File size: 1,181 Bytes
59bf836 |
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 |
{
"best_metric": 0.6864851430040411,
"best_model_checkpoint": "robertuito-finetuned-class/run-4/checkpoint-1391",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1391,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.36,
"learning_rate": 5e-05,
"loss": 0.1014,
"step": 500
},
{
"epoch": 0.72,
"learning_rate": 5e-05,
"loss": 0.0918,
"step": 1000
},
{
"epoch": 1.0,
"eval_accuracy": 0.707395498392283,
"eval_f1": 0.6864851430040411,
"eval_loss": 2.517336130142212,
"eval_recall": 0.691174006920775,
"eval_runtime": 2.732,
"eval_samples_per_second": 455.345,
"eval_steps_per_second": 14.275,
"step": 1391
}
],
"logging_steps": 500,
"max_steps": 6955,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 127848694153216.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": {
"learning_rate": 4.1843184321253836e-05,
"num_train_epochs": 5,
"per_device_train_batch_size": 4,
"seed": 9
}
}
|