 1.998548693868246e-05, | |
| "loss": 0.8159, | |
| "mean_token_accuracy": 0.7728827208280563, | |
| "num_tokens": 436775593.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2129239910869027, | |
| "grad_norm": 0.25524118542671204, | |
| "learning_rate": 1.998283012880861e-05, | |
| "loss": 0.8112, | |
| "mean_token_accuracy": 0.7736958414316177, | |
| "num_tokens": 447193940.0, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.21787571180985393, | |
| "grad_norm": 0.25364068150520325, | |
| "learning_rate": 1.9979950412306347e-05, | |
| "loss": 0.8159, | |
| "mean_token_accuracy": 0.7723533689975739, | |
| "num_tokens": 457607812.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.22282743253280515, | |
| "grad_norm": 0.23794567584991455, | |
| "learning_rate": 1.9976847874959783e-05, | |
| "loss": 0.815, | |
| "mean_token_accuracy": 0.772477874159813, | |
| "num_tokens": 468019473.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.22777915325575637, | |
| "grad_norm": 0.20496641099452972, | |
| "learning_rate": 1.9973522609190644e-05, | |
| "loss": 0.8244, | |
| "mean_token_accuracy": 0.7698849588632584, | |
| "num_tokens": 478428340.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2327308739787076, | |
| "grad_norm": 0.20776529610157013, | |
| "learning_rate": 1.996997471405555e-05, | |
| "loss": 0.7983, | |
| "mean_token_accuracy": 0.7768283516168595, | |
| "num_tokens": 488823476.0, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.23768259470165884, | |
| "grad_norm": 0.21405838429927826, | |
| "learning_rate": 1.9966204295243027e-05, | |
| "loss": 0.8111, | |
| "mean_token_accuracy": 0.7732695490121841, | |
| "num_tokens": 499220039.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.24263431542461006, | |
| "grad_norm": 0.27764108777046204, | |
| "learning_rate": 1.9962211465070386e-05, | |
| "loss": 0.824, | |
| "mean_token_accuracy": 0.7728296130895614, | |
| "num_tokens": 509612333.0, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.24758603614756128, | |
| "grad_norm": 0.2567944824695587, | |
| "learning_rate": 1.9957996342480367e-05, | |
| "loss": 0.7987, | |
| "mean_token_accuracy": 0.7764184325933456, | |
| "num_tokens": 520026049.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.2525377568705125, | |
| "grad_norm": 0.283932626247406, | |
| "learning_rate": 1.995355905303759e-05, | |
| "loss": 0.7872, | |
| "mean_token_accuracy": 0.779523742198944, | |
| "num_tokens": 530417759.0, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.25748947759346374, | |
| "grad_norm": 0.22360840439796448, | |
| "learning_rate": 1.9948899728924837e-05, | |
| "loss": 0.8079, | |
| "mean_token_accuracy": 0.7741246551275254, | |
| "num_tokens": 540815169.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.26244119831641494, | |
| "grad_norm": 0.5189192891120911, | |
| "learning_rate": 1.9944018508939086e-05, | |
| "loss": 0.8065, | |
| "mean_token_accuracy": 0.7760889768600464, | |
| "num_tokens": 551209699.0, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.2673929190393662, | |
| "grad_norm": 0.34829357266426086, | |
| "learning_rate": 1.9938915538487387e-05, | |
| "loss": 0.8066, | |
| "mean_token_accuracy": 0.7739049255847931, | |
| "num_tokens": 561624183.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.27234463976231743, | |
| "grad_norm": 0.40409669280052185, | |
| "learning_rate": 1.993359096958254e-05, | |
| "loss": 0.7932, | |
| "mean_token_accuracy": 0.7777039527893066, | |
| "num_tokens": 572002532.0, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.2772963604852686, | |
| "grad_norm": 0.6105888485908508, | |
| "learning_rate": 1.9928044960838556e-05, | |
| "loss": 0.8167, | |
| "mean_token_accuracy": 0.7729485094547272, | |
| "num_tokens": 582426743.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.28224808120821987, | |
| "grad_norm": 0.2834183871746063, | |
| "learning_rate": 1.9922277677465934e-05, | |
| "loss": 0.7975, | |
| "mean_token_accuracy": 0.7765595734119415, | |
| "num_tokens": 592847130.0, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.28719980193117106, | |
| "grad_norm": 0.3645786643028259, | |
| "learning_rate": 1.9916289291266744e-05, | |
| "loss": 0.79, | |
| "mean_token_accuracy": 0.778738671541214, | |
| "num_tokens": 603265287.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2921515226541223, | |
| "grad_norm": 0.29506251215934753, | |
| "learning_rate": 1.9910079980629505e-05, | |
| "loss": 0.8055, | |
| "mean_token_accuracy": 0.7779126793146134, | |
| "num_tokens": 613676977.0, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.29710324337707356, | |
| "grad_norm": 3.3045666217803955, | |
| "learning_rate": 1.9903649930523868e-05, | |
| "loss": 0.7906, | |
| "mean_token_accuracy": 0.7783419877290726, | |
| "num_tokens": 624102322.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.30205496410002475, | |
| "grad_norm": 0.363760769367218, | |
| "learning_rate": 1.9896999332495116e-05, | |
| "loss": 0.794, | |
| "mean_token_accuracy": 0.7770331531763077, | |
| "num_tokens": 634476562.0, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.307006684822976, | |
| "grad_norm": 1.9502851963043213, | |
| "learning_rate": 1.9890128384658442e-05, | |
| "loss": 0.8748, | |
| "mean_token_accuracy": 0.772979810833931, | |
| "num_tokens": 644878697.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.3119584055459272, | |
| "grad_norm": 0.45439156889915466, | |
| "learning_rate": 1.9883037291693072e-05, | |
| "loss": 0.801, | |
| "mean_token_accuracy": 0.7750454843044281, | |
| "num_tokens": 655255275.0, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.31691012626887843, | |
| "grad_norm": 0.2824910283088684, | |
| "learning_rate": 1.9875726264836138e-05, | |
| "loss": 0.7944, | |
| "mean_token_accuracy": 0.7767194181680679, | |
| "num_tokens": 665660530.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3218618469918297, | |
| "grad_norm": 0.31275248527526855, | |
| "learning_rate": 1.9868195521876413e-05, | |
| "loss": 0.7855, | |
| "mean_token_accuracy": 0.7794755816459655, | |
| "num_tokens": 676083912.0, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.3268135677147809, | |
| "grad_norm": 0.3284243643283844, | |
| "learning_rate": 1.9860445287147798e-05, | |
| "loss": 0.8037, | |
| "mean_token_accuracy": 0.7744458526372909, | |
| "num_tokens": 686500722.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.3317652884377321, | |
| "grad_norm": 0.24745342135429382, | |
| "learning_rate": 1.9852475791522662e-05, | |
| "loss": 0.7739, | |
| "mean_token_accuracy": 0.7818856418132782, | |
| "num_tokens": 696909303.0, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.3367170091606833, | |
| "grad_norm": 0.21039633452892303, | |
| "learning_rate": 1.9844287272404952e-05, | |
| "loss": 0.7936, | |
| "mean_token_accuracy": 0.7766739934682846, | |
| "num_tokens": 707315048.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.34166872988363456, | |
| "grad_norm": 0.2070273607969284, | |
| "learning_rate": 1.9835879973723123e-05, | |
| "loss": 0.8042, | |
| "mean_token_accuracy": 0.7737419903278351, | |
| "num_tokens": 717701231.0, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.3466204506065858, | |
| "grad_norm": 0.224740132689476, | |
| "learning_rate": 1.9827254145922865e-05, | |
| "loss": 0.7765, | |
| "mean_token_accuracy": 0.7810128808021546, | |
| "num_tokens": 728069468.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.351572171329537, | |
| "grad_norm": 0.21241162717342377, | |
| "learning_rate": 1.9818410045959663e-05, | |
| "loss": 0.7802, | |
| "mean_token_accuracy": 0.7799350917339325, | |
| "num_tokens": 738497629.0, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.35652389205248824, | |
| "grad_norm": 0.26337409019470215, | |
| "learning_rate": 1.980934793729112e-05, | |
| "loss": 0.779, | |
| "mean_token_accuracy": 0.7800916910171509, | |
| "num_tokens": 748894797.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.3614756127754395, | |
| "grad_norm": 0.21925003826618195, | |
| "learning_rate": 1.9800068089869118e-05, | |
| "loss": 0.7959, | |
| "mean_token_accuracy": 0.7759343236684799, | |
| "num_tokens": 759315710.0, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.3664273334983907, | |
| "grad_norm": 0.19071699678897858, | |
| "learning_rate": 1.979057078013178e-05, | |
| "loss": 0.7867, | |
| "mean_token_accuracy": 0.7781553447246552, | |
| "num_tokens": 769688709.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.37137905422134193, | |
| "grad_norm": 0.19490298628807068, | |
| "learning_rate": 1.978085629099523e-05, | |
| "loss": 0.7846, | |
| "mean_token_accuracy": 0.7785351812839508, | |
| "num_tokens": 780101279.0, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.3763307749442931, | |
| "grad_norm": 0.20952484011650085, | |
| "learning_rate": 1.977092491184516e-05, | |
| "loss": 0.7948, | |
| "mean_token_accuracy": 0.7759048402309418, | |
| "num_tokens": 790491283.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.38128249566724437, | |
| "grad_norm": 0.22583240270614624, | |
| "learning_rate": 1.9760776938528233e-05, | |
| "loss": 0.7779, | |
| "mean_token_accuracy": 0.7805261939764023, | |
| "num_tokens": 800875319.0, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.3862342163901956, | |
| "grad_norm": 0.21482065320014954, | |
| "learning_rate": 1.9750412673343237e-05, | |
| "loss": 0.7886, | |
| "mean_token_accuracy": 0.7774913161993027, | |
| "num_tokens": 811283375.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.3911859371131468, | |
| "grad_norm": 0.22041663527488708, | |
| "learning_rate": 1.9739832425032098e-05, | |
| "loss": 0.7808, | |
| "mean_token_accuracy": 0.7795657008886338, | |
| "num_tokens": 821657607.0, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.39613765783609806, | |
| "grad_norm": 0.2266547530889511, | |
| "learning_rate": 1.9729036508770684e-05, | |
| "loss": 0.7776, | |
| "mean_token_accuracy": 0.7801724016666413, | |
| "num_tokens": 832048749.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.40108937855904925, | |
| "grad_norm": 0.2227035015821457, | |
| "learning_rate": 1.9718025246159414e-05, | |
| "loss": 0.7841, | |
| "mean_token_accuracy": 0.77851602435112, | |
| "num_tokens": 842471488.0, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.4060410992820005, | |
| "grad_norm": 0.23665013909339905, | |
| "learning_rate": 1.970679896521368e-05, | |
| "loss": 0.7849, | |
| "mean_token_accuracy": 0.7782983154058456, | |
| "num_tokens": 852876590.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.41099282000495174, | |
| "grad_norm": 0.19461902976036072, | |
| "learning_rate": 1.9695358000354063e-05, | |
| "loss": 0.7755, | |
| "mean_token_accuracy": 0.7806118249893188, | |
| "num_tokens": 863284557.0, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.41594454072790293, | |
| "grad_norm": 0.20683637261390686, | |
| "learning_rate": 1.968370269239638e-05, | |
| "loss": 0.7735, | |
| "mean_token_accuracy": 0.7812349110841751, | |
| "num_tokens": 873712187.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4208962614508542, | |
| "grad_norm": 0.18914039433002472, | |
| "learning_rate": 1.967183338854155e-05, | |
| "loss": 0.7769, | |
| "mean_token_accuracy": 0.7802020996809006, | |
| "num_tokens": 884107732.0, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.4258479821738054, | |
| "grad_norm": 0.20901145040988922, | |
| "learning_rate": 1.9659750442365207e-05, | |
| "loss": 0.7775, | |
| "mean_token_accuracy": 0.7796809077262878, | |
| "num_tokens": 894519434.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.4307997028967566, | |
| "grad_norm": 0.19267426431179047, | |
| "learning_rate": 1.964745421380722e-05, | |
| "loss": 0.785, | |
| "mean_token_accuracy": 0.7779094964265824, | |
| "num_tokens": 904926587.0, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.43575142361970787, | |
| "grad_norm": 0.21364259719848633, | |
| "learning_rate": 1.9634945069160915e-05, | |
| "loss": 0.7784, | |
| "mean_token_accuracy": 0.779586797952652, | |
| "num_tokens": 915329182.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.44070314434265906, | |
| "grad_norm": 0.22054027020931244, | |
| "learning_rate": 1.9622223381062216e-05, | |
| "loss": 0.7799, | |
| "mean_token_accuracy": 0.7788717359304428, | |
| "num_tokens": 925694666.0, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.4456548650656103, | |
| "grad_norm": 10.010891914367676, | |
| "learning_rate": 1.960928952847851e-05, | |
| "loss": 1.0615, | |
| "mean_token_accuracy": 0.7801062256097794, | |
| "num_tokens": 936081193.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4506065857885615, | |
| "grad_norm": 0.2595425546169281, | |
| "learning_rate": 1.9596143896697377e-05, | |
| "loss": 0.7803, | |
| "mean_token_accuracy": 0.7792818278074265, | |
| "num_tokens": 946491782.0, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.45555830651151275, | |
| "grad_norm": 0.24293220043182373, | |
| "learning_rate": 1.9582786877315097e-05, | |
| "loss": 0.7737, | |
| "mean_token_accuracy": 0.7810850977897644, | |
| "num_tokens": 956901948.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.460510027234464, | |
| "grad_norm": 0.23179250955581665, | |
| "learning_rate": 1.956921886822499e-05, | |
| "loss": 0.7714, | |
| "mean_token_accuracy": 0.7815377414226532, | |
| "num_tokens": 967293443.0, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.4654617479574152, | |
| "grad_norm": 0.21295353770256042, | |
| "learning_rate": 1.9555440273605573e-05, | |
| "loss": 0.7856, | |
| "mean_token_accuracy": 0.777508807182312, | |
| "num_tokens": 977693050.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.47041346868036643, | |
| "grad_norm": 0.2277674376964569, | |
| "learning_rate": 1.954145150390851e-05, | |
| "loss": 0.7798, | |
| "mean_token_accuracy": 0.7789700716733933, | |
| "num_tokens": 988067281.0, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.4753651894033177, | |
| "grad_norm": 0.22468669712543488, | |
| "learning_rate": 1.9527252975846385e-05, | |
| "loss": 0.7745, | |
| "mean_token_accuracy": 0.7800474315881729, | |
| "num_tokens": 998455093.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.48031691012626887, | |
| "grad_norm": 0.2532201111316681, | |
| "learning_rate": 1.9512845112380293e-05, | |
| "loss": 0.7886, | |
| "mean_token_accuracy": 0.7768169581890106, | |
| "num_tokens": 1008880800.0, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.4852686308492201, | |
| "grad_norm": 0.24313411116600037, | |
| "learning_rate": 1.9498228342707236e-05, | |
| "loss": 0.7781, | |
| "mean_token_accuracy": 0.7799170076847076, | |
| "num_tokens": 1019275396.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.4902203515721713, | |
| "grad_norm": 0.24066568911075592, | |
| "learning_rate": 1.948340310224734e-05, | |
| "loss": 0.7864, | |
| "mean_token_accuracy": 0.7775434225797653, | |
| "num_tokens": 1029689644.0, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.49517207229512256, | |
| "grad_norm": 0.2265813648700714, | |
| "learning_rate": 1.946836983263089e-05, | |
| "loss": 0.7904, | |
| "mean_token_accuracy": 0.7760259002447129, | |
| "num_tokens": 1040080774.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5001237930180737, | |
| "grad_norm": 0.22151488065719604, | |
| "learning_rate": 1.945312898168516e-05, | |
| "loss": 0.7578, | |
| "mean_token_accuracy": 0.7849026411771775, | |
| "num_tokens": 1050471944.0, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.505075513741025, | |
| "grad_norm": 0.28647103905677795, | |
| "learning_rate": 1.9437681003421085e-05, | |
| "loss": 0.7702, | |
| "mean_token_accuracy": 0.7815856724977494, | |
| "num_tokens": 1060865733.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5100272344639762, | |
| "grad_norm": 0.2885425090789795, | |
| "learning_rate": 1.942202635801973e-05, | |
| "loss": 0.7734, | |
| "mean_token_accuracy": 0.7801808267831802, | |
| "num_tokens": 1071278092.0, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.5149789551869275, | |
| "grad_norm": 0.3188728094100952, | |
| "learning_rate": 1.940616551181859e-05, | |
| "loss": 0.7874, | |
| "mean_token_accuracy": 0.7791253894567489, | |
| "num_tokens": 1081688765.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5199306759098787, | |
| "grad_norm": 0.27370673418045044, | |
| "learning_rate": 1.9390098937297685e-05, | |
| "loss": 0.774, | |
| "mean_token_accuracy": 0.7808292925357818, | |
| "num_tokens": 1092085647.0, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5248823966328299, | |
| "grad_norm": 0.19921670854091644, | |
| "learning_rate": 1.9373827113065493e-05, | |
| "loss": 0.7554, | |
| "mean_token_accuracy": 0.7854314386844635, | |
| "num_tokens": 1102479708.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5298341173557811, | |
| "grad_norm": 0.23133447766304016, | |
| "learning_rate": 1.93573505238447e-05, | |
| "loss": 0.7686, | |
| "mean_token_accuracy": 0.7816448330879211, | |
| "num_tokens": 1112886556.0, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.5347858380787324, | |
| "grad_norm": 0.210884690284729, | |
| "learning_rate": 1.934066966045774e-05, | |
| "loss": 0.7708, | |
| "mean_token_accuracy": 0.7807249516248703, | |
| "num_tokens": 1123299992.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5397375588016836, | |
| "grad_norm": 0.20094110071659088, | |
| "learning_rate": 1.93237850198122e-05, | |
| "loss": 0.7579, | |
| "mean_token_accuracy": 0.7845065593719482, | |
| "num_tokens": 1133664183.0, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.5446892795246349, | |
| "grad_norm": 0.21680229902267456, | |
| "learning_rate": 1.9306697104885997e-05, | |
| "loss": 0.776, | |
| "mean_token_accuracy": 0.7794145315885543, | |
| "num_tokens": 1144090055.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.549641000247586, | |
| "grad_norm": 0.3211749494075775, | |
| "learning_rate": 1.92894064247124e-05, | |
| "loss": 0.7896, | |
| "mean_token_accuracy": 0.7807279646396637, | |
| "num_tokens": 1154463475.0, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.5545927209705372, | |
| "grad_norm": 0.24195314943790436, | |
| "learning_rate": 1.9271913494364874e-05, | |
| "loss": 0.7807, | |
| "mean_token_accuracy": 0.7783623158931732, | |
| "num_tokens": 1164866644.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.5595444416934885, | |
| "grad_norm": 0.4342971444129944, | |
| "learning_rate": 1.9254218834941727e-05, | |
| "loss": 0.7838, | |
| "mean_token_accuracy": 0.7803391963243484, | |
| "num_tokens": 1175260483.0, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.5644961624164397, | |
| "grad_norm": 0.6932039856910706, | |
| "learning_rate": 1.923632297355059e-05, | |
| "loss": 0.7772, | |
| "mean_token_accuracy": 0.7796769648790359, | |
| "num_tokens": 1185656569.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.569447883139391, | |
| "grad_norm": 0.5484419465065002, | |
| "learning_rate": 1.9218226443292717e-05, | |
| "loss": 0.7733, | |
| "mean_token_accuracy": 0.780466890335083, | |
| "num_tokens": 1196077796.0, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.5743996038623421, | |
| "grad_norm": 3.0035197734832764, | |
| "learning_rate": 1.9199929783247106e-05, | |
| "loss": 0.7854, | |
| "mean_token_accuracy": 0.78033567070961, | |
| "num_tokens": 1206462746.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5793513245852934, | |
| "grad_norm": 0.7452694773674011, | |
| "learning_rate": 1.918143353845443e-05, | |
| "loss": 0.7699, | |
| "mean_token_accuracy": 0.7816843211650848, | |
| "num_tokens": 1216838456.0, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.5843030453082446, | |
| "grad_norm": 0.4381994307041168, | |
| "learning_rate": 1.9162738259900817e-05, | |
| "loss": 0.766, | |
| "mean_token_accuracy": 0.7822736114263534, | |
| "num_tokens": 1227242988.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.5892547660311959, | |
| "grad_norm": 1.9659717082977295, | |
| "learning_rate": 1.9143844504501417e-05, | |
| "loss": 0.7787, | |
| "mean_token_accuracy": 0.779282808303833, | |
| "num_tokens": 1237636071.0, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.5942064867541471, | |
| "grad_norm": 0.2631269693374634, | |
| "learning_rate": 1.912475283508384e-05, | |
| "loss": 0.776, | |
| "mean_token_accuracy": 0.7794870853424072, | |
| "num_tokens": 1248057314.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5991582074770982, | |
| "grad_norm": 0.429813414812088, | |
| "learning_rate": 1.9105463820371346e-05, | |
| "loss": 0.7617, | |
| "mean_token_accuracy": 0.7824564576148987, | |
| "num_tokens": 1258457239.0, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.6041099282000495, | |
| "grad_norm": 0.4058431386947632, | |
| "learning_rate": 1.9085978034965957e-05, | |
| "loss": 0.7665, | |
| "mean_token_accuracy": 0.7821383327245712, | |
| "num_tokens": 1268873042.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6090616489230007, | |
| "grad_norm": 0.2880268692970276, | |
| "learning_rate": 1.9066296059331297e-05, | |
| "loss": 0.7774, | |
| "mean_token_accuracy": 0.7790426641702652, | |
| "num_tokens": 1279256133.0, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.614013369645952, | |
| "grad_norm": 0.28571274876594543, | |
| "learning_rate": 1.904641847977532e-05, | |
| "loss": 0.7649, | |
| "mean_token_accuracy": 0.7826848417520523, | |
| "num_tokens": 1289654801.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6189650903689032, | |
| "grad_norm": 0.2443043738603592, | |
| "learning_rate": 1.902634588843285e-05, | |
| "loss": 0.7845, | |
| "mean_token_accuracy": 0.7772348463535309, | |
| "num_tokens": 1300049426.0, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.6239168110918544, | |
| "grad_norm": 0.2589752674102783, | |
| "learning_rate": 1.9006078883247913e-05, | |
| "loss": 0.7682, | |
| "mean_token_accuracy": 0.7823996514081955, | |
| "num_tokens": 1310479480.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6288685318148056, | |
| "grad_norm": 0.21809199452400208, | |
| "learning_rate": 1.898561806795596e-05, | |
| "loss": 0.7831, | |
| "mean_token_accuracy": 0.7773066818714142, | |
| "num_tokens": 1320885725.0, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.6338202525377569, | |
| "grad_norm": 0.24305787682533264, | |
| "learning_rate": 1.8964964052065865e-05, | |
| "loss": 0.7689, | |
| "mean_token_accuracy": 0.781117245554924, | |
| "num_tokens": 1331277887.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6387719732607081, | |
| "grad_norm": 0.2178671658039093, | |
| "learning_rate": 1.894411745084177e-05, | |
| "loss": 0.7737, | |
| "mean_token_accuracy": 0.7797011733055115, | |
| "num_tokens": 1341663949.0, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.6437236939836594, | |
| "grad_norm": 0.21718356013298035, | |
| "learning_rate": 1.892307888528475e-05, | |
| "loss": 0.7599, | |
| "mean_token_accuracy": 0.7836619168519974, | |
| "num_tokens": 1352058279.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6486754147066105, | |
| "grad_norm": 0.20011211931705475, | |
| "learning_rate": 1.890184898211433e-05, | |
| "loss": 0.7621, | |
| "mean_token_accuracy": 0.7829108744859695, | |
| "num_tokens": 1362482075.0, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.6536271354295617, | |
| "grad_norm": 0.21650190651416779, | |
| "learning_rate": 1.88804283737498e-05, | |
| "loss": 0.7757, | |
| "mean_token_accuracy": 0.7795401126146316, | |
| "num_tokens": 1372901259.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.658578856152513, | |
| "grad_norm": 0.19840224087238312, | |
| "learning_rate": 1.8858817698291386e-05, | |
| "loss": 0.7673, | |
| "mean_token_accuracy": 0.7813610762357712, | |
| "num_tokens": 1383315389.0, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.6635305768754642, | |
| "grad_norm": 0.20623134076595306, | |
| "learning_rate": 1.883701759950124e-05, | |
| "loss": 0.7665, | |
| "mean_token_accuracy": 0.7813021749258041, | |
| "num_tokens": 1393726215.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.6684822975984155, | |
| "grad_norm": 0.199232816696167, | |
| "learning_rate": 1.881502872678425e-05, | |
| "loss": 0.7648, | |
| "mean_token_accuracy": 0.782157027721405, | |
| "num_tokens": 1404148209.0, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.6734340183213666, | |
| "grad_norm": 0.1855035424232483, | |
| "learning_rate": 1.879285173516872e-05, | |
| "loss": 0.7603, | |
| "mean_token_accuracy": 0.78330679833889, | |
| "num_tokens": 1414573560.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.6783857390443179, | |
| "grad_norm": 0.2409905195236206, | |
| "learning_rate": 1.877048728528684e-05, | |
| "loss": 0.7887, | |
| "mean_token_accuracy": 0.7781977474689483, | |
| "num_tokens": 1424968590.0, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.6833374597672691, | |
| "grad_norm": 0.2532198131084442, | |
| "learning_rate": 1.8747936043354994e-05, | |
| "loss": 0.7678, | |
| "mean_token_accuracy": 0.7814545810222626, | |
| "num_tokens": 1435377805.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.6882891804902204, | |
| "grad_norm": 0.2087397277355194, | |
| "learning_rate": 1.8725198681153955e-05, | |
| "loss": 0.7627, | |
| "mean_token_accuracy": 0.7825340062379837, | |
| "num_tokens": 1445800164.0, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.6932409012131716, | |
| "grad_norm": 0.20391027629375458, | |
| "learning_rate": 1.8702275876008823e-05, | |
| "loss": 0.7574, | |
| "mean_token_accuracy": 0.783563169836998, | |
| "num_tokens": 1456203460.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6981926219361227, | |
| "grad_norm": 0.21374066174030304, | |
| "learning_rate": 1.867916831076889e-05, | |
| "loss": 0.7737, | |
| "mean_token_accuracy": 0.7793075799942016, | |
| "num_tokens": 1466617339.0, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.703144342659074, | |
| "grad_norm": 0.45011261105537415, | |
| "learning_rate": 1.8655876673787272e-05, | |
| "loss": 0.7534, | |
| "mean_token_accuracy": 0.7848767697811126, | |
| "num_tokens": 1477041742.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.7080960633820252, | |
| "grad_norm": 0.19761380553245544, | |
| "learning_rate": 1.8632401658900415e-05, | |
| "loss": 0.7583, | |
| "mean_token_accuracy": 0.783224281668663, | |
| "num_tokens": 1487468293.0, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.7130477841049765, | |
| "grad_norm": 0.17496533691883087, | |
| "learning_rate": 1.860874396540743e-05, | |
| "loss": 0.7567, | |
| "mean_token_accuracy": 0.7842571973800659, | |
| "num_tokens": 1497855239.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.7179995048279277, | |
| "grad_norm": 0.19634433090686798, | |
| "learning_rate": 1.8584904298049244e-05, | |
| "loss": 0.7628, | |
| "mean_token_accuracy": 0.7824541956186295, | |
| "num_tokens": 1508239301.0, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.722951225550879, | |
| "grad_norm": 0.19373337924480438, | |
| "learning_rate": 1.8560883366987633e-05, | |
| "loss": 0.759, | |
| "mean_token_accuracy": 0.7833509474992753, | |
| "num_tokens": 1518639882.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.7279029462738301, | |
| "grad_norm": 0.18676340579986572, | |
| "learning_rate": 1.8536681887784037e-05, | |
| "loss": 0.7512, | |
| "mean_token_accuracy": 0.7852223426103592, | |
| "num_tokens": 1529056777.0, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.7328546669967814, | |
| "grad_norm": 0.20926012098789215, | |
| "learning_rate": 1.8512300581378267e-05, | |
| "loss": 0.7502, | |
| "mean_token_accuracy": 0.7857935458421708, | |
| "num_tokens": 1539442858.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.7378063877197326, | |
| "grad_norm": 0.1997007578611374, | |
| "learning_rate": 1.848774017406703e-05, | |
| "loss": 0.7557, | |
| "mean_token_accuracy": 0.7842215925455094, | |
| "num_tokens": 1549852249.0, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.7427581084426839, | |
| "grad_norm": 0.19928854703903198, | |
| "learning_rate": 1.8463001397482257e-05, | |
| "loss": 0.7481, | |
| "mean_token_accuracy": 0.7860120952129364, | |
| "num_tokens": 1560241267.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7477098291656351, | |
| "grad_norm": 0.19554533064365387, | |
| "learning_rate": 1.843808498856937e-05, | |
| "loss": 0.7583, | |
| "mean_token_accuracy": 0.7831324756145477, | |
| "num_tokens": 1570635303.0, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.7526615498885862, | |
| "grad_norm": 0.1927034854888916, | |
| "learning_rate": 1.8412991689565264e-05, | |
| "loss": 0.7616, | |
| "mean_token_accuracy": 0.7826423794031143, | |
| "num_tokens": 1581053637.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.7576132706115375, | |
| "grad_norm": 0.20213893055915833, | |
| "learning_rate": 1.8387722247976248e-05, | |
| "loss": 0.7664, | |
| "mean_token_accuracy": 0.7809010535478592, | |
| "num_tokens": 1591457543.0, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.7625649913344887, | |
| "grad_norm": 0.1917760670185089, | |
| "learning_rate": 1.836227741655575e-05, | |
| "loss": 0.7554, | |
| "mean_token_accuracy": 0.7842649966478348, | |
| "num_tokens": 1601863294.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.76751671205744, | |
| "grad_norm": 0.20989423990249634, | |
| "learning_rate": 1.8336657953281896e-05, | |
| "loss": 0.7615, | |
| "mean_token_accuracy": 0.78232641518116, | |
| "num_tokens": 1612243148.0, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.7724684327803912, | |
| "grad_norm": 0.20752640068531036, | |
| "learning_rate": 1.8310864621334936e-05, | |
| "loss": 0.768, | |
| "mean_token_accuracy": 0.781131848692894, | |
| "num_tokens": 1622648438.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.7774201535033424, | |
| "grad_norm": 0.6338415145874023, | |
| "learning_rate": 1.8284898189074514e-05, | |
| "loss": 0.753, | |
| "mean_token_accuracy": 0.784282636642456, | |
| "num_tokens": 1633053857.0, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.7823718742262936, | |
| "grad_norm": 0.22199805080890656, | |
| "learning_rate": 1.8258759430016767e-05, | |
| "loss": 0.7636, | |
| "mean_token_accuracy": 0.7832720100879669, | |
| "num_tokens": 1643462725.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.7873235949492449, | |
| "grad_norm": 0.19597461819648743, | |
| "learning_rate": 1.8232449122811293e-05, | |
| "loss": 0.7557, | |
| "mean_token_accuracy": 0.7838189631700516, | |
| "num_tokens": 1653883349.0, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.7922753156721961, | |
| "grad_norm": 0.2407362461090088, | |
| "learning_rate": 1.8205968051217945e-05, | |
| "loss": 0.7606, | |
| "mean_token_accuracy": 0.7830138593912125, | |
| "num_tokens": 1664275959.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7972270363951474, | |
| "grad_norm": 0.23943914473056793, | |
| "learning_rate": 1.8179317004083495e-05, | |
| "loss": 0.7651, | |
| "mean_token_accuracy": 0.7815976798534393, | |
| "num_tokens": 1674671126.0, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.8021787571180985, | |
| "grad_norm": 0.25406405329704285, | |
| "learning_rate": 1.815249677531813e-05, | |
| "loss": 0.7547, | |
| "mean_token_accuracy": 0.7842951714992523, | |
| "num_tokens": 1685037213.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.8071304778410497, | |
| "grad_norm": 0.7270509600639343, | |
| "learning_rate": 1.8125508163871798e-05, | |
| "loss": 0.7583, | |
| "mean_token_accuracy": 0.7827031821012497, | |
| "num_tokens": 1695458364.0, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.812082198564001, | |
| "grad_norm": 0.2561294436454773, | |
| "learning_rate": 1.809835197371042e-05, | |
| "loss": 0.7696, | |
| "mean_token_accuracy": 0.7809718787670136, | |
| "num_tokens": 1705848122.0, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.8170339192869522, | |
| "grad_norm": 0.23471757769584656, | |
| "learning_rate": 1.807102901379193e-05, | |
| "loss": 0.743, | |
| "mean_token_accuracy": 0.7874339818954468, | |
| "num_tokens": 1716242283.0, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.8219856400099035, | |
| "grad_norm": 0.19936513900756836, | |
| "learning_rate": 1.804354009804217e-05, | |
| "loss": 0.7516, | |
| "mean_token_accuracy": 0.7847243756055832, | |
| "num_tokens": 1726606051.0, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.8269373607328546, | |
| "grad_norm": 0.23077034950256348, | |
| "learning_rate": 1.801588604533067e-05, | |
| "loss": 0.7478, | |
| "mean_token_accuracy": 0.7857007443904876, | |
| "num_tokens": 1736984854.0, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.8318890814558059, | |
| "grad_norm": 0.27735021710395813, | |
| "learning_rate": 1.7988067679446223e-05, | |
| "loss": 0.7542, | |
| "mean_token_accuracy": 0.7848597913980484, | |
| "num_tokens": 1747365413.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.8368408021787571, | |
| "grad_norm": 0.19908802211284637, | |
| "learning_rate": 1.7960085829072373e-05, | |
| "loss": 0.7485, | |
| "mean_token_accuracy": 0.7859860509634018, | |
| "num_tokens": 1757782617.0, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.8417925229017084, | |
| "grad_norm": 0.19668538868427277, | |
| "learning_rate": 1.7931941327762708e-05, | |
| "loss": 0.7563, | |
| "mean_token_accuracy": 0.7834689766168594, | |
| "num_tokens": 1768140236.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8467442436246596, | |
| "grad_norm": 0.2182615101337433, | |
| "learning_rate": 1.790363501391604e-05, | |
| "loss": 0.7564, | |
| "mean_token_accuracy": 0.7837036728858948, | |
| "num_tokens": 1778501788.0, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.8516959643476107, | |
| "grad_norm": 1.2455408573150635, | |
| "learning_rate": 1.7875167730751432e-05, | |
| "loss": 0.7495, | |
| "mean_token_accuracy": 0.7853644698858261, | |
| "num_tokens": 1788895036.0, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.856647685070562, | |
| "grad_norm": 0.22847770154476166, | |
| "learning_rate": 1.7846540326283067e-05, | |
| "loss": 0.7466, | |
| "mean_token_accuracy": 0.786415946483612, | |
| "num_tokens": 1799277517.0, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.8615994057935132, | |
| "grad_norm": 0.22231429815292358, | |
| "learning_rate": 1.7817753653295e-05, | |
| "loss": 0.748, | |
| "mean_token_accuracy": 0.7856645524501801, | |
| "num_tokens": 1809703236.0, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.8665511265164645, | |
| "grad_norm": 0.9592680931091309, | |
| "learning_rate": 1.7788808569315753e-05, | |
| "loss": 0.7503, | |
| "mean_token_accuracy": 0.7850320547819137, | |
| "num_tokens": 1820112331.0, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.8715028472394157, | |
| "grad_norm": 0.2056133896112442, | |
| "learning_rate": 1.775970593659275e-05, | |
| "loss": 0.7597, | |
| "mean_token_accuracy": 0.7830165416002274, | |
| "num_tokens": 1830487579.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.8764545679623669, | |
| "grad_norm": 0.29589369893074036, | |
| "learning_rate": 1.7730446622066663e-05, | |
| "loss": 0.7633, | |
| "mean_token_accuracy": 0.7831792920827866, | |
| "num_tokens": 1840864368.0, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.8814062886853181, | |
| "grad_norm": 0.23890021443367004, | |
| "learning_rate": 1.7701031497345563e-05, | |
| "loss": 0.751, | |
| "mean_token_accuracy": 0.7846818000078202, | |
| "num_tokens": 1851268551.0, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.8863580094082694, | |
| "grad_norm": 0.20969191193580627, | |
| "learning_rate": 1.7671461438678968e-05, | |
| "loss": 0.7579, | |
| "mean_token_accuracy": 0.7834391385316849, | |
| "num_tokens": 1861629010.0, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.8913097301312206, | |
| "grad_norm": 0.3054754436016083, | |
| "learning_rate": 1.7641737326931735e-05, | |
| "loss": 0.7774, | |
| "mean_token_accuracy": 0.7797193497419357, | |
| "num_tokens": 1872020332.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8962614508541719, | |
| "grad_norm": 0.2975171208381653, | |
| "learning_rate": 1.7611860047557817e-05, | |
| "loss": 0.7565, | |
| "mean_token_accuracy": 0.7843641757965087, | |
| "num_tokens": 1882408874.0, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.901213171577123, | |
| "grad_norm": 0.5816043019294739, | |
| "learning_rate": 1.7581830490573887e-05, | |
| "loss": 0.7507, | |
| "mean_token_accuracy": 0.7849104583263398, | |
| "num_tokens": 1892771965.0, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.9061648923000742, | |
| "grad_norm": 1.1918472051620483, | |
| "learning_rate": 1.7551649550532842e-05, | |
| "loss": 0.7535, | |
| "mean_token_accuracy": 0.7841880857944489, | |
| "num_tokens": 1903131329.0, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.9111166130230255, | |
| "grad_norm": 0.21812961995601654, | |
| "learning_rate": 1.7521318126497124e-05, | |
| "loss": 0.7646, | |
| "mean_token_accuracy": 0.7810812026262284, | |
| "num_tokens": 1913531682.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.9160683337459767, | |
| "grad_norm": 0.18054869771003723, | |
| "learning_rate": 1.7490837122011965e-05, | |
| "loss": 0.7648, | |
| "mean_token_accuracy": 0.7809185832738876, | |
| "num_tokens": 1923930881.0, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.921020054468928, | |
| "grad_norm": 0.2776661813259125, | |
| "learning_rate": 1.7460207445078458e-05, | |
| "loss": 0.7598, | |
| "mean_token_accuracy": 0.7860252737998963, | |
| "num_tokens": 1934361093.0, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.9259717751918792, | |
| "grad_norm": 0.4657640755176544, | |
| "learning_rate": 1.7429430008126517e-05, | |
| "loss": 0.78, | |
| "mean_token_accuracy": 0.7799131125211716, | |
| "num_tokens": 1944750850.0, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.9309234959148304, | |
| "grad_norm": 0.47089236974716187, | |
| "learning_rate": 1.739850572798768e-05, | |
| "loss": 0.7609, | |
| "mean_token_accuracy": 0.783119586110115, | |
| "num_tokens": 1955154134.0, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.9358752166377816, | |
| "grad_norm": 0.20868314802646637, | |
| "learning_rate": 1.736743552586782e-05, | |
| "loss": 0.7449, | |
| "mean_token_accuracy": 0.7862414479255676, | |
| "num_tokens": 1965547370.0, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.9408269373607329, | |
| "grad_norm": 0.2700161337852478, | |
| "learning_rate": 1.733622032731968e-05, | |
| "loss": 0.7501, | |
| "mean_token_accuracy": 0.7854364097118378, | |
| "num_tokens": 1975948544.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.9457786580836841, | |
| "grad_norm": 0.25757983326911926, | |
| "learning_rate": 1.7304861062215326e-05, | |
| "loss": 0.7605, | |
| "mean_token_accuracy": 0.7821576863527298, | |
| "num_tokens": 1986371366.0, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.9507303788066354, | |
| "grad_norm": 0.2574819326400757, | |
| "learning_rate": 1.727335866471842e-05, | |
| "loss": 0.7684, | |
| "mean_token_accuracy": 0.7806459426879883, | |
| "num_tokens": 1996738288.0, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.9556820995295865, | |
| "grad_norm": 0.22203104197978973, | |
| "learning_rate": 1.724171407325642e-05, | |
| "loss": 0.7546, | |
| "mean_token_accuracy": 0.786052080988884, | |
| "num_tokens": 2007140915.0, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.9606338202525377, | |
| "grad_norm": 0.23472048342227936, | |
| "learning_rate": 1.7209928230492606e-05, | |
| "loss": 0.7517, | |
| "mean_token_accuracy": 0.7842936605215073, | |
| "num_tokens": 2017561316.0, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.965585540975489, | |
| "grad_norm": 0.36148348450660706, | |
| "learning_rate": 1.7178002083298005e-05, | |
| "loss": 0.7549, | |
| "mean_token_accuracy": 0.7834816932678222, | |
| "num_tokens": 2027964049.0, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.9705372616984402, | |
| "grad_norm": 0.19759418070316315, | |
| "learning_rate": 1.714593658272318e-05, | |
| "loss": 0.7725, | |
| "mean_token_accuracy": 0.7829167902469635, | |
| "num_tokens": 2038362855.0, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.9754889824213915, | |
| "grad_norm": 0.21052470803260803, | |
| "learning_rate": 1.7113732683969905e-05, | |
| "loss": 0.7633, | |
| "mean_token_accuracy": 0.7814028680324554, | |
| "num_tokens": 2048772898.0, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.9804407031443426, | |
| "grad_norm": 0.31858742237091064, | |
| "learning_rate": 1.7081391346362717e-05, | |
| "loss": 0.7624, | |
| "mean_token_accuracy": 0.7836154013872146, | |
| "num_tokens": 2059179537.0, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.9853924238672939, | |
| "grad_norm": 0.19801688194274902, | |
| "learning_rate": 1.7048913533320307e-05, | |
| "loss": 0.7295, | |
| "mean_token_accuracy": 0.7904259711503983, | |
| "num_tokens": 2069588587.0, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.9903441445902451, | |
| "grad_norm": 0.2109430432319641, | |
| "learning_rate": 1.7016300212326875e-05, | |
| "loss": 0.7482, | |
| "mean_token_accuracy": 0.7853594183921814, | |
| "num_tokens": 2080010530.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9952958653131964, | |
| "grad_norm": 0.2018500715494156, | |
| "learning_rate": 1.6983552354903257e-05, | |
| "loss": 0.7622, | |
| "mean_token_accuracy": 0.7815503656864167, | |
| "num_tokens": 2090415532.0, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.2757660448551178, | |
| "learning_rate": 1.6950670936578013e-05, | |
| "loss": 0.7279, | |
| "mean_token_accuracy": 0.7902535639311138, | |
| "num_tokens": 2100284200.0, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.0049517207229512, | |
| "grad_norm": 0.22684067487716675, | |
| "learning_rate": 1.6917656936858347e-05, | |
| "loss": 0.7505, | |
| "mean_token_accuracy": 0.7881647497415543, | |
| "num_tokens": 2110682669.0, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 1.0099034414459025, | |
| "grad_norm": 0.19842083752155304, | |
| "learning_rate": 1.688451133920097e-05, | |
| "loss": 0.7352, | |
| "mean_token_accuracy": 0.787742218375206, | |
| "num_tokens": 2121073690.0, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.0148551621688537, | |
| "grad_norm": 0.637569785118103, | |
| "learning_rate": 1.6851235130982737e-05, | |
| "loss": 0.7309, | |
| "mean_token_accuracy": 0.7883238166570663, | |
| "num_tokens": 2131473799.0, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.019806882891805, | |
| "grad_norm": 0.19143810868263245, | |
| "learning_rate": 1.68178293034713e-05, | |
| "loss": 0.7227, | |
| "mean_token_accuracy": 0.7909730762243271, | |
| "num_tokens": 2141863864.0, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.0247586036147562, | |
| "grad_norm": 0.20483145117759705, | |
| "learning_rate": 1.6784294851795544e-05, | |
| "loss": 0.7404, | |
| "mean_token_accuracy": 0.786355146765709, | |
| "num_tokens": 2152272201.0, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 1.0297103243377073, | |
| "grad_norm": 0.22370055317878723, | |
| "learning_rate": 1.675063277491594e-05, | |
| "loss": 0.7345, | |
| "mean_token_accuracy": 0.7874440640211106, | |
| "num_tokens": 2162687256.0, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.0346620450606585, | |
| "grad_norm": 0.18761159479618073, | |
| "learning_rate": 1.671684407559481e-05, | |
| "loss": 0.7396, | |
| "mean_token_accuracy": 0.788395956158638, | |
| "num_tokens": 2173083569.0, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 1.0396137657836098, | |
| "grad_norm": 0.6076595783233643, | |
| "learning_rate": 1.6682929760366425e-05, | |
| "loss": 0.7257, | |
| "mean_token_accuracy": 0.7897282272577286, | |
| "num_tokens": 2183435840.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.044565486506561, | |
| "grad_norm": 0.20622926950454712, | |
| "learning_rate": 1.6648890839507058e-05, | |
| "loss": 0.7346, | |
| "mean_token_accuracy": 0.7876258313655853, | |
| "num_tokens": 2193808006.0, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 1.0495172072295123, | |
| "grad_norm": 0.1940770000219345, | |
| "learning_rate": 1.661472832700485e-05, | |
| "loss": 0.7258, | |
| "mean_token_accuracy": 0.789948183298111, | |
| "num_tokens": 2204182448.0, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.0544689279524635, | |
| "grad_norm": 0.18651843070983887, | |
| "learning_rate": 1.658044324052964e-05, | |
| "loss": 0.7237, | |
| "mean_token_accuracy": 0.7907967299222947, | |
| "num_tokens": 2214609200.0, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 1.0594206486754147, | |
| "grad_norm": 0.19266949594020844, | |
| "learning_rate": 1.6546036601402628e-05, | |
| "loss": 0.7305, | |
| "mean_token_accuracy": 0.7886613547801972, | |
| "num_tokens": 2224999377.0, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.064372369398366, | |
| "grad_norm": 0.1916077733039856, | |
| "learning_rate": 1.6511509434565948e-05, | |
| "loss": 0.7208, | |
| "mean_token_accuracy": 0.791583576798439, | |
| "num_tokens": 2235407967.0, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.0693240901213172, | |
| "grad_norm": 0.19016622006893158, | |
| "learning_rate": 1.647686276855215e-05, | |
| "loss": 0.7281, | |
| "mean_token_accuracy": 0.7892949759960175, | |
| "num_tokens": 2245796359.0, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.0742758108442685, | |
| "grad_norm": 0.19595059752464294, | |
| "learning_rate": 1.6442097635453558e-05, | |
| "loss": 0.767, | |
| "mean_token_accuracy": 0.7892323851585388, | |
| "num_tokens": 2256165537.0, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 1.0792275315672195, | |
| "grad_norm": 0.2070004940032959, | |
| "learning_rate": 1.6407215070891513e-05, | |
| "loss": 0.7254, | |
| "mean_token_accuracy": 0.7902043342590332, | |
| "num_tokens": 2266536896.0, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.0841792522901708, | |
| "grad_norm": 0.20020951330661774, | |
| "learning_rate": 1.6372216113985538e-05, | |
| "loss": 0.7315, | |
| "mean_token_accuracy": 0.7884757041931152, | |
| "num_tokens": 2276919634.0, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 1.089130973013122, | |
| "grad_norm": 0.20975516736507416, | |
| "learning_rate": 1.633710180732237e-05, | |
| "loss": 0.719, | |
| "mean_token_accuracy": 0.7908209532499313, | |
| "num_tokens": 2287296356.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.0940826937360733, | |
| "grad_norm": 0.18807543814182281, | |
| "learning_rate": 1.630187319692492e-05, | |
| "loss": 0.7315, | |
| "mean_token_accuracy": 0.7885193258523941, | |
| "num_tokens": 2297692580.0, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 1.0990344144590245, | |
| "grad_norm": 0.21502210199832916, | |
| "learning_rate": 1.6266531332221097e-05, | |
| "loss": 0.7279, | |
| "mean_token_accuracy": 0.7890672951936721, | |
| "num_tokens": 2308090705.0, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.1039861351819757, | |
| "grad_norm": 0.1803969144821167, | |
| "learning_rate": 1.6231077266012545e-05, | |
| "loss": 0.7281, | |
| "mean_token_accuracy": 0.7891331762075424, | |
| "num_tokens": 2318497722.0, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 1.108937855904927, | |
| "grad_norm": 0.18801762163639069, | |
| "learning_rate": 1.6195512054443294e-05, | |
| "loss": 0.7226, | |
| "mean_token_accuracy": 0.7904093325138092, | |
| "num_tokens": 2328861172.0, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.1138895766278782, | |
| "grad_norm": 0.20595437288284302, | |
| "learning_rate": 1.6159836756968296e-05, | |
| "loss": 0.7325, | |
| "mean_token_accuracy": 0.787862503528595, | |
| "num_tokens": 2339258549.0, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.1188412973508295, | |
| "grad_norm": 0.20336276292800903, | |
| "learning_rate": 1.6124052436321846e-05, | |
| "loss": 0.7289, | |
| "mean_token_accuracy": 0.7888852953910828, | |
| "num_tokens": 2349685068.0, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.1237930180737807, | |
| "grad_norm": 0.198221817612648, | |
| "learning_rate": 1.608816015848596e-05, | |
| "loss": 0.7249, | |
| "mean_token_accuracy": 0.7904265612363816, | |
| "num_tokens": 2360095914.0, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 1.128744738796732, | |
| "grad_norm": 0.19925156235694885, | |
| "learning_rate": 1.6052160992658584e-05, | |
| "loss": 0.726, | |
| "mean_token_accuracy": 0.7895150870084763, | |
| "num_tokens": 2370491516.0, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.133696459519683, | |
| "grad_norm": 0.2183285653591156, | |
| "learning_rate": 1.6016056011221764e-05, | |
| "loss": 0.7223, | |
| "mean_token_accuracy": 0.7908050715923309, | |
| "num_tokens": 2380881645.0, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 1.1386481802426343, | |
| "grad_norm": 0.23983266949653625, | |
| "learning_rate": 1.5979846289709695e-05, | |
| "loss": 0.7261, | |
| "mean_token_accuracy": 0.7894744217395783, | |
| "num_tokens": 2391278281.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.1435999009655855, | |
| "grad_norm": 0.18753401935100555, | |
| "learning_rate": 1.5943532906776683e-05, | |
| "loss": 0.7185, | |
| "mean_token_accuracy": 0.7921951532363891, | |
| "num_tokens": 2401703056.0, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 1.1485516216885368, | |
| "grad_norm": 0.20767702162265778, | |
| "learning_rate": 1.5907116944165017e-05, | |
| "loss": 0.7294, | |
| "mean_token_accuracy": 0.7886975765228271, | |
| "num_tokens": 2412114255.0, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.153503342411488, | |
| "grad_norm": 0.2048075795173645, | |
| "learning_rate": 1.5870599486672725e-05, | |
| "loss": 0.7298, | |
| "mean_token_accuracy": 0.7886143833398819, | |
| "num_tokens": 2422532845.0, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 1.1584550631344392, | |
| "grad_norm": 0.20132844150066376, | |
| "learning_rate": 1.583398162212129e-05, | |
| "loss": 0.723, | |
| "mean_token_accuracy": 0.7906926244497299, | |
| "num_tokens": 2432907783.0, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.1634067838573905, | |
| "grad_norm": 0.24149557948112488, | |
| "learning_rate": 1.5797264441323227e-05, | |
| "loss": 0.7279, | |
| "mean_token_accuracy": 0.7897651940584183, | |
| "num_tokens": 2443315467.0, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.1683585045803417, | |
| "grad_norm": 0.22159512341022491, | |
| "learning_rate": 1.576044903804958e-05, | |
| "loss": 0.7292, | |
| "mean_token_accuracy": 0.7884950757026672, | |
| "num_tokens": 2453711162.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.173310225303293, | |
| "grad_norm": 0.20547987520694733, | |
| "learning_rate": 1.572353650899737e-05, | |
| "loss": 0.7184, | |
| "mean_token_accuracy": 0.7916571944952011, | |
| "num_tokens": 2464145240.0, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 1.178261946026244, | |
| "grad_norm": 0.21845729649066925, | |
| "learning_rate": 1.568652795375688e-05, | |
| "loss": 0.7266, | |
| "mean_token_accuracy": 0.7894676387310028, | |
| "num_tokens": 2474536824.0, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.1832136667491953, | |
| "grad_norm": 0.20706267654895782, | |
| "learning_rate": 1.5649424474778943e-05, | |
| "loss": 0.7465, | |
| "mean_token_accuracy": 0.7838758409023285, | |
| "num_tokens": 2484953507.0, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 1.1881653874721465, | |
| "grad_norm": 0.20287451148033142, | |
| "learning_rate": 1.5612227177342075e-05, | |
| "loss": 0.7305, | |
| "mean_token_accuracy": 0.788197448849678, | |
| "num_tokens": 2495362940.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.1931171081950978, | |
| "grad_norm": 0.19987879693508148, | |
| "learning_rate": 1.5574937169519567e-05, | |
| "loss": 0.7227, | |
| "mean_token_accuracy": 0.7905563831329345, | |
| "num_tokens": 2505783339.0, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 1.198068828918049, | |
| "grad_norm": 0.20694401860237122, | |
| "learning_rate": 1.5537555562146455e-05, | |
| "loss": 0.7249, | |
| "mean_token_accuracy": 0.7901411831378937, | |
| "num_tokens": 2516210266.0, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.2030205496410002, | |
| "grad_norm": 0.19224272668361664, | |
| "learning_rate": 1.5500083468786452e-05, | |
| "loss": 0.7273, | |
| "mean_token_accuracy": 0.7893536627292633, | |
| "num_tokens": 2526623484.0, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 1.2079722703639515, | |
| "grad_norm": 0.2035578191280365, | |
| "learning_rate": 1.546252200569875e-05, | |
| "loss": 0.7284, | |
| "mean_token_accuracy": 0.7887589871883393, | |
| "num_tokens": 2537014982.0, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.2129239910869027, | |
| "grad_norm": 1.5885528326034546, | |
| "learning_rate": 1.5424872291804807e-05, | |
| "loss": 0.7253, | |
| "mean_token_accuracy": 0.792636951804161, | |
| "num_tokens": 2547427138.0, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.217875711809854, | |
| "grad_norm": 0.18842822313308716, | |
| "learning_rate": 1.5387135448654968e-05, | |
| "loss": 0.7292, | |
| "mean_token_accuracy": 0.7887994408607483, | |
| "num_tokens": 2557828037.0, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.2228274325328052, | |
| "grad_norm": 0.19046075642108917, | |
| "learning_rate": 1.534931260039509e-05, | |
| "loss": 0.7311, | |
| "mean_token_accuracy": 0.7879103571176529, | |
| "num_tokens": 2568241802.0, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 1.2277791532557565, | |
| "grad_norm": 0.18367241322994232, | |
| "learning_rate": 1.5311404873733043e-05, | |
| "loss": 0.7258, | |
| "mean_token_accuracy": 0.7896815687417984, | |
| "num_tokens": 2578599008.0, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 1.2327308739787075, | |
| "grad_norm": 0.18008632957935333, | |
| "learning_rate": 1.5273413397905142e-05, | |
| "loss": 0.7133, | |
| "mean_token_accuracy": 0.7930183291435242, | |
| "num_tokens": 2589008154.0, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 1.2376825947016588, | |
| "grad_norm": 0.20123504102230072, | |
| "learning_rate": 1.5235339304642521e-05, | |
| "loss": 0.7247, | |
| "mean_token_accuracy": 0.7899129718542099, | |
| "num_tokens": 2599435416.0, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.24263431542461, | |
| "grad_norm": 0.19925780594348907, | |
| "learning_rate": 1.5197183728137402e-05, | |
| "loss": 0.7339, | |
| "mean_token_accuracy": 0.787640643119812, | |
| "num_tokens": 2609816008.0, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 1.2475860361475613, | |
| "grad_norm": 0.19969385862350464, | |
| "learning_rate": 1.5158947805009317e-05, | |
| "loss": 0.715, | |
| "mean_token_accuracy": 0.7925884634256363, | |
| "num_tokens": 2620222628.0, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 1.2525377568705125, | |
| "grad_norm": 0.1753593236207962, | |
| "learning_rate": 1.5120632674271265e-05, | |
| "loss": 0.7236, | |
| "mean_token_accuracy": 0.790338072180748, | |
| "num_tokens": 2630612525.0, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 1.2574894775934637, | |
| "grad_norm": 0.19997967779636383, | |
| "learning_rate": 1.5082239477295745e-05, | |
| "loss": 0.7236, | |
| "mean_token_accuracy": 0.7902151554822922, | |
| "num_tokens": 2640999606.0, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 1.262441198316415, | |
