SentenceTransformer based on uclanlp/plbart-java-cs

This is a sentence-transformers model finetuned from uclanlp/plbart-java-cs. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: uclanlp/plbart-java-cs
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: PLBartModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("buelfhood/SOCO-Java-PLBART-ST")
# Run inference
sentences = [
    '\nimport java.util.*;\n\npublic class WatchDog\n{\n   private Timer t;\n\n   public WatchDog()\n   {\n     t  = new Timer();\n      TimerTask task = new TimerTask()\n      {\n         public void run()\n\t {\n\t    Dog doggy = new Dog();\n\t }\n      };\n      \n      t.schedule(task, 0, 86400000);\n   }\n   public static void main( String[] args)\n   {\n      WatchDog wd = new WatchDog();\n   }\n}\n',
    'import\tjava.io.*;\n\nclass WatchDog {\n    public static void main(String args[]) {\n    \n\t    if (args.length<1)\n\t {\n       System.out.println("Correct Format Filename  email address <username@cs.rmit.edu.> of the recordkeeper"); \n        System.exit(1);\t\n\t }\n\n\twhile (true)\n\t\t{\n\t\t\n\t\t\n  FileInputStream stream=null;\n  DataInputStream word=null;\n  String input="   "; \n\n\n\ttry {\n\n\n       String ls_str;\n    \n    \t   \n\t  Process ls_proc = Runtime.getRuntime().exec("wget http://www.cs.rmit.edu./students");\n   \t\ttry {\n\t\tThread.sleep(2000);\n\t\t}catch (Exception e) {\n    System.err.println("Caught ThreadException: " +e.getMessage());\n\t  }\n\n\t\tString[] cmd = {"//sh","-c", "diff Index2.html index.html >report.txt "};\n\n\t   ls_proc = Runtime.getRuntime().exec(cmd);\n\t\t          \n\t\t\t\n\t\t\ttry {\n\t\tThread.sleep(2000);\n\t\t}catch (Exception e) {\n    System.err.println("Caught ThreadException: " +e.getMessage());\n\t  }\n\t\t\n\t\t\n\t\t\n\t\tif (ls_proc.exitValue()==2) \n\t\t{\n\t\t  \t   System.out.println("The file was checked for first time,  email sent");\n\n           Process move = Runtime.getRuntime().exec("mv index.html Index2.html");\n\t\t   \n\n\t\t}\n\t\telse\n\t\t{\n\n\t\t\t\tstream = new FileInputStream ("report.txt"); \n\t\t\t\tword =new DataInputStream(stream);\n\n\n\t\t\t\tif (word.available() !=0)\n\t\t\t\t{\n\n\t\t\t\t\ttry\n\t\t\t\t\t{\n\n\t\t\t\t\tString[] cmd1 = {"//sh","-c","diff Index2.html index.html | mail "+args[0]};\n\t\t\t\t\t Process proc = Runtime.getRuntime().exec(cmd1);\n\t\t\t\t\t Thread.sleep(2000);\n\t\t\t\t\tProcess move = Runtime.getRuntime().exec("mv index.html Index2.html");\n\t\t\t\t\tThread.sleep(2000);\n\t\t\t\t\tSystem.out.println("Difference Found  , Email Sent");\n\n\t\t\t\t\t}\n\t\t\t\t\tcatch (Exception e1) {\n\t\t\t\t\t\t\tSystem.err.println(e1);\n\t\t\t\t\t\t\tSystem.exit(1);\n\t\t\t\t\t\t\n\t\t\t\t\t  \n\t\t\t\t\t\t}\n\t\t\t\t\t \n\t \n\t \n\t\t\t\t }\n\t\t\t\t else\n\t\t\t\t\t{\n\t\t\t\t\t\t   System.out.println(" Differnce Detected");\n\n\n\t\t\t\t\t}\n\t\t}\n\t}\n\t\n\n\t catch (IOException e1) {\n\t    System.err.println(e1);\n\t    System.exit(1);\n\t\n  \n\t}\ntry\n{\nword.close();\nstream.close(); \n\t\n}\n \ncatch (IOException e)\n{ \nSystem.out.println("Error in closing input file:\\n" + e.toString()); \n} \n       \t\ntry {\nThread.sleep(20000);  \n    }\ncatch (Exception e) \n\t{\nSystem.err.println("Caught ThreadException: " +e.getMessage());\n\t}\n\t\t\n\n        }   \n\n\t} \n\t\n   }',
    '\n\n\n\nimport java.io.InputStream;\nimport java.util.Properties;\n\nimport javax.naming.Context;\nimport javax.naming.InitialContext;\nimport javax.rmi.PortableRemoteObject;\nimport javax.sql.DataSource;\n\n\n\n\npublic class BruteForcePropertyHelper {\n\n\tprivate static Properties bruteForceProps;\n\n\n\n\tpublic BruteForcePropertyHelper() {\n\t}\n\n\n\t\n\n\tpublic static String getProperty(String pKey){\n\t\ttry{\n\t\t\tinitProps();\n\t\t}\n\t\tcatch(Exception e){\n\t\t\tSystem.err.println("Error init\'ing the burteforce Props");\n\t\t\te.printStackTrace();\n\t\t}\n\t\treturn bruteForceProps.getProperty(pKey);\n\t}\n\n\n\tprivate static void initProps() throws Exception{\n\t\tif(bruteForceProps == null){\n\t\t\tbruteForceProps = new Properties();\n\n\t\t\tInputStream fis =\n\t\t\t\tBruteForcePropertyHelper.class.getResourceAsStream("/bruteforce.properties");\n\t\t\tbruteForceProps.load(fis);\n\t\t}\n\t}\n}\n\n',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

Unnamed Dataset

Size: 33,411 training samples
Columns: sentence_0, sentence_1, and label
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1 label
type string string int
details
min: 35 tokens
mean: 413.67 tokens
max: 512 tokens

min: 35 tokens
mean: 432.24 tokens
max: 512 tokens

0: ~99.70%
1: ~0.30%

	sentence_0	sentence_1	label
type	string	string	int
details	min: 35 tokens mean: 413.67 tokens max: 512 tokens	min: 35 tokens mean: 432.24 tokens max: 512 tokens	0: ~99.70% 1: ~0.30%

Samples:

sentence_0	sentence_1	label
import java.io.; import java.util.; import java.net.*; public class Dictionary { public static void main(String[] args) { String attackURL = "http://sec-crack.cs.rmit.edu./SEC/2/index.php"; String userID = ""; String Password=""; String userPassword=""; File inputFile = new File("/usr/share/lib/dict/words"); FileReader fin = null; BufferedReader bf = null; try { startmillisecond = System.currentTimeMillis(); URL url = new URL(attackURL); fin = new FileReader(inputFile); bf = new BufferedReader(fin); int count = 0; while ((Password = bf.readLine()) !=null) { if (Password.length() < 4) { count++; try { userPassword = userID + ":" + Password; System.out.println("User & Password :" + userPassword); String encoding = Base64Converter.encode (userPassword.getBytes()); URLConnection uc = url.openConnection(); uc.setRequestProperty ("Authorization", " " + enc...	public class Base64 { final static String baseTable = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"; public static String encode(byte[] bytes) { String tmp = ""; int i = 0; byte pos; for(i=0; i < (bytes.length - bytes.length%3); i+=3) { pos = (byte) ((bytes[i] >> 2) & 63); tmp = tmp + baseTable.charAt(pos); pos = (byte) (((bytes[i] & 3) << 4) + ((bytes[i+1] >> 4) & 15)); tmp = tmp + baseTable.charAt( pos ); pos = (byte) (((bytes[i+1] & 15) << 2) + ((bytes[i+2] >> 6) & 3)); tmp = tmp + baseTable.charAt(pos); pos = (byte) (((bytes[i+2]) & 63)); tmp = tmp + baseTable.charAt(pos); if(((i+2)%56) == 0) { tmp = tmp + "\r\n"; } } if(bytes.length % 3 != 0) { if(bytes.length % 3 == 2) { pos = (byte) ((bytes[i] >> 2) & 63); tmp = tmp + baseTable.charAt(pos); pos = (byte) (((bytes[i] & 3) << 4) + ((bytes[i+1] >> 4) & 15)); tmp = tmp + baseTable.charAt( pos ); ...	`0`
import java.io.*; public class Dictionary { public static void main(String args[])throws Exception { String s = null; String pass=""; int at=0; String strLine=""; int i=0; BufferedReader in = new BufferedReader(new FileReader("/usr/share/lib/dict/words")); start =System.currentTimeMillis(); try { while((pass=strLine = in.readLine()) != null) { if(pass.length()==3) { System.out.println(pass); at++; Process p = Runtime.getRuntime().exec("wget --http-user= --http-passwd="+pass+" http://sec-crack.cs.rmit.edu./SEC/2/index.php"); p.waitFor(); i = p.exitValue(); if(i==0) { finish=System.currentTimeMillis(); ...	