llama-3-8b-instruct-dpo-iter2 / all_results.json
jcmei's picture
End of training
4d09cc3 verified
raw
history blame contribute delete
216 Bytes
{
"epoch": 1.0,
"total_flos": 0.0,
"train_loss": 0.6844280029718692,
"train_runtime": 2776.587,
"train_samples": 19958,
"train_samples_per_second": 7.188,
"train_steps_per_second": 0.112
}