| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.4158415841584158, |
| "eval_steps": 500, |
| "global_step": 84, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0049504950495049506, |
| "grad_norm": 165.6728515625, |
| "learning_rate": 0.0, |
| "loss": 2.6928, |
| "mean_token_accuracy": 0.7483190298080444, |
| "num_tokens": 104498.0, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.009900990099009901, |
| "grad_norm": 161.530517578125, |
| "learning_rate": 1.020408163265306e-06, |
| "loss": 2.3319, |
| "mean_token_accuracy": 0.7603543996810913, |
| "num_tokens": 210193.0, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.01485148514851485, |
| "grad_norm": 150.32089233398438, |
| "learning_rate": 2.040816326530612e-06, |
| "loss": 2.1756, |
| "mean_token_accuracy": 0.7683653235435486, |
| "num_tokens": 320870.0, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.019801980198019802, |
| "grad_norm": 133.65406799316406, |
| "learning_rate": 3.061224489795918e-06, |
| "loss": 2.0906, |
| "mean_token_accuracy": 0.7900593280792236, |
| "num_tokens": 423958.0, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.024752475247524754, |
| "grad_norm": 74.23121643066406, |
| "learning_rate": 4.081632653061224e-06, |
| "loss": 1.5103, |
| "mean_token_accuracy": 0.8278228044509888, |
| "num_tokens": 553976.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0297029702970297, |
| "grad_norm": 46.093509674072266, |
| "learning_rate": 5.10204081632653e-06, |
| "loss": 1.1226, |
| "mean_token_accuracy": 0.8520960807800293, |
| "num_tokens": 678440.0, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.034653465346534656, |
| "grad_norm": 46.463497161865234, |
| "learning_rate": 6.122448979591836e-06, |
| "loss": 0.9491, |
| "mean_token_accuracy": 0.8520175218582153, |
| "num_tokens": 784994.0, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.039603960396039604, |
| "grad_norm": 28.580904006958008, |
| "learning_rate": 7.142857142857143e-06, |
| "loss": 0.7525, |
| "mean_token_accuracy": 0.8796514272689819, |
| "num_tokens": 903944.0, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.04455445544554455, |
| "grad_norm": 24.821674346923828, |
| "learning_rate": 8.163265306122448e-06, |
| "loss": 0.6565, |
| "mean_token_accuracy": 0.872416615486145, |
| "num_tokens": 1034570.0, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.04950495049504951, |
| "grad_norm": 10.887228012084961, |
| "learning_rate": 9.183673469387754e-06, |
| "loss": 0.4022, |
| "mean_token_accuracy": 0.8905410170555115, |
| "num_tokens": 1152867.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.054455445544554455, |
| "grad_norm": 5.107888221740723, |
| "learning_rate": 1.020408163265306e-05, |
| "loss": 0.3426, |
| "mean_token_accuracy": 0.9099155068397522, |
| "num_tokens": 1257173.0, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.0594059405940594, |
| "grad_norm": 5.273367881774902, |
| "learning_rate": 1.1224489795918365e-05, |
| "loss": 0.3159, |
| "mean_token_accuracy": 0.912696361541748, |
| "num_tokens": 1376547.0, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.06435643564356436, |
| "grad_norm": 5.543466567993164, |
| "learning_rate": 1.2244897959183673e-05, |
| "loss": 0.3551, |
| "mean_token_accuracy": 0.8995295763015747, |
| "num_tokens": 1491252.0, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.06930693069306931, |
| "grad_norm": 2.816634178161621, |
| "learning_rate": 1.3265306122448978e-05, |
| "loss": 0.2906, |
| "mean_token_accuracy": 0.914902925491333, |
| "num_tokens": 1602462.0, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.07425742574257425, |
| "grad_norm": 1.9740920066833496, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 0.2523, |
| "mean_token_accuracy": 0.9164115190505981, |
| "num_tokens": 1716250.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.07920792079207921, |
| "grad_norm": 12.809032440185547, |
| "learning_rate": 1.5306122448979588e-05, |
| "loss": 0.205, |
| "mean_token_accuracy": 0.9290636777877808, |
| "num_tokens": 1829148.0, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.08415841584158416, |
| "grad_norm": 4.836083889007568, |
| "learning_rate": 1.6326530612244897e-05, |
| "loss": 0.2509, |
