8000 Report the results · Issue #15 · localminimum/QANet · GitHub
[go: up one dir, main page]

Skip to content

Report the results #15

Open
Open

Description

@jasonwbw
Model Training Steps Size Attention Heads Data Size (aug) EM F1
My Model 60,000 128 1 87k (no aug) 70.7 79.8

The results are obtained on a K80 machine. I modify the trilinear function for memory efficiency, but the results are the same with the current version of this repository.

I'm not sure about the overfitting, the model is the last checkpoint after training 60,000 steps.

Activity

  1. jasonwbw commented on Apr 26, 2018

    @jasonwbw
    ContributorAuthor

    Ok, the F1 and EM curves on the dev set oscillate after 30k steps, but the loss curve keeps on a rise after that. Unfortunately, I have just saved the last five checkpoints.

  2. raisudeen commented on Apr 27, 2018

    @raisudeen

    @jasonwbw Can you please share the trained model if possible? So that, it will be useful for all. Thanks in advance.
    -Raisudeen.

  3. chesterkuo commented on May 5, 2018

    @chesterkuo

    Exact Match: 70.8136234626, F1: 80.0760742304

    with following parameter.
    --hidden=128 --num_heads=8 --checkpoint=2000 --num_steps=60000 --learning_rate=0.001 --batch_size=32

  4. ajay-sreeram commented on May 5, 2018

    @ajay-sreeram

    EM: 68.60, F1: 78.16

    Results obtained with CPU(8GB ram), ran for 4 and 1/2 days
    Using all default parameters but Glove42B and 35K steps instead

  5. jasonwbw commented on May 7, 2018

    @jasonwbw
    ContributorAuthor

    @raisudeen Sorry for the late replay due to the vacation. Checkpoints obtained by TF 1.4

  6. localminimum commented on May 7, 2018

    @localminimum
    Owner

    Hi @chesterkuo , is your result above obtained after this commit? f0c79cc
    Thanks for reporting your results on CPU @ajay-sreeram! That is some impressive patience. I talked to the original paper authors and they saw a performance increase after using Glove800B over 42B. Is there a reason why you used 42B?

  7. ajay-sreeram commented on May 7, 2018

    @ajay-sreeram

    Hi @localminimum , I am happy to see such a good performance results from re-implementation of QANet paper. To know the model performance with weaker embedding, I tried using Glove42B. Yes the results show that there is a decrease in the performance but that is not much, this proves the strength of QANet again.

    Word Embedding Training Steps EM F1
    Glove840B 35,000 69.0 78.6
    Glove42B 35,000 68.6 78.1
  8. changed the title [-]Report the results with 128 hidden units[/-] [+]Report the results[/+] on May 8, 2018
  9. chesterkuo commented on May 8, 2018

    @chesterkuo

    @localminimum , yes, based on new changed with Glove "glove.840B.300d"

  10. PhungVanDuy commented on May 8, 2018

    @PhungVanDuy

    @jasonwbw I tried to use your checkpoint but I got an error following:

    image
    Can you tell me how to use your checkpoint?
    Thanks you!
    @ajay-sreeram Can you please share the checkpoint? Thanks.

  11. jasonwbw commented on May 9, 2018

    @jasonwbw
    ContributorAuthor

    @PhungVanDuy Firstly, I feel sorry that I have forgot to report some details, I obtain this results upon TF 1.4 instead o F438 f 1.5, and I report the results before commit f0c79cc.
    Then I wonder that you have forgot to set save_path in the config.py according to your error.
    And the path should be train_dir/model_name/model by default.

  12. PhungVanDuy commented on May 9, 2018

    @PhungVanDuy

    @jasonwbw Thanks for your support. I have used your checkpoint, however, the result not makes sense, here is my screenshot!
    image
    EM: 0.331122
    F1: 7.059
    Can you explain to me about it!
    Thanks

  13. localminimum commented on May 9, 2018

    @localminimum
    Owner

    Hi @PhungVanDuy , it seems like you are using the latest commit. @jasonwbw mentioned in the previous comment that he used the model before commit f0c79cc. You could revert back to the previous commit and try again. The performance fluctuation would be most likely due to my latest commit, removing the activation function from the highway layers. The input distribution will be very different without the relu activation and the highway layers won't have a single clue how to deal with the unseen distribution.

  14. PhungVanDuy commented on May 9, 2018

    @PhungVanDuy

    @localminimum Thanks for your reply, I tried going back commit bb5769d (git reset --hard bb5769d) and run test. But I got an error following:
    image

    I save checkpoint in the default folder (train/FRC/model and checkpoint file: model_checkpoint_path: "model_60000_ckpt") and using tensorflow 1.4 as @jasonwbw mentioned.

    @localminimum can you share for me lastest checkpoint of this repos?

  15. jasonwbw commented on May 9, 2018

    @jasonwbw
    ContributorAuthor

    @PhungVanDuy maybe hidden size should be set to 128 in config.

  16. PhungVanDuy commented on May 9, 2018

    @PhungVanDuy

    @jasonwbw I knew it but still error! Can you share your source code stable for the checkpoint? I would be very grateful for that. I am looking forward to your reply.

  17. localminimum commented on May 9, 2018

    @localminimum
    Owner

    @PhungVanDuy can you post the error you get here?

