nlile
/

zephyr-7b-dpo-full

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

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

nlile's picture

Model save

0da90ed 12 months ago

198 Bytes

	{
	"epoch": 3.0,
	"train_loss": 0.026962732661432107,
	"train_runtime": 14195.2291,
	"train_samples": 140201,
	"train_samples_per_second": 29.63,
	"train_steps_per_second": 0.463
	}