jikaixuan
/

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

jikaixuan's picture

Model save

44e3e84 verified over 1 year ago

195 Bytes

	{
	"epoch": 1.0,
	"train_loss": 1826.8015694608227,
	"train_runtime": 32379.7062,
	"train_samples": 61135,
	"train_samples_per_second": 1.888,
	"train_steps_per_second": 0.015
	}