Yukang
/

Qwen2.5-7B-Open-R1-GRPO

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

Qwen2.5-7B-Open-R1-GRPO / all_results.json

Yukang's picture

Model save

c91757c verified 16 days ago

204 Bytes

	{
	"total_flos": 0.0,
	"train_loss": 3.769922398664146e-06,
	"train_runtime": 505.2607,
	"train_samples": 93733,
	"train_samples_per_second": 185.514,
	"train_steps_per_second": 11.596
	}