| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.976, | |
| "eval_steps": 500, | |
| "global_step": 186, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.964424488287009e-05, | |
| "loss": 0.9663, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.858710446774951e-05, | |
| "loss": 0.8691, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.685866540361456e-05, | |
| "loss": 0.8629, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 4.45081197738023e-05, | |
| "loss": 0.8412, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.160236506918098e-05, | |
| "loss": 0.8379, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.822410025817406e-05, | |
| "loss": 0.8349, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.44694721402644e-05, | |
| "loss": 0.8227, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 3.0445338968721287e-05, | |
| "loss": 0.8577, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.6266229220967818e-05, | |
| "loss": 0.7894, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.2051082071228854e-05, | |
| "loss": 0.7953, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 1.79198623329424e-05, | |
| "loss": 0.8008, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.399014621105914e-05, | |
| "loss": 0.8013, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 1.0373775035117305e-05, | |
| "loss": 0.8041, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.173672209219495e-06, | |
| "loss": 0.7816, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.480913969818098e-06, | |
| "loss": 0.7904, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.372137318741968e-06, | |
| "loss": 0.8295, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 9.073589027514789e-07, | |
| "loss": 0.7954, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.2826691520262114e-07, | |
| "loss": 0.7949, | |
| "step": 180 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 186, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 70.0, | |
| "total_flos": 8.609301374828544e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |