Minbyul
/

mistral-7b-dpo-full-sft-wo-kqa_silver_wogold

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

mistral-7b-dpo-full-sft-wo-kqa_silver_wogold / train_results.json

Minbyul's picture

Model save

f266d39 7 months ago

195 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.24172405860846555,
	"train_runtime": 5168.5497,
	"train_samples": 20204,
	"train_samples_per_second": 3.909,
	"train_steps_per_second": 0.061
	}