| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.019543464665415886, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003908692933083177, | |
| "grad_norm": 0.6370952129364014, | |
| "learning_rate": 4.98240400406663e-05, | |
| "loss": 1.4791, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.007817385866166354, | |
| "grad_norm": 0.27393946051597595, | |
| "learning_rate": 4.9628528974739973e-05, | |
| "loss": 1.3743, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.01172607879924953, | |
| "grad_norm": 0.364713191986084, | |
| "learning_rate": 4.943301790881364e-05, | |
| "loss": 1.3525, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.015634771732332707, | |
| "grad_norm": 0.33364734053611755, | |
| "learning_rate": 4.923750684288731e-05, | |
| "loss": 1.3457, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.019543464665415886, | |
| "grad_norm": 0.3672705292701721, | |
| "learning_rate": 4.904199577696098e-05, | |
| "loss": 1.3375, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 25584, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 351214239744000.0, | |
| "train_batch_size": 48, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |