glimmerz
/

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

glimmerz's picture

Model save

0891d87 12 months ago

196 Bytes

	{
	"epoch": 3.0,
	"train_loss": 0.20145473461829064,
	"train_runtime": 66730.9037,
	"train_samples": 61966,
	"train_samples_per_second": 2.786,
	"train_steps_per_second": 0.044
	}