Leena Shekhar

@wchowdhu In my case generated summaries were different but not bad like yours. I have a feeling you are not loading the ckpt, check your ckpt path and make sure...

Hi @huyingxi, I am not sure how different is "quite different" for you. I am not working on it currently, but as you could see from my post above things...

Sorry I did not mean Python2 and Python3 difference. I think the author ported the code from TF older version to new version and that might have introduced something. Again,...

I have not worked on it after that, but from experience it might be because of the training. Usually you need t train for longer steps in such models. Try...

Thank you for such a fast response. I am using this command now: python run_classifier.py --do_train=False --do_eval=True --task_name=mnli_matched --data_dir=../MNLI/MNLI --output_dir=results **--init_checkpoint=model/xlnet_cased_L-24_H-1024_A-16/xlnet_model.ckpt** --uncased=False --spiece_model_file=model/xlnet_cased_L-24_H-1024_A-16/spiece.model --model_config_path=model/xlnet_cased_L-24_H-1024_A-16/xlnet_config.json --max_seq_length=128 --eval_batch_size=8 --num_hosts=1 --num_core_per_host=1 --eval_all_ckpt=False --is_regression=False...

Ugh should have seen that. Thank you!

True. I think fine-tuning first makes sense too and MNLI has the train dataset.