This is a sentence-transformers model finetuned from microsoft/codebert-base. 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: microsoft/codebert-base
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: RobertaModel 
  (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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("buelfhood/SOCO-Java-CodeBERT-ST")
# Run inference
sentences = [
    '\nimport java.net.*;\nimport java.io.*;\n\n\npublic class Dictionary\n{\n   private String myUsername = "";\n   private String myPassword = "";\n   private String urlToCrack = "http://sec-crack.cs.rmit.edu./SEC/2";\n\n\n   public static void main (String args[])\n   {\n      Dictionary d = new Dictionary();\n   }\n\n   public Dictionary()\n   {\n      generatePassword();\n   }\n\n   \n\n   public void generatePassword()\n   {\n      try\n      {\n         BufferedReader  = new BufferedReader(new FileReader("/usr/share/lib/dict/words"));\n\n         \n         {\n            myPassword = bf.readLine();\n            crackPassword(myPassword);\n         } while (myPassword != null);\n      }\n      catch(IOException e)\n      {    }\n   }\n\n\n  \n\n  public void crackPassword(String passwordToCrack)\n  {\n     String data, dataToEncode, encodedData;\n\n     try\n     {\n         URL url = new URL (urlToCrack);\n\n         \n\n         dataToEncode = myUsername + ":" + passwordToCrack;\n\n         \n\n         encodedData = new bf.misc.BASE64Encoder().encode(dataToEncode.getBytes());\n\n         URLConnection urlCon = url.openConnection();\n         urlCon.setRequestProperty  ("Authorization", " " + encodedData);\n\n         InputStream is = (InputStream)urlCon.getInputStream();\n         InputStreamReader isr = new InputStreamReader(is);\n         BufferedReader bf  = new BufferedReader (isr);\n\n          \n          {\n             data = bf.readLine();\n             System.out.println(data);\n             displayPassword(passwordToCrack);\n         } while (data != null);\n      }\n      catch (IOException e)\n      {   }\n   }\n\n\n   public void displayPassword(String foundPassword)\n   {\n      System.out.println("\\nThe cracked password is : " + foundPassword);\n      System.exit(0);\n   }\n}\n\n\n',
    '\nimport java.io.*;\n\npublic class PasswordFile {\n    \n    private String strFilepath;\n    private String strCurrWord;\n    private File fWordFile;\n    private BufferedReader in;\n    \n    \n    public PasswordFile(String filepath) {\n        strFilepath = filepath;\n        try {\n            fWordFile = new File(strFilepath);\n            in = new BufferedReader(new FileReader(fWordFile));\n        }\n        catch(Exception e)\n        {\n            System.out.println("Could not open file " + strFilepath);\n        }\n    }\n    \n    String getPassword() {\n        return strCurrWord;\n    }\n    \n    String getNextPassword() {\n        try {\n            strCurrWord = in.readLine();\n            \n            \n            \n        }\n        catch (Exception e)\n        {\n            \n            return null;\n        }\n                \n        return strCurrWord;\n    }\n    \n}\n',
    '\n\n\nimport java.misc.BASE64Encoder;\nimport java.misc.BASE64Decoder;\n\nimport java.io.*;\nimport java.net.*;\nimport java.util.*;\n\n\npublic class BruteForce {\n  \n  static char [] passwordDataSet = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz".toCharArray();\n  \n  private int indices[] = {0,0,0};\n  \n  private String url = null;\n\n  \n  public BruteForce(String url) {\n    this.url = url;\n\n  }\n  \n  private int attempts = 0;\n  private boolean stopGen = false;\n  \n  public String getNextPassword(){\n    String nextPassword = "";\n    for(int i = 0; i <indices.length ; i++){\n      if(indices[indices.length -1 ] == passwordDataSet.length)\n        return null;\n      if(indices[i] == passwordDataSet.length ){\n        indices[i] = 0;\n        indices[i+1]++;\n      }\n      nextPassword = passwordDataSet[indices[i]]+nextPassword;\n\n      if(i == 0)\n        indices[0]++;\n\n    }\n    return nextPassword;\n  }\n  \n  public void setIndices(int size){\n    this.indices = new int[size];\n    for(int i = 0; i < size; i++)\n      this.indices[i] = 0;\n  }\n  public void setPasswordDataSet(String newDataSet){\n    this.passwordDataSet = newDataSet.toCharArray();\n  }\n  \n  public String crackPassword(String user) throws IOException, MalformedURLException{\n    URL url = null;\n    URLConnection urlConnection = null;\n    String outcome = null;\n    String  authorization = null;\n    String password = null;\n    BASE64Encoder b64enc = new BASE64Encoder();\n    InputStream content = null;\n    BufferedReader in = null;\n    String line;\n          int i = 0;\n    while(!"HTTP/1.1 200 OK".equalsIgnoreCase(outcome)){\n      url = new URL(this.url);\n      urlConnection = url.openConnection();\n      urlConnection.setDoInput(true);\n      urlConnection.setDoOutput(true);\n\n\n      urlConnection.setRequestProperty("GET", url.getPath() + " HTTP/1.1");\n      urlConnection.setRequestProperty("Host", url.getHost());\n      password = getNextPassword();\n      if(password == null)\n        return null;\n      System.out.print(password);\n      authorization = user + ":" + password;\n\n\n      urlConnection.setRequestProperty("Authorization", " "+ b64enc.encode(authorization.getBytes()));\n\n\noutcome = urlConnection.getHeaderField(null); \n\n\n\n      this.attempts ++;\n      urlConnection = null;\n      url = null;\n\n      if(this.attempts%51 == 0)\n        for(int b = 0; b < 53;b++)\n          System.out.print("\\b \\b");\n      else\n        System.out.print("\\b\\b\\b.");\n\n    }\n    return password;\n  }\n  \n  public int getAttempts(){\n    return this.attempts;\n  }\n  public static void main (String[] args) {\n    if(args.length != 2){\n      System.out.println("usage: java attacks.BruteForce <url  crack: e.g. http://sec-crack.cs.rmit.edu./SEC/2/> <username: e.g. >");\n      System.exit(1);\n    }\n\n    BruteForce bruteForce1 = new BruteForce(args[0]);\n    try{\n      Calendar cal1=null, cal2=null;\n      cal1 = Calendar.getInstance();\n      System.out.println("Cracking started at: " + cal1.getTime().toString());\n      String password = bruteForce1.crackPassword(args[1]);\n      if(password != null)\n        System.out.println("\\nPassword is: "+password);\n      else\n        System.out.println("\\nPassword could not  retrieved!");\n      cal2 = Calendar.getInstance();\n      System.out.println("Cracking finished at: " + cal2.getTime().toString());\n      Date d3 = new Date(cal2.getTime().getTime() - cal1.getTime().getTime());\n      System.out.println("Total Time taken  crack: " + (d3.getTime())/1000 + " sec");\n      System.out.println("Total attempts : "  + bruteForce1.getAttempts());\n\n    }catch(MalformedURLException mue){\n      mue.printStackTrace();\n    }\n\n    catch(IOException ioe){\n      ioe.printStackTrace();\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: 61 tokens
mean: 471.36 tokens
max: 512 tokens
min: 61 tokens
mean: 491.01 tokens
max: 512 tokens
0: ~99.50%
1: ~0.50%

Samples:

sentence_0	sentence_1	label
[object Object]public class ImageFile[object Object]{[object Object] private String imageUrl;[object Object] private int imageSize;[object Object][object Object] public ImageFile(String url, int size)[object Object] {[object Object] imageUrl=url;[object Object] imageSize=size;[object Object] }[object Object][object Object] public String getImageUrl()[object Object] {[object Object] return imageUrl;[object Object] }[object Object][object Object] public int getImageSize()[object Object] {[object Object] return imageSize;[object Object] }[object Object]}[object Object]	[object Object][object Object][object Object][object Object]import java.net.[object Object];[object Object]import java.util.Date;[object Object][object Object]public class MyMail implements Serializable[object Object]{[object Object] [object Object][object Object] [object Object] public static final int SMTPPort = 25;[object Object][object Object] [object Object] public static final char successPrefix = '2';[object Object][object Object] [object Object] public static final char morePrefix = '3';[object Object][object Object] [object Object] public static final char failurePrefix = '4';[object Object][object Object] [object Object][object Object] [object Object] private static final String CRLF = "\r\n";[object Object][object Object] [object Object] private String mailFrom = "";[object Object][object Object] [object Object] private String mailTo = "";[object Object][object Object] [object Object] private String messageSubject = "";[object Object][object Object] [object Object] private String messageBody = "";[object Object][object Object] [object Object] private String mailServer = "";[object Object][object Object] [object Object] public MyMail ()[object Object] {[object Object] [object Object] super();[object Object] }[object Object][object Object] [object Object] public MyMail ( String serverName)[object Object] {[object Object] [object Object] super();[object Object][object Object] [object Object] mailServer = serverName;[object Object] }[object Object][object Object] [object Object] public String getFrom()[object Object] {[object Object] return mailFrom;[object Object] }[object Object][object Object] [object Object] public String getTo()[object Object] {[object Object] return mailTo;[object Object] }[object Object][object Object] [object Object] public String getSubject()[object Object] {[object Object] return messageSubject;[object Object] }[object Object][object Object] [object Object] public String getMessage()[object Object] {[object Object] return messageBody;[object Object] }[object Object][object Object] [object Object] public String getMailServer()[object Object] {[object Object] return mailServer;[object Object] }[object Object][object Object] [object Object] public void setFrom( String from )[object Object] {[object Object] [object Object] mailFr...	`0`
[object Object]import java.util.[object Object];[object Object]import java.io.*;[object Object]public class WatchDog[object Object]{[object Object] private Vector init;[object Object] public WatchDog()[object Object] {[object Object] try[object Object] {[object Object] Runtime run = Runtime.getRuntime();[object Object] String command_line = "lynx [object Object] -dump";[object Object] Process result = run.exec(command_line);[object Object] BufferedReader in = new BufferedReader(new InputStreamReader(result.getInputStream()));[object Object] String inputLine;[object Object] init = new Vector();[object Object] while ((inputLine = in.readLine()) != null)[object Object] {[object Object] init.addElement(inputLine);[object Object] }[object Object] [object Object] }catch(Exception e)[object Object] {[object Object] }[object Object] }[object Object] public static void main(String args[])[object Object] {[object Object] WatchDog wd = new WatchDog();[object Object] wd.nextRead();[object Object] }[object Object][object Object] public void nextRead()[object Object] {[object Object] while(true)[object Object] {[object Object] ScheduleTask sch = new ScheduleTask(init);[object Object] if(sch.getFlag()!=0)[object Object] {[object Object] System.out.println("change happen");[object Object] WatchDog wd = new WatchDog();[object Object] wd.nextRead();[object Object] }[object Object] [object Object] }[object Object] }[object Object]}	[object Object][object Object]import java.net.[object Object];[object Object]import java.util.