| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2667852378835038, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0035571365051133837, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035571365051133837, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.2867, | |
| "eval_samples_per_second": 4.287, | |
| "eval_steps_per_second": 2.152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007114273010226767, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01067140951534015, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014228546020453535, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017785682525566917, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0213428190306803, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.024899955535793685, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02845709204090707, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03201422854602046, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.035571365051133834, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03912850155624722, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0426856380613606, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.046242774566473986, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04979991107158737, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.053357047576700754, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05691418408181414, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06047132058692752, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06402845709204091, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0675855935971543, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07114273010226767, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07469986660738105, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07825700311249444, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08181413961760782, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0853712761227212, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08892841262783459, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08892841262783459, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.3473, | |
| "eval_samples_per_second": 4.282, | |
| "eval_steps_per_second": 2.15, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09248554913294797, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.09604268563806136, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09959982214317474, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10315695864828812, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10671409515340151, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11027123165851489, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11382836816362828, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.11738550466874166, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.12094264117385504, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12449977767896843, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12805691418408183, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1316140506891952, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1351711871943086, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.13872832369942195, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14228546020453534, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14584259670964872, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1493997332147621, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1529568697198755, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.15651400622498887, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.16007114273010226, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16362827923521564, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.16718541574032902, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1707425522454424, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1742996887505558, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.17785682525566918, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17785682525566918, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.2966, | |
| "eval_samples_per_second": 4.286, | |
| "eval_steps_per_second": 2.152, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18141396176078256, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.18497109826589594, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.18852823477100933, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1920853712761227, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1956425077812361, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.19919964428634948, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.20275678079146287, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.20631391729657625, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.20987105380168963, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.21342819030680302, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2169853268119164, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.22054246331702979, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.22409959982214317, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.22765673632725655, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.23121387283236994, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.23477100933748332, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.2383281458425967, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.2418852823477101, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.24544241885282347, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.24899955535793686, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.25255669186305024, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.25611382836816365, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.259670964873277, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.2632281013783904, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.2667852378835038, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2667852378835038, | |
| "eval_loss": NaN, | |
| "eval_runtime": 55.4995, | |
| "eval_samples_per_second": 4.27, | |
| "eval_steps_per_second": 2.144, | |
| "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": 1.119015678246912e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |