Minbyul
/

llama2-7b-wo-kqa_golden-iter-dpo-step2

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

llama2-7b-wo-kqa_golden-iter-dpo-step2 / all_results.json

Minbyul's picture

Model save

24b75e4 verified 6 months ago

192 Bytes

	{
	"epoch": 0.99,
	"train_loss": 0.6775914965004757,
	"train_runtime": 852.993,
	"train_samples": 3720,
	"train_samples_per_second": 4.361,
	"train_steps_per_second": 0.068
	}