ShenaoZhang
/

0.001_3iters_bs256_nodpo_only4w_iter_1

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

0.001_3iters_bs256_nodpo_only4w_iter_1 / train_results.json

ShenaoZhang's picture

Model save

56aaa64 verified about 2 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6293867803536929,
	"train_runtime": 3116.1807,
	"train_samples": 13333,
	"train_samples_per_second": 4.279,
	"train_steps_per_second": 0.017
	}