| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.625, | |
| "eval_steps": 50000, | |
| "global_step": 50000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 15.0625, | |
| "learning_rate": 9.427649832377157e-05, | |
| "loss": 0.5293, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 17.375, | |
| "learning_rate": 7.158340961603695e-05, | |
| "loss": 0.2863, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.375, | |
| "grad_norm": 11.875, | |
| "learning_rate": 4.08424848470673e-05, | |
| "loss": 0.2011, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 16.25, | |
| "learning_rate": 1.5017755491800084e-05, | |
| "loss": 0.1537, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 12.875, | |
| "learning_rate": 5.000000103890576e-06, | |
| "loss": 0.1406, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "eval_loss": 2.7418313026428223, | |
| "eval_runtime": 50.5148, | |
| "eval_samples_per_second": 400.219, | |
| "eval_steps_per_second": 400.219, | |
| "step": 50000 | |
| } | |
| ], | |
| "logging_steps": 10000, | |
| "max_steps": 50000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |