| { | |
| "best_metric": 0.8291284403669725, | |
| "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-1054", | |
| "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": 23.897071838378906, | |
| "learning_rate": 0.0003846295223553701, | |
| "loss": 1.6014, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.823394495412844, | |
| "eval_loss": 1.887431025505066, | |
| "eval_runtime": 2.6123, | |
| "eval_samples_per_second": 333.808, | |
| "eval_steps_per_second": 2.68, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 7.1671295166015625, | |
| "learning_rate": 0.00019249705005083926, | |
| "loss": 0.674, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8291284403669725, | |
| "eval_loss": 1.8547035455703735, | |
| "eval_runtime": 2.6264, | |
| "eval_samples_per_second": 332.018, | |
| "eval_steps_per_second": 2.665, | |
| "step": 1054 | |
| } | |
| ], | |
| "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": 16141525436100.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.0036479908390928406, | |
| "learning_rate": 0.0005763974169135925, | |
| "num_train_epochs": 3, | |
| "temperature": 8 | |
| } | |
| } | |