ShenaoZ
/

0.001_idpo_same_scratch_iter_1

Text Generation

alignment-handbook

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

0.001_idpo_same_scratch_iter_1 / all_results.json

ShenaoZ's picture

Model save

7a394ab verified 2 months ago

raw history blame contribute delete

No virus

193 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.6054114065830063,
	"train_runtime": 3723.997,
	"train_samples": 20378,
	"train_samples_per_second": 5.472,
	"train_steps_per_second": 0.043
	}