Minbyul
/

llama2-7b-wo-kqa_golden-iter-sft-step1

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

llama2-7b-wo-kqa_golden-iter-sft-step1 / eval_results.json

Minbyul's picture

End of training

44f2c31 verified 6 months ago

186 Bytes

	{
	"epoch": 3.0,
	"eval_loss": 1.2119849920272827,
	"eval_runtime": 37.6346,
	"eval_samples": 4044,
	"eval_samples_per_second": 9.725,
	"eval_steps_per_second": 0.611
	}