ShenaoZ
/

0.0001_idpo_same_6iters_iter_1

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

0.0001_idpo_same_6iters_iter_1 / all_results.json

ShenaoZ's picture

Model save

6fff63b verified 2 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6432609260082245,
	"train_runtime": 1322.2943,
	"train_samples": 10189,
	"train_samples_per_second": 7.706,
	"train_steps_per_second": 0.061
	}