Tokenization issue when training: OverflowError: can't convert negative int to unsigned #2645
Comments
|
Hello! That is a bit of an odd error. It's trying to do tokenization via You can try the following: from transformers import AutoTokenizer
from sentence_transformers import SentenceTransformer
model_name = "my_model"
model = SentenceTransformer(model_name)
model[0].tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False)
model.fit("...")This no longer uses
|
tomaarsen
changed the title
|
We need to remove 11 to truncate the input but the first sequence has a length 8. |
"""
This examples trains BERT (or any other transformer model like RoBERTa, DistilBERT etc.) for the STSbenchmark from scratch. It generates sentence embeddings
that can be compared using cosine-similarity to measure the similarity.
Usage:
python training_nli.py
OR
python training_nli.py pretrained_transformer_model_name
"""
from torch.utils.data import DataLoader
import math
from sentence_transformers import SentenceTransformer, LoggingHandler, losses, models, util
from sentence_transformers.evaluation import EmbeddingSimilarityEvaluator
from sentence_transformers.readers import InputExample
import logging
from datetime import datetime
import sys
import os
import gzip
import csv
from transformers import XLNetTokenizer, XLNetModel
from sentence_transformers.models import Transformer, Pooling, Normalize
#### Just some code to print debug information to stdout
logging.basicConfig(
format="%(asctime)s - %(message)s", datefmt="%Y-%m-%d %H:%M:%S", level=logging.INFO, handlers=[LoggingHandler()]
)
#### /print debug information to stdout
# Check if dataset exists. If not, download and extract it
sts_dataset_path = "/nfs/XLNet/XLNet/stsbenchmark.tsv.gz"
if not os.path.exists(sts_dataset_path):
util.http_get("https://sbert.net/datasets/stsbenchmark.tsv.gz", sts_dataset_path)
# You can specify any huggingface/transformers pre-trained model here, for example, bert-base-uncased, roberta-base, xlm-roberta-base
model_name = '/nfs/XLNet/XLNet/xlnet-base-cased'
model = SentenceTransformer(model_name)
model[0].tokenizer = XLNetTokenizer.from_pretrained(model_name, use_fast=False)
# model_name = XLNetModel.from_pretrained("/nfs/XLNet/XLNet/xlnet-base-cased", local_files_only=True)
# tokenizer = XLNetTokenizer.from_pretrained("/nfs/XLNet/XLNet/xlnet-base-cased")
# Read the dataset
train_batch_size = 32
num_epochs = 4
model_save_path = (
"output/training_stsbenchmark_"
)
# Use Huggingface/transformers model (like BERT, RoBERTa, XLNet, XLM-R) for mapping tokens to embeddings
word_embedding_model = models.Transformer(model_name)
# Apply mean pooling to get one fixed sized sentence vector
pooling_model = models.Pooling(
word_embedding_model.get_word_embedding_dimension(),
pooling_mode_mean_tokens=True,
pooling_mode_cls_token=False,
pooling_mode_max_tokens=False,
)
# model = SentenceTransformer(modules=[word_embedding_model, pooling_model])
# Convert the dataset to a DataLoader ready for training
logging.info("Read STSbenchmark train dataset")
train_samples = []
dev_samples = []
test_samples = []
with gzip.open(sts_dataset_path, "rt", encoding="utf8") as fIn:
reader = csv.DictReader(fIn, delimiter="\t", quoting=csv.QUOTE_NONE)
for row in reader:
score = float(row["score"]) / 5.0 # Normalize score to range 0 ... 1
inp_example = InputExample(texts=[row["sentence1"], row["sentence2"]], label=score)
if row["split"] == "dev":
dev_samples.append(inp_example)
elif row["split"] == "test":
test_samples.append(inp_example)
else:
train_samples.append(inp_example)
train_dataloader = DataLoader(train_samples, shuffle=True, batch_size=train_batch_size)
train_loss = losses.CosineSimilarityLoss(model=model)
logging.info("Read STSbenchmark dev dataset")
evaluator = EmbeddingSimilarityEvaluator.from_input_examples(dev_samples, name="sts-dev")
# Configure the training. We skip evaluation in this example
warmup_steps = math.ceil(len(train_dataloader) * num_epochs * 0.1) # 10% of train data for warm-up
logging.info("Warmup-steps: {}".format(warmup_steps))
# Train the model
model.fit(
train_objectives=[(train_dataloader, train_loss)],
evaluator=evaluator,
epochs=num_epochs,
evaluation_steps=1000,
warmup_steps=warmup_steps,
output_path=model_save_path,
)
##############################################################################
#
# Load the stored model and evaluate its performance on STS benchmark dataset
#
##############################################################################
model = SentenceTransformer(model_save_path)
test_evaluator = EmbeddingSimilarityEvaluator.from_input_examples(test_samples, name="sts-test")
test_evaluator(model, output_path=model_save_path)This is my code.Is there something wrong with my code? Thank you very much for your reply！！！❤️ |
what happend?how to slove?
The text was updated successfully, but these errors were encountered: