Kadins
/

DeepSeek-R1-Distill-Qwen-7B-GRPO-v8

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

DeepSeek-R1-Distill-Qwen-7B-GRPO-v8 / train_results.json

Kadins's picture

Model save

b484df4 verified about 1 month ago

202 Bytes

	{
	"total_flos": 0.0,
	"train_loss": 0.0015093988140246698,
	"train_runtime": 5817.5821,
	"train_samples": 10800,
	"train_samples_per_second": 1.856,
	"train_steps_per_second": 0.066
	}