antalvdb's picture
Training in progress, epoch 1
f8dee93 verified
raw
history blame
1.4 kB
{
"best_metric": 0.3666014217930852,
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-42",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 42,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 0.5672691464424133,
"eval_matthews_correlation": 0.0,
"eval_runtime": 0.4893,
"eval_samples_per_second": 2131.421,
"eval_steps_per_second": 134.874,
"step": 14
},
{
"epoch": 2.0,
"eval_loss": 0.6490755677223206,
"eval_matthews_correlation": 0.32301000206570946,
"eval_runtime": 0.4762,
"eval_samples_per_second": 2190.233,
"eval_steps_per_second": 138.596,
"step": 28
},
{
"epoch": 3.0,
"eval_loss": 0.7178954482078552,
"eval_matthews_correlation": 0.3666014217930852,
"eval_runtime": 0.5039,
"eval_samples_per_second": 2069.918,
"eval_steps_per_second": 130.982,
"step": 42
}
],
"logging_steps": 500,
"max_steps": 70,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 0,
"train_batch_size": 64,
"trial_name": null,
"trial_params": {
"learning_rate": 9.881638457643646e-05,
"num_train_epochs": 5,
"per_device_train_batch_size": 64,
"seed": 17
}
}