lewtun
/

gemma-7b-sft-full-longest-1k-v0

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

gemma-7b-sft-full-longest-1k-v0 / train_results.json

lewtun's picture

lewtun HF staff

Model save

3046e76 verified 9 months ago

192 Bytes

	{
	"epoch": 15.0,
	"train_loss": 2.68501771291097,
	"train_runtime": 1215.2713,
	"train_samples": 1000,
	"train_samples_per_second": 9.121,
	"train_steps_per_second": 0.074
	}