hzy
/

Qwen2.5-3B-Knowledge-R1-GRPO

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Qwen2.5-3B-Knowledge-R1-GRPO / train_results.json

hzy's picture

Model save

4b48b2b verified about 1 year ago

201 Bytes

	{
	"total_flos": 0.0,
	"train_loss": 0.08651691437249102,
	"train_runtime": 12893.4863,
	"train_samples": 15000,
	"train_samples_per_second": 1.163,
	"train_steps_per_second": 0.166
	}