hp_ablations_qwen_bsz256 / all_results.json
sedrickkeh's picture
End of training
3dfea0c verified
{
"epoch": 2.9982905982905983,
"eval_loss": 0.6213015913963318,
"eval_runtime": 444.6851,
"eval_samples_per_second": 26.587,
"eval_steps_per_second": 0.416,
"total_flos": 2758364765356032.0,
"train_loss": 0.5923774672614808,
"train_runtime": 70850.8498,
"train_samples_per_second": 9.511,
"train_steps_per_second": 0.037
}