cygu
/

llama-2-7b-sampling-watermark-distill-kth-shift1

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

llama-2-7b-sampling-watermark-distill-kth-shift1 / all_results.json

cygu's picture

Upload folder using huggingface_hub

e6a4821 11 months ago

168 Bytes

	{
	"epoch": 1.0,
	"train_loss": 1.3342757062535537,
	"train_runtime": 12719.0865,
	"train_samples_per_second": 47.802,
	"train_steps_per_second": 0.373
	}