| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04875076173065204, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009750152346130409, | |
| "grad_norm": 0.7032998204231262, | |
| "learning_rate": 1e-05, | |
| "loss": 1.6557, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009750152346130409, | |
| "eval_loss": 1.9116276502609253, | |
| "eval_runtime": 136.3756, | |
| "eval_samples_per_second": 1.269, | |
| "eval_steps_per_second": 0.638, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.019500304692260818, | |
| "grad_norm": 0.8668947815895081, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8335, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.019500304692260818, | |
| "eval_loss": 1.898851990699768, | |
| "eval_runtime": 14.1864, | |
| "eval_samples_per_second": 12.195, | |
| "eval_steps_per_second": 6.133, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.029250457038391225, | |
| "grad_norm": 0.6870023012161255, | |
| "learning_rate": 3e-05, | |
| "loss": 1.6609, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.039000609384521635, | |
| "grad_norm": 0.6477864980697632, | |
| "learning_rate": 4e-05, | |
| "loss": 1.502, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.039000609384521635, | |
| "eval_loss": 1.8977659940719604, | |
| "eval_runtime": 14.2507, | |
| "eval_samples_per_second": 12.14, | |
| "eval_steps_per_second": 6.105, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04875076173065204, | |
| "grad_norm": 0.7418357133865356, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6092, | |
| "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": 4061069259571200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |