RikkiXu
/

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

RikkiXu's picture

Model save

960557d verified 5 months ago

196 Bytes

	{
	"epoch": 1.99,
	"train_loss": 0.6178853964672408,
	"train_runtime": 10771.3374,
	"train_samples": 46008,
	"train_samples_per_second": 8.543,
	"train_steps_per_second": 0.033
	}