| "grad_norm": 2.163191080093384, | |
| "learning_rate": 1.5043769357780798e-05, | |
| "loss": 0.743, | |
| "mean_token_accuracy": 0.7919340342283249, | |
| "num_tokens": 2651386549.0, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.2673929190393662, | |
| "grad_norm": 0.201646625995636, | |
| "learning_rate": 1.5005223461715907e-05, | |
| "loss": 0.7177, | |
| "mean_token_accuracy": 0.7917960375547409, | |
| "num_tokens": 2661786975.0, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 1.2723446397623175, | |
| "grad_norm": 0.21226562559604645, | |
| "learning_rate": 1.4966602937347863e-05, | |
| "loss": 0.7316, | |
| "mean_token_accuracy": 0.7908751904964447, | |
| "num_tokens": 2672165640.0, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 1.2772963604852685, | |
| "grad_norm": 0.20382718741893768, | |
| "learning_rate": 1.4927908935146576e-05, | |
| "loss": 0.7258, | |
| "mean_token_accuracy": 0.7896455824375153, | |
| "num_tokens": 2682549545.0, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 1.2822480812082198, | |
| "grad_norm": 0.2759467661380768, | |
| "learning_rate": 1.488914260777079e-05, | |
| "loss": 0.7178, | |
| "mean_token_accuracy": 0.7913758844137192, | |
| "num_tokens": 2692955151.0, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 1.287199801931171, | |
| "grad_norm": 0.18792249262332916, | |
| "learning_rate": 1.4850305110033747e-05, | |
| "loss": 0.7221, | |
| "mean_token_accuracy": 0.7903568297624588, | |
| "num_tokens": 2703360987.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.2921515226541223, | |
| "grad_norm": 0.20369011163711548, | |
| "learning_rate": 1.4811397598868789e-05, | |
| "loss": 0.7261, | |
| "mean_token_accuracy": 0.7895828515291214, | |
| "num_tokens": 2713747572.0, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 1.2971032433770735, | |
| "grad_norm": 0.21133604645729065, | |
| "learning_rate": 1.4772421233294898e-05, | |
| "loss": 0.7224, | |
| "mean_token_accuracy": 0.7906721025705338, | |
| "num_tokens": 2724160321.0, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 1.3020549641000247, | |
| "grad_norm": 0.1944030076265335, | |
| "learning_rate": 1.473337717438216e-05, | |
| "loss": 0.7186, | |
| "mean_token_accuracy": 0.7915155500173569, | |
| "num_tokens": 2734551031.0, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 1.307006684822976, | |
| "grad_norm": 0.18083949387073517, | |
| "learning_rate": 1.4694266585217185e-05, | |
| "loss": 0.7232, | |
| "mean_token_accuracy": 0.7904892802238465, | |
| "num_tokens": 2744930879.0, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 1.3119584055459272, | |
| "grad_norm": 0.18224333226680756, | |
| "learning_rate": 1.4655090630868458e-05, | |
| "loss": 0.7249, | |
| "mean_token_accuracy": 0.7898193567991256, | |
| "num_tokens": 2755301410.0, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.3169101262688785, | |
| "grad_norm": 0.2043742537498474, | |
| "learning_rate": 1.4615850478351637e-05, | |
| "loss": 0.7327, | |
| "mean_token_accuracy": 0.7872727513313293, | |
| "num_tokens": 2765707788.0, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 1.3218618469918297, | |
| "grad_norm": 0.22111938893795013, | |
| "learning_rate": 1.4576547296594774e-05, | |
| "loss": 0.7276, | |
| "mean_token_accuracy": 0.7887694299221039, | |
| "num_tokens": 2776117645.0, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 1.326813567714781, | |
| "grad_norm": 0.19156336784362793, | |
| "learning_rate": 1.4537182256403522e-05, | |
| "loss": 0.7338, | |
| "mean_token_accuracy": 0.7873490035533905, | |
| "num_tokens": 2786526348.0, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 1.3317652884377322, | |
| "grad_norm": 0.1943420171737671, | |
| "learning_rate": 1.4497756530426218e-05, | |
| "loss": 0.725, | |
| "mean_token_accuracy": 0.789910814166069, | |
| "num_tokens": 2796941910.0, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 1.3367170091606833, | |
| "grad_norm": 0.17877770960330963, | |
| "learning_rate": 1.4458271293118986e-05, | |
| "loss": 0.7305, | |
| "mean_token_accuracy": 0.7884226262569427, | |
| "num_tokens": 2807339154.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.3416687298836345, | |
| "grad_norm": 0.20378288626670837, | |
| "learning_rate": 1.4418727720710736e-05, | |
| "loss": 0.7261, | |
| "mean_token_accuracy": 0.7890681326389313, | |
| "num_tokens": 2817759971.0, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 1.3466204506065858, | |
| "grad_norm": 0.19834725558757782, | |
| "learning_rate": 1.4379126991168126e-05, | |
| "loss": 0.7116, | |
| "mean_token_accuracy": 0.7931619733572006, | |
| "num_tokens": 2828136169.0, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 1.351572171329537, | |
| "grad_norm": 0.1840638518333435, | |
| "learning_rate": 1.4339470284160477e-05, | |
| "loss": 0.7304, | |
| "mean_token_accuracy": 0.7882639706134796, | |
| "num_tokens": 2838563696.0, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 1.3565238920524882, | |
| "grad_norm": 0.18524734675884247, | |
| "learning_rate": 1.4299758781024615e-05, | |
| "loss": 0.7088, | |
| "mean_token_accuracy": 0.793875104188919, | |
| "num_tokens": 2848965953.0, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 1.3614756127754395, | |
| "grad_norm": 0.1821308732032776, | |
| "learning_rate": 1.4259993664729708e-05, | |
| "loss": 0.7234, | |
| "mean_token_accuracy": 0.7902139544486999, | |
| "num_tokens": 2859343681.0, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.3664273334983907, | |
| "grad_norm": 0.1937830150127411, | |
| "learning_rate": 1.4220176119841995e-05, | |
| "loss": 0.7211, | |
| "mean_token_accuracy": 0.790678608417511, | |
| "num_tokens": 2869738016.0, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 1.371379054221342, | |
| "grad_norm": 0.18466956913471222, | |
| "learning_rate": 1.4180307332489532e-05, | |
| "loss": 0.7228, | |
| "mean_token_accuracy": 0.7902078241109848, | |
| "num_tokens": 2880142465.0, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 1.376330774944293, | |
| "grad_norm": 0.1925409734249115, | |
| "learning_rate": 1.4140388490326822e-05, | |
| "loss": 0.728, | |
| "mean_token_accuracy": 0.7886234402656556, | |
| "num_tokens": 2890524591.0, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 1.3812824956672443, | |
| "grad_norm": 0.17395733296871185, | |
| "learning_rate": 1.4100420782499466e-05, | |
| "loss": 0.7159, | |
| "mean_token_accuracy": 0.7921683073043824, | |
| "num_tokens": 2900903230.0, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 1.3862342163901955, | |
| "grad_norm": 0.17405180633068085, | |
| "learning_rate": 1.4060405399608732e-05, | |
| "loss": 0.716, | |
| "mean_token_accuracy": 0.7919426709413528, | |
| "num_tokens": 2911289063.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.3911859371131468, | |
| "grad_norm": 0.17874355614185333, | |
| "learning_rate": 1.4020343533676076e-05, | |
| "loss": 0.7161, | |
| "mean_token_accuracy": 0.79238740503788, | |
| "num_tokens": 2921712270.0, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 1.396137657836098, | |
| "grad_norm": 0.19728051126003265, | |
| "learning_rate": 1.398023637810764e-05, | |
| "loss": 0.7098, | |
| "mean_token_accuracy": 0.7940772980451584, | |
| "num_tokens": 2932122921.0, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 1.4010893785590492, | |
| "grad_norm": 0.20457538962364197, | |
| "learning_rate": 1.3940085127658707e-05, | |
| "loss": 0.7338, | |
| "mean_token_accuracy": 0.7870628893375397, | |
| "num_tokens": 2942516461.0, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 1.4060410992820005, | |
| "grad_norm": 0.18084751069545746, | |
| "learning_rate": 1.389989097839811e-05, | |
| "loss": 0.7167, | |
| "mean_token_accuracy": 0.7917933404445648, | |
| "num_tokens": 2952889986.0, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 1.4109928200049517, | |
| "grad_norm": 0.17652776837348938, | |
| "learning_rate": 1.385965512767259e-05, | |
| "loss": 0.7155, | |
| "mean_token_accuracy": 0.7922806650400162, | |
| "num_tokens": 2963310857.0, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.415944540727903, | |
| "grad_norm": 0.18736056983470917, | |
| "learning_rate": 1.3819378774071139e-05, | |
| "loss": 0.7179, | |
| "mean_token_accuracy": 0.7915126740932464, | |
| "num_tokens": 2973715953.0, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 1.4208962614508542, | |
| "grad_norm": 0.1932843029499054, | |
| "learning_rate": 1.3779063117389297e-05, | |
| "loss": 0.7066, | |
| "mean_token_accuracy": 0.7942998945713043, | |
| "num_tokens": 2984126283.0, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 1.4258479821738055, | |
| "grad_norm": 0.2286568284034729, | |
| "learning_rate": 1.3738709358593398e-05, | |
| "loss": 0.7268, | |
| "mean_token_accuracy": 0.789307501912117, | |
| "num_tokens": 2994525073.0, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 1.4307997028967567, | |
| "grad_norm": 0.19728349149227142, | |
| "learning_rate": 1.3698318699784812e-05, | |
| "loss": 0.7233, | |
| "mean_token_accuracy": 0.7898936212062836, | |
| "num_tokens": 3004926101.0, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 1.435751423619708, | |
| "grad_norm": 0.20021368563175201, | |
| "learning_rate": 1.3657892344164116e-05, | |
| "loss": 0.7093, | |
| "mean_token_accuracy": 0.7938795328140259, | |
| "num_tokens": 3015334391.0, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.440703144342659, | |
| "grad_norm": 0.17851568758487701, | |
| "learning_rate": 1.3617431495995276e-05, | |
| "loss": 0.7241, | |
| "mean_token_accuracy": 0.7900084257125854, | |
| "num_tokens": 3025730657.0, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 1.4456548650656103, | |
| "grad_norm": 0.17161023616790771, | |
| "learning_rate": 1.3576937360569747e-05, | |
| "loss": 0.729, | |
| "mean_token_accuracy": 0.7888924747705459, | |
| "num_tokens": 3036137389.0, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 1.4506065857885615, | |
| "grad_norm": 0.19351643323898315, | |
| "learning_rate": 1.3536411144170584e-05, | |
| "loss": 0.7074, | |
| "mean_token_accuracy": 0.7941448390483856, | |
| "num_tokens": 3046543020.0, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 1.4555583065115127, | |
| "grad_norm": 0.18472740054130554, | |
| "learning_rate": 1.349585405403651e-05, | |
| "loss": 0.7203, | |
| "mean_token_accuracy": 0.7905257880687714, | |
| "num_tokens": 3056948582.0, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 1.460510027234464, | |
| "grad_norm": 0.1972552090883255, | |
| "learning_rate": 1.345526729832594e-05, | |
| "loss": 0.7299, | |
| "mean_token_accuracy": 0.7882571071386337, | |
| "num_tokens": 3067348021.0, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.4654617479574152, | |
| "grad_norm": 0.19973404705524445, | |
| "learning_rate": 1.341465208608101e-05, | |
| "loss": 0.718, | |
| "mean_token_accuracy": 0.7912285208702088, | |
| "num_tokens": 3077753784.0, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 1.4704134686803665, | |
| "grad_norm": 0.19882094860076904, | |
| "learning_rate": 1.3374009627191535e-05, | |
| "loss": 0.718, | |
| "mean_token_accuracy": 0.7916070431470871, | |
| "num_tokens": 3088154461.0, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 1.4753651894033177, | |
| "grad_norm": 0.18356384336948395, | |
| "learning_rate": 1.3333341132358998e-05, | |
| "loss": 0.7102, | |
| "mean_token_accuracy": 0.7933901071548461, | |
| "num_tokens": 3098576272.0, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 1.4803169101262688, | |
| "grad_norm": 0.17706668376922607, | |
| "learning_rate": 1.3292647813060462e-05, | |
| "loss": 0.7145, | |
| "mean_token_accuracy": 0.7923637479543686, | |
| "num_tokens": 3108958161.0, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 1.48526863084922, | |
| "grad_norm": 0.7771270275115967, | |
| "learning_rate": 1.325193088151248e-05, | |
| "loss": 0.7196, | |
| "mean_token_accuracy": 0.790700152516365, | |
| "num_tokens": 3119332234.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.4902203515721713, | |
| "grad_norm": 0.1887047439813614, | |
| "learning_rate": 1.3211191550635008e-05, | |
| "loss": 0.7204, | |
| "mean_token_accuracy": 0.7904630064964294, | |
| "num_tokens": 3129741365.0, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 1.4951720722951225, | |
| "grad_norm": 0.18025922775268555, | |
| "learning_rate": 1.3170431034015242e-05, | |
| "loss": 0.7219, | |
| "mean_token_accuracy": 0.7903009295463562, | |
| "num_tokens": 3140137525.0, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 1.5001237930180737, | |
| "grad_norm": 0.1742526888847351, | |
| "learning_rate": 1.31296505458715e-05, | |
| "loss": 0.7227, | |
| "mean_token_accuracy": 0.7903249442577363, | |
| "num_tokens": 3150551214.0, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 1.505075513741025, | |
| "grad_norm": 0.17877598106861115, | |
| "learning_rate": 1.3088851301017012e-05, | |
| "loss": 0.7196, | |
| "mean_token_accuracy": 0.7908366918563843, | |
| "num_tokens": 3160963988.0, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 1.5100272344639762, | |
| "grad_norm": 0.27315303683280945, | |
| "learning_rate": 1.3048034514823768e-05, | |
| "loss": 0.72, | |
| "mean_token_accuracy": 0.7911725819110871, | |
| "num_tokens": 3171338083.0, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.5149789551869275, | |
| "grad_norm": 0.20963208377361298, | |
| "learning_rate": 1.3007201403186293e-05, | |
| "loss": 0.7189, | |
| "mean_token_accuracy": 0.7909859776496887, | |
| "num_tokens": 3181728440.0, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 1.5199306759098787, | |
| "grad_norm": 0.184099942445755, | |
| "learning_rate": 1.2966353182485435e-05, | |
| "loss": 0.7179, | |
| "mean_token_accuracy": 0.7914166182279587, | |
| "num_tokens": 3192143067.0, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 1.52488239663283, | |
| "grad_norm": 0.24152904748916626, | |
| "learning_rate": 1.2925491069552126e-05, | |
| "loss": 0.8021, | |
| "mean_token_accuracy": 0.7904890239238739, | |
| "num_tokens": 3202562250.0, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 1.5298341173557812, | |
| "grad_norm": 1.4814072847366333, | |
| "learning_rate": 1.2884616281631129e-05, | |
| "loss": 0.7134, | |
| "mean_token_accuracy": 0.7926855504512786, | |
| "num_tokens": 3212962934.0, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 1.5347858380787325, | |
| "grad_norm": 1.811551809310913, | |
| "learning_rate": 1.284373003634479e-05, | |
| "loss": 0.8015, | |
| "mean_token_accuracy": 0.7890555679798126, | |
| "num_tokens": 3223382798.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.5397375588016837, | |
| "grad_norm": 0.2511199414730072, | |
| "learning_rate": 1.2802833551656764e-05, | |
| "loss": 0.7195, | |
| "mean_token_accuracy": 0.7906852185726165, | |
| "num_tokens": 3233791747.0, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 1.544689279524635, | |
| "grad_norm": 0.20060916244983673, | |
| "learning_rate": 1.276192804583571e-05, | |
| "loss": 0.7225, | |
| "mean_token_accuracy": 0.7896364331245422, | |
| "num_tokens": 3244165580.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 1.549641000247586, | |
| "grad_norm": 0.20217087864875793, | |
| "learning_rate": 1.272101473741904e-05, | |
| "loss": 0.7316, | |
| "mean_token_accuracy": 0.7900652945041656, | |
| "num_tokens": 3254572677.0, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 1.5545927209705372, | |
| "grad_norm": 0.20432990789413452, | |
| "learning_rate": 1.2680094845176584e-05, | |
| "loss": 0.726, | |
| "mean_token_accuracy": 0.7905694574117661, | |
| "num_tokens": 3264942215.0, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 1.5595444416934885, | |
| "grad_norm": 0.1891479641199112, | |
| "learning_rate": 1.2639169588074305e-05, | |
| "loss": 0.7143, | |
| "mean_token_accuracy": 0.7926017671823502, | |
| "num_tokens": 3275326524.0, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.5644961624164397, | |
| "grad_norm": 45.705196380615234, | |
| "learning_rate": 1.2598240185237973e-05, | |
| "loss": 0.738, | |
| "mean_token_accuracy": 0.7900298535823822, | |
| "num_tokens": 3285666593.0, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 1.569447883139391, | |
| "grad_norm": 0.21276827156543732, | |
| "learning_rate": 1.2557307855916864e-05, | |
| "loss": 0.7268, | |
| "mean_token_accuracy": 0.7888426870107651, | |
| "num_tokens": 3296073717.0, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 1.574399603862342, | |
| "grad_norm": 0.17950324714183807, | |
| "learning_rate": 1.251637381944743e-05, | |
| "loss": 0.7126, | |
| "mean_token_accuracy": 0.7925331711769104, | |
| "num_tokens": 3306500839.0, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 1.5793513245852933, | |
| "grad_norm": 0.18962812423706055, | |
| "learning_rate": 1.2475439295216968e-05, | |
| "loss": 0.7245, | |
| "mean_token_accuracy": 0.7894937306642532, | |
| "num_tokens": 3316903642.0, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 1.5843030453082445, | |
| "grad_norm": 0.1753559410572052, | |
| "learning_rate": 1.2434505502627321e-05, | |
| "loss": 0.7163, | |
| "mean_token_accuracy": 0.7914654940366745, | |
| "num_tokens": 3327282929.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.5892547660311958, | |
| "grad_norm": 0.17054420709609985, | |
| "learning_rate": 1.239357366105852e-05, | |
| "loss": 0.7189, | |
| "mean_token_accuracy": 0.7911906123161316, | |
| "num_tokens": 3337714929.0, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 1.594206486754147, | |
| "grad_norm": 0.1967150866985321, | |
| "learning_rate": 1.2352644989832485e-05, | |
| "loss": 0.7176, | |
| "mean_token_accuracy": 0.7913451254367828, | |
| "num_tokens": 3348136859.0, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 1.5991582074770982, | |
| "grad_norm": 0.1789763867855072, | |
| "learning_rate": 1.2311720708176697e-05, | |
| "loss": 0.7157, | |
| "mean_token_accuracy": 0.792006203532219, | |
| "num_tokens": 3358564789.0, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 1.6041099282000495, | |
| "grad_norm": 0.17656336724758148, | |
| "learning_rate": 1.2270802035187876e-05, | |
| "loss": 0.7106, | |
| "mean_token_accuracy": 0.7932015925645828, | |
| "num_tokens": 3368938593.0, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 1.6090616489230007, | |
| "grad_norm": 0.19095465540885925, | |
| "learning_rate": 1.2229890189795659e-05, | |
