Blancy
/

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 / train_results.json

Blancy's picture

Model save

68e305f verified about 1 year ago

203 Bytes

	{
	"total_flos": 0.0,
	"train_loss": -2.92552325735344e-11,
	"train_runtime": 25378.3621,
	"train_samples": 10000,
	"train_samples_per_second": 0.394,
	"train_steps_per_second": 0.014
	}