| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9578926362003592, | |
| "eval_steps": 500, | |
| "global_step": 3600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.3374135178286325e-05, | |
| "loss": 2.0021, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.672166045769026e-05, | |
| "loss": 1.8135, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.0069185737094202e-05, | |
| "loss": 1.741, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3416711016498137e-05, | |
| "loss": 1.668, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.6764236295902076e-05, | |
| "loss": 1.6507, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.0111761575306015e-05, | |
| "loss": 1.6073, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.4592868547099525e-06, | |
| "loss": 1.6171, | |
| "step": 3500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3758, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3600, | |
| "total_flos": 2.00430839660544e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |