SentenceTransformer based on huggingface/CodeBERTa-small-v1
This is a sentence-transformers model finetuned from huggingface/CodeBERTa-small-v1 on the soco_train_java dataset. 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: huggingface/CodeBERTa-small-v1
- Maximum Sequence Length: 512 tokens
- Output Dimensionality: 768 dimensions
- Similarity Function: Cosine Similarity
- Training Dataset:
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, 'architecture': '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.
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("buelfhood/SOCO-Java-codeberta-mnrl-triplets-ep1-bs16-lr3e-05-split0.1")
# Run inference
sentences = [
'import java.net.*;\nimport java.io.*;\n\npublic class BruteForce {\n private String strUserName;\n private String strURL;\n private int iAttempts;\n \n public BruteForce(String strURL,String strUserName) {\n this.strURL = strURL;\n this.strUserName = strUserName;\n this.iAttempts = 0 ;\n\n }\n \n public String getPassword(){\n URL u;\n String result ="";\n PassGenBrute PG = new PassGenBrute(3);\n URLConnection uc;\n String strPassword = new String();\n String strEncode;\n try{\n while (result.compareTo("HTTP/1.1 200 OK")!=0){\n \n strEncode = PG.getNewPassword();\n u = new URL(strURL);\n uc = u.openConnection();\n uc.setDoInput(true);\n uc.setDoOutput(true);\n strPassword = strEncode;\n strEncode = strUserName + ":" + strEncode;\n \n strEncode = new String(Base64.encode(strEncode.getBytes()));\n uc.setRequestProperty("Authorization"," " + strEncode);\n \n result = uc.getHeaderField(0);\n uc = null;\n u = null;\n iAttempts++;\n }\n\n }\n catch (Exception me) {\n System.out.println("MalformedURLException: "+me);\n }\n return(strPassword);\n }\n \n public int getAttempts(){\n return (iAttempts);\n };\n \n public static void main (String arg[]){\n timeStart = 0;\n timeEnd = 0;\n \n if (arg.length == 2) {\n BruteForce BF = new BruteForce(arg[0],arg[1]);\n System.out.println("Processing ... ");\n timeStart = System.currentTimeMillis();\n \n System.out.println("Password = " + BF.getPassword());\n timeEnd = System.currentTimeMillis();\n System.out.println("Total Time Taken = " + (timeEnd - timeStart) + " (msec)");\n System.out.println("Total Attempts = " + BF.getAttempts());\n }\n else {\n System.out.println("[Usage] java BruteForce <URL> <USERNAME>");\n\n }\n\n }\n}\n\nclass PassGenBrute {\n private char[] password;\n public PassGenBrute(int lenght) {\n password = new char[lenght];\n for (int i = 0; i < lenght; i++){\n password[i] = 65;\n }\n password[0]--;\n }\n \n public String getNewPassword()\n throws PasswordFailureException{\n password[0]++;\n\n try {\n for (int i=0; i<password.length ; i++){\n if (password[i] == 90) {\n password[i] = 97;\n }\n if (password[i] > 122) {\n password[i] = 65;\n password[i+1]++;\n }\n }\n }\n catch (RuntimeException re){\n throw new PasswordFailureException ();\n }\n return new String(password);\n }\n}\n\nclass PasswordFailureException extends RuntimeException {\n\n public PasswordFailureException() {\n }\n}',
'import java.net.*;\nimport java.io.*;\n\n\npublic class Dictionary {\n private String strUserName;\n private String strURL;\n private String strDictPath;\n private int iAttempts;\n\n \n public Dictionary(String strURL,String strUserName,String strDictPath) {\n this.strURL = strURL;\n this.strUserName = strUserName;\n this.iAttempts = 0 ;\n this.strDictPath = strDictPath;\n }\n \n\n public String getPassword(){\n URL u;\n String result ="";\n PassGenDict PG = new PassGenDict(3,strDictPath);\n URLConnection uc;\n String strPassword = new String();\n String strEncode;\n try{\n while (result.compareTo("HTTP/1.1 200 OK")!