bruel
/

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

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

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

bruel's picture

End of training

cd94a73 verified about 1 year ago

168 Bytes

	{
	"eval_loss": 0.15634740889072418,
	"eval_runtime": 139.1453,
	"eval_samples": 99,
	"eval_samples_per_second": 0.711,
	"eval_steps_per_second": 0.029
	}