|
{ |
|
"best_metric": 0.7962328767123288, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-0/checkpoint-441", |
|
"epoch": 5.0, |
|
"eval_steps": 500, |
|
"global_step": 735, |
|
"is_hyper_param_search": true, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.7688356164383562, |
|
"eval_loss": 0.5073187947273254, |
|
"eval_runtime": 3.5613, |
|
"eval_samples_per_second": 163.984, |
|
"eval_steps_per_second": 10.389, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.7825342465753424, |
|
"eval_loss": 0.5155062675476074, |
|
"eval_runtime": 3.5634, |
|
"eval_samples_per_second": 163.888, |
|
"eval_steps_per_second": 10.383, |
|
"step": 294 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.7962328767123288, |
|
"eval_loss": 0.6085470914840698, |
|
"eval_runtime": 3.5765, |
|
"eval_samples_per_second": 163.288, |
|
"eval_steps_per_second": 10.345, |
|
"step": 441 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"grad_norm": 0.9700286388397217, |
|
"learning_rate": 2.7960981562088062e-05, |
|
"loss": 0.3588, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.7808219178082192, |
|
"eval_loss": 0.7084068655967712, |
|
"eval_runtime": 3.5722, |
|
"eval_samples_per_second": 163.483, |
|
"eval_steps_per_second": 10.358, |
|
"step": 588 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.785958904109589, |
|
"eval_loss": 0.7480510473251343, |
|
"eval_runtime": 3.5839, |
|
"eval_samples_per_second": 162.949, |
|
"eval_steps_per_second": 10.324, |
|
"step": 735 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 735, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 500, |
|
"total_flos": 1296419714671410.0, |
|
"train_batch_size": 32, |
|
"trial_name": null, |
|
"trial_params": { |
|
"learning_rate": 8.745243169419031e-05, |
|
"num_train_epochs": 5, |
|
"per_device_train_batch_size": 32, |
|
"seed": 6 |
|
} |
|
} |
|
|