just1nseo
/

zephyr-dpo-qlora-gpt4-5e-6-epoch3

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

zephyr-dpo-qlora-gpt4-5e-6-epoch3 / train_results.json

just1nseo's picture

Model save

6f4d452 verified 3 months ago

193 Bytes

	{
	"epoch": 3.0,
	"train_loss": 0.1103198329137612,
	"train_runtime": 9245.0119,
	"train_samples": 5678,
	"train_samples_per_second": 1.843,
	"train_steps_per_second": 0.115
	}