lewtun
/

gemma-7b-dpo-full-ultrafeedback-beta-0.01

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

gemma-7b-dpo-full-ultrafeedback-beta-0.01 / train_results.json

lewtun's picture

lewtun HF staff

Model save

ee89efc verified 4 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5152078939433867,
	"train_runtime": 5321.4428,
	"train_samples": 61135,
	"train_samples_per_second": 11.488,
	"train_steps_per_second": 0.09
	}