给予pytorch的对BERT在MSPR数据集上的定点化

from __future__ import absolute_import, division, print_function

import logging
import numpy as np
import os
import random
import sys
import time
import torch

from argparse import Namespace
from torch.utils.data import (DataLoader, RandomSampler, SequentialSampler,
                              TensorDataset)
from tqdm import tqdm
from transformers import (BertConfig, BertForSequenceClassification, BertTokenizer,)
from transformers import glue_compute_metrics as compute_metrics
from transformers import glue_output_modes as output_modes
from transformers import glue_processors as processors
from transformers import glue_convert_examples_to_features as convert_examples_to_features

# Setup logging
logger = logging.getLogger(__name__)
logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
                    datefmt = '%m/%d/%Y %H:%M:%S',
                    level = logging.WARN)

logging.getLogger("transformers.modeling_utils").setLevel(
   logging.WARN)  # Reduce logging

print(torch.__version__)

1.5.0

!python download_glue_data.py --data_dir='glue_data' --tasks='MRPC'

Processing MRPC...
Local MRPC data not specified, downloading data from https://dl.fbaipublicfiles.com/senteval/senteval_data/msr_paraphrase_train.txt
	Completed!

torch.set_num_threads(1)
print(torch.__config__.parallel_info())

ATen/Parallel:
	at::get_num_threads() : 1
	at::get_num_interop_threads() : 3
OpenMP 201511 (a.k.a. OpenMP 4.5)
	omp_get_max_threads() : 1
Intel(R) Math Kernel Library Version 2020.0.1 Product Build 20200208 for Intel(R) 64 architecture applications
	mkl_get_max_threads() : 1
Intel(R) MKL-DNN v0.21.1 (Git Hash 7d2fd500bc78936d1d648ca713b901012f470dbc)
std::thread::hardware_concurrency() : 6
Environment variables:
	OMP_NUM_THREADS : [not set]
	MKL_NUM_THREADS : [not set]
ATen parallel backend: OpenMP

configs = Namespace()

# The output directory for the fine-tuned model, $OUT_DIR.
configs.output_dir = "./MRPC/"

# The data directory for the MRPC task in the GLUE benchmark, $GLUE_DIR/$TASK_NAME.
configs.data_dir = "./glue_data/MRPC"

# The model name or path for the pre-trained model.
configs.model_name_or_path = "bert-base-uncased"
# The maximum length of an input sequence
configs.max_seq_length = 128

# Prepare GLUE task.
configs.task_name = "MRPC".lower()
configs.processor = processors[configs.task_name]()
configs.output_mode = output_modes[configs.task_name]
configs.label_list = configs.processor.get_labels()
configs.model_type = "bert".lower()
configs.do_lower_case = True

# Set the device, batch size, topology, and caching flags.
configs.device = "cpu"
configs.per_gpu_eval_batch_size = 8
configs.n_gpu = 0
configs.local_rank = -1
configs.overwrite_cache = False


# Set random seed for reproducibility.
def set_seed(seed):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
set_seed(42)

tokenizer = BertTokenizer.from_pretrained(
    configs.output_dir, do_lower_case=configs.do_lower_case)

model = BertForSequenceClassification.from_pretrained(configs.output_dir)
model.to(configs.device)

/home/qy/.conda/envs/pytorch/lib/python3.6/site-packages/transformers-2.10.0-py3.6.egg/transformers/tokenization_utils.py:831: FutureWarning: Parameter max_len is deprecated and will be removed in a future release. Use model_max_length instead.
  category=FutureWarning,





BertForSequenceClassification(
  (bert): BertModel(
    (embeddings): BertEmbeddings(
      (word_embeddings): Embedding(30522, 768, padding_idx=0)
      (position_embeddings): Embedding(512, 768)
      (token_type_embeddings): Embedding(2, 768)
      (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
      (dropout): Dropout(p=0.1, inplace=False)
    )
    (encoder): BertEncoder(
      (layer): ModuleList(
        (0): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (1): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (2): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (3): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=768, bias=True)
              (value): Linear(in_features=768, out_features=768, bias=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
            (output): BertSelfOutput(
              (dense): Linear(in_features=768, out_features=768, bias=True)
              (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
              (dropout): Dropout(p=0.1, inplace=False)
            )
          )
          (intermediate): BertIntermediate(
            (dense): Linear(in_features=768, out_features=3072, bias=True)
          )
          (output): BertOutput(
            (dense): Linear(in_features=3072, out_features=768, bias=True)
            (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
        (4): BertLayer(
          (attention): BertAttention(
            (self): BertSelfAttention(
              (query): Linear(in_features=768, out_features=768, bias=True)
              (key): Linear(in_features=768, out_features=