File size: 1,557 Bytes
4994314 6ac55cc 4994314 6ac55cc 4994314 6ac55cc 4994314 6ac55cc 4994314 e2e8898 4994314 6ac55cc 4994314 6ac55cc e2e8898 6ac55cc 4994314 |
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": 0.5,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-48",
"epoch": 2.0,
"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": 1.6336328983306885,
"learning_rate": 8.611669739559475e-06,
"loss": 0.3627,
"step": 48
},
{
"epoch": 1.0,
"eval_accuracy": 0.5,
"eval_f1": 0.0,
"eval_loss": 0.31828778982162476,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 28.8885,
"eval_samples_per_second": 35.377,
"eval_steps_per_second": 0.554,
"step": 48
},
{
"epoch": 2.0,
"grad_norm": 0.23749461770057678,
"learning_rate": 4.3058348697797375e-06,
"loss": 0.3092,
"step": 96
},
{
"epoch": 2.0,
"eval_accuracy": 0.5,
"eval_f1": 0.0,
"eval_loss": 0.29845258593559265,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 28.7105,
"eval_samples_per_second": 35.597,
"eval_steps_per_second": 0.557,
"step": 96
}
],
"logging_steps": 500,
"max_steps": 144,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 471390394560.0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": {
"alpha": 0.340965759348954,
"learning_rate": 1.2917504609339214e-05,
"num_train_epochs": 3,
"temperature": 24
}
}
|