File size: 1,203 Bytes
7a59c50 |
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": 0.7475538160469667,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-118",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 118,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.14125657081604,
"learning_rate": 7.61866849595866e-05,
"loss": 0.532,
"step": 118
},
{
"epoch": 1.0,
"eval_accuracy": 0.7475538160469667,
"eval_f1": 0.7575187969924811,
"eval_loss": 0.4580899477005005,
"eval_precision": 0.72875226039783,
"eval_recall": 0.7886497064579256,
"eval_runtime": 30.2456,
"eval_samples_per_second": 33.79,
"eval_steps_per_second": 1.058,
"step": 118
}
],
"logging_steps": 500,
"max_steps": 354,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 26,
"trial_name": null,
"trial_params": {
"alpha": 0.7708734866574575,
"learning_rate": 0.00011428002743937991,
"num_train_epochs": 3,
"per_device_train_batch_size": 26,
"temperature": 7
}
}
|