Minbyul
/

llama2-7b-dpo-full-wo-healthsearch_qa-ep3

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

llama2-7b-dpo-full-wo-healthsearch_qa-ep3 / train_results.json

Minbyul's picture

Model save

5a4a1e6 verified 7 months ago

193 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6753969060050117,
	"train_runtime": 1121.4796,
	"train_samples": 5168,
	"train_samples_per_second": 4.608,
	"train_steps_per_second": 0.072
	}