| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 38.06896551724138, | |
| "eval_steps": 100, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.448275862068965, | |
| "grad_norm": 3.673116445541382, | |
| "learning_rate": 1.9396926207859085e-05, | |
| "loss": 7.3839, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 15.172413793103448, | |
| "grad_norm": 3.855034112930298, | |
| "learning_rate": 1.5000000000000002e-05, | |
| "loss": 7.5974, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 22.620689655172413, | |
| "grad_norm": 3.3599672317504883, | |
| "learning_rate": 8.263518223330698e-06, | |
| "loss": 7.2684, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 30.344827586206897, | |
| "grad_norm": 2.229823589324951, | |
| "learning_rate": 2.339555568810221e-06, | |
| "loss": 7.2663, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 38.06896551724138, | |
| "grad_norm": 0.8112984299659729, | |
| "learning_rate": 0.0, | |
| "loss": 7.362, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5522544383688704e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |