| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.857142857142857, | |
| "eval_steps": 1, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5714285714285714, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.7609, | |
| "eval_samples_per_second": 3.943, | |
| "eval_steps_per_second": 1.314, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.2857142857142856, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.2225, | |
| "eval_samples_per_second": 13.483, | |
| "eval_steps_per_second": 4.494, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "grad_norm": 0.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.8571428571428572, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.232, | |
| "eval_samples_per_second": 12.931, | |
| "eval_steps_per_second": 4.31, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.571428571428571, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.2227, | |
| "eval_samples_per_second": 13.473, | |
| "eval_steps_per_second": 4.491, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 3.2857142857142856, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.2232, | |
| "eval_samples_per_second": 13.442, | |
| "eval_steps_per_second": 4.481, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 3.857142857142857, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.857142857142857, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.2247, | |
| "eval_samples_per_second": 13.351, | |
| "eval_steps_per_second": 4.45, | |
| "step": 6 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 6, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 1, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8531332112056320.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |