|
{ |
|
"best_metric": 0.7876712328767124, |
|
"best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-2/checkpoint-735", |
|
"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": 0.6643835616438356, |
|
"eval_loss": 0.7592821717262268, |
|
"eval_runtime": 3.589, |
|
"eval_samples_per_second": 162.72, |
|
"eval_steps_per_second": 10.309, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.7722602739726028, |
|
"eval_loss": 0.5706833004951477, |
|
"eval_runtime": 3.5712, |
|
"eval_samples_per_second": 163.531, |
|
"eval_steps_per_second": 10.361, |
|
"step": 294 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.7671232876712328, |
|
"eval_loss": 0.5250597596168518, |
|
"eval_runtime": 3.5872, |
|
"eval_samples_per_second": 162.802, |
|
"eval_steps_per_second": 10.314, |
|
"step": 441 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"grad_norm": 3.6389541625976562, |
|
"learning_rate": 1.928469096530994e-06, |
|
"loss": 0.6489, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.785958904109589, |
|
"eval_loss": 0.5115081071853638, |
|
"eval_runtime": 3.573, |
|
"eval_samples_per_second": 163.447, |
|
"eval_steps_per_second": 10.355, |
|
"step": 588 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.7876712328767124, |
|
"eval_loss": 0.5062544345855713, |
|
"eval_runtime": 3.5999, |
|
"eval_samples_per_second": 162.226, |
|
"eval_steps_per_second": 10.278, |
|
"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": 6.031594833830981e-06, |
|
"num_train_epochs": 5, |
|
"per_device_train_batch_size": 32, |
|
"seed": 20 |
|
} |
|
} |
|
|