shenxq
/

zephyr-7b-dpo-qlora-pairrm

alignment-handbook

Generated from Trainer

4-bit precision

Model card Files Files and versions Community

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

shenxq's picture

Model save

c7bc043 verified 3 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.647387065536218,
	"train_runtime": 42673.6748,
	"train_samples": 19996,
	"train_samples_per_second": 0.469,
	"train_steps_per_second": 0.029
	}