| "loss": 0.7113, | |
| "mean_token_accuracy": 0.7929900795221329, | |
| "num_tokens": 3379336222.0, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.614013369645952, | |
| "grad_norm": 0.18307463824748993, | |
| "learning_rate": 1.2188986390726293e-05, | |
| "loss": 0.7164, | |
| "mean_token_accuracy": 0.792149567604065, | |
| "num_tokens": 3389758319.0, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 1.6189650903689032, | |
| "grad_norm": 0.18088825047016144, | |
| "learning_rate": 1.2148091856466348e-05, | |
| "loss": 0.7123, | |
| "mean_token_accuracy": 0.7924705147743225, | |
| "num_tokens": 3400160230.0, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 1.6239168110918545, | |
| "grad_norm": 0.1794070303440094, | |
| "learning_rate": 1.2107207805226388e-05, | |
| "loss": 0.7191, | |
| "mean_token_accuracy": 0.791198554635048, | |
| "num_tokens": 3410521557.0, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 1.6288685318148057, | |
| "grad_norm": 0.17816896736621857, | |
| "learning_rate": 1.20663354549047e-05, | |
| "loss": 0.7254, | |
| "mean_token_accuracy": 0.7890619933605194, | |
| "num_tokens": 3420912198.0, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 1.633820252537757, | |
| "grad_norm": 0.1971050202846527, | |
| "learning_rate": 1.2025476023051022e-05, | |
| "loss": 0.7218, | |
| "mean_token_accuracy": 0.7902753293514252, | |
| "num_tokens": 3431305496.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.6387719732607082, | |
| "grad_norm": 0.19463616609573364, | |
| "learning_rate": 1.1984630726830245e-05, | |
| "loss": 0.7125, | |
| "mean_token_accuracy": 0.7927158504724503, | |
| "num_tokens": 3441730859.0, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 1.6437236939836595, | |
| "grad_norm": 0.19123196601867676, | |
| "learning_rate": 1.194380078298619e-05, | |
| "loss": 0.7154, | |
| "mean_token_accuracy": 0.7916401147842407, | |
| "num_tokens": 3452131219.0, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 1.6486754147066105, | |
| "grad_norm": 0.1910821497440338, | |
| "learning_rate": 1.1902987407805338e-05, | |
| "loss": 0.7188, | |
| "mean_token_accuracy": 0.7912047028541564, | |
| "num_tokens": 3462547360.0, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 1.6536271354295617, | |
| "grad_norm": 0.18839426338672638, | |
| "learning_rate": 1.1862191817080597e-05, | |
| "loss": 0.7172, | |
| "mean_token_accuracy": 0.791377791762352, | |
| "num_tokens": 3472954780.0, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 1.658578856152513, | |
| "grad_norm": 0.189104825258255, | |
| "learning_rate": 1.1821415226075104e-05, | |
| "loss": 0.7141, | |
| "mean_token_accuracy": 0.7924461841583252, | |
| "num_tokens": 3483377399.0, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.6635305768754642, | |
| "grad_norm": 0.18031081557273865, | |
| "learning_rate": 1.1780658849486011e-05, | |
| "loss": 0.722, | |
| "mean_token_accuracy": 0.7899476200342178, | |
| "num_tokens": 3493799556.0, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 1.6684822975984155, | |
| "grad_norm": 0.18072226643562317, | |
| "learning_rate": 1.1739923901408292e-05, | |
| "loss": 0.7066, | |
| "mean_token_accuracy": 0.7940356642007828, | |
| "num_tokens": 3504215269.0, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 1.6734340183213665, | |
| "grad_norm": 0.2156570702791214, | |
| "learning_rate": 1.1699211595298589e-05, | |
| "loss": 0.7312, | |
| "mean_token_accuracy": 0.7876215547323226, | |
| "num_tokens": 3514619987.0, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 1.6783857390443178, | |
| "grad_norm": 0.18053479492664337, | |
| "learning_rate": 1.1658523143939073e-05, | |
| "loss": 0.7179, | |
| "mean_token_accuracy": 0.7913117349147797, | |
| "num_tokens": 3525029614.0, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 1.683337459767269, | |
| "grad_norm": 0.17777222394943237, | |
| "learning_rate": 1.1617859759401282e-05, | |
| "loss": 0.7248, | |
| "mean_token_accuracy": 0.7891001671552658, | |
| "num_tokens": 3535423120.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.6882891804902203, | |
| "grad_norm": 0.1804647594690323, | |
| "learning_rate": 1.1577222653010054e-05, | |
| "loss": 0.699, | |
| "mean_token_accuracy": 0.7962267965078353, | |
| "num_tokens": 3545809893.0, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 1.6932409012131715, | |
| "grad_norm": 0.177909716963768, | |
| "learning_rate": 1.1536613035307416e-05, | |
| "loss": 0.7351, | |
| "mean_token_accuracy": 0.7915727466344833, | |
| "num_tokens": 3556189451.0, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 1.6981926219361227, | |
| "grad_norm": 0.19596891105175018, | |
| "learning_rate": 1.1496032116016536e-05, | |
| "loss": 0.7146, | |
| "mean_token_accuracy": 0.7918591350317001, | |
| "num_tokens": 3566604450.0, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 1.703144342659074, | |
| "grad_norm": 0.1962021440267563, | |
| "learning_rate": 1.1455481104005682e-05, | |
| "loss": 0.7174, | |
| "mean_token_accuracy": 0.79123954474926, | |
| "num_tokens": 3577021485.0, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 1.7080960633820252, | |
| "grad_norm": 0.18883569538593292, | |
| "learning_rate": 1.1414961207252215e-05, | |
| "loss": 0.7258, | |
| "mean_token_accuracy": 0.788951313495636, | |
| "num_tokens": 3587445493.0, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.7130477841049765, | |
| "grad_norm": 0.8343937397003174, | |
| "learning_rate": 1.137447363280659e-05, | |
| "loss": 0.7242, | |
| "mean_token_accuracy": 0.7895885169506073, | |
| "num_tokens": 3597840209.0, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 1.7179995048279277, | |
| "grad_norm": 1.3068397045135498, | |
| "learning_rate": 1.1334019586756423e-05, | |
| "loss": 0.725, | |
| "mean_token_accuracy": 0.7885597527027131, | |
| "num_tokens": 3608260465.0, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 1.722951225550879, | |
| "grad_norm": 0.38125309348106384, | |
| "learning_rate": 1.1293600274190548e-05, | |
| "loss": 0.7258, | |
| "mean_token_accuracy": 0.7903095871210098, | |
| "num_tokens": 3618641232.0, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 1.7279029462738302, | |
| "grad_norm": 0.19886992871761322, | |
| "learning_rate": 1.125321689916311e-05, | |
| "loss": 0.7226, | |
| "mean_token_accuracy": 0.7916781276464462, | |
| "num_tokens": 3629053078.0, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 1.7328546669967815, | |
| "grad_norm": 0.2138087898492813, | |
| "learning_rate": 1.1212870664657718e-05, | |
| "loss": 0.7066, | |
| "mean_token_accuracy": 0.7945046842098236, | |
| "num_tokens": 3639448411.0, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.7378063877197327, | |
| "grad_norm": 0.8190533518791199, | |
| "learning_rate": 1.1172562772551598e-05, | |
| "loss": 0.7087, | |
| "mean_token_accuracy": 0.7934040397405624, | |
| "num_tokens": 3649820357.0, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 1.742758108442684, | |
| "grad_norm": 0.2707054316997528, | |
| "learning_rate": 1.1132294423579786e-05, | |
| "loss": 0.7295, | |
| "mean_token_accuracy": 0.78960200548172, | |
| "num_tokens": 3660192793.0, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 1.7477098291656352, | |
| "grad_norm": 0.21164794266223907, | |
| "learning_rate": 1.1092066817299369e-05, | |
| "loss": 0.7005, | |
| "mean_token_accuracy": 0.7957571446895599, | |
| "num_tokens": 3670581943.0, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 1.7526615498885862, | |
| "grad_norm": 0.18912960588932037, | |
| "learning_rate": 1.1051881152053747e-05, | |
| "loss": 0.7226, | |
| "mean_token_accuracy": 0.789606511592865, | |
| "num_tokens": 3680945884.0, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 1.7576132706115375, | |
| "grad_norm": 0.17918053269386292, | |
| "learning_rate": 1.1011738624936928e-05, | |
| "loss": 0.715, | |
| "mean_token_accuracy": 0.7915814012289047, | |
| "num_tokens": 3691335157.0, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.7625649913344887, | |
| "grad_norm": 0.16619303822517395, | |
| "learning_rate": 1.0971640431757887e-05, | |
| "loss": 0.7049, | |
| "mean_token_accuracy": 0.7950347632169723, | |
| "num_tokens": 3701768397.0, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 1.76751671205744, | |
| "grad_norm": 0.18657127022743225, | |
| "learning_rate": 1.0931587767004919e-05, | |
| "loss": 0.7103, | |
| "mean_token_accuracy": 0.792952173948288, | |
| "num_tokens": 3712191467.0, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 1.7724684327803912, | |
| "grad_norm": 0.1765134632587433, | |
| "learning_rate": 1.089158182381008e-05, | |
| "loss": 0.7078, | |
| "mean_token_accuracy": 0.7937531501054764, | |
| "num_tokens": 3722562525.0, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 1.7774201535033423, | |
| "grad_norm": 1.2603615522384644, | |
| "learning_rate": 1.0851623793913623e-05, | |
| "loss": 0.7374, | |
| "mean_token_accuracy": 0.7894641309976578, | |
| "num_tokens": 3732974589.0, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 1.7823718742262935, | |
| "grad_norm": 0.17135503888130188, | |
| "learning_rate": 1.081171486762852e-05, | |
| "loss": 0.7159, | |
| "mean_token_accuracy": 0.7918219327926636, | |
| "num_tokens": 3743352129.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.7873235949492448, | |
| "grad_norm": 0.1757970154285431, | |
| "learning_rate": 1.077185623380498e-05, | |
| "loss": 0.7071, | |
| "mean_token_accuracy": 0.7942558020353317, | |
| "num_tokens": 3753772930.0, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 1.792275315672196, | |
| "grad_norm": 0.19564303755760193, | |
| "learning_rate": 1.0732049079795055e-05, | |
| "loss": 0.7025, | |
| "mean_token_accuracy": 0.7953001827001571, | |
| "num_tokens": 3764169376.0, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 1.7972270363951472, | |
| "grad_norm": 0.1925610452890396, | |
| "learning_rate": 1.0692294591417258e-05, | |
| "loss": 0.7257, | |
| "mean_token_accuracy": 0.7887873202562332, | |
| "num_tokens": 3774596373.0, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 1.8021787571180985, | |
| "grad_norm": 0.17859354615211487, | |
| "learning_rate": 1.0652593952921233e-05, | |
| "loss": 0.7181, | |
| "mean_token_accuracy": 0.791176849603653, | |
| "num_tokens": 3784988118.0, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 1.8071304778410497, | |
| "grad_norm": 0.16981032490730286, | |
| "learning_rate": 1.0612948346952496e-05, | |
| "loss": 0.7166, | |
| "mean_token_accuracy": 0.7915939807891845, | |
| "num_tokens": 3795380218.0, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.812082198564001, | |
| "grad_norm": 0.1762877255678177, | |
| "learning_rate": 1.0573358954517196e-05, | |
| "loss": 0.7168, | |
| "mean_token_accuracy": 0.7909587293863296, | |
| "num_tokens": 3805800553.0, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 1.8170339192869522, | |
| "grad_norm": 0.17652231454849243, | |
| "learning_rate": 1.053382695494692e-05, | |
| "loss": 0.7102, | |
| "mean_token_accuracy": 0.7932070910930633, | |
| "num_tokens": 3816185346.0, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 1.8219856400099035, | |
| "grad_norm": 0.1817074567079544, | |
| "learning_rate": 1.0494353525863585e-05, | |
| "loss": 0.7217, | |
| "mean_token_accuracy": 0.7901755303144455, | |
| "num_tokens": 3826596047.0, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 1.8269373607328547, | |
| "grad_norm": 0.17128807306289673, | |
| "learning_rate": 1.0454939843144347e-05, | |
| "loss": 0.7118, | |
| "mean_token_accuracy": 0.7924787253141403, | |
| "num_tokens": 3837027683.0, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 1.831889081455806, | |
| "grad_norm": 0.17962965369224548, | |
| "learning_rate": 1.0415587080886566e-05, | |
| "loss": 0.7098, | |
| "mean_token_accuracy": 0.7930670648813247, | |
| "num_tokens": 3847429754.0, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.8368408021787572, | |
| "grad_norm": 1.3683093786239624, | |
| "learning_rate": 1.0376296411372842e-05, | |
| "loss": 0.7515, | |
| "mean_token_accuracy": 0.7930996656417847, | |
| "num_tokens": 3857793627.0, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 1.8417925229017085, | |
| "grad_norm": 0.1839543879032135, | |
| "learning_rate": 1.0337069005036092e-05, | |
| "loss": 0.7227, | |
| "mean_token_accuracy": 0.7897769540548325, | |
| "num_tokens": 3868206908.0, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 1.8467442436246597, | |
| "grad_norm": 0.18110202252864838, | |
| "learning_rate": 1.0297906030424673e-05, | |
| "loss": 0.704, | |
| "mean_token_accuracy": 0.7950334936380387, | |
| "num_tokens": 3878616740.0, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 1.8516959643476107, | |
| "grad_norm": 0.17166997492313385, | |
| "learning_rate": 1.0258808654167587e-05, | |
| "loss": 0.7203, | |
| "mean_token_accuracy": 0.7901737481355667, | |
| "num_tokens": 3889017125.0, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 1.856647685070562, | |
| "grad_norm": 0.19010046124458313, | |
| "learning_rate": 1.0219778040939721e-05, | |
| "loss": 0.7127, | |
| "mean_token_accuracy": 0.7925639122724533, | |
| "num_tokens": 3899392222.0, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.8615994057935132, | |
| "grad_norm": 0.18874190747737885, | |
| "learning_rate": 1.0180815353427145e-05, | |
| "loss": 0.7226, | |
| "mean_token_accuracy": 0.7896841555833817, | |
| "num_tokens": 3909822575.0, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 1.8665511265164645, | |
| "grad_norm": 0.18219928443431854, | |
| "learning_rate": 1.0141921752292496e-05, | |
| "loss": 0.7173, | |
| "mean_token_accuracy": 0.7909169375896454, | |
| "num_tokens": 3920246298.0, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 1.8715028472394157, | |
| "grad_norm": 0.1604100465774536, | |
| "learning_rate": 1.0103098396140385e-05, | |
| "loss": 0.7144, | |
| "mean_token_accuracy": 0.7919532001018524, | |
| "num_tokens": 3930666935.0, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 1.8764545679623668, | |
| "grad_norm": 0.18080103397369385, | |
| "learning_rate": 1.0064346441482886e-05, | |
| "loss": 0.7215, | |
| "mean_token_accuracy": 0.7898438304662705, | |
| "num_tokens": 3941086913.0, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 1.881406288685318, | |
| "grad_norm": 0.1699831187725067, | |
| "learning_rate": 1.0025667042705098e-05, | |
| "loss": 0.713, | |
| "mean_token_accuracy": 0.7922929584980011, | |
| "num_tokens": 3951506026.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.8863580094082693, | |
| "grad_norm": 0.1767495721578598, | |
| "learning_rate": 9.98706135203074e-06, | |
| "loss": 0.7198, | |
| "mean_token_accuracy": 0.7899861186742783, | |
| "num_tokens": 3961934535.0, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 1.8913097301312205, | |
| "grad_norm": 0.1642487794160843, | |
| "learning_rate": 9.948530519487834e-06, | |
| "loss": 0.7037, | |
| "mean_token_accuracy": 0.7950653046369552, | |
| "num_tokens": 3972338304.0, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 1.8962614508541717, | |
| "grad_norm": 0.1722268909215927, | |
| "learning_rate": 9.910075692874449e-06, | |
| "loss": 0.7201, | |
| "mean_token_accuracy": 0.7902722954750061, | |
| "num_tokens": 3982719240.0, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 1.901213171577123, | |
| "grad_norm": 0.19566771388053894, | |
| "learning_rate": 9.871698017724509e-06, | |
| "loss": 0.7242, | |
| "mean_token_accuracy": 0.7892561614513397, | |
| "num_tokens": 3993108969.0, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 1.9061648923000742, | |
| "grad_norm": 0.18446719646453857, | |
| "learning_rate": 9.833398637273662e-06, | |
| "loss": 0.7078, | |
| "mean_token_accuracy": 0.7935942828655242, | |
| "num_tokens": 4003510049.0, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 1.9111166130230255, | |
| "grad_norm": 0.20839688181877136, | |
| "learning_rate": 9.795178692425235e-06, | |
| "loss": 0.7053, | |
| "mean_token_accuracy": 0.7952834218740463, | |
| "num_tokens": 4013918937.0, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 1.9160683337459767, | |
| "grad_norm": 0.22153820097446442, | |
| "learning_rate": 9.757039321716239e-06, | |
| "loss": 0.7209, | |
| "mean_token_accuracy": 0.7898961067199707, | |
| "num_tokens": 4024319886.0, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 1.921020054468928, | |
| "grad_norm": 0.19979068636894226, | |
| "learning_rate": 9.718981661283451e-06, | |
| "loss": 0.7268, | |
| "mean_token_accuracy": 0.7883312404155731, | |
| "num_tokens": 4034745853.0, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 1.9259717751918792, | |
| "grad_norm": 0.2004430890083313, | |
| "learning_rate": 9.681006844829582e-06, | |
| "loss": 0.7137, | |
| "mean_token_accuracy": 0.7920163214206696, | |
| "num_tokens": 4045177229.0, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 1.9309234959148305, | |
| "grad_norm": 0.1783420294523239, | |
| "learning_rate": 9.643116003589491e-06, | |
| "loss": 0.7096, | |
| "mean_token_accuracy": 0.7934363096952438, | |
| "num_tokens": 4055559410.0, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.9358752166377817, | |
| "grad_norm": 0.18284736573696136, | |
| "learning_rate": 9.605310266296491e-06, | |
| "loss": 0.7135, | |
| "mean_token_accuracy": 0.7920771360397338, | |
| "num_tokens": 4065916546.0, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 1.940826937360733, | |
| "grad_norm": 0.16877685487270355, | |
| "learning_rate": 9.567590759148738e-06, | |
| "loss": 0.7175, | |
| "mean_token_accuracy": 0.7910897344350815, | |
| "num_tokens": 4076304579.0, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 1.9457786580836842, | |
| "grad_norm": 0.17678384482860565, | |
| "learning_rate": 9.529958605775658e-06, | |
| "loss": 0.7065, | |
| "mean_token_accuracy": 0.7940395891666412, | |
| "num_tokens": 4086724782.0, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 1.9507303788066355, | |
| "grad_norm": 0.1765850931406021, | |
| "learning_rate": 9.492414927204496e-06, | |
| "loss": 0.7253, | |
| "mean_token_accuracy": 0.7888664186000824, | |
| "num_tokens": 4097094346.0, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 1.9556820995295865, | |
| "grad_norm": 2.5579123497009277, | |
| "learning_rate": 9.454960841826909e-06, | |
| "loss": 0.7097, | |
| "mean_token_accuracy": 0.7934763431549072, | |
