ShenaoZ
/

0.001_ablation_5iters_bs256_useresponse_iter_1

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

0.001_ablation_5iters_bs256_useresponse_iter_1 / train_results.json

ShenaoZ's picture

Model save

e19844d verified about 2 months ago

raw history blame contribute delete

No virus

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6586156586805979,
	"train_runtime": 1568.8191,
	"train_samples": 12227,
	"train_samples_per_second": 7.794,
	"train_steps_per_second": 0.031
	}