File size: 1,693 Bytes
733ca36 05411bb 733ca36 05411bb 733ca36 05411bb 733ca36 05411bb 733ca36 05411bb 733ca36 05411bb 733ca36 05411bb 733ca36 05411bb 733ca36 |
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 |
{
"best_metric": 0.8003913894324853,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-192",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 192,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 2.5439341068267822,
"learning_rate": 0.00025636357557273684,
"loss": 0.5365,
"step": 96
},
{
"epoch": 1.0,
"eval_accuracy": 0.7935420743639922,
"eval_f1": 0.8087035358114234,
"eval_loss": 0.4461754560470581,
"eval_precision": 0.7533783783783784,
"eval_recall": 0.87279843444227,
"eval_runtime": 25.9122,
"eval_samples_per_second": 39.441,
"eval_steps_per_second": 1.235,
"step": 96
},
{
"epoch": 2.0,
"grad_norm": 4.693763732910156,
"learning_rate": 0.00022787873384243272,
"loss": 0.4548,
"step": 192
},
{
"epoch": 2.0,
"eval_accuracy": 0.8003913894324853,
"eval_f1": 0.8216783216783217,
"eval_loss": 0.43167614936828613,
"eval_precision": 0.7424960505529226,
"eval_recall": 0.9197651663405088,
"eval_runtime": 25.6332,
"eval_samples_per_second": 39.87,
"eval_steps_per_second": 1.248,
"step": 192
}
],
"logging_steps": 500,
"max_steps": 960,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 471390394560.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"alpha": 0.8320855687119669,
"learning_rate": 0.0002848484173030409,
"num_train_epochs": 10,
"temperature": 8
}
}
|