shenxq
/

zephyr-7b-dpo-qlora

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-dpo-qlora / train_results.json

shenxq's picture

Model save

29be7a4 verified 8 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6736802890646257,
	"train_runtime": 42164.1735,
	"train_samples": 19996,
	"train_samples_per_second": 0.474,
	"train_steps_per_second": 0.03
	}