train_math_qa_1754652175 / train_results.json
rbelanec's picture
End of training
ab89d15 verified
{
"epoch": 10.0,
"num_input_tokens_seen": 38732208,
"total_flos": 1.7440938205214147e+18,
"train_loss": 0.6449844909648225,
"train_runtime": 16798.7505,
"train_samples_per_second": 15.985,
"train_steps_per_second": 3.997
}