mistral-7b-dpo-single_pair / train_results.json
yangzhao02's picture
Model save
7556ac8 verified
raw
history blame contribute delete
233 Bytes
{
"epoch": 0.9981298423724285,
"total_flos": 0.0,
"train_loss": 0.6707821693869679,
"train_runtime": 12010.3686,
"train_samples": 59880,
"train_samples_per_second": 4.986,
"train_steps_per_second": 0.039
}