| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 66, | |
| "global_step": 131, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 3e-05, | |
| "loss": 3.7331, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3e-05, | |
| "loss": 2.345, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3e-05, | |
| "loss": 2.1491, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3e-05, | |
| "loss": 2.0739, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_accuracy": 0.6206453178068898, | |
| "eval_loss": 1.8404711484909058, | |
| "eval_runtime": 11.9883, | |
| "eval_samples_per_second": 25.024, | |
| "eval_steps_per_second": 1.585, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_exact_match": 7.666666666666667, | |
| "eval_f1": 10.221428571428572, | |
| "eval_qa_bleu": 1.4042262195131967, | |
| "eval_qa_exact_match": 0.07333333333333333, | |
| "eval_recite_bleu": 8.5956480576491, | |
| "eval_recite_exact_match": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9722, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3e-05, | |
| "loss": 2.014, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9812, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9213, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3e-05, | |
| "loss": 1.8806, | |
| "step": 126 | |
| } | |
| ], | |
| "logging_steps": 14, | |
| "max_steps": 1310, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 5898044000563200.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |