| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.079365079365079, | |
| "eval_steps": 10.0, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06349206349206349, | |
| "grad_norm": 2.6885013580322266, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 0.6802, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.12698412698412698, | |
| "grad_norm": 2.6936376094818115, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.6777, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 2.5531349182128906, | |
| "learning_rate": 3e-06, | |
| "loss": 0.6596, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.25396825396825395, | |
| "grad_norm": 2.424187421798706, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.6555, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 1.7942217588424683, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6239, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 1.8231881856918335, | |
| "learning_rate": 6e-06, | |
| "loss": 0.6026, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.5988517999649048, | |
| "learning_rate": 7e-06, | |
| "loss": 0.5792, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5079365079365079, | |
| "grad_norm": 2.9265592098236084, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.5623, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 2.3679182529449463, | |
| "learning_rate": 9e-06, | |
| "loss": 0.563, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 1.9617750644683838, | |
| "learning_rate": 1e-05, | |
| "loss": 0.531, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6984126984126984, | |
| "grad_norm": 1.6389104127883911, | |
| "learning_rate": 9.99695413509548e-06, | |
| "loss": 0.5281, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.9838264584541321, | |
| "learning_rate": 9.987820251299121e-06, | |
| "loss": 0.5047, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.8253968253968254, | |
| "grad_norm": 0.770344614982605, | |
| "learning_rate": 9.972609476841368e-06, | |
| "loss": 0.474, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.7802793383598328, | |
| "learning_rate": 9.951340343707852e-06, | |
| "loss": 0.4611, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.7216910123825073, | |
| "learning_rate": 9.924038765061042e-06, | |
| "loss": 0.4371, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0158730158730158, | |
| "grad_norm": 0.6632970571517944, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 0.4297, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.0793650793650793, | |
| "grad_norm": 0.6053202152252197, | |
| "learning_rate": 9.851478631379982e-06, | |
| "loss": 0.4069, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.6438919901847839, | |
| "learning_rate": 9.806308479691595e-06, | |
| "loss": 0.3934, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.2063492063492063, | |
| "grad_norm": 0.5374646782875061, | |
| "learning_rate": 9.755282581475769e-06, | |
| "loss": 0.3871, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.2698412698412698, | |
| "grad_norm": 0.5927333831787109, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 0.3808, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.5666782259941101, | |
| "learning_rate": 9.635919272833938e-06, | |
| "loss": 0.3862, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.3968253968253967, | |
| "grad_norm": 0.5016372799873352, | |
| "learning_rate": 9.567727288213005e-06, | |
| "loss": 0.3741, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.4603174603174602, | |
| "grad_norm": 0.49143198132514954, | |
| "learning_rate": 9.493970231495836e-06, | |
| "loss": 0.3549, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5238095238095237, | |
| "grad_norm": 0.5162219405174255, | |
| "learning_rate": 9.414737964294636e-06, | |
| "loss": 0.3651, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.5873015873015874, | |
| "grad_norm": 0.47775959968566895, | |
| "learning_rate": 9.330127018922195e-06, | |
| "loss": 0.3592, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6507936507936507, | |
| "grad_norm": 0.46834897994995117, | |
| "learning_rate": 9.24024048078213e-06, | |
| "loss": 0.3527, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.7142857142857144, | |
| "grad_norm": 0.4641563892364502, | |
| "learning_rate": 9.145187862775208e-06, | |
| "loss": 0.3529, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.4632953405380249, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.3459, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.8412698412698414, | |
| "grad_norm": 0.45019394159317017, | |
| "learning_rate": 8.94005376803361e-06, | |
| "loss": 0.3438, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.9047619047619047, | |
| "grad_norm": 0.4329588711261749, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 0.33, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.9682539682539684, | |
| "grad_norm": 0.4431888461112976, | |
| "learning_rate": 8.715724127386971e-06, | |
| "loss": 0.3447, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.0317460317460316, | |
| "grad_norm": 0.47238147258758545, | |
| "learning_rate": 8.596699001693257e-06, | |
| "loss": 0.3008, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.0952380952380953, | |
| "grad_norm": 0.5701184272766113, | |
| "learning_rate": 8.473291852294986e-06, | |
| "loss": 0.2875, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.1587301587301586, | |
| "grad_norm": 0.5064907073974609, | |
| "learning_rate": 8.345653031794292e-06, | |
| "loss": 0.2952, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.7798628807067871, | |
| "learning_rate": 8.213938048432697e-06, | |
| "loss": 0.2712, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 0.5325241684913635, | |
| "learning_rate": 8.078307376628292e-06, | |
| "loss": 0.2637, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.3492063492063493, | |
| "grad_norm": 0.49044206738471985, | |
| "learning_rate": 7.938926261462366e-06, | |
| "loss": 0.2683, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.4126984126984126, | |
| "grad_norm": 0.5916954278945923, | |
| "learning_rate": 7.795964517353734e-06, | |
| "loss": 0.2663, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.4761904761904763, | |
| "grad_norm": 0.5187512040138245, | |
| "learning_rate": 7.649596321166024e-06, | |
| "loss": 0.2549, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.5396825396825395, | |
| "grad_norm": 0.4770863652229309, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 0.256, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.6031746031746033, | |
| "grad_norm": 0.5541484951972961, | |
| "learning_rate": 7.347357813929455e-06, | |
| "loss": 0.259, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.47484439611434937, | |
