| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 210, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.8571428571428572e-05, | |
| "loss": 0.474, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2.9206349206349206e-05, | |
| "loss": 0.4638, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.7142857142857144e-05, | |
| "loss": 0.4295, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.507936507936508e-05, | |
| "loss": 0.4306, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.301587301587302e-05, | |
| "loss": 0.3871, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 2.095238095238095e-05, | |
| "loss": 0.3386, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.3411, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.6825396825396824e-05, | |
| "loss": 0.3176, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 1.4761904761904761e-05, | |
| "loss": 0.2954, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.2698412698412699e-05, | |
| "loss": 0.2926, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.0634920634920634e-05, | |
| "loss": 0.2705, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 8.571428571428571e-06, | |
| "loss": 0.2638, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 6.507936507936508e-06, | |
| "loss": 0.2702, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 2.6, | |
| "learning_rate": 4.444444444444444e-06, | |
| "loss": 0.2727, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.3809523809523808e-06, | |
| "loss": 0.2775, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.1746031746031743e-07, | |
| "loss": 0.2542, | |
| "step": 208 | |
| } | |
| ], | |
| "logging_steps": 13, | |
| "max_steps": 210, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 1.694999141941248e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |