| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0036779918164682084, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007355983632936417, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.3357, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007355983632936417, | |
| "eval_loss": NaN, | |
| "eval_runtime": 255.5239, | |
| "eval_samples_per_second": 8.962, | |
| "eval_steps_per_second": 4.481, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014711967265872833, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 270.6436, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0014711967265872833, | |
| "eval_loss": NaN, | |
| "eval_runtime": 116.4074, | |
| "eval_samples_per_second": 19.672, | |
| "eval_steps_per_second": 9.836, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002206795089880925, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 277.9041, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029423934531745666, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0029423934531745666, | |
| "eval_loss": NaN, | |
| "eval_runtime": 87.2518, | |
| "eval_samples_per_second": 26.246, | |
| "eval_steps_per_second": 13.123, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0036779918164682084, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 693.1438, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6011083806474240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |