File size: 1,391 Bytes
0687c8b |
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 |
{
"best_metric": 0.9698621929298982,
"best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-1/checkpoint-1669",
"epoch": 1.0,
"eval_steps": 500,
"global_step": 1669,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.3,
"grad_norm": 1.8941549062728882,
"learning_rate": 2.7998077239858024e-06,
"loss": 0.3584,
"step": 500
},
{
"epoch": 0.6,
"grad_norm": 0.23405538499355316,
"learning_rate": 2.5731393525491277e-06,
"loss": 0.157,
"step": 1000
},
{
"epoch": 0.9,
"grad_norm": 0.15349306166172028,
"learning_rate": 2.3464709811124533e-06,
"loss": 0.1768,
"step": 1500
},
{
"epoch": 1.0,
"eval_accuracy": 0.9698621929298982,
"eval_loss": 0.13613532483577728,
"eval_runtime": 318.6416,
"eval_samples_per_second": 52.379,
"eval_steps_per_second": 3.276,
"step": 1669
}
],
"logging_steps": 500,
"max_steps": 6676,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 1346627047993920.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": {
"learning_rate": 3.0264760954224767e-06,
"num_train_epochs": 4,
"per_device_train_batch_size": 4,
"seed": 6
}
}
|