File size: 1,469 Bytes
155642b |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.1446540880503147,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.7290322580645161,
"eval_loss": 3.165098190307617,
"eval_runtime": 2.359,
"eval_samples_per_second": 1314.116,
"eval_steps_per_second": 27.554,
"step": 318
},
{
"epoch": 1.57,
"learning_rate": 1.685534591194969e-05,
"loss": 3.6948,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.86,
"eval_loss": 1.5545812845230103,
"eval_runtime": 2.429,
"eval_samples_per_second": 1276.244,
"eval_steps_per_second": 26.76,
"step": 636
},
{
"epoch": 3.0,
"eval_accuracy": 0.9132258064516129,
"eval_loss": 0.7676715850830078,
"eval_runtime": 2.39,
"eval_samples_per_second": 1297.071,
"eval_steps_per_second": 27.197,
"step": 954
},
{
"epoch": 3.14,
"learning_rate": 1.371069182389937e-05,
"loss": 1.3265,
"step": 1000
}
],
"logging_steps": 500,
"max_steps": 3180,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 259653090321324.0,
"trial_name": null,
"trial_params": {
"alpha": 0.46774500523566587,
"num_train_epochs": 10,
"temperature": 2
}
}
|