ZHLiu627
/

zephyr-7b-dpo-full

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-dpo-full / train_results.json

ZHLiu627's picture

Model save

336d38c verified about 1 year ago

189 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.3465735912322998,
	"train_runtime": 27.0943,
	"train_samples": 30,
	"train_samples_per_second": 1.107,
	"train_steps_per_second": 0.037
	}