File size: 1,211 Bytes
e4110b5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
{
"best_metric": 0.502970297029703,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-280",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 280,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.8820645213127136,
"learning_rate": 2.4523034980957572e-05,
"loss": 0.5259,
"step": 280
},
{
"epoch": 1.0,
"eval_accuracy": 0.502970297029703,
"eval_f1": 0.07380073800738007,
"eval_loss": 0.5183532238006592,
"eval_precision": 0.5263157894736842,
"eval_recall": 0.03968253968253968,
"eval_runtime": 15.7192,
"eval_samples_per_second": 32.126,
"eval_steps_per_second": 1.018,
"step": 280
}
],
"logging_steps": 500,
"max_steps": 560,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"total_flos": 777843283140.0,
"train_batch_size": 34,
"trial_name": null,
"trial_params": {
"alpha": 0.6982252235036847,
"learning_rate": 4.9046069961915145e-05,
"num_train_epochs": 2,
"per_device_train_batch_size": 34,
"temperature": 6
}
}
|