Minbyul
/

meditron-7b-dpo-full-sft-wo-kqa_golden

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

meditron-7b-dpo-full-sft-wo-kqa_golden / train_results.json

Minbyul's picture

Model save

699090c verified about 2 months ago

raw history blame contribute delete

No virus

192 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5870200258786561,
	"train_runtime": 812.4392,
	"train_samples": 3886,
	"train_samples_per_second": 4.783,
	"train_steps_per_second": 0.075
	}