| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 1452, | |
| "global_step": 1452, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3e-05, | |
| "loss": 2.2721, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3e-05, | |
| "loss": 2.0539, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3e-05, | |
| "loss": 2.0079, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9686, | |
| "step": 1164 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.668149394347241, | |
| "eval_loss": 1.5662202835083008, | |
| "eval_runtime": 162.0164, | |
| "eval_samples_per_second": 30.861, | |
| "eval_steps_per_second": 1.932, | |
| "step": 1452 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 9.04, | |
| "eval_f1": 13.087046780017364, | |
| "eval_qa_bleu": 5.297766450359973, | |
| "eval_qa_exact_match": 0.085, | |
| "eval_recite_bleu": 14.716037077738477, | |
| "eval_recite_exact_match": 0.0, | |
| "step": 1452 | |
| } | |
| ], | |
| "logging_steps": 291, | |
| "max_steps": 29040, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 6.633652773888e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |