ondevicellm
/

zephyr-7b-dpo-full

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

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

hushell's picture

Model save

fac6a8d verified 10 months ago

195 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5274335609056563,
	"train_runtime": 22383.3635,
	"train_samples": 61135,
	"train_samples_per_second": 2.731,
	"train_steps_per_second": 0.043
	}