MichaelR207
/

mistral-sft-7b-dpo-qlora

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

mistral-sft-7b-dpo-qlora / train_results.json

MichaelR207's picture

Model save

53d9518 verified 4 months ago

raw history blame contribute delete

No virus

189 Bytes

	{
	"epoch": 5.0,
	"train_loss": 0.17302747964859008,
	"train_runtime": 39.8084,
	"train_samples": 5,
	"train_samples_per_second": 0.628,
	"train_steps_per_second": 0.126
	}