| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020930232558139535, | |
| "eval_steps": 9, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002325581395348837, | |
| "eval_loss": 5.892056941986084, | |
| "eval_runtime": 19.7546, | |
| "eval_samples_per_second": 36.65, | |
| "eval_steps_per_second": 4.607, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0069767441860465115, | |
| "grad_norm": 3.488095760345459, | |
| "learning_rate": 1.5e-05, | |
| "loss": 5.9292, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013953488372093023, | |
| "grad_norm": 2.8731729984283447, | |
| "learning_rate": 3e-05, | |
| "loss": 5.7853, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020930232558139535, | |
| "grad_norm": 4.2616777420043945, | |
| "learning_rate": 4.5e-05, | |
| "loss": 5.9753, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020930232558139535, | |
| "eval_loss": 5.681079387664795, | |
| "eval_runtime": 19.8386, | |
| "eval_samples_per_second": 36.494, | |
| "eval_steps_per_second": 4.587, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2351283906281472.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |