| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 50, | |
| "global_step": 270, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 66.44327545166016, | |
| "learning_rate": 1.6370370370370374e-05, | |
| "loss": 1.0113, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 16.887264251708984, | |
| "learning_rate": 1.2666666666666667e-05, | |
| "loss": 3.1944, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 456.6794738769531, | |
| "learning_rate": 8.962962962962963e-06, | |
| "loss": 2.3011, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 2133.9287109375, | |
| "learning_rate": 5.259259259259259e-06, | |
| "loss": 2.6631, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "grad_norm": 7.3418707847595215, | |
| "learning_rate": 1.5555555555555558e-06, | |
| "loss": 1.1036, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 270, | |
| "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": 730684353761280.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |