| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.986666666666667, | |
| "eval_steps": 500, | |
| "global_step": 336, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 0.25994792580604553, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 0.7993, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.5648312568664551, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 0.8374, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.5980075001716614, | |
| "learning_rate": 8.823529411764706e-05, | |
| "loss": 0.8079, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.3844606280326843, | |
| "learning_rate": 9.990263847374976e-05, | |
| "loss": 0.6882, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.5548301339149475, | |
| "learning_rate": 9.930902394260747e-05, | |
| "loss": 0.7328, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.655196487903595, | |
| "learning_rate": 9.818229479678158e-05, | |
| "loss": 0.6773, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.4209234416484833, | |
| "learning_rate": 9.653463289927411e-05, | |
| "loss": 0.698, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.3566646873950958, | |
| "learning_rate": 9.438385228425938e-05, | |
| "loss": 0.641, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.7979970574378967, | |
| "learning_rate": 9.175320655700406e-05, | |
| "loss": 0.7019, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.47237297892570496, | |
| "learning_rate": 8.86711374827494e-05, | |
| "loss": 0.5818, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.5796122550964355, | |
| "learning_rate": 8.517096748273951e-05, | |
| "loss": 0.591, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.4954272210597992, | |
| "learning_rate": 8.129053936203687e-05, | |
| "loss": 0.6177, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": 0.4942867159843445, | |
| "learning_rate": 7.707180716428237e-05, | |
| "loss": 0.5629, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 0.5856671929359436, | |
| "learning_rate": 7.256038257695687e-05, | |
| "loss": 0.5609, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.6764885783195496, | |
| "learning_rate": 6.780504179127734e-05, | |
| "loss": 0.5904, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.2825632095336914, | |
| "learning_rate": 6.28571981484123e-05, | |
| "loss": 0.5817, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": 0.6306120157241821, | |
| "learning_rate": 5.7770346273610254e-05, | |
| "loss": 0.4854, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.6934658288955688, | |
| "learning_rate": 5.2599483708099016e-05, | |
| "loss": 0.5222, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": 1.0303144454956055, | |
| "learning_rate": 4.740051629190099e-05, | |
| "loss": 0.5185, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.726458728313446, | |
| "learning_rate": 4.2229653726389765e-05, | |
| "loss": 0.5561, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 0.8713110089302063, | |
| "learning_rate": 3.714280185158771e-05, | |
| "loss": 0.5678, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 0.9786319732666016, | |
| "learning_rate": 3.219495820872265e-05, | |
| "loss": 0.5446, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": 1.0140025615692139, | |
| "learning_rate": 2.7439617423043145e-05, | |
| "loss": 0.5072, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.8350790143013, | |
| "learning_rate": 2.2928192835717644e-05, | |
| "loss": 0.4833, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.6110752820968628, | |
| "learning_rate": 1.8709460637963123e-05, | |
| "loss": 0.4854, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.311111111111111, | |
| "grad_norm": 0.5755019783973694, | |
| "learning_rate": 1.4829032517260489e-05, | |
| "loss": 0.5012, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.7782542109489441, | |
| "learning_rate": 1.132886251725061e-05, | |
| "loss": 0.4674, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.6320899724960327, | |
| "learning_rate": 8.246793442995954e-06, | |
| "loss": 0.406, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.5777777777777775, | |
| "grad_norm": 0.559817910194397, | |
| "learning_rate": 5.616147715740611e-06, | |
| "loss": 0.4255, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.2263851165771484, | |
| "learning_rate": 3.465367100725908e-06, | |
| "loss": 0.4769, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.7555555555555555, | |
| "grad_norm": 0.740092396736145, | |
| "learning_rate": 1.8177052032184283e-06, | |
| "loss": 0.5578, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.8888517022132874, | |
| "learning_rate": 6.909760573925561e-07, | |
| "loss": 0.4564, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.9333333333333336, | |
| "grad_norm": 1.1548091173171997, | |
| "learning_rate": 9.73615262502503e-08, | |
| "loss": 0.4484, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.986666666666667, | |
| "step": 336, | |
| "total_flos": 1.048829668048896e+16, | |
| "train_loss": 0.5756434287343707, | |
| "train_runtime": 639.1725, | |
| "train_samples_per_second": 4.224, | |
| "train_steps_per_second": 0.526 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 336, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.048829668048896e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |