fenguhao
/

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

fenguhao's picture

Model save

54e9029 verified 3 months ago

193 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5401819272219315,
	"train_runtime": 34352.758,
	"train_samples": 61135,
	"train_samples_per_second": 1.78,
	"train_steps_per_second": 0.015
	}