plaguss
/

zephyr-7b-lora-adapter-dpo-dibt-v0

Generated from Trainer

4-bit precision

Model card Files Files and versions Community

zephyr-7b-lora-adapter-dpo-dibt-v0 / train_results.json

plaguss's picture

plaguss HF staff

Model save

3e6253c verified 8 months ago

165 Bytes

	{
	"epoch": 2.0,
	"train_loss": 0.1882365908726905,
	"train_runtime": 5068.0756,
	"train_samples_per_second": 0.65,
	"train_steps_per_second": 0.041
	}