File size: 1,207 Bytes
192c0c6 |
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": 0.7181996086105675,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-55",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 55,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.115179181098938,
"learning_rate": 0.0001711445020920055,
"loss": 0.4773,
"step": 55
},
{
"epoch": 1.0,
"eval_accuracy": 0.7181996086105675,
"eval_f1": 0.7125748502994013,
"eval_loss": 0.4258935749530792,
"eval_precision": 0.7270875763747454,
"eval_recall": 0.6986301369863014,
"eval_runtime": 27.8796,
"eval_samples_per_second": 36.658,
"eval_steps_per_second": 1.148,
"step": 55
}
],
"logging_steps": 500,
"max_steps": 275,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 56,
"trial_name": null,
"trial_params": {
"alpha": 0.6575195229183988,
"learning_rate": 0.00021393062761500687,
"num_train_epochs": 5,
"per_device_train_batch_size": 56,
"temperature": 22
}
}
|