| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003207577902795354, | |
| "eval_steps": 8, | |
| "global_step": 8, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004009472378494193, | |
| "eval_loss": 1.1770294904708862, | |
| "eval_runtime": 2095.1908, | |
| "eval_samples_per_second": 4.01, | |
| "eval_steps_per_second": 2.005, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012028417135482577, | |
| "grad_norm": 0.6318249702453613, | |
| "learning_rate": 3e-05, | |
| "loss": 1.1511, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024056834270965153, | |
| "grad_norm": 0.5829982757568359, | |
| "learning_rate": 6e-05, | |
| "loss": 1.128, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003207577902795354, | |
| "eval_loss": 1.0006554126739502, | |
| "eval_runtime": 2124.74, | |
| "eval_samples_per_second": 3.954, | |
| "eval_steps_per_second": 1.977, | |
| "step": 8 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 90, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 8, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.849067939069952e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |