JayHyeon
/

Qwen2-0.5B-Reward_VPO_1e-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_1e-4 / eval_results.json

JayHyeon's picture

Model save

387dd8f verified 2 months ago

188 Bytes

	{
	"epoch": 1.0,
	"eval_accuracy": 0.648,
	"eval_loss": 0.6108577251434326,
	"eval_runtime": 35.582,
	"eval_samples_per_second": 28.104,
	"eval_steps_per_second": 0.899
	}