=0){\n \n strEncode = PG.getNewPassword();\n u = new URL(strURL);\n uc = u.openConnection();\n uc.setDoInput(true);\n uc.setDoOutput(true);\n strPassword = strEncode;\n strEncode = strUserName + ":" + strEncode;\n \n strEncode = new String(Base64.encode(strEncode.getBytes()));\n uc.setRequestProperty("Authorization"," " + strEncode);\n \n result = uc.getHeaderField(0);\n uc = null;\n u = null;\n iAttempts++;\n }\n\n }\n catch (Exception me) {\n System.out.println("MalformedURLException: "+me);\n }\n return(strPassword);\n }\n \n public int getAttempts(){\n return (iAttempts);\n };\n \n public static void main(String arg[]){\n timeStart = 0;\n timeEnd = 0;\n \n if (arg.length == 3) {\n Dictionary BF = new Dictionary(arg[0],arg[1],arg[2]);\n\n System.out.println("Processing ... ");\n timeStart = System.currentTimeMillis();\n System.out.println("Password = " + BF.getPassword());\n timeEnd = System.currentTimeMillis();\n System.out.println("Total Time Taken = " + (timeEnd - timeStart) + " (msec)");\n System.out.println("Total Attempts = " + BF.getAttempts());\n }\n else {\n System.out.println("[Usage] java BruteForce <URL> <USERNAME> <Dictionary path>");\n\n }\n\n }\n}\n\n\nclass PassGenDict {\n\n private char[] password;\n private String line;\n int iPassLenght;\n private BufferedReader inputFile;\n public PassGenDict(int lenght, String strDictPath) {\n try{\n inputFile = new BufferedReader(new FileReader(strDictPath));\n }\n catch (Exception e){\n }\n iPassLenght = lenght;\n }\n \n public String getNewPassword()\n throws PasswordFailureException{\n try {\n {\n line = inputFile.readLine();\n }while (line.length() != iPassLenght);\n\n }\n catch (Exception e){\n throw new PasswordFailureException ();\n }\n return (line);\n }\n}\n\nclass PasswordFailureException extends RuntimeException {\n\n public PasswordFailureException() {\n }\n}',
'import java.util.*;\nimport java.io.*;\nimport javax.swing.text.html.*;\n\n\npublic class WatchDog {\n\n public WatchDog() {\n\n }\n public static void main (String args[]) {\n DataInputStream newin;\n\n try{\n System.out.println("ishti");\n\n System.out.println("Downloading first copy");\n Runtime.getRuntime().exec("wget http://www.cs.rmit.edu./students/ -O oldfile.html");\n String[] cmdDiff = {"//sh", "-c", "diff oldfile.html newfile.html > Diff.txt"};\n String[] cmdMail = {"//sh", "-c", "mailx -s \\"Diffrence\\" \\"@cs.rmit.edu.\\" < Diff.txt"};\n while(true){\n Thread.sleep(24*60*60*1000);\n System.out.println("Downloading new copy");\n Runtime.getRuntime().exec("wget http://www.cs.rmit.edu./students/ -O newfile.html");\n Thread.sleep(2000);\n Runtime.getRuntime().exec(cmdDiff);\n Thread.sleep(2000);\n newin = new DataInputStream( new FileInputStream( "Diff.txt"));\n if (newin.readLine() != null){\n System.out.println("Sending Mail");\n Runtime.getRuntime().exec(cmdMail);\n Runtime.getRuntime().exec("cp newfile.html oldfile.html");\n\n }\n }\n\n }\n catch(Exception e){\n e.printStackTrace();\n }\n\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)
# tensor([[ 1.0000, 0.9496, -0.0018],
# [ 0.9496, 1.0000, 0.0477],
# [-0.0018, 0.0477, 1.0000]])
Training Details
Training Dataset
soco_train_java
- Dataset: soco_train_java at 44ca4ff
- Size: 38,664 training samples
- Columns:
anchor_code,positive_code, andnegative_code - Approximate statistics based on the first 1000 samples:
anchor_code positive_code negative_code type string string string details - min: 51 tokens
- mean: 466.15 tokens
- max: 512 tokens
- min: 51 tokens
- mean: 467.06 tokens
- max: 512 tokens
- min: 51 tokens
- mean: 454.38 tokens
- max: 512 tokens
- Samples:
anchor_code positive_code negative_code
import java.io.;
import java.net.;
import java.misc.BASE64Encoder;
public class Dictionary
{
public Dictionary()
{}
public boolean fetchURL(String urlString,String username,String password)
{
StringWriter sw= new StringWriter();
PrintWriter pw = new PrintWriter();
try{
URL url=new URL(urlString);
String userPwd= username+":"+password;
BASE64Encoder encoder = new BASE64Encoder();
String encodedStr = encoder.encode (userPwd.getBytes());
System.out.println("Original String = " + userPwd);
System.out.println("Encoded String = " + encodedStr);
HttpURLConnection huc=(HttpURLConnection) url.openConnection();
huc.setRequestProperty( "Authorization"," "+encodedStr);
InputStream content = (InputStream)huc.getInputStream();
BufferedReader in =
new BufferedReader (new InputStreamReader (content));
String line;
while ((line = in.readLine())...
import java.io.;
import java.net.;
import java.misc.BASE64Encoder;
public class BruteForce
{
public BruteForce()
{}
public boolean fetchURL(String urlString,String username,String password)
{
StringWriter = new StringWriter();
PrintWriter pw = new PrintWriter();
try{
URL url=new URL(urlString);
String userPwd= username+":"+password;
BASE64Encoder encoder = new BASE64Encoder();
String encodedStr = encoder.encode (userPwd.getBytes());
System.out.println("Original String = " + userPwd);
System.out.println("Encoded String = " + encodedStr);
HttpURLConnection huc=(HttpURLConnection) url.openConnection();
huc.setRequestProperty( "Authorization"," "+encodedStr);
InputStream content = (InputStream)huc.getInputStream();
BufferedReader in =
new BufferedReader (new InputStreamReader (content));
String line;
while ((line = in.readLine()) ...
import java.net.;
import java.io.;
import java.util.*;
public class Dictionary{
private static URL location;
private static String user;
private BufferedReader input;
private static BufferedReader dictionary;
private int maxLetters = 3;
public Dictionary() {
Authenticator.setDefault(new MyAuthenticator ());
startTime = System.currentTimeMillis();
boolean passwordMatched = false;
while (!passwordMatched) {
try {
input = new BufferedReader(new InputStreamReader(location.openStream()));
String line = input.readLine();
while (line != null) {
System.out.println(line);
line = input.readLine();
}
input.close();
passwordMatched = true;
}
catch (ProtocolException e)
{
}
catch (ConnectException e) {
System.out.println("Failed connect");
}
catch (IOException e) ...
import java.io.InputStream;
import java.util.Properties;
import javax.naming.Context;
import javax.naming.InitialContext;
import javax.rmi.PortableRemoteObject;
import javax.sql.DataSource;
public class WatchdogPropertyHelper {
private static Properties testProps;
public WatchdogPropertyHelper() {
}
public static String getProperty(String pKey){
try{
initProps();
}
catch(Exception e){
System.err.println("Error init'ing the watchddog Props");
e.printStackTrace();
}
return testProps.getProperty(pKey);
}
private static void initProps() throws Exception{
if(testProps == null){
testProps = new Properties();
InputStream fis =
WatchdogPropertyHelper.class.getResourceAsStream("/watchdog.properties");
testProps.load(fis);
}
}
}
import java.io.InputStream;
import java.util.Properties;
import javax.naming.Context;
import javax.naming.InitialContext;
import javax.rmi.PortableRemoteObject;
import javax.sql.DataSource;
public class BruteForcePropertyHelper {
private static Properties bruteForceProps;
public BruteForcePropertyHelper() {
}
public static String getProperty(String pKey){
try{
initProps();
}
catch(Exception e){
System.err.println("Error init'ing the burteforce Props");
e.printStackTrace();
}
return bruteForceProps.getProperty(pKey);
}
private static void initProps() throws Exception{
if(bruteForceProps == null){
bruteForceProps = new Properties();
InputStream fis =
BruteForcePropertyHelper.class.getResourceAsStream("/bruteforce.properties");
bruteForceProps.load(fis);
}
}
}
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...
import java.net.;
import java.io.;
public class BruteForce {
private static String password=" ";
public static void main(String[] args) {
String Result="";
if (args.length<1)
{
System.out.println("Error: Correct Format Filename, username e.g<>");
System.exit(1);
}
BruteForce bruteForce1 = new BruteForce();
Result=bruteForce1.Password("http://sec-crack.cs.rmit.edu./SEC/2/",args[0]);
System.out.println("The Password of "+args[0]+"is.."+Result);
}
private String Password(String urlString,String username)
{
int cnt=0;
t0 = System.currentTimeMillis();
for ( char ch = 'A'; ch <= 'z'; ch++ )
{
if (ch>'Z' && ch<'a')
{
ch='a';
}
for ( char ch1 = 'A'; ch1 <= 'z'; ch1++ )
{
if (ch1>'Z' && ch1<'a')
{
ch1='a';
}
for ( char ch2 = 'A'; ch2 <= 'z'; ch2++ )
{
if (ch2>'Z' && ch2<'a')
{
...
import java.net.;
import java.io.;
import java.util.Date;
public class Dictionary{
private static String password=" ";
public static void main(String[] args) {
String Result="";
if (args.length<1)
{
System.out.println("Correct Format Filename username e.g<>");
System.exit(1);
}
Dictionary dicton1 = new Dictionary();
Result=dicton1.Dict("http://sec-crack.cs.rmit.edu./SEC/2/",args[0]);
System.out.println("Cracked Password for The User "+args[0]+" The Password is.."+Result);
}
private String Dict(String urlString,String username)
{
int cnt=0;
FileInputStream stream=null;
DataInputStream word=null;
try{
stream = new FileInputStream ("/usr/share/lib/dict/words");
word =new DataInputStream(stream);
t0 = System.currentTimeMillis();
while (word.available() !=0)
{
password=word.readLine();
if (password.length()!=3)
{
continue;
}
System.out.print("...
package java.httputils;
import java.io.IOException;
import java.net.MalformedURLException;
import java.util.ArrayList;
import java.util.Iterator;
public class RunnableHttpRequest extends Thread
{
protected String targetURL = "http://localhost:8080/";
protected int requestCount = 1;
protected ArrayList timingList = new ArrayList();
protected HttpRequestClient req;
Boolean finished = new Boolean(false);
HttpRequestThreadPool pool;
public void run()
{
try
{
for (int i = 0; i < getRequestCount() && !getFinished().booleanValue(); i++)
{
try
{
req =
new HttpRequestClient(getTargetURL());
}
catch (MalformedURLException e)
{
e.printStackTrace();
break;
}
catch (IOException e)
{
... - Loss:
MultipleNegativesRankingLosswith these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim", "gather_across_devices": false }
Evaluation Dataset
soco_train_java
- Dataset: soco_train_java at 44ca4ff
- Size: 4,296 evaluation samples
- Columns:
anchor_code,positive_code, andnegative_code - Approximate statistics based on the first 1000 samples:
anchor_code positive_code negative_code type string string string details - min: 51 tokens
- mean: 465.22 tokens
- max: 512 tokens
- min: 51 tokens
- mean: 464.66 tokens
- max: 512 tokens
- min: 51 tokens
- mean: 458.05 tokens
- max: 512 tokens
- Samples:
anchor_code positive_code negative_code
import java.util.;
import java.io.;
public class WatchDog
{
public static void main(String args[])
{
Runtime rt1 = Runtime.getRuntime();
Process prss1= null;
try
{
prss1 = rt1.exec("wget -R mpg,mpeg, --output-document=first.html http://www.cs.rmit.edu./students/");
}catch(java.io.IOException e){}
MyWatchDogTimer w = new MyWatchDogTimer();
Timer time = new Timer();
time.schedule(w,864000000,864000000);
}
}
import java.util.;
import java.io.;
public class MyTimer
{
public static void main(String args[])
{
Watchdog watch = new Watchdog();
Timer time = new Timer();
time.schedule(watch,864000000,864000000);
}
}import java.net.;
import java.io.;
import java.util.Vector;
import java.util.Date;
import java.security.;
public class Dictionary {
public static BufferedReader in;
public static void main(String[] args) throws Exception {
String baseURL = "http://sec-crack.cs.rmit.edu./SEC/2/index.php";
int count=0;
Date date = new Date();
startTime=date.getTime();
int LIMITINMINUTES=45;
int TIMELIMIT=LIMITINMINUTES1000*60;
boolean timedOut=false;
boolean found=false;
Vector dictionary=new Vector(readWords());
System.out.println("Words in dictionary: "+dictionary.size());
while (found==false && timedOut==false && dictionary.elementAt(count)!=null) {
Date endDate = new Date();
endTime=endDate.getTime();
if (endTime>(TIMELIMIT+startTime)){
System.out.println("Timed out");
timedOut=true;
}
String password = "";
...
import java.io.InputStream;
import java.util.Properties;
import javax.naming.Context;
import javax.naming.InitialContext;
import javax.rmi.PortableRemoteObject;
import javax.sql.DataSource;
public class MailsendPropertyHelper {
private static Properties testProps;
public MailsendPropertyHelper() {
}
public static String getProperty(String pKey){
try{
initProps();
}
catch(Exception e){
System.err.println("Error init'ing the watchddog Props");
e.printStackTrace();
}
return testProps.getProperty(pKey);
}
private static void initProps() throws Exception{
if(testProps == null){
testProps = new Properties();
InputStream fis =
MailsendPropertyHelper.class.getResourceAsStream("/mailsend.properties");
testProps.load(fis);
}
}
}
import java.io.InputStream;
import java.util.Properties;
import javax.naming.Context;
import javax.naming.InitialContext;
import javax.rmi.PortableRemoteObject;
import javax.sql.DataSource;
public class BruteForcePropertyHelper {
private static Properties bruteForceProps;
public BruteForcePropertyHelper() {
}
public static String getProperty(String pKey){
try{
initProps();
}
catch(Exception e){
System.err.println("Error init'ing the burteforce Props");
e.printStackTrace();
}
return bruteForceProps.getProperty(pKey);
}
private static void initProps() throws Exception{
if(bruteForceProps == null){
bruteForceProps = new Properties();
InputStream fis =
BruteForcePropertyHelper.class.getResourceAsStream("/bruteforce.properties");
bruteForceProps.load(fis);
}
}
}
import java.net.;
import java.io.;
import java.Ostermiller.util.;
import java.util.;
public class MyClient2 implements Runnable
{
private String hostname;
private int port;
private String filename;
private Socket s;
private int n;
private InputStream sin;
private OutputStream sout;
private int dif;
private String myPassword;
private int status;
private int myTime;
private BruteForce myMaster;
public MyClient2(BruteForce bf , int num, int myPort, String password)
{
hostname = new String("sec-crack.cs.rmit.edu.");
port = myPort;
status = 0;
myTime = 0;
myPassword = password;
filename = new String("/SEC/2/");
myMaster = 0;
n = num;
dif = 0;
}
public getDif()
{
return dif;
}
public int getStatus()
{
return status;
}
public void run()
{
String inputLine;
String[] tokens = new String[5];
int i;
myTime = 0;
...import java.io.;
import java.net.;
import java.util.*;