| "mean_token_accuracy": 0.9245346188545227, |
| "num_tokens": 1955517.0, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.0891089108910891, |
| "grad_norm": 4.25246524810791, |
| "learning_rate": 1.7346938775510202e-05, |
| "loss": 0.2405, |
| "mean_token_accuracy": 0.9143908023834229, |
| "num_tokens": 2069041.0, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.09405940594059406, |
| "grad_norm": 3.7845351696014404, |
| "learning_rate": 1.8367346938775508e-05, |
| "loss": 0.2487, |
| "mean_token_accuracy": 0.90645432472229, |
| "num_tokens": 2181054.0, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.09900990099009901, |
| "grad_norm": 2.549825429916382, |
| "learning_rate": 1.9387755102040814e-05, |
| "loss": 0.2245, |
| "mean_token_accuracy": 0.9252662658691406, |
| "num_tokens": 2304692.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.10396039603960396, |
| "grad_norm": 1.8521400690078735, |
| "learning_rate": 2.040816326530612e-05, |
| "loss": 0.2432, |
| "mean_token_accuracy": 0.9085952043533325, |
| "num_tokens": 2405879.0, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.10891089108910891, |
| "grad_norm": 14.467047691345215, |
| "learning_rate": 2.1428571428571425e-05, |
| "loss": 0.2217, |
| "mean_token_accuracy": 0.9281641840934753, |
| "num_tokens": 2518048.0, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.11386138613861387, |
| "grad_norm": 1.6279672384262085, |
| "learning_rate": 2.244897959183673e-05, |
| "loss": 0.2203, |
| "mean_token_accuracy": 0.9257800579071045, |
| "num_tokens": 2628103.0, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.1188118811881188, |
| "grad_norm": 1.3707953691482544, |
| "learning_rate": 2.346938775510204e-05, |
| "loss": 0.1965, |
| "mean_token_accuracy": 0.9304200410842896, |
| "num_tokens": 2743629.0, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.12376237623762376, |
| "grad_norm": 1.4624476432800293, |
| "learning_rate": 2.4489795918367345e-05, |
| "loss": 0.2138, |
| "mean_token_accuracy": 0.9256216287612915, |
| "num_tokens": 2853276.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.12871287128712872, |
| "grad_norm": 1.90883207321167, |
| "learning_rate": 2.551020408163265e-05, |
| "loss": 0.2377, |
| "mean_token_accuracy": 0.9230431914329529, |
| "num_tokens": 2958468.0, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.13366336633663367, |
| "grad_norm": 2.6176726818084717, |
| "learning_rate": 2.6530612244897956e-05, |
| "loss": 0.2406, |
| "mean_token_accuracy": 0.9184833765029907, |
| "num_tokens": 3067100.0, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.13861386138613863, |
| "grad_norm": 2.280762195587158, |
| "learning_rate": 2.7551020408163262e-05, |
| "loss": 0.1831, |
| "mean_token_accuracy": 0.9332167506217957, |
| "num_tokens": 3190146.0, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.14356435643564355, |
| "grad_norm": 2.2145683765411377, |
| "learning_rate": 2.857142857142857e-05, |
| "loss": 0.1669, |
| "mean_token_accuracy": 0.9450708627700806, |
| "num_tokens": 3310558.0, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.1485148514851485, |
| "grad_norm": 2.366621494293213, |
| "learning_rate": 2.9591836734693876e-05, |
| "loss": 0.1878, |
| "mean_token_accuracy": 0.9273155331611633, |
| "num_tokens": 3420426.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.15346534653465346, |
| "grad_norm": 1.4806239604949951, |
| "learning_rate": 3.0612244897959175e-05, |
| "loss": 0.169, |
| "mean_token_accuracy": 0.9455945491790771, |
| "num_tokens": 3534704.0, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.15841584158415842, |
| "grad_norm": 1.444824457168579, |
| "learning_rate": 3.163265306122449e-05, |
| "loss": 0.1876, |
| "mean_token_accuracy": 0.9363527297973633, |
| "num_tokens": 3641047.0, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.16336633663366337, |
| "grad_norm": 1.4486163854599, |
| "learning_rate": 3.265306122448979e-05, |
| "loss": 0.1897, |
| "mean_token_accuracy": 0.9295687675476074, |
| "num_tokens": 3749990.0, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.16831683168316833, |
| "grad_norm": 1.3260676860809326, |
| "learning_rate": 3.36734693877551e-05, |
| "loss": 0.1999, |
| "mean_token_accuracy": 0.9330916404724121, |
| "num_tokens": 3862666.0, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.17326732673267325, |
| "grad_norm": 1.017840027809143, |
| "learning_rate": 3.4693877551020405e-05, |
| "loss": 0.1971, |
| "mean_token_accuracy": 0.9279285669326782, |
| "num_tokens": 3979680.0, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.1782178217821782, |
| "grad_norm": 1.6368317604064941, |
| "learning_rate": 3.571428571428571e-05, |
| "loss": 0.2097, |
| "mean_token_accuracy": 0.9269739389419556, |
| "num_tokens": 4092501.0, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.18316831683168316, |
| "grad_norm": 1.0435723066329956, |
| "learning_rate": 3.571191599318247e-05, |
| "loss": 0.1566, |
| "mean_token_accuracy": 0.9503482580184937, |
| "num_tokens": 4207843.0, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.18811881188118812, |
| "grad_norm": 0.7825528383255005, |
| "learning_rate": 3.570480766846576e-05, |
| "loss": 0.1111, |
| "mean_token_accuracy": 0.9614512324333191, |
| "num_tokens": 4324186.0, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.19306930693069307, |
| "grad_norm": 2.988823652267456, |
| "learning_rate": 3.5692963255617803e-05, |
| "loss": 0.2516, |
| "mean_token_accuracy": 0.9049086570739746, |
| "num_tokens": 4438916.0, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.19801980198019803, |
| "grad_norm": 1.458136796951294, |
| "learning_rate": 3.567638694611989e-05, |
| "loss": 0.1994, |
| "mean_token_accuracy": 0.9385653138160706, |
| "num_tokens": 4558670.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.20297029702970298, |
| "grad_norm": 1.3628311157226562, |
| "learning_rate": 3.5655084605969105e-05, |
| "loss": 0.1643, |
| "mean_token_accuracy": 0.9377856254577637, |
| "num_tokens": 4668015.0, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.2079207920792079, |
| "grad_norm": 1.4560354948043823, |
| "learning_rate": 3.5629063773602454e-05, |
| "loss": 0.1914, |
| "mean_token_accuracy": 0.9330660104751587, |
| "num_tokens": 4771756.0, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.21287128712871287, |
| "grad_norm": 0.8290072679519653, |
| "learning_rate": 3.5598333657229206e-05, |
| "loss": 0.177, |
| "mean_token_accuracy": 0.9301922917366028, |
| "num_tokens": 4883837.0, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.21782178217821782, |
| "grad_norm": 0.7425940036773682, |
| "learning_rate": 3.5562905131572275e-05, |
| "loss": 0.1596, |
| "mean_token_accuracy": 0.9404765367507935, |
| "num_tokens": 4996691.0, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.22277227722772278, |
| "grad_norm": 0.944189727306366, |
| "learning_rate": 3.5522790734019925e-05, |
| "loss": 0.1785, |
| "mean_token_accuracy": 0.9384117126464844, |
| "num_tokens": 5107561.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.22772277227722773, |
| "grad_norm": 0.812156081199646, |
| "learning_rate": 3.547800466018902e-05, |
| "loss": 0.1568, |
| "mean_token_accuracy": 0.9456015825271606, |
| "num_tokens": 5225105.0, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.23267326732673269, |
| "grad_norm": 0.7744215130805969, |
| "learning_rate": 3.542856275890153e-05, |
| "loss": 0.1525, |
| "mean_token_accuracy": 0.9495404958724976, |
| "num_tokens": 5342561.0, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.2376237623762376, |
| "grad_norm": 0.903454065322876, |
| "learning_rate": 3.5374482526575984e-05, |
| "loss": 0.1651, |
| "mean_token_accuracy": 0.9407421350479126, |
| "num_tokens": 5455591.0, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.24257425742574257, |
| "grad_norm": 1.3214086294174194, |
| "learning_rate": 3.5315783101035837e-05, |
| "loss": 0.1744, |
| "mean_token_accuracy": 0.9362902641296387, |
| "num_tokens": 5565073.0, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.24752475247524752, |
| "grad_norm": 0.8005146980285645, |
| "learning_rate": 3.525248525473702e-05, |
| "loss": 0.1454, |
| "mean_token_accuracy": 0.9459530115127563, |
| "num_tokens": 5688232.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2524752475247525, |
| "grad_norm": 0.6254926919937134, |
| "learning_rate": 3.5184611387417046e-05, |
| "loss": 0.1503, |
| "mean_token_accuracy": 0.9428662657737732, |
| "num_tokens": 5802500.0, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.25742574257425743, |
| "grad_norm": 0.9082738161087036, |
| "learning_rate": 3.5112185518168175e-05, |
| "loss": 0.1694, |
| "mean_token_accuracy": 0.9341747760772705, |
| "num_tokens": 5915781.0, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.2623762376237624, |
| "grad_norm": 0.8271608352661133, |
| "learning_rate": 3.503523327693762e-05, |
| "loss": 0.1444, |
| "mean_token_accuracy": 0.9527311325073242, |
| "num_tokens": 6022030.0, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.26732673267326734, |
| "grad_norm": 0.66136634349823, |
| "learning_rate": 3.495378189545764e-05, |
| "loss": 0.1639, |
| "mean_token_accuracy": 0.9418630003929138, |
| "num_tokens": 6135710.0, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.2722772277227723, |
| "grad_norm": 0.6775379776954651, |
| "learning_rate": 3.486786019760885e-05, |
| "loss": 0.1286, |
| "mean_token_accuracy": 0.956753134727478, |
| "num_tokens": 6263417.0, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.27722772277227725, |
| "grad_norm": 0.7992218732833862, |
| "learning_rate": 3.4777498589220016e-05, |
| "loss": 0.1453, |
| "mean_token_accuracy": 0.9437834024429321, |
| "num_tokens": 6377543.0, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.28217821782178215, |
| "grad_norm": 0.9495893716812134, |
| "learning_rate": 3.468272904730816e-05, |
| "loss": 0.1397, |
| "mean_token_accuracy": 0.9486716389656067, |
| "num_tokens": 6478040.0, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.2871287128712871, |
| "grad_norm": 0.8485062122344971, |
| "learning_rate": 3.4583585108762525e-05, |
| "loss": 0.1577, |
| "mean_token_accuracy": 0.9421030282974243, |
| "num_tokens": 6605923.0, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.29207920792079206, |
| "grad_norm": 0.734695553779602, |
| "learning_rate": 3.448010185847665e-05, |
| "loss": 0.1427, |
| "mean_token_accuracy": 0.9487179517745972, |
| "num_tokens": 6715709.0, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.297029702970297, |
| "grad_norm": 2.3073198795318604, |
| "learning_rate": 3.437231591693254e-05, |
| "loss": 0.1497, |
| "mean_token_accuracy": 0.9437426328659058, |
| "num_tokens": 6822402.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.30198019801980197, |
| "grad_norm": 1.137617826461792, |
| "learning_rate": 3.426026542724149e-05, |
| "loss": 0.1522, |
| "mean_token_accuracy": 0.9402240514755249, |
| "num_tokens": 6939378.0, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.3069306930693069, |
| "grad_norm": 1.3148894309997559, |
| "learning_rate": 3.414399004164608e-05, |
| "loss": 0.1381, |
| "mean_token_accuracy": 0.9493290185928345, |
| "num_tokens": 7064189.0, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.3118811881188119, |
| "grad_norm": 1.1512422561645508, |
| "learning_rate": 3.402353090748806e-05, |
| "loss": 0.1533, |
| "mean_token_accuracy": 0.946578860282898, |
| "num_tokens": 7170776.0, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.31683168316831684, |
| "grad_norm": 0.9241187572479248, |
| "learning_rate": 3.3898930652647245e-05, |
| "loss": 0.1775, |
| "mean_token_accuracy": 0.9367403984069824, |
| "num_tokens": 7278689.0, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.3217821782178218, |
| "grad_norm": 1.0422300100326538, |
| "learning_rate": 3.3770233370456406e-05, |
| "loss": 0.1068, |
| "mean_token_accuracy": 0.9593726396560669, |
| "num_tokens": 7392459.0, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.32673267326732675, |
| "grad_norm": 0.8059934377670288, |
| "learning_rate": 3.36374846040976e-05, |
| "loss": 0.1532, |
| "mean_token_accuracy": 0.9451424479484558, |
| "num_tokens": 7517107.0, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.3316831683168317, |
| "grad_norm": 0.6236409544944763, |
| "learning_rate": 3.35007313304854e-05, |
| "loss": 0.1187, |
| "mean_token_accuracy": 0.9510097503662109, |
| "num_tokens": 7640070.0, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.33663366336633666, |
| "grad_norm": 1.0493971109390259, |
| "learning_rate": 3.3360021943642845e-05, |
| "loss": 0.1241, |
| "mean_token_accuracy": 0.9544036388397217, |
