File size: 1,310 Bytes
c8f482b |
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 |
{
"best_metric": 0.9713600958657879,
"best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-1/checkpoint-836",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 836,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.954104254044338,
"eval_loss": 0.19407691061496735,
"eval_runtime": 591.9344,
"eval_samples_per_second": 28.196,
"eval_steps_per_second": 1.764,
"step": 418
},
{
"epoch": 1.2,
"grad_norm": 2.8940045833587646,
"learning_rate": 5.932776707197725e-05,
"loss": 0.2105,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.9713600958657879,
"eval_loss": 0.1521669328212738,
"eval_runtime": 587.4301,
"eval_samples_per_second": 28.412,
"eval_steps_per_second": 1.777,
"step": 836
}
],
"logging_steps": 500,
"max_steps": 1254,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 2092966223184000.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": {
"learning_rate": 9.86697876767367e-05,
"num_train_epochs": 3,
"per_device_train_batch_size": 16,
"seed": 14
}
}
|