| { | |
| "best_metric": 0.8176605504587156, | |
| "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-527", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1054, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 15.690781593322754, | |
| "learning_rate": 0.0004329892843734803, | |
| "loss": 1.29, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8176605504587156, | |
| "eval_loss": 1.5847134590148926, | |
| "eval_runtime": 2.4131, | |
| "eval_samples_per_second": 361.36, | |
| "eval_steps_per_second": 2.901, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 3.8686888217926025, | |
| "learning_rate": 0.0002886595229156535, | |
| "loss": 0.5557, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8142201834862385, | |
| "eval_loss": 1.6788822412490845, | |
| "eval_runtime": 2.4261, | |
| "eval_samples_per_second": 359.428, | |
| "eval_steps_per_second": 2.885, | |
| "step": 1054 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2108, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 16141525436100.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.19981548442581198, | |
| "learning_rate": 0.000577319045831307, | |
| "num_train_epochs": 4, | |
| "temperature": 6 | |
| } | |
| } | |