ShenaoZ
/

0.001_idpo_same_scratch_iter_2

Text Generation

alignment-handbook

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

0.001_idpo_same_scratch_iter_2 / all_results.json

ShenaoZ's picture

Model save

70aa0eb verified over 1 year ago

194 Bytes

	{
	"epoch": 1.0,
	"train_loss": 0.5994115610542537,
	"train_runtime": 8245.2497,
	"train_samples": 40756,
	"train_samples_per_second": 4.943,
	"train_steps_per_second": 0.039
	}