File size: 1,204 Bytes
1d278a6 |
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": 0.773972602739726,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-64",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 64,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 7.969868183135986,
"learning_rate": 0.0006324213595544264,
"loss": 0.5787,
"step": 64
},
{
"epoch": 1.0,
"eval_accuracy": 0.773972602739726,
"eval_f1": 0.8070175438596492,
"eval_loss": 0.48913490772247314,
"eval_precision": 0.7040816326530612,
"eval_recall": 0.9452054794520548,
"eval_runtime": 27.7283,
"eval_samples_per_second": 36.858,
"eval_steps_per_second": 1.154,
"step": 64
}
],
"logging_steps": 500,
"max_steps": 320,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 48,
"trial_name": null,
"trial_params": {
"alpha": 0.9990297556295253,
"learning_rate": 0.000790526699443033,
"num_train_epochs": 5,
"per_device_train_batch_size": 48,
"temperature": 30
}
}
|