| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.96, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.17174428701400757, | |
| "learning_rate": 0.0001, | |
| "loss": 1.229, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.1649257093667984, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0561, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.17078982293605804, | |
| "learning_rate": 0.0001943566591422122, | |
| "loss": 1.0143, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.17896169424057007, | |
| "learning_rate": 0.0001887133182844244, | |
| "loss": 0.9925, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.17166747152805328, | |
| "learning_rate": 0.0001830699774266366, | |
| "loss": 0.9619, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.1940702199935913, | |
| "learning_rate": 0.00017742663656884877, | |
| "loss": 0.9658, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 1872, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.328053844150272e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |