Minbyul
/

mistral-7b-dpo-full-wo-kqa_golden-ep3

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

mistral-7b-dpo-full-wo-kqa_golden-ep3 / train_results.json

Minbyul's picture

Model save

91fa69c verified 2 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.2699868052719749,
	"train_runtime": 2833.2764,
	"train_samples": 11996,
	"train_samples_per_second": 4.234,
	"train_steps_per_second": 0.066
	}