File size: 1,545 Bytes
4bc8f9c |
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": 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": 0.6267741935483871,
"eval_loss": 0.19981417059898376,
"eval_runtime": 5.7482,
"eval_samples_per_second": 539.296,
"eval_steps_per_second": 11.308,
"step": 318
},
{
"epoch": 1.57,
"learning_rate": 1.685534591194969e-05,
"loss": 0.324,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.8287096774193549,
"eval_loss": 0.09645497798919678,
"eval_runtime": 5.8849,
"eval_samples_per_second": 526.769,
"eval_steps_per_second": 11.045,
"step": 636
},
{
"epoch": 3.0,
"eval_accuracy": 0.8841935483870967,
"eval_loss": 0.061595458537340164,
"eval_runtime": 5.6926,
"eval_samples_per_second": 544.564,
"eval_steps_per_second": 11.418,
"step": 954
},
{
"epoch": 3.14,
"learning_rate": 1.371069182389937e-05,
"loss": 0.1107,
"step": 1000
}
],
"logging_steps": 500,
"max_steps": 3180,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 318901434265680.0,
"train_batch_size": 48,
"trial_name": null,
"trial_params": {
"alpha": 0.8067006596645674,
"num_train_epochs": 10,
"temperature": 10
}
}
|