import java.util.; import java.io.; public class WatchDog { public WatchDog() { } public static void main(String args[]) { DataInputStream newin; try{ System.out.println("Downloading first copy"); Runtime.getRuntime().exec("wget http://www.cs.rmit.edu./students/ -O oldfile.html"); String[] cmdDiff = {"//sh", "-c", "diff oldfile.html newfile.html > Diff.txt"}; String[] cmdMail = {"//sh", "-c", "mailx -s "Diffrence" "@cs.rmit.edu." < Diff.txt"}; while(true){ Thread.sleep(246060*1000); System.out.println("Downloading new copy"); Runtime.getRuntime().exec("wget http://www.cs.rmit.edu./students/ -O newfile.html"); Thread.sleep(2000); Runtime.getRuntime().exec(cmdDiff); Thread.sleep(2000); newin = new DataInputStream( new FileInputStream( "Diff.txt")); if (newin.readLine() != null){ System.out.println("Sending Mail"); ...	`0`
import java.Thread; import java.io.; import java.net.; public class BruteForce extends Thread { final char[] CHARACTERS = {'A','a','E','e','I','i','O','o','U','u','R','r','N','n','S','s','T','t','L','l','B','b','C','c','D','d','F','f','G','g','H','h','J','j','K','k','M','m','P','p','V','v','W','w','X','x','Z','z','Q','q','Y','y'}; final static int SUCCESS=1, FAILED=0, UNKNOWN=-1; private static String host, path, user; private Socket target; private InputStream input; private OutputStream output; private byte[] data; private int threads, threadno, response; public static boolean solved = false; BruteForce parent; public BruteForce(String host, String path, String user, int threads, int threadno, BruteForce parent) { super(); this.parent = parent; this.host = host; this.path = path; this.user ...	import java.io.; import java.net.; import javax.swing.Timer; import java.awt.event.*; import javax.swing.JOptionPane; public class WatchDog { private static Process pro = null; private static Runtime run = Runtime.getRuntime(); public static void main(String[] args) { String cmd = null; try { cmd = new String("wget -O original.txt http://www.cs.rmit.edu./students/"); pro = run.exec(cmd); System.out.println(cmd); } catch (IOException e) { } class Watch implements ActionListener { BufferedReader in = null; String str = null; Socket socket; public void actionPerformed (ActionEvent event) { try { System.out.println("in Watch!"); String cmd = new String(); int ERROR = 1; cmd = new String("wget -O new.txt http://www.cs.rmit.edu./students/"); System.out.println(cmd); cmd = new String("diff original.txt new.txt"); pro = run.exec(cmd); System.out.println(cmd); in = new Buf...	`0`

Loss: BatchAllTripletLoss

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
num_train_epochs: 1
fp16: True
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 1
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	Training Loss
0.4785	500	0.3437
0.9569	1000	0.3653

Framework Versions

Python: 3.11.13
Sentence Transformers: 4.1.0
Transformers: 4.52.4
PyTorch: 2.6.0+cu124
Accelerate: 1.7.0
Datasets: 3.6.0
Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

BatchAllTripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}