JayHyeon
/

Qwen2-0.5B-Reward_VPO_5e-4

Text Classification

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Qwen2-0.5B-Reward_VPO_5e-4 / eval_results.json

JayHyeon's picture

Model save

21e9756 verified 2 months ago

189 Bytes

	{
	"epoch": 1.0,
	"eval_accuracy": 0.663,
	"eval_loss": 0.6578302383422852,
	"eval_runtime": 36.9051,
	"eval_samples_per_second": 27.097,
	"eval_steps_per_second": 0.867
	}