fnet-large-finetuned-cola-copy5 / trainer_state.json
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"global_step": 10690,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"learning_rate": 3.5566666666666666e-05,
"loss": 0.6212,
"step": 2138
},
{
"epoch": 1.0,
"eval_loss": 0.6539720296859741,
"eval_matthews_correlation": 0.0,
"eval_runtime": 22.7284,
"eval_samples_per_second": 45.89,
"eval_steps_per_second": 5.764,
"step": 2138
},
{
"epoch": 2.0,
"learning_rate": 2.6700000000000002e-05,
"loss": 0.62,
"step": 4276
},
{
"epoch": 2.0,
"eval_loss": 0.6409146785736084,
"eval_matthews_correlation": 0.0,
"eval_runtime": 22.7182,
"eval_samples_per_second": 45.91,
"eval_steps_per_second": 5.766,
"step": 4276
},
{
"epoch": 3.0,
"learning_rate": 1.783333333333333e-05,
"loss": 0.6182,
"step": 6414
},
{
"epoch": 3.0,
"eval_loss": 0.6234332919120789,
"eval_matthews_correlation": 0.0,
"eval_runtime": 22.7216,
"eval_samples_per_second": 45.904,
"eval_steps_per_second": 5.765,
"step": 6414
},
{
"epoch": 4.0,
"learning_rate": 8.966666666666667e-06,
"loss": 0.6181,
"step": 8552
},
{
"epoch": 4.0,
"eval_loss": 0.6234201192855835,
"eval_matthews_correlation": 0.0,
"eval_runtime": 22.7101,
"eval_samples_per_second": 45.927,
"eval_steps_per_second": 5.768,
"step": 8552
},
{
"epoch": 5.0,
"learning_rate": 1e-07,
"loss": 0.6217,
"step": 10690
},
{
"epoch": 5.0,
"eval_loss": 0.6270990371704102,
"eval_matthews_correlation": 0.0,
"eval_runtime": 22.7215,
"eval_samples_per_second": 45.904,
"eval_steps_per_second": 5.765,
"step": 10690
},
{
"epoch": 5.0,
"step": 10690,
"total_flos": 2.674821632676864e+16,
"train_loss": 0.6198258174257484,
"train_runtime": 3421.027,
"train_samples_per_second": 12.498,
"train_steps_per_second": 3.125
}
],
"max_steps": 10690,
"num_train_epochs": 5,
"total_flos": 2.674821632676864e+16,
"trial_name": null,
"trial_params": null
}