just1nseo
/

zephyr-dpo-qlora-gpt4-5e-6

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

zephyr-dpo-qlora-gpt4-5e-6 / train_results.json

just1nseo's picture

Model save

c35d5de verified 5 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.24729210323011372,
	"train_runtime": 4030.3896,
	"train_samples": 5678,
	"train_samples_per_second": 1.409,
	"train_steps_per_second": 0.088
	}