| "num_tokens": 4107490115.0, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 1.9606338202525377, | |
| "grad_norm": 0.20106090605258942, | |
| "learning_rate": 9.417597465365664e-06, | |
| "loss": 0.716, | |
| "mean_token_accuracy": 0.7909161776304245, | |
| "num_tokens": 4117890651.0, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 1.965585540975489, | |
| "grad_norm": 0.1879979968070984, | |
| "learning_rate": 9.38032591084138e-06, | |
| "loss": 0.7131, | |
| "mean_token_accuracy": 0.7916456311941147, | |
| "num_tokens": 4128290404.0, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 1.9705372616984402, | |
| "grad_norm": 0.1819096952676773, | |
| "learning_rate": 9.343147288539396e-06, | |
| "loss": 0.7124, | |
| "mean_token_accuracy": 0.7923238337039947, | |
| "num_tokens": 4138709424.0, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 1.9754889824213915, | |
| "grad_norm": 0.1816423237323761, | |
| "learning_rate": 9.306062705976678e-06, | |
| "loss": 0.7298, | |
| "mean_token_accuracy": 0.7894536226987838, | |
| "num_tokens": 4149127478.0, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 1.9804407031443425, | |
| "grad_norm": 0.17591971158981323, | |
| "learning_rate": 9.26907326786884e-06, | |
| "loss": 0.721, | |
| "mean_token_accuracy": 0.7897718787193299, | |
| "num_tokens": 4159511005.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.9853924238672938, | |
| "grad_norm": 0.17198185622692108, | |
| "learning_rate": 9.232180076097231e-06, | |
| "loss": 0.7188, | |
| "mean_token_accuracy": 0.7906899690628052, | |
| "num_tokens": 4169924279.0, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 1.990344144590245, | |
| "grad_norm": 0.19029901921749115, | |
| "learning_rate": 9.195384229676104e-06, | |
| "loss": 0.7204, | |
| "mean_token_accuracy": 0.7901058614253997, | |
| "num_tokens": 4180294171.0, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 1.9952958653131962, | |
| "grad_norm": 9.313966751098633, | |
| "learning_rate": 9.158686824719886e-06, | |
| "loss": 0.7184, | |
| "mean_token_accuracy": 0.7914641767740249, | |
| "num_tokens": 4190674704.0, | |
| "step": 2015 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.20199906826019287, | |
| "learning_rate": 9.122088954410527e-06, | |
| "loss": 0.719, | |
| "mean_token_accuracy": 0.7905858504144769, | |
| "num_tokens": 4200567795.0, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 2.0049517207229512, | |
| "grad_norm": 0.2077370285987854, | |
| "learning_rate": 9.085591708964929e-06, | |
| "loss": 0.6948, | |
| "mean_token_accuracy": 0.7967542797327042, | |
| "num_tokens": 4210992609.0, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 2.0099034414459025, | |
| "grad_norm": 0.20394857227802277, | |
| "learning_rate": 9.049196175602463e-06, | |
| "loss": 0.6952, | |
| "mean_token_accuracy": 0.7959148943424225, | |
| "num_tokens": 4221400809.0, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 2.0148551621688537, | |
| "grad_norm": 0.1789093166589737, | |
| "learning_rate": 9.012903438512609e-06, | |
| "loss": 0.6889, | |
| "mean_token_accuracy": 0.7977543532848358, | |
| "num_tokens": 4231784819.0, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 2.019806882891805, | |
| "grad_norm": 0.18632952868938446, | |
| "learning_rate": 8.97671457882263e-06, | |
| "loss": 0.6979, | |
| "mean_token_accuracy": 0.7952105075120925, | |
| "num_tokens": 4242174103.0, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 2.0247586036147562, | |
| "grad_norm": 0.1823669672012329, | |
| "learning_rate": 8.940630674565371e-06, | |
| "loss": 0.6966, | |
| "mean_token_accuracy": 0.7960813373327256, | |
| "num_tokens": 4252592838.0, | |
| "step": 2045 | |
| }, | |
| { | |
| "epoch": 2.0297103243377075, | |
| "grad_norm": 0.16959789395332336, | |
| "learning_rate": 8.904652800647158e-06, | |
| "loss": 0.6833, | |
| "mean_token_accuracy": 0.7990966290235519, | |
| "num_tokens": 4263004435.0, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.0346620450606587, | |
| "grad_norm": 0.16897161304950714, | |
| "learning_rate": 8.86878202881578e-06, | |
| "loss": 0.688, | |
| "mean_token_accuracy": 0.7975217163562774, | |
| "num_tokens": 4273410737.0, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 2.03961376578361, | |
| "grad_norm": 0.189055398106575, | |
| "learning_rate": 8.833019427628531e-06, | |
| "loss": 0.6828, | |
| "mean_token_accuracy": 0.7994821727275848, | |
| "num_tokens": 4283826894.0, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 2.0445654865065612, | |
| "grad_norm": 0.18197213113307953, | |
| "learning_rate": 8.797366062420416e-06, | |
| "loss": 0.6898, | |
| "mean_token_accuracy": 0.7973693281412124, | |
| "num_tokens": 4294236593.0, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 2.0495172072295125, | |
| "grad_norm": 0.18738311529159546, | |
| "learning_rate": 8.761822995272407e-06, | |
| "loss": 0.6881, | |
| "mean_token_accuracy": 0.7976522415876388, | |
| "num_tokens": 4304594243.0, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 2.0544689279524633, | |
| "grad_norm": 0.19521503150463104, | |
| "learning_rate": 8.726391284979782e-06, | |
| "loss": 0.692, | |
| "mean_token_accuracy": 0.7969583392143249, | |
| "num_tokens": 4315024587.0, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 2.0594206486754145, | |
| "grad_norm": 0.18976199626922607, | |
| "learning_rate": 8.691071987020608e-06, | |
| "loss": 0.6901, | |
| "mean_token_accuracy": 0.7970456808805466, | |
| "num_tokens": 4325447239.0, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 2.0643723693983658, | |
| "grad_norm": 0.17422591149806976, | |
| "learning_rate": 8.655866153524293e-06, | |
| "loss": 0.6846, | |
| "mean_token_accuracy": 0.7987291067838669, | |
| "num_tokens": 4335838712.0, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 2.069324090121317, | |
| "grad_norm": 0.18757224082946777, | |
| "learning_rate": 8.620774833240242e-06, | |
| "loss": 0.692, | |
| "mean_token_accuracy": 0.7963369220495224, | |
| "num_tokens": 4346236727.0, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 2.0742758108442683, | |
| "grad_norm": 0.17361269891262054, | |
| "learning_rate": 8.585799071506617e-06, | |
| "loss": 0.6938, | |
| "mean_token_accuracy": 0.7964360475540161, | |
| "num_tokens": 4356601719.0, | |
| "step": 2095 | |
| }, | |
| { | |
| "epoch": 2.0792275315672195, | |
| "grad_norm": 0.18412835896015167, | |
| "learning_rate": 8.550939910219198e-06, | |
| "loss": 0.6917, | |
| "mean_token_accuracy": 0.7968982100486756, | |
| "num_tokens": 4367011033.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.0841792522901708, | |
| "grad_norm": 0.17574380338191986, | |
| "learning_rate": 8.516198387800341e-06, | |
| "loss": 0.6954, | |
| "mean_token_accuracy": 0.7958818316459656, | |
| "num_tokens": 4377372385.0, | |
| "step": 2105 | |
| }, | |
| { | |
| "epoch": 2.089130973013122, | |
| "grad_norm": 0.1881859004497528, | |
| "learning_rate": 8.481575539168052e-06, | |
| "loss": 0.6886, | |
| "mean_token_accuracy": 0.7973954766988754, | |
| "num_tokens": 4387782302.0, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 2.0940826937360733, | |
| "grad_norm": 0.17383810877799988, | |
| "learning_rate": 8.447072395705154e-06, | |
| "loss": 0.6877, | |
| "mean_token_accuracy": 0.7977871656417846, | |
| "num_tokens": 4398182888.0, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 2.0990344144590245, | |
| "grad_norm": 0.18243476748466492, | |
| "learning_rate": 8.412689985228561e-06, | |
| "loss": 0.7013, | |
| "mean_token_accuracy": 0.7934758394956589, | |
| "num_tokens": 4408560198.0, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 2.1039861351819757, | |
| "grad_norm": 0.1822386533021927, | |
| "learning_rate": 8.378429331958663e-06, | |
| "loss": 0.6851, | |
| "mean_token_accuracy": 0.7983981937170028, | |
| "num_tokens": 4418974578.0, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 2.108937855904927, | |
| "grad_norm": 0.1714823991060257, | |
| "learning_rate": 8.34429145648882e-06, | |
| "loss": 0.6992, | |
| "mean_token_accuracy": 0.7948953956365585, | |
| "num_tokens": 4429365226.0, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 2.1138895766278782, | |
| "grad_norm": 0.1750471293926239, | |
| "learning_rate": 8.310277375754938e-06, | |
| "loss": 0.6984, | |
| "mean_token_accuracy": 0.7947075188159942, | |
| "num_tokens": 4439768423.0, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 2.1188412973508295, | |
| "grad_norm": 0.19049614667892456, | |
| "learning_rate": 8.276388103005215e-06, | |
| "loss": 0.6953, | |
| "mean_token_accuracy": 0.7956634342670441, | |
| "num_tokens": 4450165574.0, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 2.1237930180737807, | |
| "grad_norm": 2.0906457901000977, | |
| "learning_rate": 8.24262464776992e-06, | |
| "loss": 0.6873, | |
| "mean_token_accuracy": 0.7988680183887482, | |
| "num_tokens": 4460582540.0, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 2.128744738796732, | |
| "grad_norm": 0.1667407751083374, | |
| "learning_rate": 8.208988015831328e-06, | |
| "loss": 0.6935, | |
| "mean_token_accuracy": 0.7962657779455184, | |
| "num_tokens": 4471001266.0, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.1336964595196832, | |
| "grad_norm": 0.17646174132823944, | |
| "learning_rate": 8.17547920919378e-06, | |
| "loss": 0.7014, | |
| "mean_token_accuracy": 0.7941409230232239, | |
| "num_tokens": 4481422686.0, | |
| "step": 2155 | |
| }, | |
| { | |
| "epoch": 2.1386481802426345, | |
| "grad_norm": 0.1852479875087738, | |
| "learning_rate": 8.14209922605381e-06, | |
| "loss": 0.7038, | |
| "mean_token_accuracy": 0.7935562491416931, | |
| "num_tokens": 4491809382.0, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 2.1435999009655857, | |
| "grad_norm": 0.22626833617687225, | |
| "learning_rate": 8.108849060770418e-06, | |
| "loss": 0.68, | |
| "mean_token_accuracy": 0.7999586701393128, | |
| "num_tokens": 4502218692.0, | |
| "step": 2165 | |
| }, | |
| { | |
| "epoch": 2.148551621688537, | |
| "grad_norm": 0.1789206862449646, | |
| "learning_rate": 8.075729703835452e-06, | |
| "loss": 0.6891, | |
| "mean_token_accuracy": 0.797278082370758, | |
| "num_tokens": 4512642434.0, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 2.153503342411488, | |
| "grad_norm": 0.17580756545066833, | |
| "learning_rate": 8.042742141844102e-06, | |
| "loss": 0.6885, | |
| "mean_token_accuracy": 0.7973107606172561, | |
| "num_tokens": 4523055194.0, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2.158455063134439, | |
| "grad_norm": 0.16940629482269287, | |
| "learning_rate": 8.0098873574655e-06, | |
| "loss": 0.7002, | |
| "mean_token_accuracy": 0.7944120824337005, | |
| "num_tokens": 4533448427.0, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 2.1634067838573903, | |
| "grad_norm": 0.17267808318138123, | |
| "learning_rate": 7.977166329413462e-06, | |
| "loss": 0.7099, | |
| "mean_token_accuracy": 0.7920106083154679, | |
| "num_tokens": 4543838846.0, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 2.1683585045803415, | |
| "grad_norm": 0.1663428246974945, | |
| "learning_rate": 7.944580032417327e-06, | |
| "loss": 0.6889, | |
| "mean_token_accuracy": 0.7975029587745667, | |
| "num_tokens": 4554246437.0, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 2.1733102253032928, | |
| "grad_norm": 0.1794314682483673, | |
| "learning_rate": 7.912129437192911e-06, | |
| "loss": 0.6997, | |
| "mean_token_accuracy": 0.7946099638938904, | |
| "num_tokens": 4564611339.0, | |
| "step": 2195 | |
| }, | |
| { | |
| "epoch": 2.178261946026244, | |
| "grad_norm": 0.17238175868988037, | |
| "learning_rate": 7.879815510413607e-06, | |
| "loss": 0.691, | |
| "mean_token_accuracy": 0.7968462198972702, | |
| "num_tokens": 4575030580.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.1832136667491953, | |
| "grad_norm": 0.17889876663684845, | |
| "learning_rate": 7.847639214681575e-06, | |
| "loss": 0.6966, | |
| "mean_token_accuracy": 0.7952412754297257, | |
| "num_tokens": 4585447968.0, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 2.1881653874721465, | |
| "grad_norm": 0.17377404868602753, | |
| "learning_rate": 7.815601508499082e-06, | |
| "loss": 0.6864, | |
| "mean_token_accuracy": 0.7982388496398926, | |
| "num_tokens": 4595852149.0, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 2.1931171081950978, | |
| "grad_norm": 0.16488561034202576, | |
| "learning_rate": 7.783703346239931e-06, | |
| "loss": 0.6877, | |
| "mean_token_accuracy": 0.7979268878698349, | |
| "num_tokens": 4606229002.0, | |
| "step": 2215 | |
| }, | |
| { | |
| "epoch": 2.198068828918049, | |
| "grad_norm": 0.17260773479938507, | |
| "learning_rate": 7.75194567812104e-06, | |
| "loss": 0.6918, | |
| "mean_token_accuracy": 0.796611812710762, | |
| "num_tokens": 4616635865.0, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 2.2030205496410002, | |
| "grad_norm": 0.19267019629478455, | |
| "learning_rate": 7.720329450174143e-06, | |
| "loss": 0.6893, | |
| "mean_token_accuracy": 0.7973758280277252, | |
| "num_tokens": 4627053505.0, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 2.2079722703639515, | |
| "grad_norm": 0.17944496870040894, | |
| "learning_rate": 7.68885560421759e-06, | |
| "loss": 0.693, | |
| "mean_token_accuracy": 0.795927032828331, | |
| "num_tokens": 4637478677.0, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 2.2129239910869027, | |
| "grad_norm": 0.17361298203468323, | |
| "learning_rate": 7.657525077828317e-06, | |
| "loss": 0.6875, | |
| "mean_token_accuracy": 0.7980309188365936, | |
| "num_tokens": 4647889813.0, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 2.217875711809854, | |
| "grad_norm": 0.18098437786102295, | |
| "learning_rate": 7.626338804313888e-06, | |
| "loss": 0.7123, | |
| "mean_token_accuracy": 0.7962464898824692, | |
| "num_tokens": 4658293288.0, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 2.2228274325328052, | |
| "grad_norm": 0.1930907964706421, | |
| "learning_rate": 7.595297712684715e-06, | |
| "loss": 0.6855, | |
| "mean_token_accuracy": 0.7985998451709747, | |
| "num_tokens": 4668667335.0, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 2.2277791532557565, | |
| "grad_norm": 0.17226119339466095, | |
| "learning_rate": 7.564402727626374e-06, | |
| "loss": 0.6877, | |
| "mean_token_accuracy": 0.7977766156196594, | |
| "num_tokens": 4679079824.0, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.2327308739787077, | |
| "grad_norm": 0.17223741114139557, | |
| "learning_rate": 7.533654769472053e-06, | |
| "loss": 0.6945, | |
| "mean_token_accuracy": 0.7960464268922806, | |
| "num_tokens": 4689460943.0, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 2.237682594701659, | |
| "grad_norm": 0.1818878948688507, | |
| "learning_rate": 7.5030547541751564e-06, | |
| "loss": 0.6962, | |
| "mean_token_accuracy": 0.7953739076852798, | |
| "num_tokens": 4699876523.0, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 2.2426343154246102, | |
| "grad_norm": 0.1681259423494339, | |
| "learning_rate": 7.472603593281999e-06, | |
| "loss": 0.7003, | |
| "mean_token_accuracy": 0.7943088680505752, | |
| "num_tokens": 4710260413.0, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 2.2475860361475615, | |
| "grad_norm": 0.16561447083950043, | |
| "learning_rate": 7.442302193904658e-06, | |
| "loss": 0.6824, | |
| "mean_token_accuracy": 0.7992607623338699, | |
| "num_tokens": 4720663420.0, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 2.2525377568705123, | |
| "grad_norm": 0.16674137115478516, | |
| "learning_rate": 7.4121514586939595e-06, | |
| "loss": 0.6907, | |
| "mean_token_accuracy": 0.7970253258943558, | |
| "num_tokens": 4731065687.0, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 2.257489477593464, | |
| "grad_norm": 0.18529455363750458, | |
| "learning_rate": 7.3821522858125806e-06, | |
| "loss": 0.6839, | |
| "mean_token_accuracy": 0.798730805516243, | |
| "num_tokens": 4741479922.0, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 2.2624411983164148, | |
| "grad_norm": 0.17490680515766144, | |
| "learning_rate": 7.35230556890829e-06, | |
| "loss": 0.6796, | |
| "mean_token_accuracy": 0.8002272933721543, | |
| "num_tokens": 4751874078.0, | |
| "step": 2285 | |
| }, | |
| { | |
| "epoch": 2.267392919039366, | |
| "grad_norm": 0.18105871975421906, | |
| "learning_rate": 7.322612197087338e-06, | |
| "loss": 0.7016, | |
| "mean_token_accuracy": 0.7940381079912185, | |
| "num_tokens": 4762257864.0, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 2.2723446397623173, | |
| "grad_norm": 0.1849709004163742, | |
| "learning_rate": 7.2930730548879705e-06, | |
| "loss": 0.6884, | |
| "mean_token_accuracy": 0.7976529210805893, | |
| "num_tokens": 4772666074.0, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 2.2772963604852685, | |
| "grad_norm": 0.1883031725883484, | |
| "learning_rate": 7.263689022254065e-06, | |
| "loss": 0.6792, | |
| "mean_token_accuracy": 0.7999155551195145, | |
| "num_tokens": 4783060716.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.2822480812082198, | |
| "grad_norm": 0.16609027981758118, | |
| "learning_rate": 7.234460974508933e-06, | |
| "loss": 0.6912, | |
| "mean_token_accuracy": 0.7969788700342179, | |
| "num_tokens": 4793440305.0, | |
| "step": 2305 | |
| }, | |
| { | |
| "epoch": 2.287199801931171, | |
| "grad_norm": 0.16849201917648315, | |
| "learning_rate": 7.205389782329239e-06, | |
| "loss": 0.6921, | |
| "mean_token_accuracy": 0.7968606740236283, | |
| "num_tokens": 4803826379.0, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 2.2921515226541223, | |
| "grad_norm": 0.19212591648101807, | |
| "learning_rate": 7.176476311719067e-06, | |
| "loss": 0.6811, | |
| "mean_token_accuracy": 0.7993761092424393, | |
| "num_tokens": 4814231994.0, | |
| "step": 2315 | |
| }, | |
| { | |
| "epoch": 2.2971032433770735, | |
| "grad_norm": 0.1726553738117218, | |
| "learning_rate": 7.147721423984116e-06, | |
| "loss": 0.6904, | |
| "mean_token_accuracy": 0.7971784621477127, | |
| "num_tokens": 4824582323.0, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 2.3020549641000247, | |
| "grad_norm": 0.18482866883277893, | |
| "learning_rate": 7.119125975706047e-06, | |
| "loss": 0.6856, | |
| "mean_token_accuracy": 0.79871164560318, | |
| "num_tokens": 4835008318.0, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 2.307006684822976, | |
| "grad_norm": 0.18125054240226746, | |
| "learning_rate": 7.0906908187169745e-06, | |
