| { | |
| "best_metric": 0.8107798165137615, | |
| "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/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": 16.55626678466797, | |
| "learning_rate": 5.1383294230414005e-05, | |
| "loss": 1.5907, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8061926605504587, | |
| "eval_loss": 1.2464169263839722, | |
| "eval_runtime": 2.4007, | |
| "eval_samples_per_second": 363.232, | |
| "eval_steps_per_second": 2.916, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": Infinity, | |
| "learning_rate": 4.405675241279466e-05, | |
| "loss": 0.9038, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8107798165137615, | |
| "eval_loss": 1.1235342025756836, | |
| "eval_runtime": 2.3533, | |
| "eval_samples_per_second": 370.54, | |
| "eval_steps_per_second": 2.975, | |
| "step": 1054 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4216, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "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": 0.5167874928728581, | |
| "learning_rate": 5.872376483475886e-05, | |
| "num_train_epochs": 8, | |
| "temperature": 5 | |
| } | |
| } | |