| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.680965147453083, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6429768800735474, | |
| "eval_loss": 0.5945129990577698, | |
| "eval_runtime": 45.8254, | |
| "eval_samples_per_second": 65.095, | |
| "eval_steps_per_second": 4.081, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 1.3404825737265416, | |
| "grad_norm": 10.595976829528809, | |
| "learning_rate": 8.574439800439004e-06, | |
| "loss": 0.6212, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6778411269187927, | |
| "eval_loss": 0.5707619786262512, | |
| "eval_runtime": 45.8803, | |
| "eval_samples_per_second": 65.017, | |
| "eval_steps_per_second": 4.076, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 2.680965147453083, | |
| "grad_norm": 11.34949779510498, | |
| "learning_rate": 7.247127137832347e-06, | |
| "loss": 0.5391, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3730, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 1456214116560840.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 9.90175246304566e-06, | |
| "per_device_train_batch_size": 32 | |
| } | |
| } | |