dlibf
/

zephyr-6b-dpo-full

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

zephyr-6b-dpo-full / train_results.json

dlibf's picture

Model save

5349189 verified 10 months ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6029723678173879,
	"train_runtime": 7448.3301,
	"train_samples": 61135,
	"train_samples_per_second": 8.208,
	"train_steps_per_second": 0.064
	}