| { | |
| "best_metric": 0.7786697247706422, | |
| "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": 5.95961856842041, | |
| "learning_rate": 9.55389368279823e-06, | |
| "loss": 1.5369, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7339449541284404, | |
| "eval_loss": 1.2773902416229248, | |
| "eval_runtime": 2.5957, | |
| "eval_samples_per_second": 335.939, | |
| "eval_steps_per_second": 2.697, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 15.252978324890137, | |
| "learning_rate": 8.492349940265094e-06, | |
| "loss": 1.2159, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7786697247706422, | |
| "eval_loss": 1.022659182548523, | |
| "eval_runtime": 2.5741, | |
| "eval_samples_per_second": 338.753, | |
| "eval_steps_per_second": 2.719, | |
| "step": 1054 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5270, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "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": 0.27608826195592573, | |
| "learning_rate": 1.0615437425331367e-05, | |
| "num_train_epochs": 10, | |
| "temperature": 2 | |
| } | |
| } | |