| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 102, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.1853281853281854, | |
| "grad_norm": 0.8880513310432434, | |
| "learning_rate": 9.432996531865001e-06, | |
| "loss": 0.4521, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.370656370656371, | |
| "grad_norm": 0.8268473744392395, | |
| "learning_rate": 7.169418695587791e-06, | |
| "loss": 0.3071, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 3.5559845559845558, | |
| "grad_norm": 0.836441695690155, | |
| "learning_rate": 4.04420685649314e-06, | |
| "loss": 0.2627, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 4.741312741312742, | |
| "grad_norm": 0.9326808452606201, | |
| "learning_rate": 1.298610014623423e-06, | |
| "loss": 0.2294, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 5.926640926640927, | |
| "grad_norm": 0.8116953372955322, | |
| "learning_rate": 2.3104435254008852e-08, | |
| "loss": 0.2174, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 102, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.4481701216256e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |