zhongshsh
/

zephyr-7b-sft-qlora

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

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

zhongshsh's picture

Model save

19f8e4f verified 7 months ago

196 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.9995975574413953,
	"train_runtime": 68593.2406,
	"train_samples": 207864,
	"train_samples_per_second": 2.033,
	"train_steps_per_second": 0.254
	}