ShenaoZ
/

0.0001_idpo_same_3iters_iter_1

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

0.0001_idpo_same_3iters_iter_1 / all_results.json

ShenaoZ's picture

Model save

47420b0 verified 7 months ago

193 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6025606791178385,
	"train_runtime": 4000.6914,
	"train_samples": 20378,
	"train_samples_per_second": 5.094,
	"train_steps_per_second": 0.04
	}