train_math_qa_101112_1760638065 / eval_results.json
rbelanec's picture
End of training
4a6696c verified
{
"epoch": 20.0,
"eval_loss": 1.094519853591919,
"eval_runtime": 45.4849,
"eval_samples_per_second": 65.604,
"eval_steps_per_second": 16.401,
"num_input_tokens_seen": 77914328
}