EllieS
/

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

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

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

EllieS's picture

Model save

e1de556 verified 4 months ago

raw history blame contribute delete

No virus

193 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6071469678956156,
	"train_runtime": 31823.939,
	"train_samples": 61135,
	"train_samples_per_second": 1.921,
	"train_steps_per_second": 0.24
	}