Обновить main.cpp

main.cpp

@@ -1,4 +1,5 @@
 #include <iostream>
+#include <iomanip>
 #include <vector>
 #include <string>
 #include <iomanip>
@@ -7,32 +8,16 @@
 #include <algorithm>
 #include "Xenith/core.h"
 #include "Xenith/token/token.h"
+#include <windows.h>
+#include <chrono>
 
-// Глобальные настройки
+std::string currentSystemPrompt = ""; 
-std::string currentSystemPrompt = "я робот";
 
-void printParameterCount(LayerStructure_t layers[], int numLayers) {
+LayerStructure_t layers[] = {
-    long long totalParams = 0;
+    {MAX_CONTEXT * EMBED_DIM, SIGMOID},
-    for (int i = 0; i < numLayers - 1; i++) {
+    {16, SIGMOID},
-        long long weights = (long long)layers[i].size * layers[i + 1].size;
+    {MAX_VOCAB, SIGMOID}
-        long long biases = (long long)layers[i + 1].size;
+};
-        totalParams += (weights + biases);
-    }
-
-    std::cout << "--- Xenith AI (Model Size: ";
-    if (totalParams >= 1000000000000LL)
-        std::cout << std::fixed << std::setprecision(1) << (double)totalParams / 1000000000000.0 << "t";
-    else if (totalParams >= 1000000000LL)
-        std::cout << std::fixed << std::setprecision(1) << (double)totalParams / 1000000000.0 << "b";
-    else if (totalParams >= 1000000LL)
-        std::cout << std::fixed << std::setprecision(1) << (double)totalParams / 1000000.0 << "m";
-    else if (totalParams >= 1000LL)
-        std::cout << std::fixed << std::setprecision(1) << (double)totalParams / 1000.0 << "k";
-    else
-        std::cout << totalParams;
-    
-    std::cout << " parameters) ---" << std::endl;
-}
 
 std::vector<double> buildNetInput(const std::vector<int>& tokens, Embedder& emb) {
     std::vector<double> netInput;
@@ -58,42 +43,89 @@ void trainOnSequence(NeuralNetwork& nn, Tokenizer& tok, Embedder& emb, const std
         std::cout << "Error: Sequence too short for training." << std::endl;
         return;
     }
+    int numLayers = sizeof(layers) / sizeof(layers[0]);
+    long long totalParams = 0;
+    for (int i = 0; i < numLayers - 1; i++) {
+        totalParams += (long long)layers[i].size * layers[i + 1].size + layers[i + 1].size;
+    }
+
+    std::string modelSizeStr;
+    {
+        std::stringstream ss;
+        if (totalParams >= 1e12) ss << std::fixed << std::setprecision(1) << totalParams / 1e12 << "t";
+        else if (totalParams >= 1e9) ss << std::fixed << std::setprecision(1) << totalParams / 1e9 << "b";
+        else if (totalParams >= 1e6) ss << std::fixed << std::setprecision(1) << totalParams / 1e6 << "m";
+        else if (totalParams >= 1e3) ss << std::fixed << std::setprecision(1) << totalParams / 1e3 << "k";
+        else ss << totalParams;
+        modelSizeStr = ss.str();
+    }
+
+    std::string sequenceStr = "";
+    for (int tId : allTokens) {
+        sequenceStr += "{" + tok.getWord(tId) + " (" + std::to_string(tId) + ")} ";
+    }
+
+    auto startTime = std::chrono::high_resolution_clock::now();
+    int trainSteps = 0;
+    double stepsPerSec = 0, maxLoss = 0;
 
     std::cout << "Training logic: Next Token Prediction..." << std::endl;
+
+    std::cout << "\033[s\033[999;1H" << "\033[2K" << "\033[1;30m" << "\033[F" << "\r"
+        << "DATA: " << (sequenceStr.length() > 100 ? sequenceStr.substr(0, 200) : sequenceStr) << "\033[0m\033[u";
+
     for (int e = 1; e <= epochs; e++) {
         double totalLoss = 0;
         for (size_t i = 1; i < allTokens.size(); i++) {
-            std::vector<int> context;
+            std::vector<int> context(allTokens.begin(), allTokens.begin() + i);
-            for (size_t j = 0; j < i; j++) context.push_back(allTokens[j]);
-            
             std::vector<double> target(MAX_VOCAB, 0.0);
             target[allTokens[i]] = 1.0;
-
             totalLoss += nn.train(buildNetInput(context, emb), target, lr);
+
+            trainSteps++;
+            auto currentTime = std::chrono::high_resolution_clock::now();
+            if (std::chrono::duration<double>(currentTime - startTime).count() >= 1.0) {
+                stepsPerSec = trainSteps / std::chrono::duration<double>(currentTime - startTime).count();
+                trainSteps = 0;
+                startTime = currentTime;
             }
-        std::cout << "\rEpoch " << e << "/" << epochs << " | Loss: " << std::fixed << std::setprecision(6) << totalLoss << std::flush;
+            std::cout << "\rEpoch " << std::setw(4) << e << "/" << epochs
+                << " | Token: " << std::setw(3) << i << "/" << allTokens.size()
+                << " | Loss: " << std::fixed << std::setprecision(6) << totalLoss
+                << " | Max Loss: " << std::fixed << std::setprecision(6) << maxLoss << "   \033[s";
+
+            std::cout << "\033[999;1H" << "\r";
+
+            std::cout << "SPEED: " << std::setw(6) << std::fixed << std::setprecision(1) << stepsPerSec << " st/s"
+                << " | MODEL: " << std::setw(7) << modelSizeStr
+                << " | CURRENT: [" << std::left << std::setw(15) << tok.getWord(allTokens[i]) << "] ("
+                << std::right << std::setw(4) << allTokens[i] << ")             ";
+
+            std::cout << "\033[K" << "\033[0m";
+
+            std::cout << "\033[997;1H" << "\r" << std::flush << "\033[u";
+
+        }
+        maxLoss = totalLoss;
     }
     std::cout << "\nDone!" << std::endl;
 }
 
