a-F1
/

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

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Qwen2.5-1.5B-Open-R1-Distill-mixed / train_results.json

a-F1's picture

Model save

4386296 verified about 1 year ago

199 Bytes

	{
	"total_flos": 0.0,
	"train_loss": 1.963218881252118,
	"train_runtime": 27333.3295,
	"train_samples": 16610,
	"train_samples_per_second": 0.791,
	"train_steps_per_second": 0.099
	}