just1nseo
/

zephyr-dpo-qlora-gpt4-5e-7-epoch3

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

zephyr-dpo-qlora-gpt4-5e-7-epoch3 / all_results.json

just1nseo's picture

Model save

6d917ec verified 7 months ago

193 Bytes

	{
	"epoch": 3.0,
	"train_loss": 0.4860824931955114,
	"train_runtime": 9341.4813,
	"train_samples": 5678,
	"train_samples_per_second": 1.823,
	"train_steps_per_second": 0.114
	}