OpenThinker3-7B / all_results.json
bernquant's picture
Duplicate from open-thoughts/OpenThinker3-7B
6b24b93
Raw
History Blame Contribute Delete
211 Bytes
{
"epoch": 5.0,
"total_flos": 1.8504084910768128e+17,
"train_loss": 0.0797391855489743,
"train_runtime": 13114.3231,
"train_samples_per_second": 430.543,
"train_steps_per_second": 0.841
}