bert_12_layer_model_v2 / all_results.json
gokuls's picture
End of training
810ced4
{
"epoch": 5.0,
"eval_accuracy": 0.5982814143913313,
"eval_loss": 2.1100358963012695,
"eval_runtime": 502.4632,
"eval_samples": 154178,
"eval_samples_per_second": 306.844,
"eval_steps_per_second": 4.796,
"perplexity": 8.248537371294933,
"train_loss": 3.027850917318448,
"train_runtime": 97726.2074,
"train_samples": 2929379,
"train_samples_per_second": 149.877,
"train_steps_per_second": 2.342
}