susumuota
/

Qwen2.5-1.5B-Open-R1-GRPO

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Qwen2.5-1.5B-Open-R1-GRPO / eval_results.json

susumuota's picture

End of training

c5c453f verified 15 days ago

168 Bytes

	{
	"eval_loss": 0.0070059471763670444,
	"eval_runtime": 33.0783,
	"eval_samples": 99,
	"eval_samples_per_second": 2.993,
	"eval_steps_per_second": 0.03
	}