| { | |
| "best_metric": 0.8130733944954128, | |
| "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-527", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 527, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 6.467271327972412, | |
| "learning_rate": 0.0005246601812780973, | |
| "loss": 0.349, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8130733944954128, | |
| "eval_loss": 0.5175108313560486, | |
| "eval_runtime": 2.3764, | |
| "eval_samples_per_second": 366.943, | |
| "eval_steps_per_second": 2.946, | |
| "step": 527 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1581, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 8057768762220.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.9438943885488221, | |
| "learning_rate": 0.0007869902719171459, | |
| "num_train_epochs": 3, | |
| "temperature": 2 | |
| } | |
| } | |