File size: 1,209 Bytes
953769b |
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": 0.7221135029354208,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-19/checkpoint-59",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 59,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.9501977562904358,
"learning_rate": 0.00014305210915070167,
"loss": 0.4807,
"step": 59
},
{
"epoch": 1.0,
"eval_accuracy": 0.7221135029354208,
"eval_f1": 0.7171314741035855,
"eval_loss": 0.42745766043663025,
"eval_precision": 0.7302231237322515,
"eval_recall": 0.7045009784735812,
"eval_runtime": 28.9792,
"eval_samples_per_second": 35.267,
"eval_steps_per_second": 1.104,
"step": 59
}
],
"logging_steps": 500,
"max_steps": 236,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 52,
"trial_name": null,
"trial_params": {
"alpha": 0.6660099026576007,
"learning_rate": 0.0001907361455342689,
"num_train_epochs": 4,
"per_device_train_batch_size": 52,
"temperature": 20
}
}
|