| "loss": 0.7065, | |
| "mean_token_accuracy": 0.7926204591989517, | |
| "num_tokens": 4845424240.0, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 2.3119584055459272, | |
| "grad_norm": 0.1714540421962738, | |
| "learning_rate": 7.06241680007407e-06, | |
| "loss": 0.6977, | |
| "mean_token_accuracy": 0.7951288729906082, | |
| "num_tokens": 4855856505.0, | |
| "step": 2335 | |
| }, | |
| { | |
| "epoch": 2.3169101262688785, | |
| "grad_norm": 0.1746184229850769, | |
| "learning_rate": 7.034304762034352e-06, | |
| "loss": 0.701, | |
| "mean_token_accuracy": 0.794016820192337, | |
| "num_tokens": 4866252261.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 2.3218618469918297, | |
| "grad_norm": 0.16859765350818634, | |
| "learning_rate": 7.0063555420295795e-06, | |
| "loss": 0.6943, | |
| "mean_token_accuracy": 0.7958215087652206, | |
| "num_tokens": 4876680209.0, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 2.326813567714781, | |
| "grad_norm": 0.18128663301467896, | |
| "learning_rate": 6.978569972641317e-06, | |
| "loss": 0.6926, | |
| "mean_token_accuracy": 0.7966524481773376, | |
| "num_tokens": 4887065937.0, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.3317652884377322, | |
| "grad_norm": 0.1726839542388916, | |
| "learning_rate": 6.950948881576125e-06, | |
| "loss": 0.6989, | |
| "mean_token_accuracy": 0.7947970867156983, | |
| "num_tokens": 4897475666.0, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 2.3367170091606835, | |
| "grad_norm": 0.16852743923664093, | |
| "learning_rate": 6.923493091640905e-06, | |
| "loss": 0.7026, | |
| "mean_token_accuracy": 0.7934527039527893, | |
| "num_tokens": 4907847428.0, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 2.3416687298836347, | |
| "grad_norm": 0.17816710472106934, | |
| "learning_rate": 6.896203420718393e-06, | |
| "loss": 0.6935, | |
| "mean_token_accuracy": 0.7959372758865356, | |
| "num_tokens": 4918224579.0, | |
| "step": 2365 | |
| }, | |
| { | |
| "epoch": 2.346620450606586, | |
| "grad_norm": 0.1683845818042755, | |
| "learning_rate": 6.869080681742788e-06, | |
| "loss": 0.6862, | |
| "mean_token_accuracy": 0.7984416544437408, | |
| "num_tokens": 4928627391.0, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 2.351572171329537, | |
| "grad_norm": 0.1718398779630661, | |
| "learning_rate": 6.842125682675543e-06, | |
| "loss": 0.6952, | |
| "mean_token_accuracy": 0.795421975851059, | |
| "num_tokens": 4939037179.0, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 2.356523892052488, | |
| "grad_norm": 0.1837027370929718, | |
| "learning_rate": 6.8153392264812955e-06, | |
| "loss": 0.6866, | |
| "mean_token_accuracy": 0.7978436768054962, | |
| "num_tokens": 4949421774.0, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 2.3614756127754397, | |
| "grad_norm": 1.9804030656814575, | |
| "learning_rate": 6.7887221111039404e-06, | |
| "loss": 0.7244, | |
| "mean_token_accuracy": 0.7950782805681229, | |
| "num_tokens": 4959814615.0, | |
| "step": 2385 | |
| }, | |
| { | |
| "epoch": 2.3664273334983905, | |
| "grad_norm": 0.17864683270454407, | |
| "learning_rate": 6.76227512944287e-06, | |
| "loss": 0.6973, | |
| "mean_token_accuracy": 0.7949712723493576, | |
| "num_tokens": 4970222473.0, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 2.3713790542213418, | |
| "grad_norm": 0.17018389701843262, | |
| "learning_rate": 6.735999069329342e-06, | |
| "loss": 0.6848, | |
| "mean_token_accuracy": 0.79873506128788, | |
| "num_tokens": 4980635075.0, | |
| "step": 2395 | |
| }, | |
| { | |
| "epoch": 2.376330774944293, | |
| "grad_norm": 0.177368625998497, | |
| "learning_rate": 6.709894713503031e-06, | |
| "loss": 0.6904, | |
| "mean_token_accuracy": 0.7968572080135345, | |
| "num_tokens": 4991054472.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.3812824956672443, | |
| "grad_norm": 0.1928243339061737, | |
| "learning_rate": 6.68396283958869e-06, | |
| "loss": 0.6934, | |
| "mean_token_accuracy": 0.7964109271764755, | |
| "num_tokens": 5001450135.0, | |
| "step": 2405 | |
| }, | |
| { | |
| "epoch": 2.3862342163901955, | |
| "grad_norm": 0.1850307583808899, | |
| "learning_rate": 6.658204220072993e-06, | |
| "loss": 0.7007, | |
| "mean_token_accuracy": 0.7958345085382461, | |
| "num_tokens": 5011862584.0, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 2.3911859371131468, | |
| "grad_norm": 0.166819766163826, | |
| "learning_rate": 6.63261962228153e-06, | |
| "loss": 0.7039, | |
| "mean_token_accuracy": 0.7932611912488937, | |
| "num_tokens": 5022262611.0, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 2.396137657836098, | |
| "grad_norm": 0.16802161931991577, | |
| "learning_rate": 6.607209808355945e-06, | |
| "loss": 0.6956, | |
| "mean_token_accuracy": 0.795117124915123, | |
| "num_tokens": 5032675845.0, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 2.4010893785590492, | |
| "grad_norm": 0.16795934736728668, | |
| "learning_rate": 6.5819755352312245e-06, | |
| "loss": 0.6872, | |
| "mean_token_accuracy": 0.7978654116392135, | |
| "num_tokens": 5043069802.0, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 2.4060410992820005, | |
| "grad_norm": 0.17665541172027588, | |
| "learning_rate": 6.556917554613157e-06, | |
| "loss": 0.6886, | |
| "mean_token_accuracy": 0.7966871380805969, | |
| "num_tokens": 5053447114.0, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 2.4109928200049517, | |
| "grad_norm": 0.17774540185928345, | |
| "learning_rate": 6.53203661295595e-06, | |
| "loss": 0.6903, | |
| "mean_token_accuracy": 0.7966781735420227, | |
| "num_tokens": 5063846810.0, | |
| "step": 2435 | |
| }, | |
| { | |
| "epoch": 2.415944540727903, | |
| "grad_norm": 0.1691160798072815, | |
| "learning_rate": 6.50733345143997e-06, | |
| "loss": 0.6857, | |
| "mean_token_accuracy": 0.7978695631027222, | |
| "num_tokens": 5074257776.0, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 2.4208962614508542, | |
| "grad_norm": 0.18364639580249786, | |
| "learning_rate": 6.4828088059496794e-06, | |
| "loss": 0.6961, | |
| "mean_token_accuracy": 0.7960184782743454, | |
| "num_tokens": 5084664363.0, | |
| "step": 2445 | |
| }, | |
| { | |
| "epoch": 2.4258479821738055, | |
| "grad_norm": 0.18796691298484802, | |
| "learning_rate": 6.458463407051722e-06, | |
| "loss": 0.692, | |
| "mean_token_accuracy": 0.7963404774665832, | |
| "num_tokens": 5095062991.0, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.4307997028967567, | |
| "grad_norm": 0.200786754488945, | |
| "learning_rate": 6.434297979973138e-06, | |
| "loss": 0.6953, | |
| "mean_token_accuracy": 0.7957387864589691, | |
| "num_tokens": 5105475938.0, | |
| "step": 2455 | |
| }, | |
| { | |
| "epoch": 2.435751423619708, | |
| "grad_norm": 0.18357941508293152, | |
| "learning_rate": 6.41031324457978e-06, | |
| "loss": 0.7115, | |
| "mean_token_accuracy": 0.793591657280922, | |
| "num_tokens": 5115888461.0, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 2.4407031443426592, | |
| "grad_norm": 0.17939510941505432, | |
| "learning_rate": 6.386509915354858e-06, | |
| "loss": 0.7022, | |
| "mean_token_accuracy": 0.79359290599823, | |
| "num_tokens": 5126273976.0, | |
| "step": 2465 | |
| }, | |
| { | |
| "epoch": 2.4456548650656105, | |
| "grad_norm": 0.17583215236663818, | |
| "learning_rate": 6.362888701377661e-06, | |
| "loss": 0.6951, | |
| "mean_token_accuracy": 0.7956161171197891, | |
| "num_tokens": 5136658720.0, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 2.4506065857885613, | |
| "grad_norm": 0.1758909374475479, | |
| "learning_rate": 6.3394503063024305e-06, | |
| "loss": 0.6917, | |
| "mean_token_accuracy": 0.7964052438735962, | |
| "num_tokens": 5147086462.0, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 2.455558306511513, | |
| "grad_norm": 0.17750118672847748, | |
| "learning_rate": 6.3161954283374026e-06, | |
| "loss": 0.6835, | |
| "mean_token_accuracy": 0.7991193652153015, | |
| "num_tokens": 5157489366.0, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 2.4605100272344638, | |
| "grad_norm": 0.17545007169246674, | |
| "learning_rate": 6.293124760224007e-06, | |
| "loss": 0.6899, | |
| "mean_token_accuracy": 0.7971043676137924, | |
| "num_tokens": 5167911943.0, | |
| "step": 2485 | |
| }, | |
| { | |
| "epoch": 2.465461747957415, | |
| "grad_norm": 0.411289781332016, | |
| "learning_rate": 6.270238989216233e-06, | |
| "loss": 0.6868, | |
| "mean_token_accuracy": 0.7979872524738312, | |
| "num_tokens": 5178337540.0, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 2.4704134686803663, | |
| "grad_norm": 0.1767181158065796, | |
| "learning_rate": 6.247538797060153e-06, | |
| "loss": 0.6841, | |
| "mean_token_accuracy": 0.7989832788705826, | |
| "num_tokens": 5188737081.0, | |
| "step": 2495 | |
| }, | |
| { | |
| "epoch": 2.4753651894033175, | |
| "grad_norm": 0.18555793166160583, | |
| "learning_rate": 6.225024859973614e-06, | |
| "loss": 0.6948, | |
| "mean_token_accuracy": 0.7958449482917785, | |
| "num_tokens": 5199147597.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.4803169101262688, | |
| "grad_norm": 0.17499588429927826, | |
| "learning_rate": 6.202697848626098e-06, | |
| "loss": 0.6804, | |
| "mean_token_accuracy": 0.7998959481716156, | |
| "num_tokens": 5209553370.0, | |
| "step": 2505 | |
| }, | |
| { | |
| "epoch": 2.48526863084922, | |
| "grad_norm": 0.1752438247203827, | |
| "learning_rate": 6.180558428118748e-06, | |
| "loss": 0.7002, | |
| "mean_token_accuracy": 0.794254133105278, | |
| "num_tokens": 5219967341.0, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 2.4902203515721713, | |
| "grad_norm": 0.18336161971092224, | |
| "learning_rate": 6.158607257964531e-06, | |
| "loss": 0.695, | |
| "mean_token_accuracy": 0.795548141002655, | |
| "num_tokens": 5230343704.0, | |
| "step": 2515 | |
| }, | |
| { | |
| "epoch": 2.4951720722951225, | |
| "grad_norm": 0.1759299337863922, | |
| "learning_rate": 6.136844992068629e-06, | |
| "loss": 0.6811, | |
| "mean_token_accuracy": 0.7996001183986664, | |
| "num_tokens": 5240752756.0, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 2.5001237930180737, | |
| "grad_norm": 0.1809236705303192, | |
| "learning_rate": 6.115272278708928e-06, | |
| "loss": 0.6802, | |
| "mean_token_accuracy": 0.7996293097734452, | |
| "num_tokens": 5251165282.0, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 2.505075513741025, | |
| "grad_norm": 0.17464205622673035, | |
| "learning_rate": 6.093889760516718e-06, | |
| "loss": 0.6859, | |
| "mean_token_accuracy": 0.7979602038860321, | |
| "num_tokens": 5261564857.0, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 2.5100272344639762, | |
| "grad_norm": 0.19239003956317902, | |
| "learning_rate": 6.072698074457556e-06, | |
| "loss": 0.6986, | |
| "mean_token_accuracy": 0.7947456300258636, | |
| "num_tokens": 5271950567.0, | |
| "step": 2535 | |
| }, | |
| { | |
| "epoch": 2.5149789551869275, | |
| "grad_norm": 0.1785266101360321, | |
| "learning_rate": 6.051697851812283e-06, | |
| "loss": 0.6952, | |
| "mean_token_accuracy": 0.7954322129487992, | |
| "num_tokens": 5282342097.0, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 2.5199306759098787, | |
| "grad_norm": 0.1663612723350525, | |
| "learning_rate": 6.030889718158217e-06, | |
| "loss": 0.6883, | |
| "mean_token_accuracy": 0.799082663655281, | |
| "num_tokens": 5292769240.0, | |
| "step": 2545 | |
| }, | |
| { | |
| "epoch": 2.52488239663283, | |
| "grad_norm": 0.17553378641605377, | |
| "learning_rate": 6.010274293350524e-06, | |
| "loss": 0.7082, | |
| "mean_token_accuracy": 0.7952435702085495, | |
| "num_tokens": 5303167246.0, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.5298341173557812, | |
| "grad_norm": 0.17817820608615875, | |
| "learning_rate": 5.9898521915037575e-06, | |
| "loss": 0.6898, | |
| "mean_token_accuracy": 0.7968169569969177, | |
| "num_tokens": 5313559465.0, | |
| "step": 2555 | |
| }, | |
| { | |
| "epoch": 2.5347858380787325, | |
| "grad_norm": 0.17062614858150482, | |
| "learning_rate": 5.969624020973543e-06, | |
| "loss": 0.6868, | |
| "mean_token_accuracy": 0.7981322228908538, | |
| "num_tokens": 5323956814.0, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 2.5397375588016837, | |
| "grad_norm": 0.16806785762310028, | |
| "learning_rate": 5.949590384338486e-06, | |
| "loss": 0.695, | |
| "mean_token_accuracy": 0.7956575661897659, | |
| "num_tokens": 5334313471.0, | |
| "step": 2565 | |
| }, | |
| { | |
| "epoch": 2.544689279524635, | |
| "grad_norm": 0.6380743980407715, | |
| "learning_rate": 5.929751878382195e-06, | |
| "loss": 0.6903, | |
| "mean_token_accuracy": 0.7971752375364304, | |
| "num_tokens": 5344703937.0, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 2.549641000247586, | |
| "grad_norm": 0.18080659210681915, | |
| "learning_rate": 5.910109094075522e-06, | |
| "loss": 0.693, | |
| "mean_token_accuracy": 0.7960569471120834, | |
| "num_tokens": 5355109953.0, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 2.554592720970537, | |
| "grad_norm": 0.17711760103702545, | |
| "learning_rate": 5.890662616558946e-06, | |
| "loss": 0.688, | |
| "mean_token_accuracy": 0.7974663138389587, | |
| "num_tokens": 5365491606.0, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 2.5595444416934887, | |
| "grad_norm": 0.17866727709770203, | |
| "learning_rate": 5.87141302512515e-06, | |
| "loss": 0.6975, | |
| "mean_token_accuracy": 0.7948154181241989, | |
| "num_tokens": 5375911835.0, | |
| "step": 2585 | |
| }, | |
| { | |
| "epoch": 2.5644961624164395, | |
| "grad_norm": 0.1814994066953659, | |
| "learning_rate": 5.852360893201762e-06, | |
| "loss": 0.6932, | |
| "mean_token_accuracy": 0.7965142160654068, | |
| "num_tokens": 5386334595.0, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 2.569447883139391, | |
| "grad_norm": 0.16615930199623108, | |
| "learning_rate": 5.833506788334271e-06, | |
| "loss": 0.6979, | |
| "mean_token_accuracy": 0.79442700445652, | |
| "num_tokens": 5396742866.0, | |
| "step": 2595 | |
| }, | |
| { | |
| "epoch": 2.574399603862342, | |
| "grad_norm": 9.703447341918945, | |
| "learning_rate": 5.814851272169123e-06, | |
| "loss": 0.6941, | |
| "mean_token_accuracy": 0.7948618471622467, | |
| "num_tokens": 5407147677.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.5793513245852933, | |
| "grad_norm": 0.16909906268119812, | |
| "learning_rate": 5.796394900436989e-06, | |
| "loss": 0.6898, | |
| "mean_token_accuracy": 0.7968372017145157, | |
| "num_tokens": 5417532745.0, | |
| "step": 2605 | |
| }, | |
| { | |
| "epoch": 2.5843030453082445, | |
| "grad_norm": 0.17828305065631866, | |
| "learning_rate": 5.7781382229362125e-06, | |
| "loss": 0.6961, | |
| "mean_token_accuracy": 0.7956779956817627, | |
| "num_tokens": 5427899195.0, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 2.5892547660311958, | |
| "grad_norm": 0.18194948136806488, | |
| "learning_rate": 5.760081783516425e-06, | |
| "loss": 0.6924, | |
| "mean_token_accuracy": 0.7965070128440856, | |
| "num_tokens": 5438308119.0, | |
| "step": 2615 | |
| }, | |
| { | |
| "epoch": 2.594206486754147, | |
| "grad_norm": 0.16723376512527466, | |
| "learning_rate": 5.742226120062353e-06, | |
| "loss": 0.6869, | |
| "mean_token_accuracy": 0.7979160338640213, | |
| "num_tokens": 5448715457.0, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 2.5991582074770982, | |
| "grad_norm": 0.1706143170595169, | |
| "learning_rate": 5.724571764477793e-06, | |
| "loss": 0.7131, | |
| "mean_token_accuracy": 0.7919691979885102, | |
| "num_tokens": 5459086857.0, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 2.6041099282000495, | |
| "grad_norm": 0.19008710980415344, | |
| "learning_rate": 5.707119242669762e-06, | |
| "loss": 0.7094, | |
| "mean_token_accuracy": 0.794280007481575, | |
| "num_tokens": 5469483164.0, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 2.6090616489230007, | |
| "grad_norm": 0.1769382357597351, | |
| "learning_rate": 5.689869074532833e-06, | |
| "loss": 0.6939, | |
| "mean_token_accuracy": 0.7961185723543167, | |
| "num_tokens": 5479864004.0, | |
| "step": 2635 | |
| }, | |
| { | |
| "epoch": 2.614013369645952, | |
| "grad_norm": 0.2750358581542969, | |
| "learning_rate": 5.6728217739336525e-06, | |
| "loss": 0.69, | |
| "mean_token_accuracy": 0.7972733825445175, | |
| "num_tokens": 5490263383.0, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 2.6189650903689032, | |
| "grad_norm": 0.17598873376846313, | |
| "learning_rate": 5.655977848695634e-06, | |
| "loss": 0.6925, | |
| "mean_token_accuracy": 0.7967590630054474, | |
| "num_tokens": 5500650861.0, | |
| "step": 2645 | |
| }, | |
| { | |
| "epoch": 2.6239168110918545, | |
| "grad_norm": 3.034182071685791, | |
| "learning_rate": 5.639337800583815e-06, | |
| "loss": 0.6894, | |
| "mean_token_accuracy": 0.7975974589586258, | |
| "num_tokens": 5511002438.0, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.6288685318148057, | |
| "grad_norm": 0.17671412229537964, | |
| "learning_rate": 5.622902125289927e-06, | |
| "loss": 0.6939, | |
| "mean_token_accuracy": 0.7963446021080017, | |
| "num_tokens": 5521417165.0, | |
| "step": 2655 | |
| }, | |
| { | |
| "epoch": 2.633820252537757, | |
| "grad_norm": 0.16627521812915802, | |
| "learning_rate": 5.606671312417627e-06, | |
| "loss": 0.6949, | |
| "mean_token_accuracy": 0.7957168728113174, | |
| "num_tokens": 5531803294.0, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 2.6387719732607082, | |
| "grad_norm": 0.1676947921514511, | |
| "learning_rate": 5.590645845467902e-06, | |
| "loss": 0.6887, | |
| "mean_token_accuracy": 0.7975447326898575, | |
| "num_tokens": 5542196226.0, | |
| "step": 2665 | |
| }, | |
| { | |
| "epoch": 2.6437236939836595, | |
| "grad_norm": 0.16450296342372894, | |
| "learning_rate": 5.574826201824675e-06, | |
| "loss": 0.6941, | |
| "mean_token_accuracy": 0.7963021039962769, | |
| "num_tokens": 5552607704.0, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 2.6486754147066103, | |
| "grad_norm": 0.16522452235221863, | |
| "learning_rate": 5.559212852740585e-06, | |
| "loss": 0.6911, | |
| "mean_token_accuracy": 0.7966877698898316, | |
| "num_tokens": 5563008514.0, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 2.653627135429562, | |
| "grad_norm": 0.17141982913017273, | |
| "learning_rate": 5.543806263322942e-06, | |
| "loss": 0.6764, | |
| "mean_token_accuracy": 0.8007991701364517, | |
| "num_tokens": 5573414557.0, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 2.6585788561525128, | |
