RikkiXu
/

zephyr-7b-dpo-full

Text Generation

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

RikkiXu's picture

Model save

9092f3f verified 8 months ago

197 Bytes

	{
	"epoch": 3.0,
	"train_loss": 0.007373018379906397,
	"train_runtime": 5373.2533,
	"train_samples": 61134,
	"train_samples_per_second": 34.132,
	"train_steps_per_second": 0.267
	}