vain05
/

stablelm-2-1_6b-orpo-full-v2

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

stablelm-2-1_6b-orpo-full-v2 / train_results.json

vain05's picture

Model save

2df3cc3 verified 10 months ago

195 Bytes

	{
	"epoch": 2.0,
	"train_loss": 1.2334148878183206,
	"train_runtime": 17382.4906,
	"train_samples": 60916,
	"train_samples_per_second": 7.009,
	"train_steps_per_second": 0.146
	}