File size: 1,642 Bytes
cdd22de |
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": 0.8896859247770453,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-645",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1290,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 0.19485902786254883,
"learning_rate": 5.781432585735223e-06,
"loss": 0.1549,
"step": 645
},
{
"epoch": 1.0,
"eval_accuracy": 0.8896859247770453,
"eval_f1": 0.0,
"eval_loss": 0.12795990705490112,
"eval_mcc": 0.0,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 9.951,
"eval_samples_per_second": 518.339,
"eval_steps_per_second": 16.28,
"step": 645
},
{
"epoch": 2.0,
"grad_norm": 0.2552821934223175,
"learning_rate": 0.0,
"loss": 0.1281,
"step": 1290
},
{
"epoch": 2.0,
"eval_accuracy": 0.8896859247770453,
"eval_f1": 0.0,
"eval_loss": 0.12589357793331146,
"eval_mcc": 0.0,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 9.9215,
"eval_samples_per_second": 519.881,
"eval_steps_per_second": 16.328,
"step": 1290
}
],
"logging_steps": 500,
"max_steps": 1290,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"total_flos": 3173885065200.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.30145127091544865,
"learning_rate": 1.1562865171470446e-05,
"num_train_epochs": 2,
"temperature": 15
}
}
|