| { | |
| "best_metric": 1.1686018705368042, | |
| "best_model_checkpoint": "./results/checkpoint-50", | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 2.2678768634796143, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 1.2091, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.2002060413360596, | |
| "eval_runtime": 1.1688, | |
| "eval_samples_per_second": 8.556, | |
| "eval_steps_per_second": 1.711, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.051637649536133, | |
| "learning_rate": 3e-06, | |
| "loss": 1.1933, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 1.1868062019348145, | |
| "eval_runtime": 1.1739, | |
| "eval_samples_per_second": 8.519, | |
| "eval_steps_per_second": 1.704, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.133516788482666, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.181, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 1.1769328117370605, | |
| "eval_runtime": 1.1724, | |
| "eval_samples_per_second": 8.53, | |
| "eval_steps_per_second": 1.706, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 2.1955366134643555, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 1.1728, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 1.1707799434661865, | |
| "eval_runtime": 1.1704, | |
| "eval_samples_per_second": 8.544, | |
| "eval_steps_per_second": 1.709, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.9752388000488281, | |
| "learning_rate": 0.0, | |
| "loss": 1.1683, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 1.1686018705368042, | |
| "eval_runtime": 1.1882, | |
| "eval_samples_per_second": 8.416, | |
| "eval_steps_per_second": 1.683, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2185441679769600.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |