File size: 1,619 Bytes
b793713 |
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 63 |
{
"best_metric": 0.9739134907722473,
"best_model_checkpoint": "BERT-WMM/run-0/checkpoint-136",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 136,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.4572769953051643,
"eval_loss": 1.057793140411377,
"eval_runtime": 2.1526,
"eval_samples_per_second": 989.489,
"eval_steps_per_second": 62.25,
"step": 34
},
{
"epoch": 2.0,
"eval_accuracy": 0.535680751173709,
"eval_loss": 0.9990364909172058,
"eval_runtime": 2.1045,
"eval_samples_per_second": 1012.106,
"eval_steps_per_second": 63.672,
"step": 68
},
{
"epoch": 3.0,
"eval_accuracy": 0.5384976525821596,
"eval_loss": 0.9778991937637329,
"eval_runtime": 2.072,
"eval_samples_per_second": 1028.013,
"eval_steps_per_second": 64.673,
"step": 102
},
{
"epoch": 4.0,
"eval_accuracy": 0.5413145539906103,
"eval_loss": 0.9739134907722473,
"eval_runtime": 2.9432,
"eval_samples_per_second": 723.71,
"eval_steps_per_second": 45.529,
"step": 136
}
],
"logging_steps": 500,
"max_steps": 136,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": {
"learning_rate": 1.3245164890212277e-06,
"num_train_epochs": 4,
"per_device_train_batch_size": 256,
"weight_decay": 3.536833872428622e-05
}
}
|