| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.999787067925332, | |
| "eval_steps": 500, | |
| "global_step": 21132, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00019264906930276582, | |
| "loss": 3.2485, | |
| "step": 2817 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.00016303501945525293, | |
| "loss": 2.8555, | |
| "step": 5634 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.00013342096960774005, | |
| "loss": 2.7279, | |
| "step": 8451 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00010379640340729835, | |
| "loss": 2.6605, | |
| "step": 11268 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 7.418235355978547e-05, | |
| "loss": 2.6872, | |
| "step": 14085 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.455778735934378e-05, | |
| "loss": 2.7392, | |
| "step": 16902 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.4943737511830897e-05, | |
| "loss": 2.6145, | |
| "step": 19719 | |
| } | |
| ], | |
| "logging_steps": 2817, | |
| "max_steps": 21132, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.153766776488704e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |