lewtun
/

Qwen2-0.5B-Reward

Text Classification

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Qwen2-0.5B-Reward / eval_results.json

lewtun's picture

lewtun HF staff

End of training

f52a123 verified about 2 months ago

189 Bytes

	{
	"epoch": 1.0,
	"eval_accuracy": 0.731,
	"eval_loss": 0.5211551785469055,
	"eval_runtime": 2.0022,
	"eval_samples_per_second": 499.448,
	"eval_steps_per_second": 7.991
	}