| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.184218606079214, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002456248081056187, | |
| "grad_norm": 1.075522780418396, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.3319, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002456248081056187, | |
| "eval_loss": 0.40377190709114075, | |
| "eval_runtime": 96.687, | |
| "eval_samples_per_second": 3.548, | |
| "eval_steps_per_second": 1.779, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004912496162112374, | |
| "grad_norm": 0.9468379020690918, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.2987, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00736874424316856, | |
| "grad_norm": 1.2837846279144287, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4162, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009824992324224747, | |
| "grad_norm": 0.7427715063095093, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.3942, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012281240405280933, | |
| "grad_norm": 0.455293208360672, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.2755, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01473748848633712, | |
| "grad_norm": 0.6595093607902527, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.2189, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017193736567393307, | |
| "grad_norm": 0.5849353075027466, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.2198, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019649984648449494, | |
| "grad_norm": 0.4098145365715027, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.1351, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02210623272950568, | |
| "grad_norm": 0.5752076506614685, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.2128, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024562480810561865, | |
| "grad_norm": 0.3932249844074249, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.1435, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027018728891618052, | |
| "grad_norm": 0.333332896232605, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.1337, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02947497697267424, | |
| "grad_norm": 0.25759759545326233, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1202, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03193122505373042, | |
| "grad_norm": 0.24304305016994476, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.1099, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.034387473134786614, | |
| "grad_norm": 0.18120177090168, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.0935, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0368437212158428, | |
| "grad_norm": 0.18426595628261566, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0999, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03929996929689899, | |
| "grad_norm": 0.41276195645332336, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.1368, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04175621737795517, | |
| "grad_norm": 0.22144843637943268, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.1015, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04421246545901136, | |
| "grad_norm": 0.27295783162117004, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.1443, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04666871354006755, | |
| "grad_norm": 0.15916624665260315, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0799, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04912496162112373, | |
| "grad_norm": 0.20824064314365387, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.1086, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05158120970217992, | |
| "grad_norm": 0.17067670822143555, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.089, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.054037457783236105, | |
| "grad_norm": 0.2052849531173706, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0873, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.056493705864292296, | |
| "grad_norm": 0.14692534506320953, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0732, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05894995394534848, | |
| "grad_norm": 0.17746412754058838, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0665, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06140620202640467, | |
| "grad_norm": 0.2051028162240982, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.118, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06140620202640467, | |
| "eval_loss": 0.10138817876577377, | |
| "eval_runtime": 97.3932, | |
| "eval_samples_per_second": 3.522, | |
| "eval_steps_per_second": 1.766, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06386245010746085, | |
| "grad_norm": 0.1433115303516388, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.0656, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06631869818851704, | |
| "grad_norm": 0.25121065974235535, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.1332, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06877494626957323, | |
| "grad_norm": 0.26504987478256226, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.0707, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07123119435062941, | |
| "grad_norm": 0.1881726235151291, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.1291, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0736874424316856, | |
| "grad_norm": 0.1683933287858963, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1258, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0761436905127418, | |
| "grad_norm": 0.13583755493164062, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0848, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07859993859379798, | |
| "grad_norm": 0.1867646425962448, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.096, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08105618667485416, | |
| "grad_norm": 0.1443484127521515, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0913, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08351243475591034, | |
| "grad_norm": 0.2707761228084564, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.1123, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08596868283696653, | |
| "grad_norm": 0.13740448653697968, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0693, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08842493091802273, | |
| "grad_norm": 0.16506795585155487, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1096, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09088117899907891, | |
| "grad_norm": 0.15797682106494904, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.1004, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0933374270801351, | |
| "grad_norm": 0.10705221444368362, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.0723, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09579367516119128, | |
| "grad_norm": 0.14854738116264343, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1063, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09824992324224746, | |
| "grad_norm": 0.18394620716571808, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.0951, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10070617132330366, | |
| "grad_norm": 0.11826738715171814, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.0775, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10316241940435984, | |
| "grad_norm": 0.17405179142951965, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0898, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10561866748541603, | |
| "grad_norm": 0.14838817715644836, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0919, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10807491556647221, | |
| "grad_norm": 0.14697116613388062, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.0919, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1105311636475284, | |
| "grad_norm": 0.21143025159835815, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0925, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11298741172858459, | |
| "grad_norm": 0.14245229959487915, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.0942, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11544365980964078, | |
| "grad_norm": 0.30137455463409424, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.1158, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11789990789069696, | |
| "grad_norm": 0.13550423085689545, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.079, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12035615597175314, | |
| "grad_norm": 0.13647057116031647, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.0875, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12281240405280934, | |
| "grad_norm": 0.18223483860492706, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.0927, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12281240405280934, | |
| "eval_loss": 0.09029460698366165, | |
| "eval_runtime": 97.3669, | |
| "eval_samples_per_second": 3.523, | |
| "eval_steps_per_second": 1.767, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1252686521338655, | |
| "grad_norm": 0.10938217490911484, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0813, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.1277249002149217, | |
| "grad_norm": 0.13226236402988434, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.091, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1301811482959779, | |
| "grad_norm": 0.14732792973518372, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.0968, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1326373963770341, | |
| "grad_norm": 0.14260084927082062, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.079, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13509364445809027, | |
| "grad_norm": 0.180017352104187, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0624, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.13754989253914646, | |
| "grad_norm": 0.1349073201417923, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.0839, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.14000614062020264, | |
| "grad_norm": 0.16259907186031342, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0716, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.14246238870125882, | |
| "grad_norm": 0.14453484117984772, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.0825, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.144918636782315, | |
| "grad_norm": 0.1296265572309494, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0613, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1473748848633712, | |
| "grad_norm": 0.12627637386322021, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0769, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14983113294442738, | |
| "grad_norm": 0.1232289969921112, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.0708, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1522873810254836, | |
| "grad_norm": 0.16237996518611908, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.0958, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.15474362910653977, | |
| "grad_norm": 0.12401328235864639, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0845, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.15719987718759595, | |
| "grad_norm": 0.11931698769330978, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.0764, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.15965612526865214, | |
| "grad_norm": 0.14114603400230408, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.0805, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.16211237334970832, | |
| "grad_norm": 0.13311800360679626, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0756, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1645686214307645, | |
| "grad_norm": 0.23211269080638885, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.108, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.1670248695118207, | |
| "grad_norm": 0.1735387146472931, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.0848, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.16948111759287687, | |
| "grad_norm": 0.17347167432308197, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1041, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.17193736567393306, | |
| "grad_norm": 0.16924938559532166, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.094, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.17439361375498924, | |
| "grad_norm": 0.09490655362606049, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.056, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.17684986183604545, | |
| "grad_norm": 0.139134019613266, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0558, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.17930610991710164, | |
| "grad_norm": 0.112559013068676, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.0791, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.18176235799815782, | |
| "grad_norm": 0.07158195972442627, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.0466, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.184218606079214, | |
| "grad_norm": 0.1235809400677681, | |
| "learning_rate": 0.0, | |
| "loss": 0.0568, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.184218606079214, | |
| "eval_loss": 0.08785168826580048, | |
| "eval_runtime": 97.4628, | |
| "eval_samples_per_second": 3.519, | |
| "eval_steps_per_second": 1.765, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.205566835785728e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |