| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.214285714285714, | |
| "eval_steps": 500, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 1.6877, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00011764705882352942, | |
| "loss": 1.4714, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00017647058823529413, | |
| "loss": 1.2877, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "learning_rate": 0.00019602649006622517, | |
| "loss": 1.1461, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "learning_rate": 0.0001894039735099338, | |
| "loss": 1.06, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.0001827814569536424, | |
| "loss": 0.9496, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "learning_rate": 0.000176158940397351, | |
| "loss": 0.8765, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 168, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "total_flos": 8342613648211968.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |