yjh00
/

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

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

Qwen2.5-1.5B-Open-R1-Distill / all_results.json

yjh00's picture

Model save

0fb8cef verified 3 months ago

211 Bytes

	{
	"total_flos": 28487712768000.0,
	"train_loss": 0.920774197101593,
	"train_runtime": 1759.2244,
	"train_samples": 16610,
	"train_samples_per_second": 18.19,
	"train_steps_per_second": 0.568
	}