Jerry46
/

zephyr-7b-dpo-lora

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

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

Jerry46's picture

Training in progress, epoch 1

28e7de9 about 1 year ago

192 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.3465735912322998,
	"train_runtime": 17.6734,
	"train_samples": 61966,
	"train_samples_per_second": 0.566,
	"train_steps_per_second": 0.057
	}