| "num_tokens": 7755587.0, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.3415841584158416, |
| "grad_norm": 1.0448731184005737, |
| "learning_rate": 3.321540623757577e-05, |
| "loss": 0.1662, |
| "mean_token_accuracy": 0.9405199289321899, |
| "num_tokens": 7869915.0, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.3465346534653465, |
| "grad_norm": 1.1408981084823608, |
| "learning_rate": 3.3066935388651834e-05, |
| "loss": 0.1695, |
| "mean_token_accuracy": 0.9383886456489563, |
| "num_tokens": 7970379.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.35148514851485146, |
| "grad_norm": 1.079168438911438, |
| "learning_rate": 3.291466193749027e-05, |
| "loss": 0.1735, |
| "mean_token_accuracy": 0.934720516204834, |
| "num_tokens": 8082702.0, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.3564356435643564, |
| "grad_norm": 0.5276305079460144, |
| "learning_rate": 3.275863977036896e-05, |
| "loss": 0.1335, |
| "mean_token_accuracy": 0.9506468772888184, |
| "num_tokens": 8195597.0, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.3613861386138614, |
| "grad_norm": 0.7544584274291992, |
| "learning_rate": 3.259892410015518e-05, |
| "loss": 0.1343, |
| "mean_token_accuracy": 0.9449787139892578, |
| "num_tokens": 8307743.0, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.36633663366336633, |
| "grad_norm": 0.6768516898155212, |
| "learning_rate": 3.2435571446767e-05, |
| "loss": 0.1643, |
| "mean_token_accuracy": 0.9405124187469482, |
| "num_tokens": 8421272.0, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.3712871287128713, |
| "grad_norm": 0.7120800018310547, |
| "learning_rate": 3.2268639617172096e-05, |
| "loss": 0.1561, |
| "mean_token_accuracy": 0.9421091079711914, |
| "num_tokens": 8530414.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.37623762376237624, |
| "grad_norm": 0.505757749080658, |
| "learning_rate": 3.209818768493114e-05, |
| "loss": 0.1274, |
| "mean_token_accuracy": 0.9512355923652649, |
| "num_tokens": 8643782.0, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.3811881188118812, |
| "grad_norm": 0.5018423795700073, |
| "learning_rate": 3.19242759692929e-05, |
| "loss": 0.1129, |
| "mean_token_accuracy": 0.9565746188163757, |
| "num_tokens": 8763614.0, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.38613861386138615, |
| "grad_norm": 0.8065747022628784, |
| "learning_rate": 3.174696601384859e-05, |
| "loss": 0.149, |
| "mean_token_accuracy": 0.9399038553237915, |
| "num_tokens": 8879769.0, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.3910891089108911, |
| "grad_norm": 1.257886290550232, |
| "learning_rate": 3.156632056475294e-05, |
| "loss": 0.1498, |
| "mean_token_accuracy": 0.9473065733909607, |
| "num_tokens": 8987862.0, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.39603960396039606, |
| "grad_norm": 0.935289204120636, |
| "learning_rate": 3.1382403548519666e-05, |
| "loss": 0.1421, |
| "mean_token_accuracy": 0.9476122856140137, |
| "num_tokens": 9099431.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.400990099009901, |
| "grad_norm": 0.7874135971069336, |
| "learning_rate": 3.1195280049399274e-05, |
| "loss": 0.1815, |
| "mean_token_accuracy": 0.931415319442749, |
| "num_tokens": 9214239.0, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.40594059405940597, |
| "grad_norm": 0.711197555065155, |
| "learning_rate": 3.100501628634714e-05, |
| "loss": 0.1499, |
| "mean_token_accuracy": 0.942011833190918, |
| "num_tokens": 9325292.0, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.41089108910891087, |
| "grad_norm": 0.712134838104248, |
| "learning_rate": 3.081167958959007e-05, |
| "loss": 0.1444, |
| "mean_token_accuracy": 0.944846510887146, |
| "num_tokens": 9444221.0, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.4158415841584158, |
| "grad_norm": 0.9208251237869263, |
| "learning_rate": 3.061533837679957e-05, |
| "loss": 0.1531, |
| "mean_token_accuracy": 0.9469999074935913, |
| "num_tokens": 9561630.0, |
| "step": 84 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 202, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.236132347441316e+17, |
| "train_batch_size": 40, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
