EllieS
/

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

alignment-handbook

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

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

EllieS's picture

Model save

b314125 verified 4 months ago

raw history blame contribute delete

No virus

195 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5599543302822287,
	"train_runtime": 34322.3587,
	"train_samples": 61135,
	"train_samples_per_second": 1.781,
	"train_steps_per_second": 0.445
	}