public class Dictionary
{
public static void main (String args[])
{
Calendar cal = Calendar.getInstance();
Date now=cal.getTime();
double startTime = now.getTime();
String password=getPassword(startTime);
System.out.println("The password is " + password);
}
public static String getPassword(double startTime)
{
String password="";
int requests=0;
try
{
FileReader fRead = new FileReader("/usr/share/lib/dict/words");
BufferedReader buf = new BufferedReader(fRead);
password=buf.readLine();
while (password != null)
{
if (password.length()<=3)
{
requests++;
if (testPassword(password, startTime, requests))
return password;
}
password = buf.readLine();
}
}
catch (IOException ioe)
{
}
return password;
}
private static boolean testPassword(String password, double startTime, int requests)
{
try
{
U...import java.io.;
import java.net.;
import java.util.*;
public class BruteForce
{
public static void main(String args[])
{
Calendar cal = Calendar.getInstance();
Date now=cal.getTime();
double startTime = now.getTime();
String password=getPassword(startTime);
System.out.println("The password is " + password);
}
public static String getPassword(double startTime)
{
char first, second, third;
String password="";
int requests=0;
for (int i=65; i<123; i++)
{
requests++;
first = (char) i;
password = first + "";
if (testPassword(password, startTime, requests))
return password;
for (int j=65; j<123; j++)
{
requests++;
second = (char) j;
password = first + "" + second;
if (testPassword(password, startTime, requests))
return password;
for (int k=65; k<123; k++)
{
requests++;
third = (char) k;
password = first + "" + second + "" + third;
if (test...
import java.misc.BASE64Encoder;
import java.misc.BASE64Decoder;
import java.io.;
import java.net.;
import java.util.*;
public class Dictionary {
public Dictionary(String url, String dictionaryFile) {
try{
this.url = url;
this.dictionaryPath = dictionaryFile;
InputStream fis = new FileInputStream(this.dictionaryPath);
dict = new BufferedReader(new InputStreamReader(fis));
}catch(IOException ioe){
System.out.println("Error opening dictionary file:\n" +ioe);
}
}
private String url = null;
private String dictionaryPath = null;
private BufferedReader dict = null;
private int attempts = 0;
private int passwordSize = 3;
public void setPasswordSize(int size){
this.passwordSize = size;
}
public String getNextPassword()throws IOException{
String line = dict.readLine();
while(line!=null&&line.length()!=this.passwordSize )
line = dict.readLine();
return line;
}
publ... - Loss:
MultipleNegativesRankingLosswith these parameters:{ "scale": 20.0, "similarity_fct": "cos_sim", "gather_across_devices": false }
Training Hyperparameters
Non-Default Hyperparameters
per_device_train_batch_size: 16learning_rate: 3e-05num_train_epochs: 1warmup_ratio: 0.1fp16: Truebatch_sampler: no_duplicates
All Hyperparameters
Click to expand
overwrite_output_dir: Falsedo_predict: Falseeval_strategy: noprediction_loss_only: Trueper_device_train_batch_size: 16per_device_eval_batch_size: 8per_gpu_train_batch_size: Noneper_gpu_eval_batch_size: Nonegradient_accumulation_steps: 1eval_accumulation_steps: Nonetorch_empty_cache_steps: Nonelearning_rate: 3e-05weight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08max_grad_norm: 1.0num_train_epochs: 1max_steps: -1lr_scheduler_type: linearlr_scheduler_kwargs: {}warmup_ratio: 0.1warmup_steps: 0log_level: passivelog_level_replica: warninglog_on_each_node: Truelogging_nan_inf_filter: Truesave_safetensors: Truesave_on_each_node: Falsesave_only_model: Falserestore_callback_states_from_checkpoint: Falseno_cuda: Falseuse_cpu: Falseuse_mps_device: Falseseed: 42data_seed: Nonejit_mode_eval: Falsebf16: Falsefp16: Truefp16_opt_level: O1half_precision_backend: autobf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonelocal_rank: 0ddp_backend: Nonetpu_num_cores: Nonetpu_metrics_debug: Falsedebug: []dataloader_drop_last: Falsedataloader_num_workers: 0dataloader_prefetch_factor: Nonepast_index: -1disable_tqdm: Falseremove_unused_columns: Truelabel_names: Noneload_best_model_at_end: Falseignore_data_skip: Falsefsdp: []fsdp_min_num_params: 0fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}fsdp_transformer_layer_cls_to_wrap: Noneaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}parallelism_config: Nonedeepspeed: Nonelabel_smoothing_factor: 0.0optim: adamw_torch_fusedoptim_args: Noneadafactor: Falsegroup_by_length: Falselength_column_name: lengthproject: huggingfacetrackio_space_id: trackioddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falsedataloader_pin_memory: Truedataloader_persistent_workers: Falseskip_memory_metrics: Trueuse_legacy_prediction_loop: Falsepush_to_hub: Falseresume_from_checkpoint: Nonehub_model_id: Nonehub_strategy: every_savehub_private_repo: Nonehub_always_push: Falsehub_revision: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Noneinclude_inputs_for_metrics: Falseinclude_for_metrics: []eval_do_concat_batches: Truefp16_backend: autopush_to_hub_model_id: Nonepush_to_hub_organization: Nonemp_parameters:auto_find_batch_size: Falsefull_determinism: Falsetorchdynamo: Noneray_scope: lastddp_timeout: 1800torch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneinclude_tokens_per_second: Falseinclude_num_input_tokens_seen: noneftune_noise_alpha: Noneoptim_target_modules: Nonebatch_eval_metrics: Falseeval_on_start: Falseuse_liger_kernel: Falseliger_kernel_config: Noneeval_use_gather_object: Falseaverage_tokens_across_devices: Trueprompts: Nonebatch_sampler: no_duplicatesmulti_dataset_batch_sampler: proportionalrouter_mapping: {}learning_rate_mapping: {}
Training Logs
| Epoch | Step | Training Loss |
|---|---|---|
| 0.0414 | 100 | 1.1345 |
| 0.0827 | 200 | 0.3666 |
| 0.1241 | 300 | 0.3803 |
| 0.1655 | 400 | 0.3192 |
| 0.2069 | 500 | 0.3572 |
| 0.2482 | 600 | 0.3331 |
| 0.2896 | 700 | 0.3284 |
| 0.3310 | 800 | 0.3241 |
| 0.3724 | 900 | 0.3251 |
| 0.4137 | 1000 | 0.3429 |
| 0.4551 | 1100 | 0.3165 |
| 0.4965 | 1200 | 0.3045 |
| 0.5379 | 1300 | 0.3252 |
| 0.5792 | 1400 | 0.3292 |
| 0.6206 | 1500 | 0.3201 |
| 0.6620 | 1600 | 0.341 |
| 0.7034 | 1700 | 0.2984 |
| 0.7447 | 1800 | 0.3067 |
| 0.7861 | 1900 | 0.3131 |
| 0.8275 | 2000 | 0.2834 |
| 0.8688 | 2100 | 0.2931 |
| 0.9102 | 2200 | 0.2988 |
| 0.9516 | 2300 | 0.3035 |
| 0.9930 | 2400 | 0.365 |
Framework Versions
- Python: 3.12.3
- Sentence Transformers: 5.1.1
- Transformers: 4.57.0
- PyTorch: 2.8.0+cu128
- Accelerate: 1.10.1
- Datasets: 4.1.1
- Tokenizers: 0.22.1
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",
}
MultipleNegativesRankingLoss
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
- Downloads last month
- 9
Model tree for buelfhood/SOCO-Java-codeberta-mnrl-triplets-ep1-bs16-lr3e-05-split0.1
Base model
huggingface/CodeBERTa-small-v1