| { |
| "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 |
| } |
|
|
