i’m doing a text classification using distilbert model but before passing the encoder layers to a connected neural network , i want to save this output as pickle so i can have an array of length 738 in a sheet that i can use it later on for any task
here you are my code :
tokenizer = DistilBertTokenizer.from_pretrained(‘distilbert-base-uncased’, do_lower_case=True)
max_len = 0
for sentence in text:
input_ids = tokenizer.encode(sentence, add_special_tokens=True, truncation = True )
max_len = max(max_len, len(input_ids))
print('Max sentence length in the abstract is : ', max_len)
input_ids = []
attention_masks = []
for sentence in text:
encoded_dict = tokenizer.encode_plus(
sentence,
add_special_tokens = True,
max_length = 64,
pad_to_max_length = True,
return_attention_mask = True,
return_tensors = ‘pt’,
truncation= True
)
input_ids.append(encoded_dict['input_ids'])
attention_masks.append(encoded_dict['attention_mask'])
input_ids = torch.cat(input_ids, dim=0)
attention_masks = torch.cat(attention_masks, dim=0)
labels = torch.tensor(labels)
print('Original: ', text[0])
print(‘Token IDs:’, input_ids[0])
from torch.utils.data import TensorDataset, random_split
dataset = TensorDataset(input_ids, attention_masks, labels)
train_size = int(0.8 * len(dataset))
val_size = len(dataset) - train_size
train_dataset, val_dataset = random_split(dataset, [train_size, val_size])
print(’{:>5,} training samples’.format(train_size))
print(’{:>5,} validation samples’.format(val_size))
from torch.utils.data import DataLoader, RandomSampler, SequentialSampler
batch_size = 16
train_dataloader = DataLoader(
train_dataset, # The training samples.
sampler = RandomSampler(train_dataset), # Select batches randomly
batch_size = batch_size # Trains with this batch size.
)
validation_dataloader = DataLoader(
val_dataset, # The validation samples.
sampler = SequentialSampler(val_dataset), # Pull out batches sequentially.
batch_size = batch_size # Evaluate with this batch size.
)
from transformers import DistilBertForSequenceClassification, AdamW, DistilBertConfig
model = DistilBertForSequenceClassification.from_pretrained(
“distilbert-base-uncased”, # Use the 12-layer BERT model, with an uncased vocab.
num_labels = 2, # The number of output labels–2 for binary classification (could be increased)
output_attentions = False, # Whether the model returns attentions weights.
output_hidden_states = False, # Whether the model returns all hidden-states.
)
model.to(device)
DistilBertForSequenceClassification(
(distilbert): DistilBertModel(
(embeddings): Embeddings(
(word_embeddings): Embedding(30522, 768, padding_idx=0)
(position_embeddings): Embedding(512, 768)
(LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.1, inplace=False)
)
(transformer): Transformer(
(layer): ModuleList(
(0): TransformerBlock(
(attention): MultiHeadSelfAttention(
(dropout): Dropout(p=0.1, inplace=False)
(q_lin): Linear(in_features=768, out_features=768, bias=True)
(k_lin): Linear(in_features=768, out_features=768, bias=True)
(v_lin): Linear(in_features=768, out_features=768, bias=True)
(out_lin): Linear(in_features=768, out_features=768, bias=True)
)
(sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(ffn): FFN(
(dropout): Dropout(p=0.1, inplace=False)
(lin1): Linear(in_features=768, out_features=3072, bias=True)
(lin2): Linear(in_features=3072, out_features=768, bias=True)
)
(output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
)
(1): TransformerBlock(
(attention): MultiHeadSelfAttention(
(dropout): Dropout(p=0.1, inplace=False)
(q_lin): Linear(in_features=768, out_features=768, bias=True)
(k_lin): Linear(in_features=768, out_features=768, bias=True)
(v_lin): Linear(in_features=768, out_features=768, bias=True)
(out_lin): Linear(in_features=768, out_features=768, bias=True)
)
(sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(ffn): FFN(
(dropout): Dropout(p=0.1, inplace=False)
(lin1): Linear(in_features=768, out_features=3072, bias=True)
(lin2): Linear(in_features=3072, out_features=768, bias=True)
)
(output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
)
(2): TransformerBlock(
(attention): MultiHeadSelfAttention(
(dropout): Dropout(p=0.1, inplace=False)
(q_lin): Linear(in_features=768, out_features=768, bias=True)
(k_lin): Linear(in_features=768, out_features=768, bias=True)
(v_lin): Linear(in_features=768, out_features=768, bias=True)
(out_lin): Linear(in_features=768, out_features=768, bias=True)
)
(sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(ffn): FFN(
(dropout): Dropout(p=0.1, inplace=False)
(lin1): Linear(in_features=768, out_features=3072, bias=True)
(lin2): Linear(in_features=3072, out_features=768, bias=True)
)
(output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
)
(3): TransformerBlock(
(attention): MultiHeadSelfAttention(
(dropout): Dropout(p=0.1, inplace=False)
(q_lin): Linear(in_features=768, out_features=768, bias=True)
(k_lin): Linear(in_features=768, out_features=768, bias=True)
(v_lin): Linear(in_features=768, out_features=768, bias=True)
(out_lin): Linear(in_features=768, out_features=768, bias=True)
)
(sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(ffn): FFN(
(dropout): Dropout(p=0.1, inplace=False)
(lin1): Linear(in_features=768, out_features=3072, bias=True)
(lin2): Linear(in_features=3072, out_features=768, bias=True)
)
(output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
)
(4): TransformerBlock(
(attention): MultiHeadSelfAttention(
(dropout): Dropout(p=0.1, inplace=False)
(q_lin): Linear(in_features=768, out_features=768, bias=True)
(k_lin): Linear(in_features=768, out_features=768, bias=True)
(v_lin): Linear(in_features=768, out_features=768, bias=True)
(out_lin): Linear(in_features=768, out_features=768, bias=True)
)
(sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(ffn): FFN(
(dropout): Dropout(p=0.1, inplace=False)
(lin1): Linear(in_features=768, out_features=3072, bias=True)
(lin2): Linear(in_features=3072, out_features=768, bias=True)
)
(output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
)
(5): TransformerBlock(
(attention): MultiHeadSelfAttention(
(dropout): Dropout(p=0.1, inplace=False)
(q_lin): Linear(in_features=768, out_features=768, bias=True)
(k_lin): Linear(in_features=768, out_features=768, bias=True)
(v_lin): Linear(in_features=768, out_features=768, bias=True)
(out_lin): Linear(in_features=768, out_features=768, bias=True)
)
(sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
(ffn): FFN(
(dropout): Dropout(p=0.1, inplace=False)
(lin1): Linear(in_features=768, out_features=3072, bias=True)
(lin2): Linear(in_features=3072, out_features=768, bias=True)
)
(output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)
)
)
)
)
(pre_classifier): Linear(in_features=768, out_features=768, bias=True)
(classifier): Linear(in_features=768, out_features=2, bias=True)
(dropout): Dropout(p=0.2, inplace=False)
)
i just put the last output to make the code more readable
i clue how to do this task ?