ShenaoZhang
/

0.001_5iters_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_5iters_bs256_nodpo_only4w_iter_1 / all_results.json

ShenaoZhang's picture

Model save

80574e2 verified about 2 months ago

raw history blame contribute delete

No virus

218 Bytes

	{
	"epoch": 0.992,
	"total_flos": 0.0,
	"train_loss": 0.6603157808703761,
	"train_runtime": 1409.3993,
	"train_samples": 8000,
	"train_samples_per_second": 5.676,
	"train_steps_per_second": 0.022
	}