File size: 1,711 Bytes
1630d72 a624889 1630d72 a624889 1630d72 a624889 1630d72 a624889 1630d72 a624889 1630d72 a624889 1630d72 a624889 1630d72 a624889 1630d72 a624889 1630d72 a624889 1630d72 |
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 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 |
{
"best_metric": 0.676078431372549,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/checkpoint-320",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 320,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 2.012742280960083,
"learning_rate": 0.0007591954920690624,
"loss": 0.5869,
"step": 160
},
{
"epoch": 1.0,
"eval_accuracy": 0.6666666666666666,
"eval_f1": 0.0,
"eval_loss": 0.5785399675369263,
"eval_mcc": 0.0,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 1.8697,
"eval_samples_per_second": 681.924,
"eval_steps_per_second": 21.394,
"step": 160
},
{
"epoch": 2.0,
"grad_norm": 2.057482957839966,
"learning_rate": 0.0006642960555604296,
"loss": 0.5715,
"step": 320
},
{
"epoch": 2.0,
"eval_accuracy": 0.676078431372549,
"eval_f1": 0.4411366711772666,
"eval_loss": 0.5550761222839355,
"eval_mcc": 0.22526645932553852,
"eval_precision": 0.5191082802547771,
"eval_recall": 0.3835294117647059,
"eval_runtime": 1.8672,
"eval_samples_per_second": 682.827,
"eval_steps_per_second": 21.422,
"step": 320
}
],
"logging_steps": 500,
"max_steps": 1440,
"num_input_tokens_seen": 0,
"num_train_epochs": 9,
"save_steps": 500,
"total_flos": 583510875840.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.9116955099903541,
"learning_rate": 0.0008540949285776952,
"num_train_epochs": 9,
"temperature": 21
}
}
|