+
+
 int main() {
+    SetConsoleOutputCP(CP_UTF8);
+    SetConsoleCP(CP_UTF8);
+
     Tokenizer tok;
     Embedder emb(MAX_VOCAB, EMBED_DIM);
-    LayerStructure_t layers[] = {
+    
-        {MAX_CONTEXT * EMBED_DIM, SIGMOID}, 
-        {16, SIGMOID}, 
-        {MAX_VOCAB, SIGMOID}
-    };
     int numLayers = sizeof(layers) / sizeof(layers[0]);
 
     NeuralNetwork nn(layers, numLayers);
-    printParameterCount(layers, numLayers);
-
-    std::cout << "\n--- MENU ---" << std::endl;
-    std::cout << "/train\n/trainFile\n/help\n/exit\n";
 
     while (true) {
-        std::cout << "\nxentith~$ ";
+        std::cout << "xentith~$ ";
 
         std::string cmdIn;
         std::getline(std::cin, cmdIn);
@@ -164,16 +196,43 @@ int main() {
             std::getline(std::cin, currentSystemPrompt);
             std::cout << "System Prompt updated!" << std::endl;
 
-        } else if (cmdIn == "/help") {
+        }
+        else if (cmdIn == "/help") {
             std::cout << "\n--- MENU ---" << std::endl;
             std::cout << "/train\n/trainFile\n/sysPrompt\n/help\n/exit\n";
 
+        } else if (cmdIn == "/clr") {
+
+            std::cout << "\033[2J\033[1;1H";
+
         } else {
             std::string prompt = "[SYS]" + currentSystemPrompt + "[USER]" + cmdIn + "[AI]";
             std::vector<int> currentTokens = tok.textToTokens(prompt);
 
             std::cout << "AI: ";
-            for (int g = 0; g < 30; g++) {
+            long long totalParams = 0;
+            for (int i = 0; i < numLayers - 1; i++) {
+                long long weights = (long long)layers[i].size * layers[i + 1].size;
+                long long biases = (long long)layers[i + 1].size;
+                totalParams += (weights + biases);
+            }
+            std::string modelSizeStr;
+            {
+                std::stringstream ss;
+                if (totalParams >= 1000000000000LL) ss << std::fixed << std::setprecision(1) << (double)totalParams / 1000000000000.0 << "t";
+                else if (totalParams >= 1000000000LL) ss << std::fixed << std::setprecision(1) << (double)totalParams / 1000000000.0 << "b";
+                else if (totalParams >= 1000000LL) ss << std::fixed << std::setprecision(1) << (double)totalParams / 1000000.0 << "m";
+                else if (totalParams >= 1000LL) ss << std::fixed << std::setprecision(1) << (double)totalParams / 1000.0 << "k";
+                else ss << totalParams;
+                modelSizeStr = ss.str();
+            }
+
+            // Переменные для замера скорости
+            auto startTime = std::chrono::high_resolution_clock::now();
+            int tokensInSecond = 0;
+            double tokensPerSec = 0;
+
+            for (int g = 0; g < 1024; g++) {
                 std::vector<double> out = nn.feedForward(buildNetInput(currentTokens, emb));
 
                 int bestId = 0;
@@ -183,11 +242,28 @@ int main() {
 
                 if (bestId == 0) break;
 
+                tokensInSecond++;
+                auto currentTime = std::chrono::high_resolution_clock::now();
+                std::chrono::duration<double> elapsed = currentTime - startTime;
+
+                if (elapsed.count() >= 0.1) {
+                    tokensPerSec = tokensInSecond / elapsed.count();
+                    tokensInSecond = 0;
+                    startTime = currentTime;
+                }
+
                 std::string word = tok.getWord(bestId);
                 std::cout << word << std::flush;
 
+                std::cout << "\033[s" << "\033[999;1H" << "\033[2K"
+                    << "--- [ID: " << bestId << "] | "
+                    << "Speed: " << std::fixed << std::setprecision(1) << tokensPerSec*10 << " t/s | "
+                    << "Model: " << modelSizeStr << " params ---"
+                    << "\033[u" << std::flush;
+
                 currentTokens.push_back(bestId);
             }
+            // Чтобы курсор не остался внизу после генерации
             std::cout << std::endl;
         }
     }