silviasapora
/

gemma-7b-orpo-noisy-1e-5-norm

Text Generation

Generated from Trainer

alignment-handbook

text-generation-inference

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

gemma-7b-orpo-noisy-1e-5-norm / train_results.json

silviasapora's picture

Model save

c2b98d9 verified 10 days ago

history blame contribute delete

230 Bytes

	{
	"epoch": 2.9765925925925925,
	"total_flos": 0.0,
	"train_loss": 95.27591378348214,
	"train_runtime": 8112.4006,
	"train_samples": 6750,
	"train_samples_per_second": 2.496,
	"train_steps_per_second": 0.039
	}