  18. PhungVanDuy commented on May 9, 2018

    @PhungVanDuy

    @localminimum I reproduce the checkpoint of @jasonwbw with commit bb5769d (git reset --hard bb5769d).
    I put the checkpoint to default folder: train/FRC/model.
    And then I got an error:

    Loading model...
    Total number of trainable parameters: 1295938
    2018-05-09 00:32:32.496830: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX
    2018-05-09 00:32:36.431273: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key Context_to_Query_Attention_Layer/trilinear/trilinear/linear_bias/ExponentialMovingAverage not found in checkpoint
    2018-05-09 00:32:36.432023: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key Context_to_Query_Attention_Layer/trilinear/trilinear/linear_kernel/ExponentialMovingAverage not found in checkpoint
    2018-05-09 00:32:36.432842: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key Context_to_Query_Attention_Layer/trilinear/trilinear/linear_kernel not found in checkpoint
    2018-05-09 00:32:36.434867: W tensorflow/core/framework/op_kernel.cc:1192] Not found: Key Context_to_Query_Attention_Layer/trilinear/trilinear/linear_bias not found in checkpoint
    Traceback (most recent call last):
    File "config.py", line 145, in <module>
    tf.app.run()
    File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
    File "config.py", line 136, in main
    test(config)
    File "/mnt/hdd1/pvduy/QA/Try/QANet/main.py", line 159, in test
    saver.restore(sess, tf.train.latest_checkpoint(config.save_dir))
    File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1666, in restore
    {self.saver_def.filename_tensor_name: save_path})
    File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 889, in run
    	run_metadata_ptr)
    	File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1120, in _run
    		feed_dict_tensor, options, run_metadata)
    		File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1317, in _do_run
    		options, run_metadata)
    			File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1336, in _do_call
    			raise type(e)(node_def, op, message)
    tensorflow.python.framework.errors_impl.NotFoundError: Key Context_to_Query_Attention_Layer/trilinear/trilinear/linear_bias/ExponentialMovingAverage not found in checkpoint
    	[[Node: save/RestoreV2_9 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_9/tensor_names, save/RestoreV2_9/shape_and_slices)]]
    
    	Caused by op u'save/RestoreV2_9', defined at:
    	File "config.py", line 145, in <module>
    	tf.app.run()
    File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
    File "config.py", line 136, in main
    test(config)
    File "/mnt/hdd1/pvduy/QA/Try/QANet/main.py", line 158, in test
    saver = tf.train.Saver()
    File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1218, in __init__
    self.build()
    File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1227, in build
    self._build(self._filename, build_save=True, build_restore=True)
    File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1263, in _build
    build_save=build_save, build_restore=build_restore)
    File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 751, in _build_internal
    	restore_sequentially, reshape)
    	File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 427, in _AddRestoreOps
    		tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
    File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 267, in restore_op
    [spec.tensor.dtype])[0])
    File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_io_ops.py", line 1021, in restore_v2
    	shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)
    		File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    			op_def=op_def)
    			File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
    			op_def=op_def)
    				File "/mnt/hdd1/pvduy/vlen2new/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1470, in __init__
    				self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access
    
    				NotFoundError (see above for traceback): Key Context_to_Query_Attention_Layer/trilinear/trilinear/linear_bias/ExponentialMovingAverage not found in checkpoint
    										[[Node: save/RestoreV2_9 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_9/tensor_names, save/RestoreV2_9/shape_and_slices)]]
    

    My system:

    • Python: 2.7
    • Tensorflow: 1.4.0
  19. localminimum commented on May 9, 2018

    @localminimum
    Owner

    @jasonwbw looking at the error above, did you use the old trilinear function for the pretrained model above? It seems like the optimised trilinear function exponential moving average is missing.

  20. localminimum commented on May 9, 2018

    @localminimum
    Owner

    @PhungVanDuy comment out the old trilinear function as it is in the latest commit. Only use the optimied trilinear function and try again. It seems like you are trying to load weights that are not present in the checkpoints which belong to the old trilinear function.

  21. PhungVanDuy commented on May 9, 2018

    @PhungVanDuy

    @localminimum Thank you for your supports I solved it!
    image

  22. gowthamrang commented on Jun 26, 2018

    @gowthamrang

    Great work folks! :)This information is very helpful. One other piece of information that would help some audience, I guess, is the time taken for inference. @jasonwbw , @ajay-sreeram (CPU), @chesterkuo ?

    • thank you :)
  23. GuoYL36 commented on Jul 19, 2018

    @GuoYL36

    Hi, I use all default parameters and get results worse than that you presented.
    EM: 67.975, F1: 78.015 with following parameter.
    --hidden=96 --num_heads=1 --num_steps=35000
    I don't know why it happens?

  24. GuoYL36 commented on Jul 20, 2018

    @GuoYL36

    I try to modify the character embedding size to train again with following parameter
    --hidden=96 --num_heads=1 --num_steps=35000 --char_emb_size=200(original paper using)
    And I get the results: EM: 69.196, F1:78.66.

  25. localminimum commented on Jul 20, 2018

    @localminimum
    Owner

    Hi @webdaren , is there a reason why you've trained specifically for 35000 steps? All the listed results are based on models trained for 60k steps or longer.

  26. GuoYL36 commented on Jul 20, 2018

    @GuoYL36

    @localminimum Thank you for your answer! I just want to compare with the result of the first row in listed results. I get the result (EM: 67.975, F1: 78.015) worse than that in listed results when I used these parameters of the first row in listed results(specially, the value of char_emb_size is 64 in config.py).
    Of course, I also train the model for 60K steps and get the result (EM: 67.8, F1: 77.82) worst than all results. And I will train the model for 60K steps using the modified value of char_emb_size (original paper using).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions

      0