File size: 3,514 Bytes
2359bda |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
"""
This example loads the pre-trained SentenceTransformer model 'nli-distilroberta-base-v2' from the server.
It then fine-tunes this model for some epochs on the STS benchmark dataset.
Note: In this example, you must specify a SentenceTransformer model.
If you want to fine-tune a huggingface/transformers model like bert-base-uncased, see training_nli.py and training_stsbenchmark.py
"""
from torch.utils.data import DataLoader
import math
from sentence_transformers import SentenceTransformer, LoggingHandler, losses, util, InputExample
from sentence_transformers.evaluation import EmbeddingSimilarityEvaluator
import logging
from datetime import datetime
import os
import gzip
import csv
#### 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 exsist. If not, download and extract it
sts_dataset_path = 'datasets/stsbenchmark.tsv.gz'
if not os.path.exists(sts_dataset_path):
util.http_get('https://sbert.net/datasets/stsbenchmark.tsv.gz', sts_dataset_path)
# Read the dataset
model_name = 'nli-distilroberta-base-v2'
train_batch_size = 16
num_epochs = 4
model_save_path = 'output/training_stsbenchmark_continue_training-'+model_name+'-'+datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
# Load a pre-trained sentence transformer model
model = SentenceTransformer(model_name)
# 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)
# Development set: Measure correlation between cosine score and gold labels
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) |