EllieS
/

zephyr-7b-dpo-lora-pubmedqa-ultrafeedback

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-dpo-lora-pubmedqa-ultrafeedback / train_results.json

EllieS's picture

Model save

9428d29 verified 11 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6024045768410584,
	"train_runtime": 59158.061,
	"train_samples": 61135,
	"train_samples_per_second": 1.033,
	"train_steps_per_second": 0.129
	}