| "grad_norm": 0.17562955617904663, | |
| "learning_rate": 5.5286068925198765e-06, | |
| "loss": 0.6979, | |
| "mean_token_accuracy": 0.7948395520448684, | |
| "num_tokens": 5583823220.0, | |
| "step": 2685 | |
| }, | |
| { | |
| "epoch": 2.6635305768754645, | |
| "grad_norm": 0.17200249433517456, | |
| "learning_rate": 5.513615193106667e-06, | |
| "loss": 0.6858, | |
| "mean_token_accuracy": 0.7980019062757492, | |
| "num_tokens": 5594181697.0, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 2.6684822975984153, | |
| "grad_norm": 0.17699338495731354, | |
| "learning_rate": 5.4988316116722555e-06, | |
| "loss": 0.7016, | |
| "mean_token_accuracy": 0.7940513700246811, | |
| "num_tokens": 5604576881.0, | |
| "step": 2695 | |
| }, | |
| { | |
| "epoch": 2.6734340183213665, | |
| "grad_norm": 0.16659849882125854, | |
| "learning_rate": 5.484256588605935e-06, | |
| "loss": 0.6883, | |
| "mean_token_accuracy": 0.797638863325119, | |
| "num_tokens": 5614973477.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.6783857390443178, | |
| "grad_norm": 0.1654004156589508, | |
| "learning_rate": 5.469890558084242e-06, | |
| "loss": 0.6812, | |
| "mean_token_accuracy": 0.7997693717479706, | |
| "num_tokens": 5625405892.0, | |
| "step": 2705 | |
| }, | |
| { | |
| "epoch": 2.683337459767269, | |
| "grad_norm": 0.16663256287574768, | |
| "learning_rate": 5.455733948058014e-06, | |
| "loss": 0.6762, | |
| "mean_token_accuracy": 0.8006632030010223, | |
| "num_tokens": 5635805330.0, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 2.6882891804902203, | |
| "grad_norm": 0.1796761006116867, | |
| "learning_rate": 5.441787180239646e-06, | |
| "loss": 0.6917, | |
| "mean_token_accuracy": 0.7965221852064133, | |
| "num_tokens": 5646169943.0, | |
| "step": 2715 | |
| }, | |
| { | |
| "epoch": 2.6932409012131715, | |
| "grad_norm": 0.1693544238805771, | |
| "learning_rate": 5.428050670090523e-06, | |
| "loss": 0.6975, | |
| "mean_token_accuracy": 0.7954508185386657, | |
| "num_tokens": 5656576200.0, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 2.6981926219361227, | |
| "grad_norm": 0.1761597841978073, | |
| "learning_rate": 5.414524826808656e-06, | |
| "loss": 0.6924, | |
| "mean_token_accuracy": 0.7965936124324798, | |
| "num_tokens": 5666959999.0, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 2.703144342659074, | |
| "grad_norm": 0.17307810485363007, | |
| "learning_rate": 5.401210053316473e-06, | |
| "loss": 0.6841, | |
| "mean_token_accuracy": 0.7984808474779129, | |
| "num_tokens": 5677341800.0, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 2.7080960633820252, | |
| "grad_norm": 0.17702001333236694, | |
| "learning_rate": 5.388106746248834e-06, | |
| "loss": 0.6888, | |
| "mean_token_accuracy": 0.7974687486886978, | |
| "num_tokens": 5687738690.0, | |
| "step": 2735 | |
| }, | |
| { | |
| "epoch": 2.7130477841049765, | |
| "grad_norm": 0.1849050223827362, | |
| "learning_rate": 5.3752152959412085e-06, | |
| "loss": 0.6864, | |
| "mean_token_accuracy": 0.7980557024478913, | |
| "num_tokens": 5698119448.0, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 2.7179995048279277, | |
| "grad_norm": 0.18502669036388397, | |
| "learning_rate": 5.3625360864180435e-06, | |
| "loss": 0.692, | |
| "mean_token_accuracy": 0.7966047704219819, | |
| "num_tokens": 5708509953.0, | |
| "step": 2745 | |
| }, | |
| { | |
| "epoch": 2.722951225550879, | |
| "grad_norm": 0.17855456471443176, | |
| "learning_rate": 5.350069495381334e-06, | |
| "loss": 0.6839, | |
| "mean_token_accuracy": 0.7987709194421768, | |
| "num_tokens": 5718908781.0, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.7279029462738302, | |
| "grad_norm": 0.16434764862060547, | |
| "learning_rate": 5.33781589419936e-06, | |
| "loss": 0.6972, | |
| "mean_token_accuracy": 0.7953177213668823, | |
| "num_tokens": 5729301053.0, | |
| "step": 2755 | |
| }, | |
| { | |
| "epoch": 2.7328546669967815, | |
| "grad_norm": 0.18237145245075226, | |
| "learning_rate": 5.325775647895633e-06, | |
| "loss": 0.6962, | |
| "mean_token_accuracy": 0.7954672813415528, | |
| "num_tokens": 5739704125.0, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 2.7378063877197327, | |
| "grad_norm": 0.1780317723751068, | |
| "learning_rate": 5.313949115138022e-06, | |
| "loss": 0.6883, | |
| "mean_token_accuracy": 0.7975771814584732, | |
| "num_tokens": 5750099908.0, | |
| "step": 2765 | |
| }, | |
| { | |
| "epoch": 2.742758108442684, | |
| "grad_norm": 0.17902548611164093, | |
| "learning_rate": 5.302336648228057e-06, | |
| "loss": 0.6927, | |
| "mean_token_accuracy": 0.7963612645864486, | |
| "num_tokens": 5760493836.0, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 2.747709829165635, | |
| "grad_norm": 0.17271076142787933, | |
| "learning_rate": 5.290938593090451e-06, | |
| "loss": 0.6909, | |
| "mean_token_accuracy": 0.7966414868831635, | |
| "num_tokens": 5770888761.0, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 2.752661549888586, | |
| "grad_norm": 0.18384882807731628, | |
| "learning_rate": 5.279755289262787e-06, | |
| "loss": 0.6833, | |
| "mean_token_accuracy": 0.7987092226743698, | |
| "num_tokens": 5781269276.0, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 2.7576132706115377, | |
| "grad_norm": 0.1778169870376587, | |
| "learning_rate": 5.268787069885398e-06, | |
| "loss": 0.6823, | |
| "mean_token_accuracy": 0.7990261852741242, | |
| "num_tokens": 5791688485.0, | |
| "step": 2785 | |
| }, | |
| { | |
| "epoch": 2.7625649913344885, | |
| "grad_norm": 0.16034454107284546, | |
| "learning_rate": 5.258034261691453e-06, | |
| "loss": 0.6815, | |
| "mean_token_accuracy": 0.7992457032203675, | |
| "num_tokens": 5802114157.0, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 2.76751671205744, | |
| "grad_norm": 0.16529497504234314, | |
| "learning_rate": 5.2474971849972255e-06, | |
| "loss": 0.6847, | |
| "mean_token_accuracy": 0.7985988527536392, | |
| "num_tokens": 5812530733.0, | |
| "step": 2795 | |
| }, | |
| { | |
| "epoch": 2.772468432780391, | |
| "grad_norm": 0.16325139999389648, | |
| "learning_rate": 5.237176153692536e-06, | |
| "loss": 0.6901, | |
| "mean_token_accuracy": 0.796726056933403, | |
| "num_tokens": 5822937339.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.7774201535033423, | |
| "grad_norm": 0.16805361211299896, | |
| "learning_rate": 5.2270714752314165e-06, | |
| "loss": 0.6956, | |
| "mean_token_accuracy": 0.7955878287553787, | |
| "num_tokens": 5833351943.0, | |
| "step": 2805 | |
| }, | |
| { | |
| "epoch": 2.7823718742262935, | |
| "grad_norm": 0.1664312332868576, | |
| "learning_rate": 5.217183450622946e-06, | |
| "loss": 0.6949, | |
| "mean_token_accuracy": 0.7956264704465866, | |
| "num_tokens": 5843761929.0, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 2.7873235949492448, | |
| "grad_norm": 0.17172367870807648, | |
| "learning_rate": 5.207512374422286e-06, | |
| "loss": 0.6951, | |
| "mean_token_accuracy": 0.7955891370773316, | |
| "num_tokens": 5854173653.0, | |
| "step": 2815 | |
| }, | |
| { | |
| "epoch": 2.792275315672196, | |
| "grad_norm": 0.1718735694885254, | |
| "learning_rate": 5.198058534721901e-06, | |
| "loss": 0.6852, | |
| "mean_token_accuracy": 0.7985197186470032, | |
| "num_tokens": 5864593712.0, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 2.7972270363951472, | |
| "grad_norm": 0.16640879213809967, | |
| "learning_rate": 5.188822213142984e-06, | |
| "loss": 0.7016, | |
| "mean_token_accuracy": 0.7935741305351257, | |
| "num_tokens": 5875001155.0, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 2.8021787571180985, | |
| "grad_norm": 0.17045748233795166, | |
| "learning_rate": 5.179803684827059e-06, | |
| "loss": 0.6986, | |
| "mean_token_accuracy": 0.795042735338211, | |
| "num_tokens": 5885336862.0, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 2.8071304778410497, | |
| "grad_norm": 0.16793885827064514, | |
| "learning_rate": 5.1710032184277946e-06, | |
| "loss": 0.6857, | |
| "mean_token_accuracy": 0.7980520844459533, | |
| "num_tokens": 5895740091.0, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 2.812082198564001, | |
| "grad_norm": 0.1670074313879013, | |
| "learning_rate": 5.1624210761029904e-06, | |
| "loss": 0.6815, | |
| "mean_token_accuracy": 0.7995127648115158, | |
| "num_tokens": 5906130721.0, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 2.8170339192869522, | |
| "grad_norm": 1.144707441329956, | |
| "learning_rate": 5.154057513506772e-06, | |
| "loss": 0.6905, | |
| "mean_token_accuracy": 0.7972240179777146, | |
| "num_tokens": 5916514276.0, | |
| "step": 2845 | |
| }, | |
| { | |
| "epoch": 2.8219856400099035, | |
| "grad_norm": 0.16775400936603546, | |
| "learning_rate": 5.145912779781981e-06, | |
| "loss": 0.688, | |
| "mean_token_accuracy": 0.7972176611423493, | |
| "num_tokens": 5926925572.0, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.8269373607328547, | |
| "grad_norm": 0.16344526410102844, | |
| "learning_rate": 5.137987117552745e-06, | |
| "loss": 0.7021, | |
| "mean_token_accuracy": 0.7939132809638977, | |
| "num_tokens": 5937352792.0, | |
| "step": 2855 | |
| }, | |
| { | |
| "epoch": 2.831889081455806, | |
| "grad_norm": 0.16780716180801392, | |
| "learning_rate": 5.130280762917252e-06, | |
| "loss": 0.7046, | |
| "mean_token_accuracy": 0.7929495930671692, | |
| "num_tokens": 5947785733.0, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 2.8368408021787572, | |
| "grad_norm": 0.16962361335754395, | |
| "learning_rate": 5.12279394544072e-06, | |
| "loss": 0.6894, | |
| "mean_token_accuracy": 0.7973616749048233, | |
| "num_tokens": 5958207857.0, | |
| "step": 2865 | |
| }, | |
| { | |
| "epoch": 2.8417925229017085, | |
| "grad_norm": 0.17526820302009583, | |
| "learning_rate": 5.11552688814856e-06, | |
| "loss": 0.6918, | |
| "mean_token_accuracy": 0.7963843405246734, | |
| "num_tokens": 5968621626.0, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 2.8467442436246597, | |
| "grad_norm": 0.17461900413036346, | |
| "learning_rate": 5.10847980751972e-06, | |
| "loss": 0.6854, | |
| "mean_token_accuracy": 0.7982411950826644, | |
| "num_tokens": 5979010182.0, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 2.851695964347611, | |
| "grad_norm": 0.17215755581855774, | |
| "learning_rate": 5.101652913480259e-06, | |
| "loss": 0.694, | |
| "mean_token_accuracy": 0.7959240406751633, | |
| "num_tokens": 5989447180.0, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 2.8566476850705618, | |
| "grad_norm": 0.17169933021068573, | |
| "learning_rate": 5.095046409397067e-06, | |
| "loss": 0.6948, | |
| "mean_token_accuracy": 0.7955931961536408, | |
| "num_tokens": 5999857552.0, | |
| "step": 2885 | |
| }, | |
| { | |
| "epoch": 2.8615994057935135, | |
| "grad_norm": 0.17529842257499695, | |
| "learning_rate": 5.088660492071825e-06, | |
| "loss": 0.6841, | |
| "mean_token_accuracy": 0.798897260427475, | |
| "num_tokens": 6010272989.0, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 2.8665511265164643, | |
| "grad_norm": 0.1800571084022522, | |
| "learning_rate": 5.0824953517351405e-06, | |
| "loss": 0.6984, | |
| "mean_token_accuracy": 0.7946085125207901, | |
| "num_tokens": 6020661047.0, | |
| "step": 2895 | |
| }, | |
| { | |
| "epoch": 2.871502847239416, | |
| "grad_norm": 0.17649812996387482, | |
| "learning_rate": 5.076551172040875e-06, | |
| "loss": 0.6959, | |
| "mean_token_accuracy": 0.7954695582389831, | |
| "num_tokens": 6031045781.0, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.8764545679623668, | |
| "grad_norm": 0.16285355389118195, | |
| "learning_rate": 5.070828130060673e-06, | |
| "loss": 0.6855, | |
| "mean_token_accuracy": 0.798177295923233, | |
| "num_tokens": 6041474006.0, | |
| "step": 2905 | |
| }, | |
| { | |
| "epoch": 2.881406288685318, | |
| "grad_norm": 0.16973961889743805, | |
| "learning_rate": 5.065326396278693e-06, | |
| "loss": 0.6925, | |
| "mean_token_accuracy": 0.796346840262413, | |
| "num_tokens": 6051837040.0, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 2.8863580094082693, | |
| "grad_norm": 0.16173960268497467, | |
| "learning_rate": 5.0600461345865285e-06, | |
| "loss": 0.6896, | |
| "mean_token_accuracy": 0.7969261765480041, | |
| "num_tokens": 6062203773.0, | |
| "step": 2915 | |
| }, | |
| { | |
| "epoch": 2.8913097301312205, | |
| "grad_norm": 0.1653313934803009, | |
| "learning_rate": 5.054987502278314e-06, | |
| "loss": 0.6951, | |
| "mean_token_accuracy": 0.7956225961446762, | |
| "num_tokens": 6072598868.0, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 2.8962614508541717, | |
| "grad_norm": 0.17829228937625885, | |
| "learning_rate": 5.050150650046057e-06, | |
| "loss": 0.6903, | |
| "mean_token_accuracy": 0.7967943876981736, | |
| "num_tokens": 6082977828.0, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 2.901213171577123, | |
| "grad_norm": 0.17155008018016815, | |
| "learning_rate": 5.045535721975139e-06, | |
| "loss": 0.6914, | |
| "mean_token_accuracy": 0.7963936567306519, | |
| "num_tokens": 6093369909.0, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 2.9061648923000742, | |
| "grad_norm": 0.17488369345664978, | |
| "learning_rate": 5.04114285554002e-06, | |
| "loss": 0.6966, | |
| "mean_token_accuracy": 0.7955116271972656, | |
| "num_tokens": 6103768699.0, | |
| "step": 2935 | |
| }, | |
| { | |
| "epoch": 2.9111166130230255, | |
| "grad_norm": 0.16874125599861145, | |
| "learning_rate": 5.036972181600154e-06, | |
| "loss": 0.6881, | |
| "mean_token_accuracy": 0.7975889980793, | |
| "num_tokens": 6114197901.0, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 2.9160683337459767, | |
| "grad_norm": 0.1702135056257248, | |
| "learning_rate": 5.033023824396082e-06, | |
| "loss": 0.7025, | |
| "mean_token_accuracy": 0.7945420503616333, | |
| "num_tokens": 6124566479.0, | |
| "step": 2945 | |
| }, | |
| { | |
| "epoch": 2.921020054468928, | |
| "grad_norm": 0.16955436766147614, | |
| "learning_rate": 5.0292979015457325e-06, | |
| "loss": 0.6916, | |
| "mean_token_accuracy": 0.7963980317115784, | |
| "num_tokens": 6134987535.0, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.9259717751918792, | |
| "grad_norm": 0.1785793900489807, | |
| "learning_rate": 5.025794524040922e-06, | |
| "loss": 0.6845, | |
| "mean_token_accuracy": 0.7987745195627213, | |
| "num_tokens": 6145413537.0, | |
| "step": 2955 | |
| }, | |
| { | |
| "epoch": 2.9309234959148305, | |
| "grad_norm": 0.17144745588302612, | |
| "learning_rate": 5.0225137962440465e-06, | |
| "loss": 0.697, | |
| "mean_token_accuracy": 0.7954545766115189, | |
| "num_tokens": 6155794207.0, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 2.9358752166377817, | |
| "grad_norm": 0.18841952085494995, | |
| "learning_rate": 5.019455815884967e-06, | |
| "loss": 0.6879, | |
| "mean_token_accuracy": 0.7973819732666015, | |
| "num_tokens": 6166202934.0, | |
| "step": 2965 | |
| }, | |
| { | |
| "epoch": 2.940826937360733, | |
| "grad_norm": 0.17883515357971191, | |
| "learning_rate": 5.016620674058109e-06, | |
| "loss": 0.6978, | |
| "mean_token_accuracy": 0.7950917452573776, | |
| "num_tokens": 6176607746.0, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 2.945778658083684, | |
| "grad_norm": 0.17126841843128204, | |
| "learning_rate": 5.014008455219739e-06, | |
| "loss": 0.694, | |
| "mean_token_accuracy": 0.795988991856575, | |
| "num_tokens": 6187015848.0, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 2.9507303788066355, | |
| "grad_norm": 0.17282164096832275, | |
| "learning_rate": 5.011619237185454e-06, | |
| "loss": 0.7228, | |
| "mean_token_accuracy": 0.7966022878885269, | |
| "num_tokens": 6197382990.0, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 2.9556820995295867, | |
| "grad_norm": 0.1636972278356552, | |
| "learning_rate": 5.0094530911278624e-06, | |
| "loss": 0.6867, | |
| "mean_token_accuracy": 0.7977098762989044, | |
| "num_tokens": 6207775709.0, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 2.9606338202525375, | |
| "grad_norm": 0.1713937222957611, | |
| "learning_rate": 5.007510081574464e-06, | |
| "loss": 0.6793, | |
| "mean_token_accuracy": 0.7998199731111526, | |
| "num_tokens": 6218181373.0, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 2.965585540975489, | |
| "grad_norm": 0.17157921195030212, | |
| "learning_rate": 5.005790266405726e-06, | |
| "loss": 0.6885, | |
| "mean_token_accuracy": 0.7975385636091232, | |
| "num_tokens": 6228604799.0, | |
| "step": 2995 | |
| }, | |
| { | |
| "epoch": 2.97053726169844, | |
| "grad_norm": 0.17099162936210632, | |
| "learning_rate": 5.004293696853359e-06, | |
| "loss": 0.6769, | |
| "mean_token_accuracy": 0.8003452003002167, | |
| "num_tokens": 6238963168.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.9754889824213917, | |
| "grad_norm": 0.16633567214012146, | |
| "learning_rate": 5.003020417498797e-06, | |
| "loss": 0.6817, | |
| "mean_token_accuracy": 0.7993758976459503, | |
| "num_tokens": 6249324175.0, | |
| "step": 3005 | |
| }, | |
| { | |
| "epoch": 2.9804407031443425, | |
| "grad_norm": 0.1645272821187973, | |
| "learning_rate": 5.001970466271859e-06, | |
| "loss": 0.6825, | |
| "mean_token_accuracy": 0.7992853671312332, | |
| "num_tokens": 6259719042.0, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 2.9853924238672938, | |
| "grad_norm": 0.16467167437076569, | |
| "learning_rate": 5.001143874449626e-06, | |
| "loss": 0.6878, | |
| "mean_token_accuracy": 0.7971955716609955, | |
| "num_tokens": 6270117034.0, | |
| "step": 3015 | |
| }, | |
| { | |
| "epoch": 2.990344144590245, | |
| "grad_norm": 0.1758957952260971, | |
| "learning_rate": 5.000540666655511e-06, | |
| "loss": 0.6922, | |
| "mean_token_accuracy": 0.7962426990270615, | |
| "num_tokens": 6280527402.0, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 2.9952958653131962, | |
| "grad_norm": 0.16724340617656708, | |
| "learning_rate": 5.000160860858517e-06, | |
| "loss": 0.6957, | |
| "mean_token_accuracy": 0.7955468863248825, | |
| "num_tokens": 6290951944.0, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.1897646188735962, | |
| "learning_rate": 5.00000446837271e-06, | |
| "loss": 0.6911, | |
| "mean_token_accuracy": 0.7958593180305079, | |
| "num_tokens": 6300851025.0, | |
| "step": 3030 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 3030, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 450, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3290528460679152e+19, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |