lewtun
/

gemma-7b-dpo-full-openhermes-mix1-beta-0.4

Text Generation

alignment-handbook

generated_from_trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

gemma-7b-dpo-full-openhermes-mix1-beta-0.4 / train_results.json

lewtun's picture

lewtun HF staff

Model save

fc518be verified 3 months ago

raw history blame contribute delete

No virus

193 Bytes

	{
	"epoch": 0.99,
	"train_loss": 1.981816053390503,
	"train_runtime": 574.1146,
	"train_samples": 6750,
	"train_samples_per_second": 11.757,
	"train_steps_per_second": 0.091
	}