zharry29
/

order_benchmark_xlnet

Multiple Choice Transformers PyTorch xlnet Inference Endpoints

Model card Files Files and versions Community

order_benchmark_xlnet / is_test_false_eval_results.txt

system's picture

system HF staff

Update is_test_false_eval_results.txt

f1bb99b over 3 years ago

raw history blame contribute delete

No virus

178 Bytes

	model =xlnet-base-cased
	total batch size=32
	train num epochs=1
	fp16 =False
	max seq length =80
	eval_acc = 0.8264516129032258
	eval_loss = 0.41941473571602833