| "learning_rate": 7.191855733945388e-06, | |
| "loss": 0.2416, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.7301587301587302, | |
| "grad_norm": 0.45593154430389404, | |
| "learning_rate": 7.033683215379002e-06, | |
| "loss": 0.2516, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.7936507936507935, | |
| "grad_norm": 0.44038310647010803, | |
| "learning_rate": 6.873032967079562e-06, | |
| "loss": 0.2441, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.857142857142857, | |
| "grad_norm": 0.4913359582424164, | |
| "learning_rate": 6.710100716628345e-06, | |
| "loss": 0.2457, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.9206349206349205, | |
| "grad_norm": 0.4418066740036011, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.2496, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.984126984126984, | |
| "grad_norm": 0.4195603132247925, | |
| "learning_rate": 6.378186779084996e-06, | |
| "loss": 0.2426, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 3.0476190476190474, | |
| "grad_norm": 0.6628987789154053, | |
| "learning_rate": 6.209609477998339e-06, | |
| "loss": 0.2219, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 3.111111111111111, | |
| "grad_norm": 0.6746863722801208, | |
| "learning_rate": 6.039558454088796e-06, | |
| "loss": 0.1861, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 3.1746031746031744, | |
| "grad_norm": 0.6161021590232849, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 0.1909, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.238095238095238, | |
| "grad_norm": 0.9144973754882812, | |
| "learning_rate": 5.695865504800328e-06, | |
| "loss": 0.1914, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.3015873015873014, | |
| "grad_norm": 0.6513699293136597, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 0.1826, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.365079365079365, | |
| "grad_norm": 0.628818154335022, | |
| "learning_rate": 5.348782368720627e-06, | |
| "loss": 0.1832, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 3.4285714285714284, | |
| "grad_norm": 0.6313244700431824, | |
| "learning_rate": 5.174497483512506e-06, | |
| "loss": 0.1863, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 3.492063492063492, | |
| "grad_norm": 0.5745488405227661, | |
| "learning_rate": 5e-06, | |
| "loss": 0.1827, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.5330630540847778, | |
| "learning_rate": 4.825502516487497e-06, | |
| "loss": 0.1874, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.619047619047619, | |
| "grad_norm": 0.5816968679428101, | |
| "learning_rate": 4.651217631279374e-06, | |
| "loss": 0.1774, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 3.682539682539683, | |
| "grad_norm": 0.5633692145347595, | |
| "learning_rate": 4.477357683661734e-06, | |
| "loss": 0.1804, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 3.746031746031746, | |
| "grad_norm": 0.5499540567398071, | |
| "learning_rate": 4.304134495199675e-06, | |
| "loss": 0.1818, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 3.8095238095238093, | |
| "grad_norm": 0.5262036323547363, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.1807, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 3.873015873015873, | |
| "grad_norm": 0.49341198801994324, | |
| "learning_rate": 3.960441545911205e-06, | |
| "loss": 0.1776, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 3.9365079365079367, | |
| "grad_norm": 0.5164974331855774, | |
| "learning_rate": 3.790390522001662e-06, | |
| "loss": 0.1718, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.5291624665260315, | |
| "learning_rate": 3.6218132209150047e-06, | |
| "loss": 0.1861, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 4.063492063492063, | |
| "grad_norm": 0.7828826904296875, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.1443, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 4.1269841269841265, | |
| "grad_norm": 0.6188538074493408, | |
| "learning_rate": 3.289899283371657e-06, | |
| "loss": 0.143, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 4.190476190476191, | |
| "grad_norm": 0.5868484377861023, | |
| "learning_rate": 3.12696703292044e-06, | |
| "loss": 0.1404, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 4.253968253968254, | |
| "grad_norm": 0.788356602191925, | |
| "learning_rate": 2.966316784621e-06, | |
| "loss": 0.1375, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 4.317460317460317, | |
| "grad_norm": 0.7399100661277771, | |
| "learning_rate": 2.8081442660546126e-06, | |
| "loss": 0.1339, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 4.380952380952381, | |
| "grad_norm": 0.6355120539665222, | |
| "learning_rate": 2.6526421860705474e-06, | |
| "loss": 0.1237, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.6141270399093628, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 0.1266, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 4.507936507936508, | |
| "grad_norm": 0.5580875873565674, | |
| "learning_rate": 2.3504036788339763e-06, | |
| "loss": 0.1322, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 0.5608181357383728, | |
| "learning_rate": 2.204035482646267e-06, | |
| "loss": 0.1347, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 4.634920634920634, | |
| "grad_norm": 0.5324044227600098, | |
| "learning_rate": 2.061073738537635e-06, | |
| "loss": 0.13, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 4.698412698412699, | |
| "grad_norm": 0.5037662982940674, | |
| "learning_rate": 1.9216926233717087e-06, | |
| "loss": 0.1315, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 0.5133729577064514, | |
| "learning_rate": 1.7860619515673034e-06, | |
| "loss": 0.1275, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 4.825396825396825, | |
| "grad_norm": 0.5318549275398254, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 0.1222, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 4.888888888888889, | |
| "grad_norm": 0.5464989542961121, | |
| "learning_rate": 1.5267081477050132e-06, | |
| "loss": 0.1338, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 4.9523809523809526, | |
| "grad_norm": 0.5057982802391052, | |
| "learning_rate": 1.4033009983067454e-06, | |
| "loss": 0.13, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 5.015873015873016, | |
| "grad_norm": 0.5163548588752747, | |
| "learning_rate": 1.2842758726130283e-06, | |
| "loss": 0.1156, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 5.079365079365079, | |
| "grad_norm": 0.6905339360237122, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.1051, | |
| "step": 80 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.8886781958723994e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |