AlexiaJM
/

zephyr-7b-dpo-full-repnew

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

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

AlexiaJM's picture

Model save

e8ddc6a verified 4 months ago

raw history blame contribute delete

No virus

196 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.08043583084202413,
	"train_runtime": 2697.0957,
	"train_samples": 61135,
	"train_samples_per_second": 22.667,
	"train_steps_per_second": 0.177
	}