Dongwei
/

DeepSeek-R1-Distill-Qwen-7B-GRPO_Math

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

DeepSeek-R1-Distill-Qwen-7B-GRPO_Math / eval_results.json

Dongwei's picture

Model save

6c50d3f verified 12 days ago

169 Bytes

	{
	"eval_loss": -7.450580596923828e-09,
	"eval_runtime": 18.8159,
	"eval_samples": 7,
	"eval_samples_per_second": 0.372,
	"eval_steps_per_second": 0.053
	}