lewtun
/

gemma-7b-dpo-full-mix2-beta-0.1

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

gemma-7b-dpo-full-mix2-beta-0.1 / train_results.json

lewtun's picture

lewtun HF staff

Model save

b4276b8 verified 8 months ago

195 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5623811487565961,
	"train_runtime": 6612.2068,
	"train_samples": 72994,
	"train_samples_per_second": 11.039,
	"train_steps_per_second": 0.086
	}