| { | |
| "best_metric": 0.8176605504587156, | |
| "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": 30.242748260498047, | |
| "learning_rate": 0.000111895725910844, | |
| "loss": 2.3991, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8153669724770642, | |
| "eval_loss": 1.9181628227233887, | |
| "eval_runtime": 2.3714, | |
| "eval_samples_per_second": 367.708, | |
| "eval_steps_per_second": 2.952, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 76.58197784423828, | |
| "learning_rate": 8.95250705409598e-05, | |
| "loss": 1.1199, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8176605504587156, | |
| "eval_loss": 1.8561229705810547, | |
| "eval_runtime": 2.3966, | |
| "eval_samples_per_second": 363.855, | |
| "eval_steps_per_second": 2.921, | |
| "step": 1054 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3162, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 0.051381532356201576, | |
| "learning_rate": 0.0001342239322193053, | |
| "num_train_epochs": 6, | |
| "temperature": 23 | |
| } | |
| } | |