*;[object Object][object Object]public class Dictionary{[object Object][object Object] private static URL location;[object Object] private static String user;[object Object] private BufferedReader input;[object Object] private static BufferedReader dictionary;[object Object] private int maxLetters = 3;[object Object][object Object] [object Object][object Object] public Dictionary() {[object Object] [object Object] Authenticator.setDefault(new MyAuthenticator ());[object Object][object Object] startTime = System.currentTimeMillis();[object Object] boolean passwordMatched = false;[object Object] while (!passwordMatched) {[object Object] try {[object Object] input = new BufferedReader(new InputStreamReader(location.openStream()));[object Object] String line = input.readLine();[object Object] while (line != null) {[object Object] System.out.println(line);[object Object] line = input.readLine();[object Object] }[object Object] input.close();[object Object] passwordMatched = true;[object Object] }[object Object] catch (ProtocolException e)[object Object] {[object Object] [object Object] [object Object] }[object Object] catch (ConnectException e) {[object Object] System.out.println("Failed connect");[object Object] }[object Object] catch (IOException e) ...	`0`
[object Object]import java.util.[object Object];[object Object]import java.io.*;[object Object]public class ScheduleTask extends Thread[object Object]{[object Object][object Object] private int flag=0,count1=0,count2=0;[object Object] private Vector change;[object Object] public ScheduleTask(Vector init)[object Object] {[object Object] try[object Object] {[object Object][object Object] Runtime run = Runtime.getRuntime();[object Object] String command_line = "lynx [object Object] -dump";[object Object] Process result = run.exec(command_line);[object Object] BufferedReader in = new BufferedReader(new InputStreamReader(result.getInputStream()));[object Object] String inputLine;[object Object] Vector newVector = new Vector();[object Object] change = new Vector();[object Object] while ((inputLine = in.readLine()) != null)[object Object] {[object Object] newVector.addElement(inputLine);[object Object] }[object Object] if(init.size()>newVector.size())[object Object] {[object Object] for(int k=0;k<newVector.size();k++)[object Object] {[object Object] if(!newVector.elementAt(k).toString().equals(init.elementAt(k).toString()))[object Object] ch...	import java.io.[object Object];[object Object]import java.util.*;[object Object][object Object][object Object]public class Dictionary[object Object]{[object Object] public static void main (String args[])[object Object] {[object Object] [object Object] [object Object] Calendar cal = Calendar.getInstance();[object Object] Date now=cal.getTime();[object Object] double startTime = now.getTime();[object Object][object Object] String password=getPassword(startTime);[object Object] System.out.println("The password is " + password);[object Object] }[object Object][object Object] public static String getPassword(double startTime)[object Object] {[object Object] String password="";[object Object] int requests=0;[object Object][object Object] try[object Object] {[object Object] [object Object] FileReader fRead = new FileReader("/usr/share/lib/dict/words");[object Object] BufferedReader buf = new BufferedReader(fRead);[object Object][object Object] password=buf.readLine();[object Object][object Object] while (password != null)[object Object] {[object Object] [object Object] if (password.length()<=3)[object Object] {[object Object] requests++;[object Object] if (testPassword(password, startTime, requests))[object Object] return password;[object Object] }[object Object][object Object] password = buf.readLine();[object Object][object Object] }[object Object] }[object Object] catch (IOException ioe)[object Object] {[object Object][object Object] }[object Object][object Object] return password;[object Object] }[object Object][object Object] private static boolean testPassword(String password, double startTime, int requests)[object Object] {[object Object] try[object Object] {[object Object] [object Object] [object Object] U...	`0`

Loss: BatchAllTripletLoss

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 1
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: 16
per_device_eval_batch_size: 16
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: False
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
0.2393	500	0.1875
0.4787	1000	0.1815
0.7180	1500	0.24
0.9574	2000	0.1596

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

bibtex

@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

bibtex

@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}
}

	sentence_0	sentence_1	label
type	string	string	int
details	min: 61 tokens mean: 471.36 tokens max: 512 tokens	min: 61 tokens mean: 491.01 tokens max: 512 tokens	0: ~99.50% 1: ~0.50%