anamelchor's picture
Training in progress, epoch 1
4940d35 verified
raw
history blame
1.4 kB
{
"best_metric": 0.3342982430724728,
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-81",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 81,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 0.5924028158187866,
"eval_matthews_correlation": 0.0,
"eval_runtime": 0.7139,
"eval_samples_per_second": 1460.954,
"eval_steps_per_second": 92.448,
"step": 27
},
{
"epoch": 2.0,
"eval_loss": 0.5790226459503174,
"eval_matthews_correlation": 0.2712686505720511,
"eval_runtime": 0.7744,
"eval_samples_per_second": 1346.766,
"eval_steps_per_second": 85.222,
"step": 54
},
{
"epoch": 3.0,
"eval_loss": 0.6065369248390198,
"eval_matthews_correlation": 0.3342982430724728,
"eval_runtime": 1.2898,
"eval_samples_per_second": 808.645,
"eval_steps_per_second": 51.17,
"step": 81
}
],
"logging_steps": 500,
"max_steps": 135,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": {
"learning_rate": 3.196781434256157e-05,
"num_train_epochs": 5,
"per_device_train_batch_size": 32,
"seed": 15
}
}