Llama-3.1-8B-Instruct-SFT-400 / all_results.json
chchen's picture
End of training
3e63deb verified
{
"epoch": 9.777777777777779,
"eval_loss": 0.06450273841619492,
"eval_runtime": 1.0476,
"eval_samples_per_second": 38.182,
"eval_steps_per_second": 19.091,
"total_flos": 1.959093130965811e+16,
"train_loss": 0.4326907604932785,
"train_runtime": 310.7933,
"train_samples_per_second": 11.583,
"train_steps_per_second": 0.708
}