a1_math_big_math / all_results.json
ryanmarten's picture
End of training
8518f5f verified
raw
history blame contribute delete
224 Bytes
{
"epoch": 4.988354430379747,
"total_flos": 1.3796467879622738e+18,
"train_loss": 0.21418862139609288,
"train_runtime": 44832.7347,
"train_samples_per_second": 3.524,
"train_steps_per_second": 0.027
}