File size: 1,453 Bytes
09faf57 |
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 |
{
"best_metric": 0.5091743119266054,
"best_model_checkpoint": "electra-distilled-sst\\run-2\\checkpoint-527",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 1054,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 3.510751485824585,
"learning_rate": 0.0007235764985208607,
"loss": 4.9041,
"step": 527
},
{
"epoch": 1.0,
"eval_accuracy": 0.5091743119266054,
"eval_loss": 4.841418266296387,
"eval_runtime": 1.4537,
"eval_samples_per_second": 599.861,
"eval_steps_per_second": 4.815,
"step": 527
},
{
"epoch": 2.0,
"grad_norm": 0.5188323259353638,
"learning_rate": 0.0005789160983992775,
"loss": 4.9002,
"step": 1054
},
{
"epoch": 2.0,
"eval_accuracy": 0.5091743119266054,
"eval_loss": 4.816441059112549,
"eval_runtime": 1.4412,
"eval_samples_per_second": 605.042,
"eval_steps_per_second": 4.857,
"step": 1054
}
],
"logging_steps": 500,
"max_steps": 3162,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 500,
"total_flos": 373776249469380.0,
"train_batch_size": 128,
"trial_name": null,
"trial_params": {
"alpha": 0.2011698337552854,
"learning_rate": 0.0008679624007294999,
"num_train_epochs": 6,
"temperature": 5
}
}
|