zephyr-7b-dpo-qlora-pairrm / train_results.json
shenxq's picture
Model save
c7bc043 verified
{
"epoch": 1.0,
"train_loss": 0.647387065536218,
"train_runtime": 42673.6748,
"train_samples": 19996,
"train_samples_per_second": 0.469,
"train_steps_per_second": 0.029
}