| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.8277289187790998, |
| "eval_steps": 200, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05173305742369374, |
| "grad_norm": 44.211517333984375, |
| "learning_rate": 9.50413223140496e-06, |
| "loss": 5.16752197265625, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.10346611484738748, |
| "grad_norm": 12.28664493560791, |
| "learning_rate": 8.987603305785125e-06, |
| "loss": 1.049238815307617, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1551991722710812, |
| "grad_norm": 0.41502949595451355, |
| "learning_rate": 8.47107438016529e-06, |
| "loss": 0.24581172943115234, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.20693222969477496, |
| "grad_norm": 0.2254221886396408, |
| "learning_rate": 7.954545454545455e-06, |
| "loss": 0.2015397071838379, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.2586652871184687, |
| "grad_norm": 0.23295480012893677, |
| "learning_rate": 7.43801652892562e-06, |
| "loss": 0.18340133666992187, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.3103983445421624, |
| "grad_norm": 0.28120383620262146, |
| "learning_rate": 6.921487603305785e-06, |
| "loss": 0.17128438949584962, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.3621314019658562, |
| "grad_norm": 0.2782818377017975, |
| "learning_rate": 6.404958677685951e-06, |
| "loss": 0.14969505310058595, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.4138644593895499, |
| "grad_norm": 0.23748408257961273, |
| "learning_rate": 5.888429752066116e-06, |
| "loss": 0.13814952850341797, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4138644593895499, |
| "eval_loss": 0.13955296576023102, |
| "eval_runtime": 348.0073, |
| "eval_samples_per_second": 2.468, |
| "eval_steps_per_second": 0.31, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4655975168132437, |
| "grad_norm": 0.3907519578933716, |
| "learning_rate": 5.371900826446281e-06, |
| "loss": 0.1370067024230957, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.5173305742369374, |
| "grad_norm": 0.3136274814605713, |
| "learning_rate": 4.855371900826447e-06, |
| "loss": 0.13053615570068358, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.5690636316606311, |
| "grad_norm": 0.28285646438598633, |
| "learning_rate": 4.338842975206612e-06, |
| "loss": 0.13400994300842284, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.6207966890843248, |
| "grad_norm": 0.3491869866847992, |
| "learning_rate": 3.822314049586777e-06, |
| "loss": 0.1300451374053955, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.6725297465080187, |
| "grad_norm": 0.35684749484062195, |
| "learning_rate": 3.3057851239669424e-06, |
| "loss": 0.13070807456970215, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.7242628039317124, |
| "grad_norm": 0.3009154796600342, |
| "learning_rate": 2.789256198347108e-06, |
| "loss": 0.12986770629882813, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.7759958613554061, |
| "grad_norm": 0.39449068903923035, |
| "learning_rate": 2.2727272727272728e-06, |
| "loss": 0.12787361145019532, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.8277289187790998, |
| "grad_norm": 0.26200222969055176, |
| "learning_rate": 1.7561983471074381e-06, |
| "loss": 0.13064990043640137, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.8277289187790998, |
| "eval_loss": 0.12793640792369843, |
| "eval_runtime": 347.793, |
| "eval_samples_per_second": 2.47, |
| "eval_steps_per_second": 0.311, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 25, |
| "max_steps": 484, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.39935268995072e+17, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
