File size: 1,547 Bytes
80b7165 |
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 |
{
"best_metric": 0.45008318903303624,
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1069",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1069,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.4677268475210477,
"grad_norm": 4.435796737670898,
"learning_rate": 1.7076894081996187e-05,
"loss": 0.5421,
"step": 500
},
{
"epoch": 0.9354536950420954,
"grad_norm": 13.997383117675781,
"learning_rate": 1.3922683871062276e-05,
"loss": 0.5008,
"step": 1000
},
{
"epoch": 1.0,
"eval_loss": 0.4736253321170807,
"eval_matthews_correlation": 0.45008318903303624,
"eval_runtime": 0.7693,
"eval_samples_per_second": 1355.736,
"eval_steps_per_second": 85.79,
"step": 1069
}
],
"logging_steps": 500,
"max_steps": 3207,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 37678695705216.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": {
"learning_rate": 2.0231104292930096e-05,
"num_train_epochs": 3,
"per_device_train_batch_size": 8,
"seed": 39
}
}
|