| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.051282051282051, | |
| "eval_steps": 25, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 0.02189767174422741, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3786, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "eval_loss": 10.376591682434082, | |
| "eval_runtime": 0.0427, | |
| "eval_samples_per_second": 772.186, | |
| "eval_steps_per_second": 70.199, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 0.020329630002379417, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3782, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 0.04133369401097298, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 17.6251, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.641025641025641, | |
| "grad_norm": 0.034894246608018875, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 10.2643, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 0.03917449712753296, | |
| "learning_rate": 0.0, | |
| "loss": 16.7843, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8553611919360.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |