zephyr-7b-dpo-lora-ultrafeedback / train_results.json
EllieS's picture
Model save
87d88a2 verified
{
"epoch": 1.0,
"train_loss": 0.6084560017191406,
"train_runtime": 59476.7244,
"train_samples": 61135,
"train_samples_per_second": 1.028,
"train_steps_per_second": 0.128
}