mashinaalive
/

zephyr-7b-dpo-qlora

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Metrics Training metrics Community

zephyr-7b-dpo-qlora / train_results.json

mashinaalive's picture

Model save

b01c0e2 verified 3 months ago

raw history blame contribute delete

No virus

196 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5464587531257954,
	"train_runtime": 239691.3187,
	"train_samples": 61135,
	"train_samples_per_second": 0.255,
	"train_steps_per_second": 0.064
	}