microsoft / hmnet Goto Github PK

    # self-attention
    a = self.attn(query, key, value, None, one_dir_visible=True)
    # batch x len x n_state

    n = self.ln_1(y + a) # residual

    if 'NO_HIERARCHY' in self.opt:
        q = y
        r = n
    else:
        # src-tgt attention on sentences
        q = self.sent_attn(n, sent_enc_key, sent_enc_value, None)
        r = self.ln_3(n + q) # residual
        # batch x len x n_state

    # src-tgt attention on tokens
    o = self.token_attn(r, token_enc_key, token_enc_value, None)
    p = self.ln_2(r + o) # residual
    # batch x len x n_state


    m = self.mlp(p)
    h = self.ln_4(p + m)
    return 

ENV LC_ALL=C.UTF-8
ENV LANG=C.UTF-8
RUN export LD_LIBRARY_PATH=/usr/local/cuda/lib64/stubs:$LD_LIBRARY_PATH && \
        ln -s /usr/local/cuda/lib64/stubs/libcuda.so /usr/local/cuda/lib64/stubs/libcuda.so.1 && \
        python -m spacy download en

tagger = [x[1] for x in nlp.pipeline if x[0] == 'tagger']
assert len(tagger) == 1
tagger = tagger[0]

entity = [x[1] for x in nlp.pipeline if x[0] == 'ner']
assert len(entity) == 1
entity = entity[0]

POS = {w: i for i, w in enumerate([''] + list(tagger.labels))}
ENT = {w: i for i, w in enumerate([''] + list(entity.move_names))}

Error(s) in loading state_dict for MeetingNet_Transformer:
	size mismatch for encoder.pos_embed.weight: copying a param with shape torch.Size([51, 16]) from checkpoint, the shape in current model is torch.Size([50, 16])

{'MODEL': 'MeetingNet_Transformer', 'TASK': 'HMNet', 'CRITERION': 'MLECriterion', 'SEED': 1033, 'RESUME': True, 'MAX_NUM_EPOCHS': 20, 'SAVE_PER_UPDATE_NUM': 400, 'UPDATES_PER_EPOCH': 2000, 'OPTIMIZER': 'RAdam', 'NO_AUTO_LR_SCALING': True, 'START_LEARNING_RATE': 0.001, 'LR_SCHEDULER': 'LnrWrmpInvSqRtDcyScheduler', 'WARMUP_STEPS': 16000, 'WARMUP_INIT_LR': 0.0001, 'WARMUP_END_LR': 0.001, 'GRADIENT_ACCUMULATE_STEP': 20, 'GRAD_CLIPPING': 2, 'USE_REL_DATA_PATH': True, 'TRAIN_FILE': '../ExampleRawData/meeting_summarization/AMI_proprec/train_ami.json', 'DEV_FILE': '../ExampleRawData/meeting_summarization/AMI_proprec/valid_ami.json', 'TEST_FILE': '../ExampleRawData/meeting_summarization/AMI_proprec/test_ami.json', 'ROLE_DICT_FILE': '../ExampleRawData/meeting_summarization/role_dict_ext.json', 'MINI_BATCH': 1, 'MAX_PADDING_RATIO': 1, 'BATCH_READ_AHEAD': 10, 'DOC_SHUFFLE_BUF_SIZE': 10, 'SAMPLE_SHUFFLE_BUFFER_SIZE': 10, 'BATCH_SHUFFLE_BUFFER_SIZE': 10, 'MAX_TRANSCRIPT_WORD': 8300, 'MAX_SENT_LEN': 30, 'MAX_SENT_NUM': 300, 'DROPOUT': 0.1, 'VOCAB_DIM': 512, 'ROLE_SIZE': 32, 'ROLE_DIM': 16, 'POS_DIM': 16, 'ENT_DIM': 16, 'USE_ROLE': True, 'USE_POSENT': True, 'USE_BOS_TOKEN': True, 'USE_EOS_TOKEN': True, 'TRANSFORMER_EMBED_DROPOUT': 0.1, 'TRANSFORMER_RESIDUAL_DROPOUT': 0.1, 'TRANSFORMER_ATTENTION_DROPOUT': 0.1, 'TRANSFORMER_LAYER': 6, 'TRANSFORMER_HEAD': 8, 'TRANSFORMER_POS_DISCOUNT': 80, 'PRE_TOKENIZER': 'TransfoXLTokenizer', 'PRE_TOKENIZER_PATH': '../ExampleInitModel/transfo-xl-wt103', 'PYLEARN_MODEL': '../ExampleInitModel/HMNet-pretrained', 'EXTRA_IDS': 1000, 'BEAM_WIDTH': 6, 'MAX_GEN_LENGTH': 512, 'MIN_GEN_LENGTH': 320, 'EVAL_TOKENIZED': True, 'EVAL_LOWERCASE': True, 'NO_REPEAT_NGRAM_SIZE': 3, 'cuda': True, 'confFile': 'ExampleConf/conf_hmnet_AMI', 'datadir': 'ExampleConf', 'basename': 'conf_hmnet_AMI', 'command': 'train', 'conf_file': 'ExampleConf/conf_hmnet_AMI', 'cluster': 'local', 'dist_init_path': './tmp', 'fp16': False, 'fp16_opt_level': 'O1', 'no_cuda': False}
Using Cuda

Saving logs, model, checkpoint, and evaluation in ExampleConf/conf_hmnet_AMI_conf~/run_2
 1.2.0  is high
Number of GPUs is  1 
Effective batch size is increased from  1  to  1 
Gradient accumulation steps =  20 
Effective batch size =  20 
[9d66c296629d:03515] pml_ucx.c:285  Error: UCP worker does not support MPI_THREAD_MULTIPLE
Select command: train
train on rank 0
-----------------------------------------------
Initializing model...
Loading Tokenizer from ExampleConf/../ExampleInitModel/transfo-xl-wt103...
Using pad_token, but it is not set yet.
Using bos_token, but it is not set yet.
Use POS and ENT
USE_ROLE

Total trainable parameters: 204488240
Loaded data on rank 0.
Using custom optimizer: RAdam
Optimizer parameters: {'lr': 0.001}
Using custom lr scheduler: LnrWrmpInvSqRtDcyScheduler
Lr scheduler parameters: {'warmup_steps': 16000, 'warmup_init_lr': 0.0001, 'warmup_end_lr': 0.001}
Cannot find checkpoint path from conf_hmnet_AMI_resume_checkpoint.json.
Make sure ExampleConf/conf_hmnet_AMI_resume_checkpoint.json exists.
Continue without loading checkpoint
Epoch 0
Traceback (most recent call last):
  File "PyLearn.py", line 71, in <module>
    trainer.train()
  File "/root/HMNet/Models/Trainers/HMNetTrainer.py", line 273, in train
    self.update(batch)
  File "/root/HMNet/Models/Trainers/HMNetTrainer.py", line 358, in update
    loss = self.network(batch)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/root/HMNet/Models/Trainers/HMNetTrainer.py", line 38, in forward
    output = self.model(batch)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/root/HMNet/Models/Networks/MeetingNet_Transformer.py", line 100, in forward
    outputs = self._forward(**batch)
  File "/root/HMNet/Models/Networks/MeetingNet_Transformer.py", line 125, in _forward
    token_encoder_outputs, sent_encoder_outputs = self.encoder(encoder_input_ids, encoder_input_roles, encoder_input_pos, encoder_input_ent)
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/root/HMNet/Models/Networks/MeetingNet_Transformer.py", line 1130, in forward
    embedded = self.embedder(vocab_x.view(batch_size, -1))
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/root/HMNet/Models/Networks/Transformer.py", line 387, in forward
    x_pos = self.pos_emb(torch.arange(x_len).type(torch.cuda.FloatTensor)) # len x n_state
  File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/root/HMNet/Models/Networks/Transformer.py", line 86, in forward
    sinusoid_inp = torch.ger(pos_seq, self.inv_freq)
RuntimeError: cublas runtime error : the GPU program failed to execute at /pytorch/aten/src/THC/THCBlas.cu:120
--------------------------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

  Process name: [[42501,1],0]
  Exit code:    1
--------------------------------------------------------------------------