File size: 1,152 Bytes
aaff26e a0e6abd aaff26e a0e6abd aaff26e a0e6abd aaff26e a0e6abd aaff26e a0e6abd aaff26e a0e6abd aaff26e |
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 |
{
"best_metric": 0.50293542074364,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-9/checkpoint-96",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 96,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.7869714498519897,
"learning_rate": 1.3073475217173054e-05,
"loss": 0.6637,
"step": 96
},
{
"epoch": 1.0,
"eval_accuracy": 0.50293542074364,
"eval_f1": 0.03422053231939163,
"eval_loss": 0.6569339036941528,
"eval_precision": 0.6,
"eval_recall": 0.01761252446183953,
"eval_runtime": 28.4278,
"eval_samples_per_second": 35.951,
"eval_steps_per_second": 1.126,
"step": 96
}
],
"logging_steps": 500,
"max_steps": 768,
"num_input_tokens_seen": 0,
"num_train_epochs": 8,
"save_steps": 500,
"total_flos": 235695197280.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.9372925528810219,
"learning_rate": 1.4941114533912061e-05,
"num_train_epochs": 8,
"temperature": 17
}
}
|