ShenaoZ
/

0.0_idpo_same_3iters_debug_iter_1

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

0.0_idpo_same_3iters_debug_iter_1 / train_results.json

ShenaoZ's picture

Model save

297b8ec verified 2 months ago

raw history blame contribute delete

No virus

193 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6025606791178385,
	"train_runtime": 2664.2013,
	"train_samples": 20378,
	"train_samples_per_second": 7.649,
	"train_steps_per_second": 0.06
	}