ZHZisZZ
/

zephyr-7b-dpo-full

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

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

ZHZisZZ's picture

Model save

5b955bd verified 2 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5374924991918907,
	"train_runtime": 7413.7576,
	"train_samples": 61134,
	"train_samples_per_second": 8.246,
	"train_steps_per_second": 0.064
	}