mistral-7b-dpo-all_pairs / train_results.json
yangzhao02's picture
Model save
2205144 verified
raw
history blame contribute delete
233 Bytes
{
"epoch": 0.9981298423724285,
"total_flos": 0.0,
"train_loss": 0.3941320441264412,
"train_runtime": 39337.3566,
"train_samples": 59880,
"train_samples_per_second": 1.522,
"train_steps_per_second": 0.012
}