| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 3, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08333333333333333, | |
| "eval_loss": 0.7944757342338562, | |
| "eval_runtime": 0.2942, | |
| "eval_samples_per_second": 10.197, | |
| "eval_steps_per_second": 6.798, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 0.7276734709739685, | |
| "eval_runtime": 0.2951, | |
| "eval_samples_per_second": 10.168, | |
| "eval_steps_per_second": 6.779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 0.575480043888092, | |
| "eval_runtime": 0.304, | |
| "eval_samples_per_second": 9.868, | |
| "eval_steps_per_second": 6.579, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 0.4864470660686493, | |
| "eval_runtime": 0.3074, | |
| "eval_samples_per_second": 9.76, | |
| "eval_steps_per_second": 6.507, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 1.1259316205978394, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6216, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.41837990283966064, | |
| "eval_runtime": 0.3135, | |
| "eval_samples_per_second": 9.568, | |
| "eval_steps_per_second": 6.379, | |
| "step": 12 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 12, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3015219232112640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |