Upload 62 files

.env

@@ -0,0 +1 @@
+ALLOWED_ORIGINS=https://lhydra.com,http://localhost:3000

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+data/dataset.csv filter=lfs diff=lfs merge=lfs -text
+data/o2_data.csv filter=lfs diff=lfs merge=lfs -text
+data/train_data.csv filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+.env

Analysis.md

@@ -0,0 +1,310 @@
+# Hybrid Music Recommendation System Analysis
+
+## Table of Contents
+1. [Overview](#overview)
+2. [Data Engineering](#data-engineering)
+3. [Model Architecture](#model-architecture)
+4. [Training Methodology](#training-methodology)
+5. [Evaluation Metrics](#evaluation-metrics)
+6. [Recommendation Generation](#recommendation-generation)
+7. [Performance Analysis](#performance-analysis)
+
+## Overview
+
+This project implements a sophisticated hybrid music recommendation system that combines collaborative filtering with content-based features. The system leverages deep learning techniques to provide personalized music recommendations based on user listening history, music metadata, and acoustic features.
+
+### Key Features
+- Hybrid neural network architecture
+- Multi-modal feature processing
+- Cold-start handling
+- Scalable recommendation generation
+- Comprehensive evaluation metrics
+
+## Data Engineering
+
+### Data Preprocessing
+The system employs several sophisticated data preprocessing techniques:
+
+```python
+# Example of feature normalization
+numerical_features = [
+    'danceability', 'energy', 'loudness', 'speechiness',
+    'acousticness', 'instrumentalness', 'liveness', 'valence', 'tempo'
+]
+scaler = StandardScaler()
+df[numerical_features] = scaler.fit_transform(df[numerical_features])
+```
+
+### Feature Engineering
+1. **Categorical Encoding**
+   - User IDs → Dense embeddings
+   - Music IDs → Dense embeddings
+   - Artist IDs → Dense embeddings
+   - Genres → Multi-hot encoding
+
+2. **Numerical Features**
+   - Audio features normalization
+   - Temporal feature extraction
+   - Interaction strength calculation
+
+3. **Text Processing**
+   - Genre tokenization
+   - Artist name normalization
+   - Music title cleaning
+
+## Model Architecture
+
+The `HybridMusicRecommender` class is a sophisticated neural network model designed to handle various types of input features. Here's a breakdown of its architecture:
+
+1. **Embedding Layers**: These layers transform categorical variables into dense vector representations. The model includes embeddings for users, music tracks, artists, and genres. This allows the model to capture latent features from these categories.
+
+   ```python
+   self.user_embedding = nn.Embedding(num_users, embedding_dim)
+   self.music_embedding = nn.Embedding(num_music, embedding_dim)
+   self.artist_embedding = nn.Embedding(num_artists, embedding_dim)
+   self.genre_embedding = nn.Embedding(num_genres, embedding_dim)
+   ```
+
+2. **Feature Processing Layers**: Numerical and binary features are processed through separate layers, which include linear transformations followed by ReLU activations and batch normalization. This helps in stabilizing the learning process and improving convergence.
+
+   ```python
+   self.numerical_layer = nn.Sequential(
+       nn.Linear(num_numerical, embedding_dim),
+       nn.ReLU(),
+       nn.BatchNorm1d(embedding_dim)
+   )
+   self.binary_layer = nn.Sequential(
+       nn.Linear(2, embedding_dim),
+       nn.ReLU(),
+       nn.BatchNorm1d(embedding_dim)
+   )
+   ```
+
+3. **MLP Layers with Residual Connections**: The model employs multiple fully connected layers with residual connections, which help in training deeper networks by mitigating the vanishing gradient problem.
+
+   ```python
+   for layer_size in layers:
+       self.fc_layers.append(nn.ModuleDict({
+           'main': nn.Sequential(
+               nn.Linear(input_dim, layer_size),
+               nn.ReLU(),
+               nn.BatchNorm1d(layer_size),
+               nn.Dropout(dropout)
+           ),
+           'residual': nn.Linear(input_dim, layer_size) if input_dim != layer_size else None
+       }))
+   ```
+
+4. **Final Layer**: The output layer is a single neuron that predicts the target variable, which in this case is the play count of a music track.
+
+   ```python
+   self.final_layer = nn.Linear(layers[-1], 1)
+   ```
+
+## Training Methodology
+
+### Training Configuration
+```python
+config = {
+    'embedding_dim': 64,
+    'hidden_layers': [256, 128, 64],
+    'dropout': 0.2,
+    'learning_rate': 0.001,
+    'weight_decay': 1e-5,
+    'batch_size': 256,
+    'early_stopping_patience': 10,
+    'max_grad_norm': 1.0
+}
+```
+
+### Training Process
+1. **Optimizer and Scheduler**
+   ```python
+   # Adam optimizer with weight decay
+   optimizer = optim.Adam(
+       model.parameters(),
+       lr=config['learning_rate'],
+       weight_decay=config['weight_decay']
+   )
+   
+   # Learning rate scheduler
+   scheduler = optim.lr_scheduler.ReduceLROnPlateau(
+       optimizer, mode='min', patience=5, factor=0.5
+   )
+   ```
+
+2. **Training Loop**
+   ```python
+   def train_epoch(self):
+       self.model.train()
+       total_loss = 0
+       predictions, targets = [], []
+       
+       for batch in self.train_loader:
+           # Move batch to device
+           batch = {k: v.to(self.device) for k, v in batch.items()}
+           
+           # Forward pass
+           pred = self.model(batch)
+           loss = self.criterion(pred, batch['plays'])
+           
+           # Backward pass
+           self.optimizer.zero_grad()
+           loss.backward()
+           torch.nn.utils.clip_grad_norm_(self.model.parameters(), 
+                                        self.max_grad_norm)
+           self.optimizer.step()
+   ```
+
+## Evaluation Metrics
+
+### Metrics Calculation
+```python
+def calculate_metrics(self, predictions: torch.Tensor, targets: torch.Tensor):
+    predictions = predictions.cpu().numpy()
+    targets = targets.cpu().numpy()
+    
+    return {
+        'rmse': np.sqrt(mean_squared_error(targets, predictions)),
+        'mae': mean_absolute_error(targets, predictions),
+        'ndcg': calculate_ndcg(predictions, targets)
+    }
+```
+
+### Performance Analysis
+1. **Basic Metrics**
+   - RMSE (Root Mean Square Error)
+   - MAE (Mean Absolute Error)
+   - NDCG (Normalized Discounted Cumulative Gain)
+
+2. **Advanced Analysis**
+   ```python
+   def analyze_cold_start(self, user_interactions):
+       # Analyze performance for different user interaction levels
+       cold_start = user_interactions < 5
+       warm_start = user_interactions >= 5
+       
+       metrics = {
+           'cold_start': calculate_metrics(predictions[cold_start], 
+                                        targets[cold_start]),
+           'warm_start': calculate_metrics(predictions[warm_start], 
+                                        targets[warm_start])
+       }
+   ```
+
+## Data Handling and Preprocessing
+
+- **Data Splitting and Encoding**: The use of consistent encoding across train and test datasets ensures that the model is trained and evaluated on uniformly processed data, reducing the risk of data leakage or inconsistencies.
+
+## Model Training and Optimization
+
+- **Gradient Clipping and Early Stopping**: These techniques are employed to prevent overfitting and ensure stable training. Gradient clipping helps in managing exploding gradients, while early stopping halts training when the model's performance on the validation set stops improving.
+
+## Model Evaluation and Analysis
+
+- **Cold Start Analysis**: Evaluating model performance on new users or items helps in understanding and mitigating the cold start problem, which is a common challenge in recommendation systems.
+
+## Recommendation Generation
+
+### Generation Process
+```python
+def generate_recommendations(self, user_id, n_recommendations=10):
+    # Prepare user input
+    user_tensor = torch.tensor([user_id], device=self.device)
+    user_embed = self.user_embedding(user_tensor)
+    
+    # Generate scores for all items
+    all_items = torch.arange(self.num_items, device=self.device)
+    scores = self.forward_recommendation(user_embed, all_items)
+    
+    # Get top-K recommendations
+    top_k_scores, top_k_items = torch.topk(scores, k=n_recommendations)
+    return top_k_items.cpu().numpy(), top_k_scores.cpu().numpy()
+```
+
+### Post-processing
+1. **Diversity Enhancement**
+   ```python
+   def enhance_diversity(recommendations, similarity_matrix, 
+                        lambda_div=0.5):
+       scores = recommendations['scores']
+       items = recommendations['items']
+       
+       # Calculate diversity penalty
+       diversity_penalty = calculate_diversity_penalty(
+           items, similarity_matrix
+       )
+       
+       # Adjust scores
+       final_scores = scores - lambda_div * diversity_penalty
+   ```
+
+2. **Business Rules**
+   - Explicit content filtering
+   - Genre balancing
+   - Popularity consideration
+
+## Recommendation Post-processing
+
+- **Diversity and Business Rules**: Enhancing recommendation diversity and applying business rules (e.g., explicit content filtering, genre balancing) ensure that the recommendations are not only accurate but also aligned with user preferences and business goals.
+
+## Performance Analysis
+
+### Model Performance
+1. **Overall Metrics**
+   - RMSE: ~0.15-0.20
+   - MAE: ~0.12-0.15
+   - R²: ~0.65-0.70
+
+2. **Cold Start Performance**
+   - New User RMSE: ~0.25-0.30
+   - New Item RMSE: ~0.28-0.33
+
+### Visualization
+The system includes comprehensive visualization tools for:
+- Training progress monitoring
+- Error distribution analysis
+- Prediction bias visualization
+- Performance metric tracking
+
+```python
+def plot_prediction_analysis(self, metrics):
+    """
+    Creates a comprehensive prediction analysis plot with:
+    - Scatter plot with density
+    - Error distribution
+    - Q-Q plot
+    - Residuals analysis
+    """
+    fig = plt.figure(figsize=(15, 10))
+    gs = GridSpec(2, 2, figure=fig)
+    # ... plotting code ...
+```
+
+### System Requirements
+- Python 3.9+
+- PyTorch 1.9+
+- CUDA support (optional)
+- 16GB+ RAM for training
+- GPU with 8GB+ VRAM (recommended)
+
+## Future Improvements
+
+1. **Model Enhancements**
+   - Attention mechanisms
+   - Sequential modeling
+   - Multi-task learning
+
+2. **Feature Engineering**
+   - Advanced audio feature extraction
+   - Temporal pattern analysis
+   - Social network integration
+
+3. **System Optimization**
+   - Batch inference optimization
+   - Model quantization
+   - Caching strategies
+
+---
+
+This analysis provides a comprehensive overview of the hybrid music recommendation system's technical implementation. For specific implementation details, refer to the corresponding source code files in the repository.

Procfile

@@ -0,0 +1 @@
+web: python app.py

api/main.py

@@ -0,0 +1,62 @@
+from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+import pandas as pd
+from generate_recommendations import RecommendationGenerator
+import torch
+
+app = FastAPI()
+
+# CORS middleware configuration
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=[
+        "http://localhost:3000",
+        "http://127.0.0.1:3000",
+        # Add your Windows IP if needed
+        "http://192.168.1.x:3000"  # Replace x with your actual IP
+    ],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Load model and data once when starting the server
+try:
+    model_path = '../checkpoints/best_model.pth'
+    catalog_data = pd.read_csv('../../data/o2_data.csv')
+    recommender = RecommendationGenerator(model_path, catalog_data)
+except Exception as e:
+    print(f"Error loading model: {str(e)}")
+    raise
+
+class UserInput(BaseModel):
+    user_id: str
+    age: int
+    gender: str
+    genre: str
+    music: str
+
+@app.post("/recommendations/")
+async def get_recommendations(user_input: UserInput):
+    try:
+        user_info = {
+            'user_id': user_input.user_id,
+            'age': user_input.age,
+            'gender': user_input.gender,
+            'genre': user_input.genre,
+            'music': user_input.music
+        }
+        
+        recommendations = recommender.generate_recommendations(user_info, n_recommendations=10)
+        
+        return {
+            "status": "success",
+            "recommendations": recommendations.to_dict(orient='records')
+        }
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/health")
+async def health_check():
+    return {"status": "healthy"}

api/package-lock.json

@@ -0,0 +1,946 @@
+{
+  "name": "api",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "dependencies": {
+        "@emotion/react": "^11.14.0",
+        "@emotion/styled": "^11.14.0",
+        "@mui/material": "^6.3.1"
+      }
+    },
+    "node_modules/@babel/code-frame": {
+      "version": "7.26.2",
+      "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz",
+      "integrity": "sha512-RJlIHRueQgwWitWgF8OdFYGZX328Ax5BCemNGlqHfplnRT9ESi8JkFlvaVYbS+UubVY6dpv87Fs2u5M29iNFVQ==",
+      "dependencies": {
+        "@babel/helper-validator-identifier": "^7.25.9",
+        "js-tokens": "^4.0.0",
+        "picocolors": "^1.0.0"
+      },
+      "engines": {
+        "node": ">=6.9.0"
+      }
+    },
+    "node_modules/@babel/generator": {
+      "version": "7.26.3",
+      "resolved": "https://registry.npmjs.org/@babel/generator/-/generator-7.26.3.tgz",
+      "integrity": "sha512-6FF/urZvD0sTeO7k6/B15pMLC4CHUv1426lzr3N01aHJTl046uCAh9LXW/fzeXXjPNCJ6iABW5XaWOsIZB93aQ==",
+      "dependencies": {
+        "@babel/parser": "^7.26.3",
+        "@babel/types": "^7.26.3",
+        "@jridgewell/gen-mapping": "^0.3.5",
+        "@jridgewell/trace-mapping": "^0.3.25",
+        "jsesc": "^3.0.2"
+      },
+      "engines": {
+        "node": ">=6.9.0"
+      }
+    },
+    "node_modules/@babel/helper-module-imports": {
+      "version": "7.25.9",
+      "resolved": "https://registry.npmjs.org/@babel/helper-module-imports/-/helper-module-imports-7.25.9.tgz",
+      "integrity": "sha512-tnUA4RsrmflIM6W6RFTLFSXITtl0wKjgpnLgXyowocVPrbYrLUXSBXDgTs8BlbmIzIdlBySRQjINYs2BAkiLtw==",
+      "dependencies": {
+        "@babel/traverse": "^7.25.9",
+        "@babel/types": "^7.25.9"
+      },
+      "engines": {
+        "node": ">=6.9.0"
+      }
+    },
+    "node_modules/@babel/helper-string-parser": {
+      "version": "7.25.9",
+      "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.25.9.tgz",
+      "integrity": "sha512-4A/SCr/2KLd5jrtOMFzaKjVtAei3+2r/NChoBNoZ3EyP/+GlhoaEGoWOZUmFmoITP7zOJyHIMm+DYRd8o3PvHA==",
+      "engines": {
+        "node": ">=6.9.0"
+      }
+    },
+    "node_modules/@babel/helper-validator-identifier": {
+      "version": "7.25.9",
+      "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.25.9.tgz",
+      "integrity": "sha512-Ed61U6XJc3CVRfkERJWDz4dJwKe7iLmmJsbOGu9wSloNSFttHV0I8g6UAgb7qnK5ly5bGLPd4oXZlxCdANBOWQ==",
+      "engines": {
+        "node": ">=6.9.0"
+      }
+    },
+    "node_modules/@babel/parser": {
+      "version": "7.26.3",
+      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.26.3.tgz",
+      "integrity": "sha512-WJ/CvmY8Mea8iDXo6a7RK2wbmJITT5fN3BEkRuFlxVyNx8jOKIIhmC4fSkTcPcf8JyavbBwIe6OpiCOBXt/IcA==",
+      "dependencies": {
+        "@babel/types": "^7.26.3"
+      },
+      "bin": {
+        "parser": "bin/babel-parser.js"
+      },
+      "engines": {
+        "node": ">=6.0.0"
+      }
+    },
+    "node_modules/@babel/runtime": {
+      "version": "7.26.0",
+      "resolved": "https://registry.npmjs.org/@babel/runtime/-/runtime-7.26.0.tgz",
+      "integrity": "sha512-FDSOghenHTiToteC/QRlv2q3DhPZ/oOXTBoirfWNx1Cx3TMVcGWQtMMmQcSvb/JjpNeGzx8Pq/b4fKEJuWm1sw==",
+      "dependencies": {
+        "regenerator-runtime": "^0.14.0"
+      },
+      "engines": {
+        "node": ">=6.9.0"
+      }
+    },
+    "node_modules/@babel/template": {
+      "version": "7.25.9",
+      "resolved": "https://registry.npmjs.org/@babel/template/-/template-7.25.9.tgz",
+      "integrity": "sha512-9DGttpmPvIxBb/2uwpVo3dqJ+O6RooAFOS+lB+xDqoE2PVCE8nfoHMdZLpfCQRLwvohzXISPZcgxt80xLfsuwg==",
+      "dependencies": {
+        "@babel/code-frame": "^7.25.9",
+        "@babel/parser": "^7.25.9",
+        "@babel/types": "^7.25.9"
+      },
+      "engines": {
+        "node": ">=6.9.0"
+      }
+    },
+    "node_modules/@babel/traverse": {
+      "version": "7.26.4",
+      "resolved": "https://registry.npmjs.org/@babel/traverse/-/traverse-7.26.4.tgz",
+      "integrity": "sha512-fH+b7Y4p3yqvApJALCPJcwb0/XaOSgtK4pzV6WVjPR5GLFQBRI7pfoX2V2iM48NXvX07NUxxm1Vw98YjqTcU5w==",
+      "dependencies": {
+        "@babel/code-frame": "^7.26.2",
+        "@babel/generator": "^7.26.3",
+        "@babel/parser": "^7.26.3",
+        "@babel/template": "^7.25.9",
+        "@babel/types": "^7.26.3",
+        "debug": "^4.3.1",
+        "globals": "^11.1.0"
+      },
+      "engines": {
+        "node": ">=6.9.0"
+      }
+    },
+    "node_modules/@babel/types": {
+      "version": "7.26.3",
+      "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.26.3.tgz",
+      "integrity": "sha512-vN5p+1kl59GVKMvTHt55NzzmYVxprfJD+ql7U9NFIfKCBkYE55LYtS+WtPlaYOyzydrKI8Nezd+aZextrd+FMA==",
+      "dependencies": {
+        "@babel/helper-string-parser": "^7.25.9",
+        "@babel/helper-validator-identifier": "^7.25.9"
+      },
+      "engines": {
+        "node": ">=6.9.0"
+      }
+    },
+    "node_modules/@emotion/babel-plugin": {
+      "version": "11.13.5",
+      "resolved": "https://registry.npmjs.org/@emotion/babel-plugin/-/babel-plugin-11.13.5.tgz",
+      "integrity": "sha512-pxHCpT2ex+0q+HH91/zsdHkw/lXd468DIN2zvfvLtPKLLMo6gQj7oLObq8PhkrxOZb/gGCq03S3Z7PDhS8pduQ==",
+      "dependencies": {
+        "@babel/helper-module-imports": "^7.16.7",
+        "@babel/runtime": "^7.18.3",
+        "@emotion/hash": "^0.9.2",
+        "@emotion/memoize": "^0.9.0",
+        "@emotion/serialize": "^1.3.3",
+        "babel-plugin-macros": "^3.1.0",
+        "convert-source-map": "^1.5.0",
+        "escape-string-regexp": "^4.0.0",
+        "find-root": "^1.1.0",
+        "source-map": "^0.5.7",
+        "stylis": "4.2.0"
+      }
+    },
+    "node_modules/@emotion/cache": {
+      "version": "11.14.0",
+      "resolved": "https://registry.npmjs.org/@emotion/cache/-/cache-11.14.0.tgz",
+      "integrity": "sha512-L/B1lc/TViYk4DcpGxtAVbx0ZyiKM5ktoIyafGkH6zg/tj+mA+NE//aPYKG0k8kCHSHVJrpLpcAlOBEXQ3SavA==",
+      "dependencies": {
+        "@emotion/memoize": "^0.9.0",
+        "@emotion/sheet": "^1.4.0",
+        "@emotion/utils": "^1.4.2",
+        "@emotion/weak-memoize": "^0.4.0",
+        "stylis": "4.2.0"
+      }
+    },
+    "node_modules/@emotion/hash": {
+      "version": "0.9.2",
+      "resolved": "https://registry.npmjs.org/@emotion/hash/-/hash-0.9.2.tgz",
+      "integrity": "sha512-MyqliTZGuOm3+5ZRSaaBGP3USLw6+EGykkwZns2EPC5g8jJ4z9OrdZY9apkl3+UP9+sdz76YYkwCKP5gh8iY3g=="
+    },
+    "node_modules/@emotion/is-prop-valid": {
+      "version": "1.3.1",
+      "resolved": "https://registry.npmjs.org/@emotion/is-prop-valid/-/is-prop-valid-1.3.1.tgz",
+      "integrity": "sha512-/ACwoqx7XQi9knQs/G0qKvv5teDMhD7bXYns9N/wM8ah8iNb8jZ2uNO0YOgiq2o2poIvVtJS2YALasQuMSQ7Kw==",
+      "dependencies": {
+        "@emotion/memoize": "^0.9.0"
+      }
+    },
+    "node_modules/@emotion/memoize": {
+      "version": "0.9.0",
+      "resolved": "https://registry.npmjs.org/@emotion/memoize/-/memoize-0.9.0.tgz",
+      "integrity": "sha512-30FAj7/EoJ5mwVPOWhAyCX+FPfMDrVecJAM+Iw9NRoSl4BBAQeqj4cApHHUXOVvIPgLVDsCFoz/hGD+5QQD1GQ=="
+    },
+    "node_modules/@emotion/react": {
+      "version": "11.14.0",
+      "resolved": "https://registry.npmjs.org/@emotion/react/-/react-11.14.0.tgz",
+      "integrity": "sha512-O000MLDBDdk/EohJPFUqvnp4qnHeYkVP5B0xEG0D/L7cOKP9kefu2DXn8dj74cQfsEzUqh+sr1RzFqiL1o+PpA==",
+      "dependencies": {
+        "@babel/runtime": "^7.18.3",
+        "@emotion/babel-plugin": "^11.13.5",
+        "@emotion/cache": "^11.14.0",
+        "@emotion/serialize": "^1.3.3",
+        "@emotion/use-insertion-effect-with-fallbacks": "^1.2.0",
+        "@emotion/utils": "^1.4.2",
+        "@emotion/weak-memoize": "^0.4.0",
+        "hoist-non-react-statics": "^3.3.1"
+      },
+      "peerDependencies": {
+        "react": ">=16.8.0"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@emotion/serialize": {
+      "version": "1.3.3",
+      "resolved": "https://registry.npmjs.org/@emotion/serialize/-/serialize-1.3.3.tgz",
+      "integrity": "sha512-EISGqt7sSNWHGI76hC7x1CksiXPahbxEOrC5RjmFRJTqLyEK9/9hZvBbiYn70dw4wuwMKiEMCUlR6ZXTSWQqxA==",
+      "dependencies": {
+        "@emotion/hash": "^0.9.2",
+        "@emotion/memoize": "^0.9.0",
+        "@emotion/unitless": "^0.10.0",
+        "@emotion/utils": "^1.4.2",
+        "csstype": "^3.0.2"
+      }
+    },
+    "node_modules/@emotion/sheet": {
+      "version": "1.4.0",
+      "resolved": "https://registry.npmjs.org/@emotion/sheet/-/sheet-1.4.0.tgz",
+      "integrity": "sha512-fTBW9/8r2w3dXWYM4HCB1Rdp8NLibOw2+XELH5m5+AkWiL/KqYX6dc0kKYlaYyKjrQ6ds33MCdMPEwgs2z1rqg=="
+    },
+    "node_modules/@emotion/styled": {
+      "version": "11.14.0",
+      "resolved": "https://registry.npmjs.org/@emotion/styled/-/styled-11.14.0.tgz",
+      "integrity": "sha512-XxfOnXFffatap2IyCeJyNov3kiDQWoR08gPUQxvbL7fxKryGBKUZUkG6Hz48DZwVrJSVh9sJboyV1Ds4OW6SgA==",
+      "dependencies": {
+        "@babel/runtime": "^7.18.3",
+        "@emotion/babel-plugin": "^11.13.5",
+        "@emotion/is-prop-valid": "^1.3.0",
+        "@emotion/serialize": "^1.3.3",
+        "@emotion/use-insertion-effect-with-fallbacks": "^1.2.0",
+        "@emotion/utils": "^1.4.2"
+      },
+      "peerDependencies": {
+        "@emotion/react": "^11.0.0-rc.0",
+        "react": ">=16.8.0"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@emotion/unitless": {
+      "version": "0.10.0",
+      "resolved": "https://registry.npmjs.org/@emotion/unitless/-/unitless-0.10.0.tgz",
+      "integrity": "sha512-dFoMUuQA20zvtVTuxZww6OHoJYgrzfKM1t52mVySDJnMSEa08ruEvdYQbhvyu6soU+NeLVd3yKfTfT0NeV6qGg=="
+    },
+    "node_modules/@emotion/use-insertion-effect-with-fallbacks": {
+      "version": "1.2.0",
+      "resolved": "https://registry.npmjs.org/@emotion/use-insertion-effect-with-fallbacks/-/use-insertion-effect-with-fallbacks-1.2.0.tgz",
+      "integrity": "sha512-yJMtVdH59sxi/aVJBpk9FQq+OR8ll5GT8oWd57UpeaKEVGab41JWaCFA7FRLoMLloOZF/c/wsPoe+bfGmRKgDg==",
+      "peerDependencies": {
+        "react": ">=16.8.0"
+      }
+    },
+    "node_modules/@emotion/utils": {
+      "version": "1.4.2",
+      "resolved": "https://registry.npmjs.org/@emotion/utils/-/utils-1.4.2.tgz",
+      "integrity": "sha512-3vLclRofFziIa3J2wDh9jjbkUz9qk5Vi3IZ/FSTKViB0k+ef0fPV7dYrUIugbgupYDx7v9ud/SjrtEP8Y4xLoA=="
+    },
+    "node_modules/@emotion/weak-memoize": {
+      "version": "0.4.0",
+      "resolved": "https://registry.npmjs.org/@emotion/weak-memoize/-/weak-memoize-0.4.0.tgz",
+      "integrity": "sha512-snKqtPW01tN0ui7yu9rGv69aJXr/a/Ywvl11sUjNtEcRc+ng/mQriFL0wLXMef74iHa/EkftbDzU9F8iFbH+zg=="
+    },
+    "node_modules/@jridgewell/gen-mapping": {
+      "version": "0.3.8",
+      "resolved": "https://registry.npmjs.org/@jridgewell/gen-mapping/-/gen-mapping-0.3.8.tgz",
+      "integrity": "sha512-imAbBGkb+ebQyxKgzv5Hu2nmROxoDOXHh80evxdoXNOrvAnVx7zimzc1Oo5h9RlfV4vPXaE2iM5pOFbvOCClWA==",
+      "dependencies": {
+        "@jridgewell/set-array": "^1.2.1",
+        "@jridgewell/sourcemap-codec": "^1.4.10",
+        "@jridgewell/trace-mapping": "^0.3.24"
+      },
+      "engines": {
+        "node": ">=6.0.0"
+      }
+    },
+    "node_modules/@jridgewell/resolve-uri": {
+      "version": "3.1.2",
+      "resolved": "https://registry.npmjs.org/@jridgewell/resolve-uri/-/resolve-uri-3.1.2.tgz",
+      "integrity": "sha512-bRISgCIjP20/tbWSPWMEi54QVPRZExkuD9lJL+UIxUKtwVJA8wW1Trb1jMs1RFXo1CBTNZ/5hpC9QvmKWdopKw==",
+      "engines": {
+        "node": ">=6.0.0"
+      }
+    },
+    "node_modules/@jridgewell/set-array": {
+      "version": "1.2.1",
+      "resolved": "https://registry.npmjs.org/@jridgewell/set-array/-/set-array-1.2.1.tgz",
+      "integrity": "sha512-R8gLRTZeyp03ymzP/6Lil/28tGeGEzhx1q2k703KGWRAI1VdvPIXdG70VJc2pAMw3NA6JKL5hhFu1sJX0Mnn/A==",
+      "engines": {
+        "node": ">=6.0.0"
+      }
+    },
+    "node_modules/@jridgewell/sourcemap-codec": {
+      "version": "1.5.0",
+      "resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.5.0.tgz",
+      "integrity": "sha512-gv3ZRaISU3fjPAgNsriBRqGWQL6quFx04YMPW/zD8XMLsU32mhCCbfbO6KZFLjvYpCZ8zyDEgqsgf+PwPaM7GQ=="
+    },
+    "node_modules/@jridgewell/trace-mapping": {
+      "version": "0.3.25",
+      "resolved": "https://registry.npmjs.org/@jridgewell/trace-mapping/-/trace-mapping-0.3.25.tgz",
+      "integrity": "sha512-vNk6aEwybGtawWmy/PzwnGDOjCkLWSD2wqvjGGAgOAwCGWySYXfYoxt00IJkTF+8Lb57DwOb3Aa0o9CApepiYQ==",
+      "dependencies": {
+        "@jridgewell/resolve-uri": "^3.1.0",
+        "@jridgewell/sourcemap-codec": "^1.4.14"
+      }
+    },
+    "node_modules/@mui/core-downloads-tracker": {
+      "version": "6.3.1",
+      "resolved": "https://registry.npmjs.org/@mui/core-downloads-tracker/-/core-downloads-tracker-6.3.1.tgz",
+      "integrity": "sha512-2OmnEyoHpj5//dJJpMuxOeLItCCHdf99pjMFfUFdBteCunAK9jW+PwEo4mtdGcLs7P+IgZ+85ypd52eY4AigoQ==",
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/mui-org"
+      }
+    },
+    "node_modules/@mui/material": {
+      "version": "6.3.1",
+      "resolved": "https://registry.npmjs.org/@mui/material/-/material-6.3.1.tgz",
+      "integrity": "sha512-ynG9ayhxgCsHJ/dtDcT1v78/r2GwQyP3E0hPz3GdPRl0uFJz/uUTtI5KFYwadXmbC+Uv3bfB8laZ6+Cpzh03gA==",
+      "dependencies": {
+        "@babel/runtime": "^7.26.0",
+        "@mui/core-downloads-tracker": "^6.3.1",
+        "@mui/system": "^6.3.1",
+        "@mui/types": "^7.2.21",
+        "@mui/utils": "^6.3.1",
+        "@popperjs/core": "^2.11.8",
+        "@types/react-transition-group": "^4.4.12",
+        "clsx": "^2.1.1",
+        "csstype": "^3.1.3",
+        "prop-types": "^15.8.1",
+        "react-is": "^19.0.0",
+        "react-transition-group": "^4.4.5"
+      },
+      "engines": {
+        "node": ">=14.0.0"
+      },
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/mui-org"
+      },
+      "peerDependencies": {
+        "@emotion/react": "^11.5.0",
+        "@emotion/styled": "^11.3.0",
+        "@mui/material-pigment-css": "^6.3.1",
+        "@types/react": "^17.0.0 || ^18.0.0 || ^19.0.0",
+        "react": "^17.0.0 || ^18.0.0 || ^19.0.0",
+        "react-dom": "^17.0.0 || ^18.0.0 || ^19.0.0"
+      },
+      "peerDependenciesMeta": {
+        "@emotion/react": {
+          "optional": true
+        },
+        "@emotion/styled": {
+          "optional": true
+        },
+        "@mui/material-pigment-css": {
+          "optional": true
+        },
+        "@types/react": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@mui/private-theming": {
+      "version": "6.3.1",
+      "resolved": "https://registry.npmjs.org/@mui/private-theming/-/private-theming-6.3.1.tgz",
+      "integrity": "sha512-g0u7hIUkmXmmrmmf5gdDYv9zdAig0KoxhIQn1JN8IVqApzf/AyRhH3uDGx5mSvs8+a1zb4+0W6LC260SyTTtdQ==",
+      "dependencies": {
+        "@babel/runtime": "^7.26.0",
+        "@mui/utils": "^6.3.1",
+        "prop-types": "^15.8.1"
+      },
+      "engines": {
+        "node": ">=14.0.0"
+      },
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/mui-org"
+      },
+      "peerDependencies": {
+        "@types/react": "^17.0.0 || ^18.0.0 || ^19.0.0",
+        "react": "^17.0.0 || ^18.0.0 || ^19.0.0"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@mui/styled-engine": {
+      "version": "6.3.1",
+      "resolved": "https://registry.npmjs.org/@mui/styled-engine/-/styled-engine-6.3.1.tgz",
+      "integrity": "sha512-/7CC0d2fIeiUxN5kCCwYu4AWUDd9cCTxWCyo0v/Rnv6s8uk6hWgJC3VLZBoDENBHf/KjqDZuYJ2CR+7hD6QYww==",
+      "dependencies": {
+        "@babel/runtime": "^7.26.0",
+        "@emotion/cache": "^11.13.5",
+        "@emotion/serialize": "^1.3.3",
+        "@emotion/sheet": "^1.4.0",
+        "csstype": "^3.1.3",
+        "prop-types": "^15.8.1"
+      },
+      "engines": {
+        "node": ">=14.0.0"
+      },
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/mui-org"
+      },
+      "peerDependencies": {
+        "@emotion/react": "^11.4.1",
+        "@emotion/styled": "^11.3.0",
+        "react": "^17.0.0 || ^18.0.0 || ^19.0.0"
+      },
+      "peerDependenciesMeta": {
+        "@emotion/react": {
+          "optional": true
+        },
+        "@emotion/styled": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@mui/system": {
+      "version": "6.3.1",
+      "resolved": "https://registry.npmjs.org/@mui/system/-/system-6.3.1.tgz",
+      "integrity": "sha512-AwqQ3EAIT2np85ki+N15fF0lFXX1iFPqenCzVOSl3QXKy2eifZeGd9dGtt7pGMoFw5dzW4dRGGzRpLAq9rkl7A==",
+      "dependencies": {
+        "@babel/runtime": "^7.26.0",
+        "@mui/private-theming": "^6.3.1",
+        "@mui/styled-engine": "^6.3.1",
+        "@mui/types": "^7.2.21",
+        "@mui/utils": "^6.3.1",
+        "clsx": "^2.1.1",
+        "csstype": "^3.1.3",
+        "prop-types": "^15.8.1"
+      },
+      "engines": {
+        "node": ">=14.0.0"
+      },
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/mui-org"
+      },
+      "peerDependencies": {
+        "@emotion/react": "^11.5.0",
+        "@emotion/styled": "^11.3.0",
+        "@types/react": "^17.0.0 || ^18.0.0 || ^19.0.0",
+        "react": "^17.0.0 || ^18.0.0 || ^19.0.0"
+      },
+      "peerDependenciesMeta": {
+        "@emotion/react": {
+          "optional": true
+        },
+        "@emotion/styled": {
+          "optional": true
+        },
+        "@types/react": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@mui/types": {
+      "version": "7.2.21",
+      "resolved": "https://registry.npmjs.org/@mui/types/-/types-7.2.21.tgz",
+      "integrity": "sha512-6HstngiUxNqLU+/DPqlUJDIPbzUBxIVHb1MmXP0eTWDIROiCR2viugXpEif0PPe2mLqqakPzzRClWAnK+8UJww==",
+      "peerDependencies": {
+        "@types/react": "^17.0.0 || ^18.0.0 || ^19.0.0"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@mui/utils": {
+      "version": "6.3.1",
+      "resolved": "https://registry.npmjs.org/@mui/utils/-/utils-6.3.1.tgz",
+      "integrity": "sha512-sjGjXAngoio6lniQZKJ5zGfjm+LD2wvLwco7FbKe1fu8A7VIFmz2SwkLb+MDPLNX1lE7IscvNNyh1pobtZg2tw==",
+      "dependencies": {
+        "@babel/runtime": "^7.26.0",
+        "@mui/types": "^7.2.21",
+        "@types/prop-types": "^15.7.14",
+        "clsx": "^2.1.1",
+        "prop-types": "^15.8.1",
+        "react-is": "^19.0.0"
+      },
+      "engines": {
+        "node": ">=14.0.0"
+      },
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/mui-org"
+      },
+      "peerDependencies": {
+        "@types/react": "^17.0.0 || ^18.0.0 || ^19.0.0",
+        "react": "^17.0.0 || ^18.0.0 || ^19.0.0"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/@popperjs/core": {
+      "version": "2.11.8",
+      "resolved": "https://registry.npmjs.org/@popperjs/core/-/core-2.11.8.tgz",
+      "integrity": "sha512-P1st0aksCrn9sGZhp8GMYwBnQsbvAWsZAX44oXNNvLHGqAOcoVxmjZiohstwQ7SqKnbR47akdNi+uleWD8+g6A==",
+      "funding": {
+        "type": "opencollective",
+        "url": "https://opencollective.com/popperjs"
+      }
+    },
+    "node_modules/@types/parse-json": {
+      "version": "4.0.2",
+      "resolved": "https://registry.npmjs.org/@types/parse-json/-/parse-json-4.0.2.tgz",
+      "integrity": "sha512-dISoDXWWQwUquiKsyZ4Ng+HX2KsPL7LyHKHQwgGFEA3IaKac4Obd+h2a/a6waisAoepJlBcx9paWqjA8/HVjCw=="
+    },
+    "node_modules/@types/prop-types": {
+      "version": "15.7.14",
+      "resolved": "https://registry.npmjs.org/@types/prop-types/-/prop-types-15.7.14.tgz",
+      "integrity": "sha512-gNMvNH49DJ7OJYv+KAKn0Xp45p8PLl6zo2YnvDIbTd4J6MER2BmWN49TG7n9LvkyihINxeKW8+3bfS2yDC9dzQ=="
+    },
+    "node_modules/@types/react": {
+      "version": "19.0.2",
+      "resolved": "https://registry.npmjs.org/@types/react/-/react-19.0.2.tgz",
+      "integrity": "sha512-USU8ZI/xyKJwFTpjSVIrSeHBVAGagkHQKPNbxeWwql/vDmnTIBgx+TJnhFnj1NXgz8XfprU0egV2dROLGpsBEg==",
+      "peer": true,
+      "dependencies": {
+        "csstype": "^3.0.2"
+      }
+    },
+    "node_modules/@types/react-transition-group": {
+      "version": "4.4.12",
+      "resolved": "https://registry.npmjs.org/@types/react-transition-group/-/react-transition-group-4.4.12.tgz",
+      "integrity": "sha512-8TV6R3h2j7a91c+1DXdJi3Syo69zzIZbz7Lg5tORM5LEJG7X/E6a1V3drRyBRZq7/utz7A+c4OgYLiLcYGHG6w==",
+      "peerDependencies": {
+        "@types/react": "*"
+      }
+    },
+    "node_modules/babel-plugin-macros": {
+      "version": "3.1.0",
+      "resolved": "https://registry.npmjs.org/babel-plugin-macros/-/babel-plugin-macros-3.1.0.tgz",
+      "integrity": "sha512-Cg7TFGpIr01vOQNODXOOaGz2NpCU5gl8x1qJFbb6hbZxR7XrcE2vtbAsTAbJ7/xwJtUuJEw8K8Zr/AE0LHlesg==",
+      "dependencies": {
+        "@babel/runtime": "^7.12.5",
+        "cosmiconfig": "^7.0.0",
+        "resolve": "^1.19.0"
+      },
+      "engines": {
+        "node": ">=10",
+        "npm": ">=6"
+      }
+    },
+    "node_modules/callsites": {
+      "version": "3.1.0",
+      "resolved": "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz",
+      "integrity": "sha512-P8BjAsXvZS+VIDUI11hHCQEv74YT67YUi5JJFNWIqL235sBmjX4+qx9Muvls5ivyNENctx46xQLQ3aTuE7ssaQ==",
+      "engines": {
+        "node": ">=6"
+      }
+    },
+    "node_modules/clsx": {
+      "version": "2.1.1",
+      "resolved": "https://registry.npmjs.org/clsx/-/clsx-2.1.1.tgz",
+      "integrity": "sha512-eYm0QWBtUrBWZWG0d386OGAw16Z995PiOVo2B7bjWSbHedGl5e0ZWaq65kOGgUSNesEIDkB9ISbTg/JK9dhCZA==",
+      "engines": {
+        "node": ">=6"
+      }
+    },
+    "node_modules/convert-source-map": {
+      "version": "1.9.0",
+      "resolved": "https://registry.npmjs.org/convert-source-map/-/convert-source-map-1.9.0.tgz",
+      "integrity": "sha512-ASFBup0Mz1uyiIjANan1jzLQami9z1PoYSZCiiYW2FczPbenXc45FZdBZLzOT+r6+iciuEModtmCti+hjaAk0A=="
+    },
+    "node_modules/cosmiconfig": {
+      "version": "7.1.0",
+      "resolved": "https://registry.npmjs.org/cosmiconfig/-/cosmiconfig-7.1.0.tgz",
+      "integrity": "sha512-AdmX6xUzdNASswsFtmwSt7Vj8po9IuqXm0UXz7QKPuEUmPB4XyjGfaAr2PSuELMwkRMVH1EpIkX5bTZGRB3eCA==",
+      "dependencies": {
+        "@types/parse-json": "^4.0.0",
+        "import-fresh": "^3.2.1",
+        "parse-json": "^5.0.0",
+        "path-type": "^4.0.0",
+        "yaml": "^1.10.0"
+      },
+      "engines": {
+        "node": ">=10"
+      }
+    },
+    "node_modules/csstype": {
+      "version": "3.1.3",
+      "resolved": "https://registry.npmjs.org/csstype/-/csstype-3.1.3.tgz",
+      "integrity": "sha512-M1uQkMl8rQK/szD0LNhtqxIPLpimGm8sOBwU7lLnCpSbTyY3yeU1Vc7l4KT5zT4s/yOxHH5O7tIuuLOCnLADRw=="
+    },
+    "node_modules/debug": {
+      "version": "4.4.0",
+      "resolved": "https://registry.npmjs.org/debug/-/debug-4.4.0.tgz",
+      "integrity": "sha512-6WTZ/IxCY/T6BALoZHaE4ctp9xm+Z5kY/pzYaCHRFeyVhojxlrm+46y68HA6hr0TcwEssoxNiDEUJQjfPZ/RYA==",
+      "dependencies": {
+        "ms": "^2.1.3"
+      },
+      "engines": {
+        "node": ">=6.0"
+      },
+      "peerDependenciesMeta": {
+        "supports-color": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/dom-helpers": {
+      "version": "5.2.1",
+      "resolved": "https://registry.npmjs.org/dom-helpers/-/dom-helpers-5.2.1.tgz",
+      "integrity": "sha512-nRCa7CK3VTrM2NmGkIy4cbK7IZlgBE/PYMn55rrXefr5xXDP0LdtfPnblFDoVdcAfslJ7or6iqAUnx0CCGIWQA==",
+      "dependencies": {
+        "@babel/runtime": "^7.8.7",
+        "csstype": "^3.0.2"
+      }
+    },
+    "node_modules/error-ex": {
+      "version": "1.3.2",
+      "resolved": "https://registry.npmjs.org/error-ex/-/error-ex-1.3.2.tgz",
+      "integrity": "sha512-7dFHNmqeFSEt2ZBsCriorKnn3Z2pj+fd9kmI6QoWw4//DL+icEBfc0U7qJCisqrTsKTjw4fNFy2pW9OqStD84g==",
+      "dependencies": {
+        "is-arrayish": "^0.2.1"
+      }
+    },
+    "node_modules/escape-string-regexp": {
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/escape-string-regexp/-/escape-string-regexp-4.0.0.tgz",
+      "integrity": "sha512-TtpcNJ3XAzx3Gq8sWRzJaVajRs0uVxA2YAkdb1jm2YkPz4G6egUFAyA3n5vtEIZefPk5Wa4UXbKuS5fKkJWdgA==",
+      "engines": {
+        "node": ">=10"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
+    "node_modules/find-root": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/find-root/-/find-root-1.1.0.tgz",
+      "integrity": "sha512-NKfW6bec6GfKc0SGx1e07QZY9PE99u0Bft/0rzSD5k3sO/vwkVUpDUKVm5Gpp5Ue3YfShPFTX2070tDs5kB9Ng=="
+    },
+    "node_modules/function-bind": {
+      "version": "1.1.2",
+      "resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
+      "integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==",
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/globals": {
+      "version": "11.12.0",
+      "resolved": "https://registry.npmjs.org/globals/-/globals-11.12.0.tgz",
+      "integrity": "sha512-WOBp/EEGUiIsJSp7wcv/y6MO+lV9UoncWqxuFfm8eBwzWNgyfBd6Gz+IeKQ9jCmyhoH99g15M3T+QaVHFjizVA==",
+      "engines": {
+        "node": ">=4"
+      }
+    },
+    "node_modules/hasown": {
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz",
+      "integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==",
+      "dependencies": {
+        "function-bind": "^1.1.2"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
+    "node_modules/hoist-non-react-statics": {
+      "version": "3.3.2",
+      "resolved": "https://registry.npmjs.org/hoist-non-react-statics/-/hoist-non-react-statics-3.3.2.tgz",
+      "integrity": "sha512-/gGivxi8JPKWNm/W0jSmzcMPpfpPLc3dY/6GxhX2hQ9iGj3aDfklV4ET7NjKpSinLpJ5vafa9iiGIEZg10SfBw==",
+      "dependencies": {
+        "react-is": "^16.7.0"
+      }
+    },
+    "node_modules/hoist-non-react-statics/node_modules/react-is": {
+      "version": "16.13.1",
+      "resolved": "https://registry.npmjs.org/react-is/-/react-is-16.13.1.tgz",
+      "integrity": "sha512-24e6ynE2H+OKt4kqsOvNd8kBpV65zoxbA4BVsEOB3ARVWQki/DHzaUoC5KuON/BiccDaCCTZBuOcfZs70kR8bQ=="
+    },
+    "node_modules/import-fresh": {
+      "version": "3.3.0",
+      "resolved": "https://registry.npmjs.org/import-fresh/-/import-fresh-3.3.0.tgz",
+      "integrity": "sha512-veYYhQa+D1QBKznvhUHxb8faxlrwUnxseDAbAp457E0wLNio2bOSKnjYDhMj+YiAq61xrMGhQk9iXVk5FzgQMw==",
+      "dependencies": {
+        "parent-module": "^1.0.0",
+        "resolve-from": "^4.0.0"
+      },
+      "engines": {
+        "node": ">=6"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
+    "node_modules/is-arrayish": {
+      "version": "0.2.1",
+      "resolved": "https://registry.npmjs.org/is-arrayish/-/is-arrayish-0.2.1.tgz",
+      "integrity": "sha512-zz06S8t0ozoDXMG+ube26zeCTNXcKIPJZJi8hBrF4idCLms4CG9QtK7qBl1boi5ODzFpjswb5JPmHCbMpjaYzg=="
+    },
+    "node_modules/is-core-module": {
+      "version": "2.16.1",
+      "resolved": "https://registry.npmjs.org/is-core-module/-/is-core-module-2.16.1.tgz",
+      "integrity": "sha512-UfoeMA6fIJ8wTYFEUjelnaGI67v6+N7qXJEvQuIGa99l4xsCruSYOVSQ0uPANn4dAzm8lkYPaKLrrijLq7x23w==",
+      "dependencies": {
+        "hasown": "^2.0.2"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/js-tokens": {
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-4.0.0.tgz",
+      "integrity": "sha512-RdJUflcE3cUzKiMqQgsCu06FPu9UdIJO0beYbPhHN4k6apgJtifcoCtT9bcxOpYBtpD2kCM6Sbzg4CausW/PKQ=="
+    },
+    "node_modules/jsesc": {
+      "version": "3.1.0",
+      "resolved": "https://registry.npmjs.org/jsesc/-/jsesc-3.1.0.tgz",
+      "integrity": "sha512-/sM3dO2FOzXjKQhJuo0Q173wf2KOo8t4I8vHy6lF9poUp7bKT0/NHE8fPX23PwfhnykfqnC2xRxOnVw5XuGIaA==",
+      "bin": {
+        "jsesc": "bin/jsesc"
+      },
+      "engines": {
+        "node": ">=6"
+      }
+    },
+    "node_modules/json-parse-even-better-errors": {
+      "version": "2.3.1",
+      "resolved": "https://registry.npmjs.org/json-parse-even-better-errors/-/json-parse-even-better-errors-2.3.1.tgz",
+      "integrity": "sha512-xyFwyhro/JEof6Ghe2iz2NcXoj2sloNsWr/XsERDK/oiPCfaNhl5ONfp+jQdAZRQQ0IJWNzH9zIZF7li91kh2w=="
+    },
+    "node_modules/lines-and-columns": {
+      "version": "1.2.4",
+      "resolved": "https://registry.npmjs.org/lines-and-columns/-/lines-and-columns-1.2.4.tgz",
+      "integrity": "sha512-7ylylesZQ/PV29jhEDl3Ufjo6ZX7gCqJr5F7PKrqc93v7fzSymt1BpwEU8nAUXs8qzzvqhbjhK5QZg6Mt/HkBg=="
+    },
+    "node_modules/loose-envify": {
+      "version": "1.4.0",
+      "resolved": "https://registry.npmjs.org/loose-envify/-/loose-envify-1.4.0.tgz",
+      "integrity": "sha512-lyuxPGr/Wfhrlem2CL/UcnUc1zcqKAImBDzukY7Y5F/yQiNdko6+fRLevlw1HgMySw7f611UIY408EtxRSoK3Q==",
+      "dependencies": {
+        "js-tokens": "^3.0.0 || ^4.0.0"
+      },
+      "bin": {
+        "loose-envify": "cli.js"
+      }
+    },
+    "node_modules/ms": {
+      "version": "2.1.3",
+      "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
+      "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA=="
+    },
+    "node_modules/object-assign": {
+      "version": "4.1.1",
+      "resolved": "https://registry.npmjs.org/object-assign/-/object-assign-4.1.1.tgz",
+      "integrity": "sha512-rJgTQnkUnH1sFw8yT6VSU3zD3sWmu6sZhIseY8VX+GRu3P6F7Fu+JNDoXfklElbLJSnc3FUQHVe4cU5hj+BcUg==",
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
+    "node_modules/parent-module": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/parent-module/-/parent-module-1.0.1.tgz",
+      "integrity": "sha512-GQ2EWRpQV8/o+Aw8YqtfZZPfNRWZYkbidE9k5rpl/hC3vtHHBfGm2Ifi6qWV+coDGkrUKZAxE3Lot5kcsRlh+g==",
+      "dependencies": {
+        "callsites": "^3.0.0"
+      },
+      "engines": {
+        "node": ">=6"
+      }
+    },
+    "node_modules/parse-json": {
+      "version": "5.2.0",
+      "resolved": "https://registry.npmjs.org/parse-json/-/parse-json-5.2.0.tgz",
+      "integrity": "sha512-ayCKvm/phCGxOkYRSCM82iDwct8/EonSEgCSxWxD7ve6jHggsFl4fZVQBPRNgQoKiuV/odhFrGzQXZwbifC8Rg==",
+      "dependencies": {
+        "@babel/code-frame": "^7.0.0",
+        "error-ex": "^1.3.1",
+        "json-parse-even-better-errors": "^2.3.0",
+        "lines-and-columns": "^1.1.6"
+      },
+      "engines": {
+        "node": ">=8"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/sindresorhus"
+      }
+    },
+    "node_modules/path-parse": {
+      "version": "1.0.7",
+      "resolved": "https://registry.npmjs.org/path-parse/-/path-parse-1.0.7.tgz",
+      "integrity": "sha512-LDJzPVEEEPR+y48z93A0Ed0yXb8pAByGWo/k5YYdYgpY2/2EsOsksJrq7lOHxryrVOn1ejG6oAp8ahvOIQD8sw=="
+    },
+    "node_modules/path-type": {
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/path-type/-/path-type-4.0.0.tgz",
+      "integrity": "sha512-gDKb8aZMDeD/tZWs9P6+q0J9Mwkdl6xMV8TjnGP3qJVJ06bdMgkbBlLU8IdfOsIsFz2BW1rNVT3XuNEl8zPAvw==",
+      "engines": {
+        "node": ">=8"
+      }
+    },
+    "node_modules/picocolors": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz",
+      "integrity": "sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA=="
+    },
+    "node_modules/prop-types": {
+      "version": "15.8.1",
+      "resolved": "https://registry.npmjs.org/prop-types/-/prop-types-15.8.1.tgz",
+      "integrity": "sha512-oj87CgZICdulUohogVAR7AjlC0327U4el4L6eAvOqCeudMDVU0NThNaV+b9Df4dXgSP1gXMTnPdhfe/2qDH5cg==",
+      "dependencies": {
+        "loose-envify": "^1.4.0",
+        "object-assign": "^4.1.1",
+        "react-is": "^16.13.1"
+      }
+    },
+    "node_modules/prop-types/node_modules/react-is": {
+      "version": "16.13.1",
+      "resolved": "https://registry.npmjs.org/react-is/-/react-is-16.13.1.tgz",
+      "integrity": "sha512-24e6ynE2H+OKt4kqsOvNd8kBpV65zoxbA4BVsEOB3ARVWQki/DHzaUoC5KuON/BiccDaCCTZBuOcfZs70kR8bQ=="
+    },
+    "node_modules/react": {
+      "version": "19.0.0",
+      "resolved": "https://registry.npmjs.org/react/-/react-19.0.0.tgz",
+      "integrity": "sha512-V8AVnmPIICiWpGfm6GLzCR/W5FXLchHop40W4nXBmdlEceh16rCN8O8LNWm5bh5XUX91fh7KpA+W0TgMKmgTpQ==",
+      "peer": true,
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
+    "node_modules/react-dom": {
+      "version": "19.0.0",
+      "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.0.0.tgz",
+      "integrity": "sha512-4GV5sHFG0e/0AD4X+ySy6UJd3jVl1iNsNHdpad0qhABJ11twS3TTBnseqsKurKcsNqCEFeGL3uLpVChpIO3QfQ==",
+      "peer": true,
+      "dependencies": {
+        "scheduler": "^0.25.0"
+      },
+      "peerDependencies": {
+        "react": "^19.0.0"
+      }
+    },
+    "node_modules/react-is": {
+      "version": "19.0.0",
+      "resolved": "https://registry.npmjs.org/react-is/-/react-is-19.0.0.tgz",
+      "integrity": "sha512-H91OHcwjZsbq3ClIDHMzBShc1rotbfACdWENsmEf0IFvZ3FgGPtdHMcsv45bQ1hAbgdfiA8SnxTKfDS+x/8m2g=="
+    },
+    "node_modules/react-transition-group": {
+      "version": "4.4.5",
+      "resolved": "https://registry.npmjs.org/react-transition-group/-/react-transition-group-4.4.5.tgz",
+      "integrity": "sha512-pZcd1MCJoiKiBR2NRxeCRg13uCXbydPnmB4EOeRrY7480qNWO8IIgQG6zlDkm6uRMsURXPuKq0GWtiM59a5Q6g==",
+      "dependencies": {
+        "@babel/runtime": "^7.5.5",
+        "dom-helpers": "^5.0.1",
+        "loose-envify": "^1.4.0",
+        "prop-types": "^15.6.2"
+      },
+      "peerDependencies": {
+        "react": ">=16.6.0",
+        "react-dom": ">=16.6.0"
+      }
+    },
+    "node_modules/regenerator-runtime": {
+      "version": "0.14.1",
+      "resolved": "https://registry.npmjs.org/regenerator-runtime/-/regenerator-runtime-0.14.1.tgz",
+      "integrity": "sha512-dYnhHh0nJoMfnkZs6GmmhFknAGRrLznOu5nc9ML+EJxGvrx6H7teuevqVqCuPcPK//3eDrrjQhehXVx9cnkGdw=="
+    },
+    "node_modules/resolve": {
+      "version": "1.22.10",
+      "resolved": "https://registry.npmjs.org/resolve/-/resolve-1.22.10.tgz",
+      "integrity": "sha512-NPRy+/ncIMeDlTAsuqwKIiferiawhefFJtkNSW0qZJEqMEb+qBt/77B/jGeeek+F0uOeN05CDa6HXbbIgtVX4w==",
+      "dependencies": {
+        "is-core-module": "^2.16.0",
+        "path-parse": "^1.0.7",
+        "supports-preserve-symlinks-flag": "^1.0.0"
+      },
+      "bin": {
+        "resolve": "bin/resolve"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/resolve-from": {
+      "version": "4.0.0",
+      "resolved": "https://registry.npmjs.org/resolve-from/-/resolve-from-4.0.0.tgz",
+      "integrity": "sha512-pb/MYmXstAkysRFx8piNI1tGFNQIFA3vkE3Gq4EuA1dF6gHp/+vgZqsCGJapvy8N3Q+4o7FwvquPJcnZ7RYy4g==",
+      "engines": {
+        "node": ">=4"
+      }
+    },
+    "node_modules/scheduler": {
+      "version": "0.25.0",
+      "resolved": "https://registry.npmjs.org/scheduler/-/scheduler-0.25.0.tgz",
+      "integrity": "sha512-xFVuu11jh+xcO7JOAGJNOXld8/TcEHK/4CituBUeUb5hqxJLj9YuemAEuvm9gQ/+pgXYfbQuqAkiYu+u7YEsNA==",
+      "peer": true
+    },
+    "node_modules/source-map": {
+      "version": "0.5.7",
+      "resolved": "https://registry.npmjs.org/source-map/-/source-map-0.5.7.tgz",
+      "integrity": "sha512-LbrmJOMUSdEVxIKvdcJzQC+nQhe8FUZQTXQy6+I75skNgn3OoQ0DZA8YnFa7gp8tqtL3KPf1kmo0R5DoApeSGQ==",
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
+    "node_modules/stylis": {
+      "version": "4.2.0",
+      "resolved": "https://registry.npmjs.org/stylis/-/stylis-4.2.0.tgz",
+      "integrity": "sha512-Orov6g6BB1sDfYgzWfTHDOxamtX1bE/zo104Dh9e6fqJ3PooipYyfJ0pUmrZO2wAvO8YbEyeFrkV91XTsGMSrw=="
+    },
+    "node_modules/supports-preserve-symlinks-flag": {
+      "version": "1.0.0",
+      "resolved": "https://registry.npmjs.org/supports-preserve-symlinks-flag/-/supports-preserve-symlinks-flag-1.0.0.tgz",
+      "integrity": "sha512-ot0WnXS9fgdkgIcePe6RHNk1WA8+muPa6cSjeR3V8K27q9BB1rTE3R1p7Hv0z1ZyAc8s6Vvv8DIyWf681MAt0w==",
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/yaml": {
+      "version": "1.10.2",
+      "resolved": "https://registry.npmjs.org/yaml/-/yaml-1.10.2.tgz",
+      "integrity": "sha512-r3vXyErRCYJ7wg28yvBY5VSoAF8ZvlcW9/BwUzEtUsjvX/DKs24dIkuwjtuprwJJHsbyUbLApepYTR1BN4uHrg==",
+      "engines": {
+        "node": ">= 6"
+      }
+    }
+  }
+}

api/package.json

@@ -0,0 +1,7 @@
+{
+  "dependencies": {
+    "@emotion/react": "^11.14.0",
+    "@emotion/styled": "^11.14.0",
+    "@mui/material": "^6.3.1"
+  }
+}

app.py

@@ -0,0 +1,124 @@
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+import pandas as pd
+import sys
+import os
+
+# Add parent directory to path for imports
+sys.path.append(os.path.dirname(os.path.abspath(__file__)))
+from generate_recommendations import RecommendationGenerator
+
+app = Flask(__name__)
+CORS(app, resources={r"/*": {"origins": "*"}}, supports_credentials=True)
+# # Load allowed origins from environment variable
+# allowed_origins = os.environ.get("ALLOWED_ORIGINS", "http://localhost:3000").split(",")
+# CORS(app, resources={r"/*": {"origins": allowed_origins}}, supports_credentials=True)
+# print("CORS is configured with allowed origins:", allowed_origins)
+
+# Setup paths relative to the project structure
+ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
+MODEL_PATH = os.path.join(ROOT_DIR, 'checkpoints', 'best_model.pth')
+DATA_PATH = os.path.join(ROOT_DIR, 'data', 'test_data.csv')
+ENCODERS_PATH = os.path.join(ROOT_DIR, 'data', 'data_encoders.pt')
+
+print(f"Root directory: {ROOT_DIR}")
+print(f"Model path: {MODEL_PATH}")
+print(f"Data path: {DATA_PATH}")
+print(f"Encoders path: {ENCODERS_PATH}")
+
+# Initialize model and data
+try:
+    if not os.path.exists(MODEL_PATH):
+        raise FileNotFoundError(f"Model file not found at {MODEL_PATH}")
+    if not os.path.exists(DATA_PATH):
+        raise FileNotFoundError(f"Data file not found at {DATA_PATH}")
+    if not os.path.exists(ENCODERS_PATH):
+        raise FileNotFoundError(f"Encoders file not found at {ENCODERS_PATH}")
+    
+    catalog_data = pd.read_csv(DATA_PATH)
+    recommender = RecommendationGenerator(
+        model_path=MODEL_PATH,
+        catalog_data=catalog_data,
+        encoders_path=ENCODERS_PATH
+    )
+    print("Model loaded successfully")
+except Exception as e:
+    print(f"Error loading model: {str(e)}")
+    raise
+
+@app.route('/routes', methods=['GET'])
+def list_routes():
+    routes = []
+    for rule in app.url_map.iter_rules():
+        routes.append({
+            "endpoint": rule.endpoint,
+            "methods": list(rule.methods),
+            "url": str(rule)
+        })
+    return {"routes": routes}, 200
+
+@app.route('/')
+def home():
+    return "Welcome to the app!"
+
+# @app.route('/api/recommendations', methods=['POST'])
+# def get_recommendations():
+#     try:
+#         data = request.json
+#         user_info = {
+#             'user_id': data['user_id'],
+#             'age': int(data['age']),
+#             'gender': data['gender'],
+#             'genre': data['genre'],
+#             'music': data['music']
+#         }
+        
+#         recommendations = recommender.generate_recommendations(user_info, n_recommendations=5)
+        
+#         return jsonify({
+#             'status': 'success',
+#             'recommendations': recommendations.to_dict(orient='records')
+#         })
+#     except Exception as e:
+#         return jsonify({
+#             'status': 'error',
+#             'message': str(e)
+#         }), 500
+@app.route('/api/recommendations', methods=['POST'])
+def get_recommendations():
+    try:
+        print("Request received")  # Log start
+        data = request.json
+        print("Request data:", data)  # Log data
+        
+        user_info = {
+            'user_id': data['user_id'],
+            'age': int(data['age']),
+            'gender': data['gender'],
+            'genre': data['genre'],
+            'music': data['music']
+        }
+        print("Generating recommendations...")  # Log before calling the model
+
+        recommendations = recommender.generate_recommendations(user_info, n_recommendations=5)
+
+        print("Recommendations generated")  # Log success
+        return jsonify({
+            'status': 'success',
+            'recommendations': recommendations.to_dict(orient='records')
+        })
+    except Exception as e:
+        print("Error occurred:", str(e))  # Log errors
+        return jsonify({
+            'status': 'error',
+            'message': str(e)
+        }), 500
+
+
+@app.route('/api/health', methods=['GET'])
+def health_check():
+    return jsonify({'status': 'healthy'})
+
+if __name__ == '__main__':
+    port = int(os.environ.get('PORT', 8000))
+    app.run(host='0.0.0.0', port=port, debug=True)

checkpoints/best_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed66806af3d4a2fc27871e0967ebed8889755299ad77a9dfaf60d62253ce2b9a
+size 21607885

checkpoints/best_model_cv.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fbbfc7ff7c43624a789097920c582a9931903a21fb05b3cddacd9638fa666c
+size 8273787

checkpoints/latest_checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc336bee4aec71e695821d0f9747638bd27235d7e5e195f060528c98aa52beaf
+size 21608914

config/model_config.json

@@ -0,0 +1,18 @@
+{
+    "learning_rate": 0.001,
+    "weight_decay": 1e-05,
+    "epochs": 20,
+    "batch_size": 32,
+    "embedding_dim": 64,
+    "model_dir": "models",
+    "hidden_layers": [
+        256,
+        128,
+        64
+    ],
+    "dropout": 0.3,
+    "early_stopping_patience": 2,
+    "max_grad_norm": 1.0,
+    "l1_lambda": 1e-05,
+    "n_splits": 5
+}

data/data_encoders.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e60f8ec993e84b8d4475484010774a10bb4c19a13e452e94b797c2583be973
+size 1788856

data/dataset.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:650c373cadce8479ba15f3602867392c90b61aeceeb731f6098d9532f96f49d4
+size 13859442

data/o2_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b23097172f8f50e089acdea0c9c9f10e5b9162d926aa017578b751c6561d1dc
+size 13122336

data/train_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d52510a2e92b5907e5e07710f60f515920fd5b836d325485f9863cd3e24f934
+size 24971750

data_utils.py

@@ -0,0 +1,115 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+import os
+import logging
+from encoder_utils import DataEncoder
+import torch
+import numpy as np
+from tqdm import tqdm
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+def generate_negative_samples(df: pd.DataFrame, num_negatives: int = 4) -> pd.DataFrame:
+    """
+    Generate negative samples for each user by randomly sampling items they haven't interacted with.
+    
+    Args:
+        df: DataFrame containing user-item interactions
+        num_negatives: Number of negative samples per positive interaction
+    
+    Returns:
+        DataFrame with both positive and negative samples
+    """
+    # Create a set of all items
+    all_items = set(df['music_id'].unique())
+    
+    negative_samples = []
+    for user_id in tqdm(df['user_id'].unique(), desc="Generating negative samples"):
+        # Get items the user has interacted with
+        user_items = set(df[df['user_id'] == user_id]['music_id'])
+        
+        # Get items the user hasn't interacted with
+        negative_items = list(all_items - user_items)
+        
+        if len(negative_items) > 0:
+            # Sample negative items
+            num_samples = min(len(negative_items), num_negatives)
+            sampled_negatives = np.random.choice(negative_items, size=num_samples, replace=False)
+            
+            # Create negative samples
+            user_data = df[df['user_id'] == user_id].iloc[0].to_dict()
+            for item_id in sampled_negatives:
+                negative = user_data.copy()
+                negative['music_id'] = item_id
+                negative['playcount'] = 0  # Mark as negative sample
+                negative_samples.append(negative)
+    
+    # Convert negative samples to DataFrame
+    negative_df = pd.DataFrame(negative_samples)
+    
+    # Combine positive and negative samples
+    combined_df = pd.concat([df, negative_df], ignore_index=True)
+    
+    return combined_df
+
+def split_and_save_data(data_path: str, test_size: float = 0.2, random_state: int = 42):
+    """
+    Split data into train and test sets while maintaining consistent encoding.
+    """
+    # Read data
+    df = pd.read_csv(data_path)
+    logger.info(f"Total records: {len(df)}")
+    
+    # Generate negative samples
+    df = generate_negative_samples(df)
+    logger.info(f"Total records after negative sampling: {len(df)}")
+    
+    # Initialize and fit encoders on full dataset
+    encoder = DataEncoder()
+    encoder.fit(df)
+    
+    # Split by user to avoid data leakage
+    users = df['user_id'].unique()
+    train_users, test_users = train_test_split(
+        users,
+        test_size=test_size,
+        random_state=random_state
+    )
+    
+    train_data = df[df['user_id'].isin(train_users)]
+    test_data = df[df['user_id'].isin(test_users)]
+    
+    # Save splits
+    data_dir = os.path.dirname(data_path)
+    os.makedirs(data_dir, exist_ok=True)
+    
+    train_path = os.path.join(data_dir, 'train_data.csv')
+    test_path = os.path.join(data_dir, 'test_data.csv')
+    encoder_path = os.path.join(data_dir, 'data_encoders.pt')
+    
+    # Save data splits
+    train_data.to_csv(train_path, index=False)
+    test_data.to_csv(test_path, index=False)
+    
+    # Save encoders
+    torch.save(encoder.get_encoders(), encoder_path)
+    
+    logger.info(f"Training set size: {len(train_data)}")
+    logger.info(f"Test set size: {len(test_data)}")
+    logger.info(f"\nFiles saved to:")
+    logger.info(f"Training data: {train_path}")
+    logger.info(f"Test data: {test_path}")
+    logger.info(f"Encoders: {encoder_path}")
+    
+    # Log some statistics about the encodings
+    dims = encoder.get_dims()
+    logger.info("\nEncoding dimensions:")
+    for key, value in dims.items():
+        logger.info(f"{key}: {value}")
+    
+    return train_path, test_path, encoder_path
+
+if __name__ == "__main__":
+    data_path = 'data/o2_data.csv'
+    train_path, test_path, encoder_path = split_and_save_data(data_path)

encoder_utils.py

@@ -0,0 +1,56 @@
+from sklearn.preprocessing import LabelEncoder, RobustScaler
+import pandas as pd
+from typing import Dict, Any
+import numpy as np
+
+class DataEncoder:
+    def __init__(self):
+        self.user_encoder = LabelEncoder()
+        self.music_encoder = LabelEncoder()
+        self.artist_encoder = LabelEncoder()
+        self.genre_encoder = LabelEncoder()
+        self.scaler = RobustScaler()
+        
+        self.numerical_features = [
+            'age', 'duration', 'acousticness', 'key', 'mode', 'speechiness',
+            'instrumentalness', 'liveness', 'tempo', 'time_signature',
+            'energy_loudness', 'dance_valence'  # Removed 'playcount'
+        ]
+    
+    def fit(self, df: pd.DataFrame) -> None:
+        """Fit all encoders on the full dataset."""
+        self.user_encoder.fit(df['user_id'].values)
+        self.music_encoder.fit(df['music_id'].values)
+        self.artist_encoder.fit(df['artist_id'].values)
+        self.genre_encoder.fit(df['main_genre'].values)
+        self.scaler.fit(df[self.numerical_features].values)
+    
+    def transform(self, df: pd.DataFrame) -> Dict[str, np.ndarray]:
+        """Transform data using fitted encoders."""
+        return {
+            'users': self.user_encoder.transform(df['user_id'].values),
+            'music': self.music_encoder.transform(df['music_id'].values),
+            'artists': self.artist_encoder.transform(df['artist_id'].values),
+            'genres': self.genre_encoder.transform(df['main_genre'].values),
+            'numerical_features': self.scaler.transform(df[self.numerical_features].values)
+        }
+    
+    def get_dims(self) -> Dict[str, int]:
+        """Get dimensions for model initialization."""
+        return {
+            'num_users': len(self.user_encoder.classes_),
+            'num_music': len(self.music_encoder.classes_),
+            'num_artists': len(self.artist_encoder.classes_),
+            'num_genres': len(self.genre_encoder.classes_),
+            'num_numerical': len(self.numerical_features)
+        }
+    
+    def get_encoders(self) -> Dict[str, Any]:
+        """Get all encoders for saving."""
+        return {
+            'user_encoder': self.user_encoder,
+            'music_encoder': self.music_encoder,
+            'artist_encoder': self.artist_encoder,
+            'genre_encoder': self.genre_encoder,
+            'scaler': self.scaler
+        }

evaluate_model.py

@@ -0,0 +1,497 @@
+import torch
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score, ndcg_score
+from typing import Dict, List, Tuple
+import json
+import os
+from train_model import HybridMusicRecommender, MusicRecommenderDataset
+from torch.utils.data import DataLoader
+import logging
+from sklearn.preprocessing import LabelEncoder
+from sklearn.model_selection import ParameterGrid, train_test_split
+
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.FileHandler('model_evaluation.log'),
+        logging.StreamHandler()
+    ]
+)
+logger = logging.getLogger(__name__)
+
+class ModelEvaluator:
+    def __init__(self, model_path: str, test_data: pd.DataFrame, batch_size: int = 32):
+        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        self.model_path = model_path
+        self.test_data = test_data
+        self.batch_size = batch_size
+        
+        # Load model and config
+        torch.serialization.add_safe_globals([LabelEncoder])
+        self.checkpoint = torch.load(model_path, map_location=self.device, weights_only=False)
+        self.config = self.checkpoint['config']
+        self.encoders = self.checkpoint['encoders']
+        
+        # Initialize model
+        self.model = self._initialize_model()
+        self.test_loader = self._prepare_data()
+        
+        # Create metrics directory with absolute path
+        self.metrics_dir = os.path.join(os.path.dirname(model_path), 'metrics')
+        os.makedirs(self.metrics_dir, exist_ok=True)
+        
+    def _initialize_model(self, custom_config: Dict = None) -> HybridMusicRecommender:
+        """Initialize and load the model from checkpoint."""
+        # Use custom config if provided, otherwise use default
+        config = custom_config if custom_config else self.config
+        
+        model = HybridMusicRecommender(
+            num_users=len(self.encoders['user_encoder'].classes_),
+            num_music=len(self.encoders['music_encoder'].classes_),
+            num_artists=len(self.encoders['artist_encoder'].classes_),
+            num_genres=len(self.encoders['genre_encoder'].classes_),
+            num_numerical=12,
+            embedding_dim=config['embedding_dim'],
+            layers=config['hidden_layers'],
+            dropout=config['dropout']
+        )
+        
+        # Only load state dict if using default config
+        if not custom_config:
+            model.load_state_dict(self.checkpoint['model_state_dict'])
+        
+        model = model.to(self.device)
+        model.eval()
+        return model
+    
+    def _prepare_data(self) -> DataLoader:
+        """Prepare test data loader using saved encoders."""
+        # Create a custom dataset for test data with the saved encoders
+        test_dataset = MusicRecommenderDataset(
+            self.test_data, 
+            mode='test',
+            encoders=self.encoders
+        )
+        
+        logger.info(f"Prepared test dataset with {len(self.test_data)} samples")
+        return DataLoader(test_dataset, batch_size=self.batch_size, shuffle=False)
+    
+    def calculate_metrics(self) -> Dict[str, float]:
+        """Calculate various performance metrics."""
+        true_values = []
+        predictions = []
+        
+        with torch.no_grad():
+            for batch in self.test_loader:
+                batch = {k: v.to(self.device) for k, v in batch.items()}
+                pred = self.model(batch)
+                true_values.extend(batch['playcount'].cpu().numpy())
+                predictions.extend(pred.cpu().numpy())
+        
+        true_values = np.array(true_values)
+        predictions = np.array(predictions)
+        
+        metrics = {
+            'mse': float(mean_squared_error(true_values, predictions)),
+            'rmse': float(np.sqrt(mean_squared_error(true_values, predictions))),
+            'mae': float(mean_absolute_error(true_values, predictions)),
+            'r2': float(r2_score(true_values, predictions))
+        }
+        
+        # Calculate prediction distribution statistics
+        metrics.update({
+            'pred_mean': float(np.mean(predictions)),
+            'pred_std': float(np.std(predictions)),
+            'true_mean': float(np.mean(true_values)),
+            'true_std': float(np.std(true_values))
+        })
+        
+        return metrics
+    
+    def analyze_prediction_bias(self) -> Dict[str, float]:
+        """Analyze prediction bias across different value ranges."""
+        true_values = []
+        predictions = []
+        
+        with torch.no_grad():
+            for batch in self.test_loader:
+                batch = {k: v.to(self.device) for k, v in batch.items()}
+                pred = self.model(batch)
+                true_values.extend(batch['playcount'].cpu().numpy())
+                predictions.extend(pred.cpu().numpy())
+        
+        true_values = np.array(true_values)
+        predictions = np.array(predictions)
+        
+        # Calculate bias for different value ranges
+        percentiles = np.percentile(true_values, [25, 50, 75])
+        ranges = [
+            (float('-inf'), percentiles[0]),
+            (percentiles[0], percentiles[1]),
+            (percentiles[1], percentiles[2]),
+            (percentiles[2], float('inf'))
+        ]
+        
+        bias_analysis = {}
+        for i, (low, high) in enumerate(ranges):
+            mask = (true_values >= low) & (true_values < high)
+            if np.any(mask):
+                bias = np.mean(predictions[mask] - true_values[mask])
+                bias_analysis[f'bias_range_{i+1}'] = float(bias)
+        
+        return bias_analysis
+    
+    def plot_prediction_distribution(self, save_dir: str = None):
+        """Plot the distribution of predictions vs true values."""
+        if save_dir is None:
+            save_dir = self.metrics_dir
+            
+        true_values = []
+        predictions = []
+        
+        with torch.no_grad():
+            for batch in self.test_loader:
+                batch = {k: v.to(self.device) for k, v in batch.items()}
+                pred = self.model(batch)
+                true_values.extend(batch['playcount'].cpu().numpy())
+                predictions.extend(pred.cpu().numpy())
+        
+        true_values = np.array(true_values)
+        predictions = np.array(predictions)
+        
+        # Create scatter plot
+        plt.figure(figsize=(10, 6))
+        plt.scatter(true_values, predictions, alpha=0.5)
+        plt.plot([true_values.min(), true_values.max()], 
+                [true_values.min(), true_values.max()], 
+                'r--', lw=2)
+        plt.xlabel('True Values')
+        plt.ylabel('Predictions')
+        plt.title('Prediction vs True Values')
+        
+        try:
+            # Save plot with absolute path
+            plot_path = os.path.join(save_dir, 'prediction_distribution.png')
+            plt.savefig(plot_path)
+            plt.close()
+            logger.info(f"Saved prediction distribution plot to: {plot_path}")
+        except Exception as e:
+            logger.error(f"Error saving prediction distribution plot: {str(e)}")
+            
+    def plot_error_distribution(self, save_dir: str = None):
+        """Plot the distribution of prediction errors."""
+        if save_dir is None:
+            save_dir = self.metrics_dir
+            
+        true_values = []
+        predictions = []
+        
+        with torch.no_grad():
+            for batch in self.test_loader:
+                batch = {k: v.to(self.device) for k, v in batch.items()}
+                pred = self.model(batch)
+                true_values.extend(batch['playcount'].cpu().numpy())
+                predictions.extend(pred.cpu().numpy())
+        
+        errors = np.array(predictions) - np.array(true_values)
+        
+        plt.figure(figsize=(10, 6))
+        sns.histplot(errors, kde=True)
+        plt.xlabel('Prediction Error')
+        plt.ylabel('Count')
+        plt.title('Distribution of Prediction Errors')
+        
+        try:
+            plot_path = os.path.join(save_dir, 'error_distribution.png')
+            plt.savefig(plot_path)
+            plt.close()
+            logger.info(f"Saved error distribution plot to: {plot_path}")
+        except Exception as e:
+            logger.error(f"Error saving error distribution plot: {str(e)}")
+    
+    def evaluate_top_k_recommendations(self, k: int = 10) -> Dict[str, float]:
+        """Evaluate top-K recommendation metrics."""
+        user_metrics = []
+        
+        # Group by user to evaluate per-user recommendations
+        for user_id in self.test_data['user_id'].unique():
+            user_mask = self.test_data['user_id'] == user_id
+            user_data = self.test_data[user_mask]
+            
+            # Skip users with too few interactions
+            if len(user_data) < k:
+                continue
+            
+            user_dataset = MusicRecommenderDataset(
+                user_data,
+                mode='test',
+                encoders=self.encoders
+            )
+            user_loader = DataLoader(user_dataset, batch_size=len(user_data), shuffle=False)
+            
+            with torch.no_grad():
+                batch = next(iter(user_loader))
+                batch = {k: v.to(self.device) for k, v in batch.items()}
+                predictions = self.model(batch).cpu().numpy()
+                true_values = batch['playcount'].cpu().numpy()
+                
+                # Normalize predictions and true values to [0, 1] range
+                true_values = (true_values - true_values.min()) / (true_values.max() - true_values.min() + 1e-8)
+                predictions = (predictions - predictions.min()) / (predictions.max() - predictions.min() + 1e-8)
+                
+                # Calculate metrics for this user
+                top_k_pred_idx = np.argsort(predictions)[-k:][::-1]
+                top_k_true_idx = np.argsort(true_values)[-k:][::-1]
+                
+                # Calculate NDCG
+                dcg = self._calculate_dcg(true_values, top_k_pred_idx, k)
+                idcg = self._calculate_dcg(true_values, top_k_true_idx, k)
+                
+                # Handle edge case where idcg is 0
+                ndcg = dcg / idcg if idcg > 0 else 0.0
+                
+                # Calculate precision and recall
+                relevant_items = set(top_k_true_idx)
+                recommended_items = set(top_k_pred_idx)
+                
+                precision = len(relevant_items & recommended_items) / k
+                recall = len(relevant_items & recommended_items) / len(relevant_items)
+                
+                user_metrics.append({
+                    'ndcg': ndcg,
+                    'precision': precision,
+                    'recall': recall
+                })
+        
+        # Average metrics across users
+        avg_metrics = {
+            'ndcg@10': float(np.mean([m['ndcg'] for m in user_metrics])),
+            'precision@10': float(np.mean([m['precision'] for m in user_metrics])),
+            'recall@10': float(np.mean([m['recall'] for m in user_metrics]))
+        }
+        
+        return avg_metrics
+
+    def _calculate_dcg(self, true_values: np.ndarray, indices: np.ndarray, k: int) -> float:
+        """Helper method to calculate DCG with numerical stability."""
+        relevance = true_values[indices[:k]]
+        # Cap the relevance values to prevent overflow
+        max_relevance = 10  # Set a reasonable maximum value
+        relevance = np.clip(relevance, 0, max_relevance)
+        
+        # Use log2(rank + 1) directly instead of creating array
+        gains = (2 ** relevance - 1) / np.log2(np.arange(2, len(relevance) + 2))
+        return float(np.sum(gains))
+    
+    def evaluate_cold_start(self, min_interactions: int = 5) -> Dict[str, Dict[str, float]]:
+        """
+        Evaluate model performance on cold-start scenarios.
+        
+        Args:
+            min_interactions: Minimum number of interactions to consider a user/item as non-cold
+        
+        Returns:
+            Dictionary containing metrics for different cold-start scenarios
+        """
+        # Get all unique users and items
+        all_users = self.test_data['user_id'].unique()
+        all_items = self.test_data['music_id'].unique()
+        
+        # Count interactions per user and item
+        user_counts = self.test_data['user_id'].value_counts()
+        item_counts = self.test_data['music_id'].value_counts()
+        
+        # Identify cold users and items
+        cold_users = set(user_counts[user_counts < min_interactions].index)
+        cold_items = set(item_counts[item_counts < min_interactions].index)
+        
+        # Create masks for different scenarios
+        cold_user_mask = self.test_data['user_id'].isin(cold_users)
+        cold_item_mask = self.test_data['music_id'].isin(cold_items)
+        cold_user_warm_item = cold_user_mask & ~cold_item_mask
+        warm_user_cold_item = ~cold_user_mask & cold_item_mask
+        cold_both = cold_user_mask & cold_item_mask
+        warm_both = ~cold_user_mask & ~cold_item_mask
+        
+        scenarios = {
+            'cold_user_warm_item': cold_user_warm_item,
+            'warm_user_cold_item': warm_user_cold_item,
+            'cold_both': cold_both,
+            'warm_both': warm_both
+        }
+        
+        results = {}
+        for scenario_name, mask in scenarios.items():
+            if not any(mask):
+                logger.warning(f"No samples found for scenario: {scenario_name}")
+                continue
+                
+            scenario_data = self.test_data[mask].copy()
+            
+            # Create a temporary dataset and dataloader for this scenario
+            scenario_dataset = MusicRecommenderDataset(
+                scenario_data,
+                mode='test',
+                encoders=self.encoders
+            )
+            
+            scenario_loader = DataLoader(
+                scenario_dataset,
+                batch_size=self.batch_size,
+                shuffle=False
+            )
+            
+            # Collect predictions and true values
+            true_values = []
+            predictions = []
+            
+            with torch.no_grad():
+                for batch in scenario_loader:
+                    batch = {k: v.to(self.device) for k, v in batch.items()}
+                    pred = self.model(batch)
+                    true_values.extend(batch['playcount'].cpu().numpy())
+                    predictions.extend(pred.cpu().numpy())
+            
+            true_values = np.array(true_values)
+            predictions = np.array(predictions)
+            
+            # Calculate metrics
+            metrics = {
+                'count': len(true_values),
+                'mse': float(mean_squared_error(true_values, predictions)),
+                'rmse': float(np.sqrt(mean_squared_error(true_values, predictions))),
+                'mae': float(mean_absolute_error(true_values, predictions)),
+                'r2': float(r2_score(true_values, predictions)),
+                'pred_mean': float(np.mean(predictions)),
+                'pred_std': float(np.std(predictions)),
+                'true_mean': float(np.mean(true_values)),
+                'true_std': float(np.std(true_values))
+            }
+            
+            results[scenario_name] = metrics
+            
+            # Log results for this scenario
+            logger.info(f"\n{scenario_name} Metrics (n={metrics['count']}):")
+            for metric, value in metrics.items():
+                if metric != 'count':
+                    logger.info(f"{metric}: {value:.4f}")
+        
+        return results
+    
+    def save_evaluation_results(self, save_dir: str = 'metrics'):
+        """Run all evaluations and save results."""
+        os.makedirs(save_dir, exist_ok=True)
+        
+        # Calculate all metrics
+        results = {
+            'basic_metrics': self.calculate_metrics(),
+            'bias_analysis': self.analyze_prediction_bias(),
+            'top_k_metrics': self.evaluate_top_k_recommendations(),
+            'cold_start_metrics': self.evaluate_cold_start(min_interactions=5)
+        }
+        
+        # Save results to JSON
+        results_file = os.path.join(save_dir, 'evaluation_results.json')
+        with open(results_file, 'w') as f:
+            json.dump(results, f, indent=4)
+        
+        logger.info(f"Evaluation completed. Results saved to: {save_dir}")
+        
+        return results
+
+    def tune_hyperparameters(self, param_grid: Dict[str, List], val_data: pd.DataFrame) -> Dict:
+        """
+        Tune hyperparameters using validation set.
+        
+        Args:
+            param_grid: Dictionary of parameters to try
+            val_data: Validation data
+            
+        Returns:
+            Best parameters found
+        """
+        best_score = float('inf')
+        best_params = None
+        
+        # Create validation dataset
+        val_dataset = MusicRecommenderDataset(val_data, mode='test', encoders=self.encoders)
+        val_loader = DataLoader(val_dataset, batch_size=self.batch_size, shuffle=False)
+        
+        # Try all parameter combinations
+        for params in ParameterGrid(param_grid):
+            # Create a new config with updated parameters
+            current_config = self.config.copy()
+            current_config.update(params)
+            
+            # Initialize model with current parameters
+            self.model = self._initialize_model(custom_config=current_config)
+            
+            # Evaluate on validation set
+            metrics = self.calculate_metrics()
+            score = metrics['rmse']  # Use RMSE as scoring metric
+            
+            if score < best_score:
+                best_score = score
+                best_params = params
+                logger.info(f"New best parameters found: {params} (RMSE: {score:.4f})")
+        
+        return best_params
+
+def main():
+    # Load test data and check for data compatibility
+    ROOT_DIR = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+    test_path = os.path.join(ROOT_DIR, 'data', 'test_data.csv')
+    model_path = os.path.join(ROOT_DIR, 'data_engineered_v3', 'rs_main_v2_refactored', 'checkpoints', 'best_model.pth')
+    
+    test_data = pd.read_csv(test_path)
+    logger.info(f"Loaded test data with {len(test_data)} samples")
+    
+    # Split test data into validation and test
+    val_data, test_data = train_test_split(test_data, test_size=0.5, random_state=42)
+    
+    try:
+        # Initialize evaluator
+        evaluator = ModelEvaluator(
+            model_path=model_path,
+            test_data=test_data,
+            batch_size=32
+        )
+        
+        # Tune hyperparameters
+        param_grid = {
+            'embedding_dim': [32, 64, 128],
+            'dropout': [0.1, 0.2, 0.3],
+            'hidden_layers': [[128, 64], [256, 128, 64], [512, 256, 128]]
+        }
+        
+        best_params = evaluator.tune_hyperparameters(param_grid, val_data)
+        logger.info(f"Best parameters: {best_params}")
+        
+        # Run evaluation
+        results = evaluator.save_evaluation_results()
+        
+        # Print summary
+        logger.info("\nEvaluation Summary:")
+        logger.info("Basic Metrics:")
+        for metric, value in results['basic_metrics'].items():
+            logger.info(f"{metric}: {value:.4f}")
+        
+        logger.info("\nTop-K Metrics:")
+        for metric, value in results['top_k_metrics'].items():
+            logger.info(f"{metric}: {value:.4f}")
+        
+        logger.info("\nBias Analysis:")
+        for range_name, bias in results['bias_analysis'].items():
+            logger.info(f"{range_name}: {bias:.4f}")
+        
+    except Exception as e:
+        logger.error(f"Error during evaluation: {str(e)}")
+        raise
+
+if __name__ == "__main__":
+    main()
+

generate_recommendations.py

@@ -0,0 +1,312 @@
+import torch
+import torch.nn as nn
+import pandas as pd
+import numpy as np
+import json
+import logging
+from sklearn.preprocessing import LabelEncoder
+from torch.utils.data import DataLoader
+import os
+from train_model import HybridMusicRecommender, MusicRecommenderDataset
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Add safe globals for numpy types
+torch.serialization.add_safe_globals([
+    np.generic,  # Allow numpy scalar types
+    np.ndarray,  # Allow numpy arrays
+    np.dtype,    # Allow numpy dtypes
+    np.float64,  # Allow specific numpy types
+    np.float32,
+    np.int64,
+    np.int32
+])
+
+class RecommendationGenerator:
+    def __init__(self, model_path: str, catalog_data: pd.DataFrame, encoders_path: str):
+        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        self.catalog_data = catalog_data
+        
+        # Load model checkpoint with safety settings
+        logger.info(f"Loading model from {model_path}")
+        try:
+            self.checkpoint = torch.load(model_path, map_location=self.device)
+            logger.info("Model loaded successfully")
+        except Exception as e:
+            logger.error(f"Error loading model: {str(e)}")
+            raise
+        
+        # Get config and encoders from the checkpoint
+        self.config = self.checkpoint.get('config', {})
+        if not self.config:
+            # Try loading from config file as fallback
+            try:
+                with open('config/model_config.json', 'r') as f:
+                    self.config = json.load(f)
+            except FileNotFoundError:
+                logger.warning("Config file not found, using default values")
+                self.config = {
+                    'embedding_dim': 64,
+                    'hidden_layers': [256, 128, 64],
+                    'dropout': 0.3
+                }
+        
+        # Load encoders with safety settings
+        torch.serialization.add_safe_globals([LabelEncoder])
+        self.encoders = torch.load(encoders_path, weights_only=False)
+        
+        # Print shape info for debugging
+        logger.info("Encoder class counts:")
+        for key, encoder in self.encoders.items():
+            if isinstance(encoder, LabelEncoder):
+                logger.info(f"{key}: {len(encoder.classes_)}")
+        
+        # Get state dict dimensions with safety checks
+        state_dict = self.checkpoint['model_state_dict']
+        self.embedding_dims = {
+            'num_users': state_dict['user_embedding.weight'].shape[0],
+            'num_music': state_dict['music_embedding.weight'].shape[0],
+            'num_artists': state_dict['artist_embedding.weight'].shape[0],
+            'num_genres': len(self.encoders['genre_encoder'].classes_),
+            'num_numerical': 12
+        }
+        
+        logger.info("Model dimensions from state dict:")
+        for key, value in self.embedding_dims.items():
+            logger.info(f"{key}: {value}")
+        
+        # Safety check for catalog data
+        max_music_id = self.catalog_data['music_id'].nunique()
+        if max_music_id >= self.embedding_dims['num_music']:
+            logger.warning(f"Catalog contains music IDs larger than model capacity. Filtering out excess items.")
+            valid_music_ids = set(self.encoders['music_encoder'].transform(
+                self.encoders['music_encoder'].classes_[:self.embedding_dims['num_music']]
+            ))
+            self.catalog_data = self.catalog_data[
+                self.catalog_data['music_id'].apply(
+                    lambda x: self.encoders['music_encoder'].transform([x])[0] in valid_music_ids
+                )
+            ]
+            logger.info(f"Filtered catalog size: {len(self.catalog_data)}")
+        
+        self.model = self._initialize_model(self.embedding_dims)
+        
+    def _initialize_model(self, embedding_dims):
+        """Initialize and load the model from checkpoint."""
+        # Get dimensions from encoders
+        model = HybridMusicRecommender(
+            num_users=embedding_dims['num_users'],
+            num_music=embedding_dims['num_music'],
+            num_artists=embedding_dims['num_artists'],
+            num_genres=embedding_dims['num_genres'],
+            num_numerical=embedding_dims['num_numerical'],
+            embedding_dim=64,
+            layers=[256, 128, 64],
+            dropout=0.2
+        )
+        
+        # Load state dict from checkpoint
+        state_dict = self.checkpoint['model_state_dict']
+        model.load_state_dict(state_dict)
+        
+        # Move model to device and set to eval mode
+        model = model.to(self.device)
+        model.eval()
+        
+        return model
+    
+    def generate_recommendations(self, user_info: dict, n_recommendations: int = 10) -> pd.DataFrame:
+        """
+        Generate music recommendations for a specific user.
+        
+        Args:
+            user_info: Dictionary containing user information (age, gender, user_id)
+            n_recommendations: Number of recommendations to generate
+            
+        Returns:
+            DataFrame containing recommended songs with predicted play counts
+        """
+        # Create a temporary DataFrame with all songs for the user
+        user_candidates = self.catalog_data.copy()
+        user_candidates['age'] = user_info['age']
+        user_candidates['gender'] = user_info['gender']
+        user_candidates['user_id'] = user_info['user_id']
+        
+        # Debug user encoding with more detailed error handling
+        try:
+            encoded_user = self.encoders['user_encoder'].transform([user_info['user_id']])[0]
+            logger.info(f"User ID {user_info['user_id']} encoded as: {encoded_user}")
+        except Exception as e:
+            logger.warning(f"Error encoding user ID: {str(e)}")
+            logger.warning("Using default encoding (0)")
+            encoded_user = 0
+            user_candidates['user_id'] = '0'  # Use default user ID
+        
+        # Debug catalog data
+        print(f"\nCatalog Statistics:")
+        print(f"Total songs: {len(user_candidates)}")
+        print(f"Unique artists: {user_candidates['artist_name'].nunique()}")
+        print(f"Unique genres: {user_candidates['main_genre'].nunique()}")
+        
+        try:
+            # Create dataset with safety checks
+            test_dataset = MusicRecommenderDataset(
+                user_candidates,
+                mode='test',
+                encoders=self.encoders,
+                embedding_dims=self.embedding_dims  # Pass embedding dimensions
+            )
+            test_loader = DataLoader(test_dataset, batch_size=128, shuffle=False)
+            
+            # Generate predictions
+            predictions = []
+            indices = []
+            
+            with torch.no_grad():
+                for i, batch in enumerate(test_loader):
+                    batch = {k: v.to(self.device) for k, v in batch.items()}
+                    pred = self.model(batch)
+                    predictions.extend(pred.cpu().numpy())
+                    indices.extend(range(i * test_loader.batch_size, 
+                                      min((i + 1) * test_loader.batch_size, len(test_dataset))))
+        except Exception as e:
+            logger.error(f"Error generating recommendations: {str(e)}")
+            raise
+        
+        # Create recommendations DataFrame and ensure uniqueness
+        recommendations = pd.DataFrame({
+            'music': user_candidates['music'].values[indices],
+            'artist_name': user_candidates['artist_name'].values[indices],
+            'genre': user_candidates['main_genre'].values[indices],
+            'predicted_plays': predictions
+        })
+        
+        # Drop duplicates keeping first occurrence (highest predicted play count)
+        recommendations = recommendations.drop_duplicates(subset=['music'], keep='first')
+        
+        # Convert predictions to scalar values and sort
+        recommendations['predicted_plays'] = recommendations['predicted_plays'].apply(lambda x: float(x[0]))
+        
+        # Sort by predicted plays and get top N recommendations
+        recommendations = recommendations.sort_values('predicted_plays', ascending=False)
+        recommendations = recommendations.head(n_recommendations)
+        
+        # Debug predictions
+        print(f"\nPrediction Statistics:")
+        min_pred = recommendations['predicted_plays'].min()
+        max_pred = recommendations['predicted_plays'].max()
+        std_pred = recommendations['predicted_plays'].std()
+        print(f"Prediction range: {min_pred:.2f} to {max_pred:.2f}")
+        print(f"Prediction std: {std_pred:.2f}")
+        
+        # Print top recommendations with better formatting
+        print("\nTop 10 Recommended Songs:")
+        pd.set_option('display.max_columns', None)
+        pd.set_option('display.width', None)
+        print(recommendations.to_string(index=False, float_format=lambda x: '{:.2f}'.format(x) if isinstance(x, (float, np.float32, np.float64)) else str(x)))
+        
+        return recommendations.reset_index(drop=True)
+
+class HybridMusicRecommender(nn.Module):
+    def __init__(self, num_users, num_music, num_artists, num_genres, num_numerical,
+                 embedding_dim=64, layers=[256, 128, 64], dropout=0.2):
+        super().__init__()
+        
+        # Embedding layers
+        self.user_embedding = nn.Embedding(num_users, embedding_dim)
+        self.music_embedding = nn.Embedding(num_music, embedding_dim)
+        self.artist_embedding = nn.Embedding(num_artists, embedding_dim)
+        self.genre_embedding = nn.Embedding(num_genres, embedding_dim)
+        
+        # Feature processing layers with residual connections
+        self.numerical_layer = nn.Sequential(
+            nn.Linear(num_numerical, embedding_dim),
+            nn.ReLU(),
+            nn.BatchNorm1d(embedding_dim)
+        )
+        
+        self.binary_layer = nn.Sequential(
+            nn.Linear(2, embedding_dim),
+            nn.ReLU(),
+            nn.BatchNorm1d(embedding_dim)
+        )
+        
+        # Calculate total input features
+        total_features = embedding_dim * 6  # 4 embeddings + numerical + binary
+        
+        # MLP layers with residual connections
+        self.fc_layers = nn.ModuleList()
+        input_dim = total_features
+        
+        for layer_size in layers:
+            self.fc_layers.append(nn.ModuleDict({
+                'main': nn.Sequential(
+                    nn.Linear(input_dim, layer_size),
+                    nn.ReLU(),
+                    nn.BatchNorm1d(layer_size),
+                    nn.Dropout(dropout)
+                ),
+                'residual': nn.Linear(input_dim, layer_size) if input_dim != layer_size else None
+            }))
+            input_dim = layer_size
+        
+        self.final_layer = nn.Linear(layers[-1], 1)
+    
+    def forward(self, batch):
+        # Get embeddings
+        user_emb = self.user_embedding(batch['user_id'])
+        music_emb = self.music_embedding(batch['music_id'])
+        artist_emb = self.artist_embedding(batch['artist_id'])
+        genre_emb = self.genre_embedding(batch['genre_id'])
+        
+        # Process numerical features
+        numerical = self.numerical_layer(batch['numerical_features'])
+        
+        # Process binary features
+        binary = torch.stack([batch['explicit'], batch['gender']], dim=1).float()
+        binary = self.binary_layer(binary)
+        
+        # Concatenate all features
+        x = torch.cat([
+            user_emb, music_emb, artist_emb, genre_emb, numerical, binary
+        ], dim=1)
+        
+        # Apply MLP layers with residual connections
+        for layer in self.fc_layers:
+            identity = x
+            x = layer['main'](x)
+            if layer['residual'] is not None:
+                x = x + layer['residual'](identity)
+        
+        # Final prediction
+        return self.final_layer(x)
+
+def main():
+    # Example usage
+    BASE_DIR = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+    model_path = 'checkpoints/best_model.pth'
+    catalog_data = pd.read_csv(os.path.join(BASE_DIR, 'data', 'test_data.csv'))
+    encoders_path = os.path.join(BASE_DIR, 'data', 'data_encoders.pt')
+    
+    # Initialize recommendation generator
+    recommender = RecommendationGenerator(model_path, catalog_data, encoders_path)
+    
+    # Example user
+    user_info = {
+        'age': 32,
+        'gender': 'M',
+        'genre': 'Pop',
+        'music': 'Shape of You',
+        'user_id': '44d39c6e5e7b45bfc2187fb3c89be58c5a3dc6a54d2a0075402c551c14ea1459'
+    }
+    
+    # Generate recommendations
+    recommendations = recommender.generate_recommendations(user_info, n_recommendations=10)
+    
+    print("\nTop 10 Recommended Songs:")
+    print(recommendations.to_string(index=False))
+
+if __name__ == "__main__":
+    main()

metrics/evaluation_results.json

@@ -0,0 +1,67 @@
+{
+    "basic_metrics": {
+        "mse": 3079.0234375,
+        "rmse": 55.488948822021484,
+        "mae": 23.4454402923584,
+        "r2": -0.21279525756835938,
+        "pred_mean": -1.0994174480438232,
+        "pred_std": 9.724736213684082,
+        "true_mean": 19.224706649780273,
+        "true_std": 50.38633346557617
+    },
+    "bias_analysis": {
+        "bias_range_3": -2.6668460369110107,
+        "bias_range_4": -67.3138656616211
+    },
+    "top_k_metrics": {
+        "ndcg@10": 0.76645658997246,
+        "precision@10": 0.8794117647058824,
+        "recall@10": 0.8794117647058824
+    },
+    "cold_start_metrics": {
+        "cold_user_warm_item": {
+            "count": 139,
+            "mse": 1254.147705078125,
+            "rmse": 35.41394805908203,
+            "mae": 24.895784378051758,
+            "r2": -0.9901391267776489,
+            "pred_mean": 1.0831069946289062,
+            "pred_std": 11.065825462341309,
+            "true_mean": 23.73381233215332,
+            "true_std": 25.103404998779297
+        },
+        "warm_user_cold_item": {
+            "count": 1751,
+            "mse": 365.7469177246094,
+            "rmse": 19.12451171875,
+            "mae": 12.106451034545898,
+            "r2": -0.924481987953186,
+            "pred_mean": -0.9319719672203064,
+            "pred_std": 10.093915939331055,
+            "true_mean": 7.401484966278076,
+            "true_std": 13.785845756530762
+        },
+        "cold_both": {
+            "count": 4107,
+            "mse": 169.58038330078125,
+            "rmse": 13.022303581237793,
+            "mae": 8.721110343933105,
+            "r2": -1.5553205013275146,
+            "pred_mean": -1.2563493251800537,
+            "pred_std": 8.511791229248047,
+            "true_mean": 4.080350399017334,
+            "true_std": 8.14638900756836
+        },
+        "warm_both": {
+            "count": 714,
+            "mse": 26994.263671875,
+            "rmse": 164.29931640625,
+            "mae": 136.50509643554688,
+            "r2": -2.396286725997925,
+            "pred_mean": -1.9450238943099976,
+            "pred_std": 13.863030433654785,
+            "true_mean": 134.4537811279297,
+            "true_std": 89.15250396728516
+        }
+    }
+}

metrics/training_metrics_20250102_064900.json

@@ -0,0 +1,290 @@
+{
+    "train_loss": [
+        27.87820368424011,
+        0.8559115440289997,
+        0.5168477836848956,
+        0.421229469199382,
+        0.33146533420268165,
+        0.31913505295583317,
+        0.27628301501810504,
+        0.1922393307175275,
+        0.22288809188706446,
+        0.2036261794325318,
+        0.17079091021242918,
+        0.13815377909827187,
+        0.1524550925849648,
+        0.1501235003079158,
+        0.1421720849812809,
+        0.1081244022875753,
+        0.09324924281689256,
+        0.1108920008247671,
+        0.09771170746442961,
+        0.09051197385297546,
+        0.08150478607652226,
+        0.0860889327385952,
+        0.05988402931827203,
+        0.049674075748550386,
+        0.05377031577186647,
+        0.04540467359397495,
+        0.04073900714773785,
+        0.03540054572981199,
+        0.033688442806066365,
+        0.025686628671688663
+    ],
+    "train_rmse": [
+        3.6065338792777895,
+        0.7172188698897799,
+        0.5629538247819917,
+        0.4971097810866635,
+        0.4503646820492115,
+        0.4126986173330652,
+        0.3966659381984858,
+        0.3457994023430261,
+        0.3494550960797524,
+        0.33324397309356185,
+        0.3095208795818895,
+        0.2862384810888418,
+        0.2971145911978121,
+        0.294086353497263,
+        0.2809138228068532,
+        0.2536127242472163,
+        0.24007327436595324,
+        0.2581924051221915,
+        0.231609092571742,
+        0.23556566189850986,
+        0.21719404996320857,
+        0.22204710487363657,
+        0.18534403303185937,
+        0.17526732037716256,
+        0.16678127027175485,
+        0.16144292278880193,
+        0.15759382268230296,
+        0.151095087343919,
+        0.1478537986232017,
+        0.13138720508414045
+    ],
+    "train_mae": [
+        2.485820442273081,
+        0.39211485435879684,
+        0.2973032114626486,
+        0.26411598030760697,
+        0.23414922938269528,
+        0.21794895377434506,
+        0.20361037203405477,
+        0.18592927409218082,
+        0.1848273886002223,
+        0.1786883569593671,
+        0.1653798102177208,
+        0.1611096473599348,
+        0.1563368417393369,
+        0.1569892016263042,
+        0.15296285591217912,
+        0.1440688233728273,
+        0.13509617341517272,
+        0.14298199075922557,
+        0.1298971869982779,
+        0.1322182358855594,
+        0.12218869595988831,
+        0.12325722614562587,
+        0.10556309332752813,
+        0.10367214477538497,
+        0.09859485125546402,
+        0.09540063718958652,
+        0.091572887579545,
+        0.08790545361234417,
+        0.08544569545354741,
+        0.0796616122427196
+    ],
+    "train_ndcg": [
+        0.7553261820231697,
+        0.980978106254641,
+        0.9915008039414128,
+        0.9941110056412371,
+        0.9949865918370742,
+        0.9959262692475621,
+        0.996802295404899,
+        0.9977287187983718,
+        0.9980168807544286,
+        0.9981021317122858,
+        0.9982030255885064,
+        0.9981919676065445,
+        0.9981716039437282,
+        0.9983992185207862,
+        0.9986318444149404,
+        0.9986614803724652,
+        0.9986458724435372,
+        0.9988089872500564,
+        0.9986771755392039,
+        0.9989267108561117,
+        0.9989624058332625,
+        0.9990676654667794,
+        0.9993524018533623,
+        0.9992948143353945,
+        0.9993984651150583,
+        0.9994121940830086,
+        0.9994110327355469,
+        0.9993546765439117,
+        0.9993868231584754,
+        0.9994757758288444
+    ],
+    "val_loss": [
+        2.6038931080887857,
+        0.42139411665184395,
+        0.5583879465342197,
+        0.5912148774745809,
+        0.1528182963211037,
+        0.0660524533038408,
+        0.06361346382936331,
+        0.2829914318502579,
+        0.08077898435294628,
+        0.1952337881510841,
+        0.021767998960288897,
+        0.08877882309926963,
+        0.10638422484863812,
+        0.09464026343497173,
+        0.17117542348487277,
+        0.01830679320559745,
+        0.23323201920351827,
+        0.019560120029138848,
+        0.35590659407898784,
+        0.02099220870836625,
+        0.044291495658706506,
+        0.07464934456404823,
+        0.012729868114906244,
+        0.03145649619269329,
+        0.050918724355091094,
+        0.03800152110109683,
+        0.017424330367824772,
+        0.021061579725528006,
+        0.022086826497426545,
+        0.09187827698728988
+    ],
+    "val_rmse": [
+        1.227388935805597,
+        0.5224974024123069,
+        0.6048934326354144,
+        0.6049047626572546,
+        0.3302447454209666,
+        0.23142119054455396,
+        0.2183617163470732,
+        0.4530892844997041,
+        0.24832345713733542,
+        0.3671097701498112,
+        0.12747864468838,
+        0.2430218135282559,
+        0.30256272023257963,
+        0.2506676406163341,
+        0.3361681103043667,
+        0.12415225520053427,
+        0.40363619780248056,
+        0.1291709818860191,
+        0.4182344907318643,
+        0.12986300297695713,
+        0.1892241361203728,
+        0.21875232263482927,
+        0.10009871166199444,
+        0.15774307681073538,
+        0.18965065946268103,
+        0.16470045194214208,
+        0.1186338556556314,
+        0.126187734792172,
+        0.1361035455701023,
+        0.24475607175453948
+    ],
+    "val_mae": [
+        0.48379497796716825,
+        0.23567856250094696,
+        0.23373650455139053,
+        0.23686996742453373,
+        0.14755814968490263,
+        0.11753897017366449,
+        0.10286616764857735,
+        0.19093803421292507,
+        0.11378036680775629,
+        0.1527806678918046,
+        0.06928311026012393,
+        0.0994793389412299,
+        0.13523404830148522,
+        0.10427081506227104,
+        0.1191780242386838,
+        0.0704273562091337,
+        0.14606773890030217,
+        0.07778757238681887,
+        0.12943885727247723,
+        0.06381919528816787,
+        0.08109805966451974,
+        0.08783078723600213,
+        0.05034292317454664,
+        0.07293910756182502,
+        0.07728687141248038,
+        0.06920250056600066,
+        0.05822602801129852,
+        0.054009364550592194,
+        0.06341128547111867,
+        0.09263877749023303
+    ],
+    "val_ndcg": [
+        0.9763069874803785,
+        0.9905599171007183,
+        0.9956201222580923,
+        0.9944330084491784,
+        0.9976292898957159,
+        0.9979534023244616,
+        0.9982731333920654,
+        0.99887366362021,
+        0.9985417631310476,
+        0.9982523078649816,
+        0.9987894985037791,
+        0.9986976905607842,
+        0.9984535944293922,
+        0.9988085778666215,
+        0.9989596126784741,
+        0.999552890448503,
+        0.9992313611675316,
+        0.9991534839213734,
+        0.9993672387700685,
+        0.9993135954292727,
+        0.9997000123413515,
+        0.9991327692085589,
+        0.9997313878905605,
+        0.9998314808791792,
+        0.9997146868369948,
+        0.999613323681791,
+        0.9994647427343987,
+        0.9998794181246153,
+        0.9998371995670695,
+        0.999895690192639
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.00025,
+        0.00025
+    ]
+}

metrics/training_metrics_20250102_200715.json

@@ -0,0 +1,200 @@
+{
+    "train_loss": [
+        16.630361146328948,
+        1.0519671638413697,
+        0.6806203248362422,
+        0.5999031775878577,
+        0.38576608685529024,
+        0.37990841519712365,
+        0.32125464765520034,
+        0.32947756348714186,
+        0.2796809829740573,
+        0.26263155958606405,
+        0.22337860409450375,
+        0.21770194551282668,
+        0.20779085973472206,
+        0.19294912434887448,
+        0.16268228239429927,
+        0.14605150811663015,
+        0.10150069270660228,
+        0.09985721124044349,
+        0.08507130466603462,
+        0.07544498139980567
+    ],
+    "train_rmse": [
+        2.863982798072898,
+        0.8541538475465146,
+        0.6655497856482756,
+        0.581696385112508,
+        0.49990246750103334,
+        0.4743720037700144,
+        0.4505155451364705,
+        0.43122559500317537,
+        0.3971644740236298,
+        0.39396504545080907,
+        0.3645592624501923,
+        0.35849524360048596,
+        0.35538791011264326,
+        0.323913015413718,
+        0.30786606214792145,
+        0.29631268685022677,
+        0.25046254811820845,
+        0.23011919047341975,
+        0.22660661390438122,
+        0.22238455647548008
+    ],
+    "train_mae": [
+        2.03278648278004,
+        0.5439351351012157,
+        0.40516641280979293,
+        0.33099308163163405,
+        0.2850040086910506,
+        0.26743246170491736,
+        0.25230235576959725,
+        0.23815869162731532,
+        0.22401378526576335,
+        0.21376478848860989,
+        0.19854636769741774,
+        0.19313653017971902,
+        0.19581266243270115,
+        0.17797640798896364,
+        0.17057573761720257,
+        0.16374789397644846,
+        0.14231451646766707,
+        0.136660557045731,
+        0.13092111585119479,
+        0.1310928447372457
+    ],
+    "train_ndcg": [
+        0.7903884568124939,
+        0.9611835469362102,
+        0.9845947593073302,
+        0.9888029080591624,
+        0.9926418597939648,
+        0.9949627612965016,
+        0.9956346042925799,
+        0.9959749847273284,
+        0.995856225396259,
+        0.9971607260500328,
+        0.9975389946676507,
+        0.9979873643834379,
+        0.9976527691830562,
+        0.9976573833559133,
+        0.9981214035349556,
+        0.9984748543629164,
+        0.9988606087391889,
+        0.9986500904152665,
+        0.9987482092803037,
+        0.9989969030588488
+    ],
+    "val_loss": [
+        0.9391880847618613,
+        0.33018025593228745,
+        0.29448598827904376,
+        0.10832524415053113,
+        0.09883832279592752,
+        0.3074022309172531,
+        0.04706974979490042,
+        4398.830707835696,
+        0.06168749292289287,
+        0.04185816639719505,
+        0.3049863429123562,
+        0.10778629867701044,
+        0.06723947737785713,
+        0.15211456833066236,
+        0.07834466032250981,
+        0.11750198668524833,
+        0.06605192532920291,
+        0.037398795541507046,
+        0.06266450706515199,
+        0.12772463355869265
+    ],
+    "val_rmse": [
+        0.8742571992372088,
+        0.5188966228554525,
+        0.44921875046319315,
+        0.2970077133693569,
+        0.27803433719802095,
+        0.44352033814287356,
+        0.1965003144412618,
+        8.122202649888228,
+        0.2323713941352663,
+        0.18472808669509327,
+        0.45586269918615224,
+        0.2856760431654221,
+        0.23925698861051023,
+        0.3356445257421406,
+        0.22166776637524868,
+        0.28559799659439566,
+        0.23039545566113326,
+        0.17412639513748637,
+        0.22186359509402045,
+        0.31559877438923417
+    ],
+    "val_mae": [
+        0.5880991115536488,
+        0.2766197122318644,
+        0.275182307186261,
+        0.18265998478926404,
+        0.15468566203621073,
+        0.2013326367022286,
+        0.11106940243445651,
+        1.5140733947111686,
+        0.13223919471804524,
+        0.1058114748185789,
+        0.18697005872365455,
+        0.14604388649614763,
+        0.1279687943383002,
+        0.17097019593060855,
+        0.095513791265622,
+        0.1156781678363471,
+        0.11046315509248787,
+        0.0784462515894376,
+        0.0981923619836149,
+        0.12334266032131624
+    ],
+    "val_ndcg": [
+        0.9549657870346392,
+        0.9888905731725021,
+        0.9928302638967272,
+        0.9962951557737001,
+        0.9976059718870781,
+        0.9967397762016511,
+        0.9963979788229499,
+        0.9976575357813231,
+        0.996619462966919,
+        0.9973971952854748,
+        0.9986196420562099,
+        0.9986509705933047,
+        0.9987828496476294,
+        0.9985354710632647,
+        0.9992627098526753,
+        0.9986722528094977,
+        0.9993009642815925,
+        0.9996941467406044,
+        0.9993367253894537,
+        0.9993710811709015
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.0005
+    ]
+}

metrics/training_metrics_20250102_203004.json

@@ -0,0 +1,191 @@
+{
+    "train_loss": [
+        1647.3079700711407,
+        271.8049797589266,
+        125.04480907585048,
+        77.73157471493829,
+        57.64490697353701,
+        47.655617599245865,
+        38.39268538318103,
+        35.70278034481821,
+        31.083040306085273,
+        28.446285428880135,
+        25.850659030902236,
+        22.36630686928954,
+        20.566794234740584,
+        18.177497906020925,
+        15.825210771983183,
+        14.747446770154976,
+        13.595882269400585,
+        12.136639672744122,
+        11.482755628567707
+    ],
+    "train_rmse": [
+        36.2100092540611,
+        15.789009180868153,
+        10.837184203620641,
+        8.55066505615135,
+        7.395000940441376,
+        6.741258009334249,
+        6.064591712646066,
+        5.836212617014259,
+        5.463458494168958,
+        5.219115193044183,
+        4.991978818769204,
+        4.644320877131546,
+        4.456296742640931,
+        4.190699669415659,
+        3.9148655267239025,
+        3.7699117465426917,
+        3.6200522574294958,
+        3.415201579531864,
+        3.32776171304689
+    ],
+    "train_mae": [
+        24.187040963504888,
+        10.407274974297874,
+        7.378058982423589,
+        6.026885859196699,
+        5.331949593145636,
+        4.930537258145176,
+        4.537671755386304,
+        4.348816263524792,
+        4.134116251068779,
+        3.9585593863378596,
+        3.805101910346671,
+        3.5380139833764184,
+        3.3881275284139414,
+        3.198319486424893,
+        2.985232395650465,
+        2.8795697855044016,
+        2.7671318642700773,
+        2.594415445116502,
+        2.544669221096401
+    ],
+    "train_ndcg": [
+        0.8654950500430563,
+        0.9803339956870561,
+        0.9905076340029512,
+        0.9933372302145898,
+        0.9951020953587338,
+        0.9954008313862583,
+        0.9961625558288791,
+        0.9965977871531173,
+        0.9968882183296771,
+        0.997179942794993,
+        0.9975472675471366,
+        0.9977047993223879,
+        0.9980483460652677,
+        0.9982810467481613,
+        0.9984322096916693,
+        0.9985130795195133,
+        0.9987035832261737,
+        0.9988488200344617,
+        0.9990080705360521
+    ],
+    "val_loss": [
+        305.71448699521346,
+        160.61727652751225,
+        80.21698145799233,
+        98.31909397286428,
+        49.420991561782195,
+        59.082267438861685,
+        43.67495231897059,
+        72.63750117933246,
+        48.056477439235636,
+        41.66889061726315,
+        35.77338268387486,
+        35.76565934570743,
+        31.368162182015432,
+        33.274764087838186,
+        33.155672825558085,
+        35.2773457245088,
+        27.710626266372035,
+        31.434065845650686,
+        34.327566388627176
+    ],
+    "val_rmse": [
+        17.022804091540404,
+        12.271968236097596,
+        8.72418977659167,
+        9.709547110801775,
+        6.7575173606994605,
+        7.409723379025435,
+        6.299271141309055,
+        8.006477652290222,
+        6.648790959508824,
+        6.184272301984485,
+        5.669115998567993,
+        5.690017370100179,
+        5.339802895383791,
+        5.477513496694701,
+        5.518767848296002,
+        5.65460351262253,
+        5.089552422218077,
+        5.38412636710746,
+        5.598072784959465
+    ],
+    "val_mae": [
+        10.921298624764026,
+        8.098800907672292,
+        5.978513751231449,
+        6.6365152278416595,
+        4.7836375807372615,
+        5.320080206427775,
+        4.492307612593745,
+        5.221484758484531,
+        4.820733540494677,
+        4.5011892285145505,
+        4.127895778333637,
+        4.077923868743467,
+        3.8279382947465064,
+        3.8839682491732317,
+        4.023950902509018,
+        3.9869604480098673,
+        3.7528539744900984,
+        3.9172230438447335,
+        4.0608437061309814
+    ],
+    "val_ndcg": [
+        0.9772571300117063,
+        0.9857122864521725,
+        0.9920756976369401,
+        0.9934450102524018,
+        0.9934527152021166,
+        0.9938533314516846,
+        0.9945179601790199,
+        0.9936678846117476,
+        0.9944843129372932,
+        0.9952997682799756,
+        0.9957836681688336,
+        0.9954666562483344,
+        0.9959287416767066,
+        0.9957366736841874,
+        0.9958119459555183,
+        0.9955161961031632,
+        0.9962866423835217,
+        0.9957908878863697,
+        0.9961979238080306
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250102_210550.json

@@ -0,0 +1,200 @@
+{
+    "train_loss": [
+        1573.4106846580023,
+        241.66802635675745,
+        129.58585886110234,
+        81.33055539976192,
+        60.043437613716605,
+        49.388961017886295,
+        42.711713415157945,
+        37.04401670226568,
+        31.510297592682175,
+        28.098169061202036,
+        24.962806463996067,
+        22.979653856422328,
+        20.624650590781926,
+        18.37248856508279,
+        16.41032188376294,
+        15.106652148162262,
+        13.923152925092962,
+        12.319169042608406,
+        11.82735844239404,
+        11.080743769301645
+    ],
+    "train_rmse": [
+        34.87875299744444,
+        14.987261795962356,
+        11.041098153423027,
+        8.77760558087468,
+        7.553408715871261,
+        6.851181174457468,
+        6.383387834579968,
+        5.959030248017024,
+        5.510335440600911,
+        5.21213214792664,
+        4.909669503700807,
+        4.7199303371251276,
+        4.454014988545468,
+        4.2114133277321955,
+        3.98082874088483,
+        3.8168967012856276,
+        3.6601786489112054,
+        3.4488687216236493,
+        3.381452993476122,
+        3.263646540076566
+    ],
+    "train_mae": [
+        23.23654489577571,
+        9.965823018852669,
+        7.528117040290108,
+        6.2109670386284215,
+        5.483522375550451,
+        5.0336463987072815,
+        4.707722712921191,
+        4.446547166078905,
+        4.185598470364945,
+        3.958317776646795,
+        3.72663677229157,
+        3.6098021332976185,
+        3.396712816968749,
+        3.2209290422593493,
+        3.036197697437262,
+        2.9069111562227903,
+        2.789865439639816,
+        2.63726353588738,
+        2.5662053268921525,
+        2.475501270045208
+    ],
+    "train_ndcg": [
+        0.8705413748474815,
+        0.9820866142458553,
+        0.9893646090279652,
+        0.993068425055546,
+        0.9943591235559198,
+        0.995412773252288,
+        0.9958077484293829,
+        0.9964935148629961,
+        0.9967850607029999,
+        0.9972585009623177,
+        0.9974314333705963,
+        0.9975759675608405,
+        0.9978548384542707,
+        0.9979887845206864,
+        0.9983101436231709,
+        0.9985514830184888,
+        0.998682281261758,
+        0.9987842735799053,
+        0.9989815183644053,
+        0.9989825742720049
+    ],
+    "val_loss": [
+        242.48699736259354,
+        110.35868351896045,
+        104.70559149728695,
+        81.94685237508425,
+        59.759863571381906,
+        63.3234116460236,
+        51.44393080053195,
+        47.11555201570753,
+        44.119545775400084,
+        50.042676992819345,
+        38.21174539646632,
+        36.11512255332839,
+        33.29190435543866,
+        36.34482394473653,
+        34.90276159367091,
+        36.881933789857676,
+        30.79913027857391,
+        29.94282915222813,
+        26.5078580345906,
+        28.964485262481258
+    ],
+    "val_rmse": [
+        15.222749438304598,
+        10.259006386057093,
+        9.975184629147016,
+        8.64159275856882,
+        7.390977598876305,
+        7.406066388447391,
+        6.88580765737273,
+        6.4700765907057844,
+        6.344710511920356,
+        6.7324958332755,
+        5.816017498074644,
+        5.647238446646834,
+        5.485007851809264,
+        5.67274044556089,
+        5.584264915042236,
+        5.748266146448996,
+        5.254208615862825,
+        5.175323364620961,
+        4.899611512774226,
+        5.034349147356589
+    ],
+    "val_mae": [
+        10.016210032181002,
+        7.133039588659582,
+        6.888899380052593,
+        5.7716174830853095,
+        5.325613498687744,
+        5.063329330632384,
+        4.936540596921679,
+        4.571258101664799,
+        4.56014216114098,
+        4.771088475912389,
+        4.026445123511301,
+        4.005806899406541,
+        3.9677629907366256,
+        4.055088516692041,
+        4.026658931248624,
+        4.182556256442003,
+        3.76256963568674,
+        3.6913866660964323,
+        3.554204907215817,
+        3.5717549458355973
+    ],
+    "val_ndcg": [
+        0.981707148988482,
+        0.9877026433676062,
+        0.9903137557943102,
+        0.9918068135288399,
+        0.9937682865371167,
+        0.9937528178725444,
+        0.993917101705578,
+        0.9942726148685939,
+        0.9948195336570202,
+        0.9943590919736406,
+        0.9952160749636906,
+        0.9956254682070772,
+        0.995776547512538,
+        0.9952850341796875,
+        0.9950294519813967,
+        0.9960594983168052,
+        0.9959340909836998,
+        0.9961577998080724,
+        0.9958094618689846,
+        0.9958491266613275
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250103_030301.json

@@ -0,0 +1,56 @@
+{
+    "train_loss": [
+        6039.769612179527,
+        5941.704713169533,
+        5914.564727203756,
+        5836.091276820702
+    ],
+    "train_rmse": [
+        75.06372706676143,
+        74.61218414418902,
+        74.47395658940658,
+        73.67107757410997
+    ],
+    "train_mae": [
+        50.31086837792699,
+        50.907999479317965,
+        50.94638104076627,
+        50.31608098368101
+    ],
+    "train_ndcg": [
+        0.36966318728496567,
+        0.3835963750894688,
+        0.38830770708950635,
+        0.451513979324623
+    ],
+    "val_loss": [
+        5906.023872482944,
+        5803.814482353103,
+        5709.954079211598,
+        5801.15322489134
+    ],
+    "val_rmse": [
+        74.61562375812093,
+        72.7763033395989,
+        72.59723830805083,
+        73.05621628711616
+    ],
+    "val_mae": [
+        57.40647469104176,
+        45.45087704188387,
+        49.78841300749443,
+        49.173527166876994
+    ],
+    "val_ndcg": [
+        0.3630109893184313,
+        0.4052694315012072,
+        0.7254581948820974,
+        0.3376818069479835
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250103_030828.json

@@ -0,0 +1,200 @@
+{
+    "train_loss": [
+        1475.7049554993835,
+        379.17743226546276,
+        170.54567088960093,
+        104.06700551057163,
+        76.1038736602928,
+        59.17003956625733,
+        51.22404585005362,
+        43.72882807405689,
+        40.60840407806107,
+        34.13230947754051,
+        31.245400774328015,
+        27.855964557279513,
+        26.76359580589246,
+        24.135131220274335,
+        21.92132758415198,
+        20.577230770376666,
+        19.48057757072811,
+        18.04268748850762,
+        17.653404054007954,
+        17.05115290684036
+    ],
+    "train_rmse": [
+        34.1962431550628,
+        18.801574966118118,
+        12.689654892251957,
+        9.87278275161242,
+        8.449554354098428,
+        7.44580231768099,
+        6.920708883027974,
+        6.429545916515828,
+        6.19063189467571,
+        5.708895129538141,
+        5.46680839896866,
+        5.169277343994283,
+        5.062612587674039,
+        4.822805409506358,
+        4.588967730179266,
+        4.45248032017342,
+        4.333507796834372,
+        4.169329592103006,
+        4.1118980921011445,
+        4.041849615971436
+    ],
+    "train_mae": [
+        22.27033799509459,
+        12.89405941812298,
+        8.832277373422551,
+        6.853627974473977,
+        5.98043404764767,
+        5.36616400299193,
+        5.0564211214645,
+        4.735194380902037,
+        4.577013487302804,
+        4.306544921820676,
+        4.119050872854039,
+        3.942401315969757,
+        3.8522814964946313,
+        3.6689407468973836,
+        3.5085206480720377,
+        3.4013164577227606,
+        3.3126965953579433,
+        3.1720640664990944,
+        3.1186785250902176,
+        3.043237811779674
+    ],
+    "train_ndcg": [
+        0.8878439911464348,
+        0.9664217960796778,
+        0.9849025442064563,
+        0.9909372538139548,
+        0.992851044181027,
+        0.9944684115014498,
+        0.9955004250890092,
+        0.9954500748198244,
+        0.9963730471798137,
+        0.9967452410278441,
+        0.9970897467264647,
+        0.997403313936312,
+        0.9972991103990169,
+        0.9975678757587566,
+        0.9974553273825706,
+        0.9980509397161158,
+        0.9981773383443868,
+        0.998248864295362,
+        0.9982810442960715,
+        0.9985020799161513
+    ],
+    "val_loss": [
+        518.2866107779489,
+        196.49689827502613,
+        108.25126443782322,
+        82.35544583495233,
+        64.4055624142499,
+        64.73163228639415,
+        69.00259841327936,
+        73.7572065541442,
+        46.70021191449233,
+        51.2034899348944,
+        59.88945630570532,
+        46.171227925260304,
+        38.14610894968812,
+        41.36720026043099,
+        40.145658331857604,
+        40.95807745758916,
+        36.44995172258834,
+        37.648309882258026,
+        40.110850562512034,
+        34.8642008741137
+    ],
+    "val_rmse": [
+        22.175751544849163,
+        13.627327422581926,
+        10.084425877541213,
+        8.7474406358769,
+        7.698267432884312,
+        7.714951849599426,
+        7.970698293332266,
+        8.308298844563378,
+        6.3903562067549045,
+        6.7515749053250795,
+        7.348427681843771,
+        6.375031763854914,
+        5.864137658752988,
+        6.080929566007648,
+        5.97723259149377,
+        6.083237096050345,
+        5.640871318599802,
+        5.7711622988360025,
+        5.998258900137503,
+        5.628703590478307
+    ],
+    "val_mae": [
+        15.3913011416583,
+        9.468683840523303,
+        6.864865544816138,
+        6.077065958103663,
+        5.370076864538058,
+        5.423657706086065,
+        5.450087026810982,
+        5.731729675346697,
+        4.450722744767095,
+        4.684651660247588,
+        5.084945682068946,
+        4.410807441657697,
+        4.10906414246895,
+        4.262183797191566,
+        4.182462527718343,
+        4.403699760705653,
+        3.9841212252495994,
+        4.099793424069042,
+        4.281244986493823,
+        4.025566181666415
+    ],
+    "val_ndcg": [
+        0.9491317574407013,
+        0.9809850437540404,
+        0.9894338082259809,
+        0.9927881418819159,
+        0.9925727038316323,
+        0.993241311798633,
+        0.9938505401074047,
+        0.9935763100503197,
+        0.9939105409971425,
+        0.9937452371691314,
+        0.9939587519202434,
+        0.9940523916566876,
+        0.9945629667228376,
+        0.9945879385504924,
+        0.9951134777404893,
+        0.9949196988428143,
+        0.9954190170261222,
+        0.9959209158386982,
+        0.9951174175235588,
+        0.9956686404389394
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250103_033513.json

@@ -0,0 +1,200 @@
+{
+    "train_loss": [
+        1435.060329775267,
+        352.2340569315077,
+        164.56359785417968,
+        96.81200471105454,
+        67.34939731525469,
+        53.12608155419555,
+        44.58751765987541,
+        38.42660973796362,
+        34.44303543205503,
+        31.319766175897815,
+        28.912457778484008,
+        27.199046002913125,
+        25.081022571913802,
+        22.87438059079496,
+        20.80075543439841,
+        20.669258119939247,
+        18.51449005965945,
+        17.437184510351738,
+        15.839009639205813,
+        14.724061391021632
+    ],
+    "train_rmse": [
+        34.16462143750128,
+        18.133741742649008,
+        12.479908767197573,
+        9.533131123991046,
+        7.993323629576951,
+        7.129096690749047,
+        6.538397691999737,
+        6.06964856221789,
+        5.755456311497981,
+        5.487252373904924,
+        5.260899197134256,
+        5.112084049532784,
+        4.906783164787575,
+        4.686919144259876,
+        4.482920539985945,
+        4.449389267406377,
+        4.2221425125174985,
+        4.077745623309648,
+        3.9076029899822107,
+        3.7612553914109483
+    ],
+    "train_mae": [
+        22.42367218717744,
+        12.666036196147338,
+        8.629599928101406,
+        6.682308893792237,
+        5.701853976219515,
+        5.185871489440339,
+        4.8233660508560225,
+        4.548375989440121,
+        4.338121420220483,
+        4.163119960057585,
+        3.989376880700075,
+        3.886762281761894,
+        3.732258479806441,
+        3.5699768172034734,
+        3.437376656864263,
+        3.360495426986791,
+        3.2160783613784405,
+        3.0981060236315185,
+        2.9636218747760674,
+        2.8468211540315727
+    ],
+    "train_ndcg": [
+        0.8861735068686023,
+        0.9673905631975283,
+        0.9857557027400294,
+        0.9915234359759318,
+        0.9942724066255968,
+        0.9951469133360477,
+        0.9957965078610408,
+        0.9963700529895251,
+        0.9968566370161274,
+        0.9970038944407354,
+        0.9973822481270078,
+        0.9971672230506246,
+        0.9975094205782383,
+        0.9977648538313334,
+        0.9980179846664018,
+        0.9981356275421155,
+        0.998470520105543,
+        0.9984775487380692,
+        0.9987470709447619,
+        0.9987366080661363
+    ],
+    "val_loss": [
+        410.4469845194212,
+        182.80695052885673,
+        106.04734818364533,
+        68.17160872338523,
+        50.6360629444391,
+        68.64627241752517,
+        45.423886285701265,
+        78.9354918305303,
+        44.831697356533,
+        41.634061155184895,
+        43.157917936083294,
+        40.68462800308013,
+        39.753396558089996,
+        44.02809227688212,
+        48.21740244475888,
+        35.52609372474778,
+        42.4773176891703,
+        39.13388240169471,
+        34.04803727378308,
+        56.9983289745492
+    ],
+    "val_rmse": [
+        19.807712859563207,
+        13.154047283218882,
+        9.973827810514075,
+        7.9165926582847925,
+        6.7908423920085985,
+        7.912192454970619,
+        6.277257651484929,
+        8.45227570668767,
+        6.338847829619797,
+        6.025232891791129,
+        6.0758578337285165,
+        5.943435587770236,
+        5.847326947488449,
+        6.090798816429889,
+        6.580154817004584,
+        5.534270403127238,
+        6.03797093456972,
+        5.794032251456846,
+        5.2841298330328055,
+        7.244037790588833
+    ],
+    "val_mae": [
+        14.308727197244133,
+        8.982651488881716,
+        6.783395169486462,
+        5.465634762401312,
+        4.799200672498891,
+        5.412561322601748,
+        4.415327538906689,
+        5.735453635873929,
+        4.556723201778573,
+        4.222258715562417,
+        4.230704216889932,
+        4.195163380931801,
+        4.090030817918374,
+        4.1431486237217,
+        4.625208894971391,
+        3.9091772327960377,
+        4.2994451388506825,
+        4.042285610252703,
+        3.663872933723557,
+        5.090360748935753
+    ],
+    "val_ndcg": [
+        0.9563382897578495,
+        0.9829646886234552,
+        0.9902353975134837,
+        0.9931762016994853,
+        0.9938783435754373,
+        0.9936022330337847,
+        0.9940772854106527,
+        0.9942635306170289,
+        0.994526959640879,
+        0.994710107084731,
+        0.9943417713675701,
+        0.9952644856882767,
+        0.9947412333018343,
+        0.9947131947732307,
+        0.9957452072224147,
+        0.9959601877440869,
+        0.9957177504687242,
+        0.9960256244095278,
+        0.9959515937617127,
+        0.9956882721941236
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250103_043332.json

@@ -0,0 +1,200 @@
+{
+    "train_loss": [
+        1351.0113486277905,
+        352.3077262866346,
+        167.32429698750943,
+        103.08953188944467,
+        69.1875813610946,
+        54.25784658631192,
+        44.57601911055891,
+        40.01520497285867,
+        34.644554676888866,
+        31.293750059001052,
+        28.812668193744706,
+        26.442434762097612,
+        23.031041573874557,
+        22.20530678350714,
+        19.99327388669871,
+        18.68147025908096,
+        16.995510369916506,
+        15.845708420005026,
+        15.787844214258314,
+        14.747453052031842
+    ],
+    "train_rmse": [
+        33.209800136624345,
+        18.2435796333922,
+        12.549612336516933,
+        9.841988781026261,
+        8.071622587094533,
+        7.137606808702729,
+        6.477514088010586,
+        6.162852056927469,
+        5.755617270195042,
+        5.477392564370788,
+        5.256519986669205,
+        5.046400770248145,
+        4.708584689891357,
+        4.619441727399584,
+        4.395451810730182,
+        4.227234469912232,
+        4.049099866559392,
+        3.9108673639536904,
+        3.8833373469625383,
+        3.755766218028664
+    ],
+    "train_mae": [
+        22.03341102298302,
+        12.686087564577031,
+        8.723137673697893,
+        6.865933564644825,
+        5.739644124915328,
+        5.1618613159354725,
+        4.776871337920805,
+        4.587744018699549,
+        4.33242931773391,
+        4.157995220981067,
+        3.993489240543752,
+        3.8578739743443986,
+        3.6205275092698352,
+        3.532670849486242,
+        3.3538063560860065,
+        3.2110798879514766,
+        3.0780662824458713,
+        2.972256003301355,
+        2.912875095122977,
+        2.8233952163895473
+    ],
+    "train_ndcg": [
+        0.8791214263514627,
+        0.9651105227538302,
+        0.9844696806578697,
+        0.9911428662606433,
+        0.9935568665401845,
+        0.9948240366729,
+        0.9953797318135635,
+        0.995786432223984,
+        0.9964222386479378,
+        0.9969813658655444,
+        0.9970793777817413,
+        0.9971918700427949,
+        0.9978629457233827,
+        0.9979353491452676,
+        0.9979386804979059,
+        0.9981750877031798,
+        0.9985391404243964,
+        0.9983644762748405,
+        0.9987040338448331,
+        0.99851057178612
+    ],
+    "val_loss": [
+        416.53340750680843,
+        190.91952998201612,
+        104.1640454144545,
+        72.3938918315189,
+        73.03941280741087,
+        49.85962137034242,
+        48.56202842819859,
+        48.4794106281979,
+        40.51393108636561,
+        43.22256162133015,
+        41.64596470308975,
+        37.488306649973694,
+        41.163437480657876,
+        40.262249718249684,
+        41.858627131287484,
+        33.52191503283004,
+        35.463427651096396,
+        34.34374282729458,
+        35.07537248772635,
+        35.725776531326936
+    ],
+    "val_rmse": [
+        20.037238599342864,
+        13.578766652473123,
+        9.972929540364614,
+        8.205374721377183,
+        8.255005243890967,
+        6.720256714664904,
+        6.593885938298914,
+        6.5710771451384025,
+        5.956024617439825,
+        6.109059175367006,
+        6.1021625173050005,
+        5.629496071562468,
+        6.040688794055788,
+        6.02400883553649,
+        6.181112128194623,
+        5.4490271083728095,
+        5.579791722023324,
+        5.5375956799899,
+        5.512524228406886,
+        5.587302219995305
+    ],
+    "val_mae": [
+        13.448163207148163,
+        9.25817228370989,
+        6.8640187357513,
+        5.719145002499433,
+        5.654466313375553,
+        4.759454754036917,
+        4.746351557718197,
+        4.631843724720914,
+        4.244970445901576,
+        4.2405674323229725,
+        4.311174513588489,
+        3.970265506019055,
+        4.271067021598278,
+        4.344380452599324,
+        4.383088038001262,
+        3.914992782431589,
+        3.9759923236470827,
+        3.9289716364632192,
+        3.853868887458049,
+        3.879887836080202
+    ],
+    "val_ndcg": [
+        0.9552615352079902,
+        0.9803778302501625,
+        0.9900085867290765,
+        0.9927245554789691,
+        0.9929810569319927,
+        0.9937699966027703,
+        0.9954146490970128,
+        0.9936058378555406,
+        0.9941671062523211,
+        0.9947078941573559,
+        0.9938346449757965,
+        0.9955057291917397,
+        0.9949795964738013,
+        0.9951892134169458,
+        0.9950296677334208,
+        0.9954134653991377,
+        0.9948479037889293,
+        0.9956618916820472,
+        0.9953685369290096,
+        0.9951692357869215
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250103_044652.json

@@ -0,0 +1,200 @@
+{
+    "train_loss": [
+        1568.4600394526615,
+        380.66691172877444,
+        186.19200922869427,
+        100.4270657587655,
+        63.62437669989429,
+        54.30184430562997,
+        44.79294805285297,
+        39.49484346335447,
+        34.37678491465653,
+        33.189656402491316,
+        28.456958789614184,
+        26.819092845614954,
+        24.388968602011474,
+        22.539706074738806,
+        21.393888397307336,
+        21.72506937346881,
+        18.861068978339812,
+        18.040212118927435,
+        16.478899402708947,
+        16.40729931562762
+    ],
+    "train_rmse": [
+        35.548012435356554,
+        18.833375530651306,
+        13.181894009336585,
+        9.730285929416734,
+        7.768600108746146,
+        7.177732931851947,
+        6.531449950219701,
+        6.137238532111352,
+        5.733839722016422,
+        5.634765137953384,
+        5.231876051724629,
+        5.0846880401971495,
+        4.860513306432777,
+        4.66520351242637,
+        4.541058985538234,
+        4.54559837113959,
+        4.258056244870012,
+        4.154343473970143,
+        3.975153880119614,
+        3.9717052584565744
+    ],
+    "train_mae": [
+        23.885840191116817,
+        12.806354168095167,
+        8.911165521869176,
+        6.75464779704432,
+        5.5718319597123545,
+        5.191718755643579,
+        4.798439809415914,
+        4.567531941812249,
+        4.311504548863519,
+        4.217083642377129,
+        3.9817271043982685,
+        3.8729505618161792,
+        3.722985306118108,
+        3.5677872411435163,
+        3.455016141450858,
+        3.4211620231972466,
+        3.250691982198365,
+        3.1469848567171943,
+        3.0175175525342364,
+        2.981323989886272
+    ],
+    "train_ndcg": [
+        0.8788194583398821,
+        0.966001775162884,
+        0.9844999542530579,
+        0.9917020818477944,
+        0.9941305821832223,
+        0.9949844571985776,
+        0.9958647024593775,
+        0.99609034367,
+        0.9968955215962627,
+        0.9968772376828556,
+        0.9968342000170599,
+        0.9971945462158963,
+        0.9974722178487838,
+        0.9978334335963938,
+        0.9980168634954887,
+        0.9980882780649994,
+        0.9983908321849907,
+        0.9983578184737435,
+        0.9985815234765222,
+        0.9986211659410332
+    ],
+    "val_loss": [
+        480.90674945670116,
+        221.32546642464652,
+        119.41638223889848,
+        71.85167360977388,
+        61.77250488711075,
+        50.31877966330085,
+        45.95686971637565,
+        47.26317527932181,
+        42.16901689180186,
+        48.815807651466045,
+        43.76307472712557,
+        47.48831813436159,
+        39.1390000464211,
+        45.411110475029744,
+        37.73349936579315,
+        39.927634789910115,
+        36.944171274212046,
+        41.41304953669159,
+        35.50801792950698,
+        32.267287845342935
+    ],
+    "val_rmse": [
+        21.523574966213687,
+        14.500466189588247,
+        10.713845038053803,
+        8.220808155284956,
+        7.514927146441144,
+        6.752058818549558,
+        6.462109366346076,
+        6.511514011606931,
+        6.158016624407551,
+        6.581518399887021,
+        6.202932100631911,
+        6.500268678699365,
+        5.90938766806474,
+        6.40362695837909,
+        5.69099401318934,
+        5.916818186110754,
+        5.705122979201211,
+        6.073733684418374,
+        5.6619658280147735,
+        5.327907316202149
+    ],
+    "val_mae": [
+        14.952053258116816,
+        9.653207577450175,
+        7.315994601854136,
+        5.805767361546906,
+        5.203530687681386,
+        4.783049848717703,
+        4.532520059128882,
+        4.608333439894126,
+        4.3324834057982535,
+        4.6344721921732726,
+        4.302189464300451,
+        4.506923057663609,
+        4.166391057027897,
+        4.4321763280411846,
+        3.919857750476246,
+        4.015890766197527,
+        4.011639339823119,
+        4.196899498012704,
+        4.0046954658669485,
+        3.760457559370659
+    ],
+    "val_ndcg": [
+        0.951992391700476,
+        0.977657847001519,
+        0.9905902751734559,
+        0.9921590744609564,
+        0.9932476533970362,
+        0.9936211083976316,
+        0.9946853535276063,
+        0.9945137148172083,
+        0.9951216788359092,
+        0.9952481229540328,
+        0.9955367848906719,
+        0.9950585843811572,
+        0.9953058387192202,
+        0.9952809441257531,
+        0.9950784814189857,
+        0.99469767322003,
+        0.9955671723459808,
+        0.9958358297885304,
+        0.9950448165477161,
+        0.9960291091824921
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250103_092757.json

@@ -0,0 +1,200 @@
+{
+    "train_loss": [
+        35.48313679539044,
+        0.3329015611376189,
+        0.2187574881724306,
+        0.18027265684950294,
+        0.1406513607848577,
+        0.1254000432385556,
+        0.11406336508874039,
+        0.10675579064991325,
+        0.09156012369313903,
+        0.07837757181090338,
+        0.07272699182923836,
+        0.06715140057598017,
+        0.062056878547750036,
+        0.05528454597276058,
+        0.041029059951476564,
+        0.0335420139783793,
+        0.036650182961492174,
+        0.029730955377159217,
+        0.028419958240399727,
+        0.02979619682197683
+    ],
+    "train_rmse": [
+        3.566621652047163,
+        0.530789752552005,
+        0.42882655275830606,
+        0.39050047079668965,
+        0.3451002656171299,
+        0.3198269751787553,
+        0.3001346394637745,
+        0.2921615258101418,
+        0.2725297490255808,
+        0.2540439729435462,
+        0.246652456054755,
+        0.23201455367153614,
+        0.22159482499638555,
+        0.2105041584167228,
+        0.17940080854646312,
+        0.16423403010169302,
+        0.16818002084247397,
+        0.156031105634702,
+        0.15166975253445347,
+        0.15514037664907793
+    ],
+    "train_mae": [
+        2.474846361275715,
+        0.35925816277725786,
+        0.2973010249176546,
+        0.2712645805028232,
+        0.23956697093487916,
+        0.22156769500550214,
+        0.20947162143273068,
+        0.20169177190459606,
+        0.18987821878370229,
+        0.17740302610717998,
+        0.16870605046094594,
+        0.15788957317465846,
+        0.15054547920516587,
+        0.14159253656369034,
+        0.12221413583765868,
+        0.11224046216310957,
+        0.1128907774315699,
+        0.10629052081133557,
+        0.10315093468827537,
+        0.10465153291986524
+    ],
+    "train_ndcg": [
+        0.7558364655765044,
+        0.9866188587267187,
+        0.9924304947445665,
+        0.9944303837380831,
+        0.9945827830064146,
+        0.9955582045301606,
+        0.9960351542015619,
+        0.9960824549198151,
+        0.9969269312635253,
+        0.9973954099077212,
+        0.9975902201442779,
+        0.9975214942912513,
+        0.9980273539129692,
+        0.9979620438210571,
+        0.9985541199581532,
+        0.9987976839648017,
+        0.9990266956671884,
+        0.9990728838911539,
+        0.99896576755409,
+        0.9988336536703231
+    ],
+    "val_loss": [
+        0.1295502951342455,
+        0.2112117204028116,
+        0.06708751296178556,
+        0.07748625563903594,
+        0.026657289018670857,
+        0.03803096673595653,
+        0.11389587175520793,
+        0.019189091058264315,
+        9.442593926262163,
+        0.06281777142389665,
+        0.04309269220200958,
+        0.028098553369923587,
+        0.028143494626061177,
+        0.029877805413389708,
+        0.06912251699610915,
+        0.017713357130406608,
+        0.023466069523481205,
+        0.040607516850594064,
+        0.01309489512907892,
+        0.05713046110615554
+    ],
+    "val_rmse": [
+        0.3452739258859094,
+        0.38631782291620353,
+        0.2544532690529006,
+        0.26332937789789096,
+        0.15258707677027508,
+        0.180040440315543,
+        0.317377862802537,
+        0.1345261631668834,
+        0.6976586474660478,
+        0.23486453598215457,
+        0.19250496017195456,
+        0.15698165336840292,
+        0.159735350016474,
+        0.16061959243152069,
+        0.25054671630297654,
+        0.1271297410243889,
+        0.14636496537083996,
+        0.18951016164216974,
+        0.1060548357531114,
+        0.2244844007582963
+    ],
+    "val_mae": [
+        0.24210304588499204,
+        0.21295641247235553,
+        0.17747273296117783,
+        0.16516592374569933,
+        0.09974751967779348,
+        0.11922594799961843,
+        0.1758638471364975,
+        0.09786017784770105,
+        0.21067505287872235,
+        0.12701583128999655,
+        0.10494426013508314,
+        0.09307881859196744,
+        0.11108123605519953,
+        0.10864213707161621,
+        0.1366678663122822,
+        0.0756039809907826,
+        0.08223065046567313,
+        0.10061165155239508,
+        0.06615498132059272,
+        0.1153957793935084
+    ],
+    "val_ndcg": [
+        0.9898358978016276,
+        0.9916317068355184,
+        0.9960200240914251,
+        0.9962448696015587,
+        0.9982525723081239,
+        0.9980665319402453,
+        0.9982161471541499,
+        0.9984719904375748,
+        0.9983214626849537,
+        0.9979129400051815,
+        0.9987074657225273,
+        0.9983981830973021,
+        0.9983506748374079,
+        0.998569496080909,
+        0.9996046138481355,
+        0.9992532646152336,
+        0.9991910919337206,
+        0.9996341869864666,
+        0.9994951436217402,
+        0.9995241685652397
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.0005,
+        0.0005
+    ]
+}

metrics/training_metrics_20250103_165619.json

@@ -0,0 +1,65 @@
+{
+    "train_loss": [
+        17.839974135632,
+        0.3717077037531741,
+        0.27244204249162274,
+        0.20226187456717504,
+        0.15897851241192532
+    ],
+    "train_rmse": [
+        2.513843766362758,
+        0.5616386250729694,
+        0.4718983753994247,
+        0.4053866316095696,
+        0.3614962610700034
+    ],
+    "train_mae": [
+        1.8133598699034015,
+        0.41028543391936945,
+        0.34171164455481723,
+        0.2959879683448544,
+        0.2629419069595729
+    ],
+    "train_ndcg": [
+        0.7995104605473483,
+        0.9858645969365216,
+        0.9920885355412206,
+        0.9945323769993419,
+        0.9957412415290181
+    ],
+    "val_loss": [
+        3.491730105079396,
+        0.11632824206436185,
+        0.0817769760606994,
+        0.04945154333303512,
+        0.032795523575336584
+    ],
+    "val_rmse": [
+        0.6826991777101171,
+        0.3341630921570146,
+        0.2778393792775709,
+        0.21099134118754137,
+        0.16966517827770045
+    ],
+    "val_mae": [
+        0.3260452077842095,
+        0.2573499553640124,
+        0.1916451218052649,
+        0.13111490493928882,
+        0.11222708917839426
+    ],
+    "val_ndcg": [
+        0.9786449779926891,
+        0.9901216953573092,
+        0.9963186937318721,
+        0.9982596190882401,
+        0.9985142963033327
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_000005.json

@@ -0,0 +1,83 @@
+{
+    "train_loss": [
+        25.03897695070062,
+        0.4459359470071106,
+        0.27832151357603224,
+        0.20583774432940763,
+        0.18026240458240425,
+        0.14846552507008745,
+        0.13040077824387228
+    ],
+    "train_rmse": [
+        3.0084060317310333,
+        0.6273383269022131,
+        0.490819894011052,
+        0.4215487596927151,
+        0.38429657859467986,
+        0.34830508471687494,
+        0.32169545626989093
+    ],
+    "train_mae": [
+        2.131225818838877,
+        0.4455115708133465,
+        0.348309932229451,
+        0.30484239554292036,
+        0.27675854565599295,
+        0.2519048037879829,
+        0.23417054670803908
+    ],
+    "train_ndcg": [
+        0.7440686262193537,
+        0.9760115248493001,
+        0.9892069459715976,
+        0.9922320850287811,
+        0.9943632159052016,
+        0.9953864646863334,
+        0.996499631035177
+    ],
+    "val_loss": [
+        1.486161563702872,
+        0.22653832601409563,
+        0.13026042740372284,
+        0.660742336411921,
+        0.05408989013710492,
+        235.78654905395504,
+        230.38252206704198
+    ],
+    "val_rmse": [
+        0.6370334281670409,
+        0.4570268694023932,
+        0.31359623377048396,
+        0.3187152725970594,
+        0.22422285815586,
+        2.016764449154497,
+        1.9790944850806804
+    ],
+    "val_mae": [
+        0.35360592939484287,
+        0.34342973102146473,
+        0.173662431538105,
+        0.16381227319509212,
+        0.15005545307632903,
+        0.4578449399748319,
+        0.43453011346954695
+    ],
+    "val_ndcg": [
+        0.9759331832469349,
+        0.990474347497376,
+        0.9955524055051131,
+        0.9955590568797689,
+        0.9953686981134011,
+        0.9971668946910912,
+        0.9971519842953749
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_002329.json

@@ -0,0 +1,65 @@
+{
+    "train_loss": [
+        654.9977416510918,
+        133.8768731886014,
+        77.50994042476334,
+        57.487973242325296,
+        45.93395253734918
+    ],
+    "train_rmse": [
+        21.76599518576593,
+        10.92139800435689,
+        8.43026184290633,
+        7.31956257053143,
+        6.586492155885355
+    ],
+    "train_mae": [
+        12.904080948823319,
+        7.260352644629054,
+        6.020984615146085,
+        5.396023633153948,
+        4.993897577364289
+    ],
+    "train_ndcg": [
+        0.8222233522745223,
+        0.9201224937560074,
+        0.935419495184108,
+        0.9456507629191733,
+        0.9510964462323335
+    ],
+    "val_loss": [
+        233.38946832929338,
+        94.92865151450748,
+        84.01622210230146,
+        88.02083689825875,
+        251.29637086959113
+    ],
+    "val_rmse": [
+        14.416855071947188,
+        9.046542380697913,
+        8.66063907904624,
+        8.716143566689402,
+        8.070561499731667
+    ],
+    "val_mae": [
+        9.039377394176665,
+        6.144316837901161,
+        6.062099817253294,
+        5.8308244077932265,
+        5.27947231843358
+    ],
+    "val_ndcg": [
+        0.901470630740126,
+        0.9210642547391,
+        0.9303346751701265,
+        0.934778360561246,
+        0.9401383463382011
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_003816.json

@@ -0,0 +1,101 @@
+{
+    "train_loss": [
+        655.2924103831865,
+        137.81348060136773,
+        77.87851923997026,
+        60.0420509011622,
+        46.96173634598771,
+        40.52427888644802,
+        35.571622559115546,
+        31.858311056299197,
+        27.281973488302345
+    ],
+    "train_rmse": [
+        21.63339813905697,
+        11.078644741924332,
+        8.481624908336705,
+        7.476557546854199,
+        6.660614014874347,
+        6.191670639031987,
+        5.810964058506354,
+        5.503427484370053,
+        5.096925591852883
+    ],
+    "train_mae": [
+        12.795672080114702,
+        7.30440814957359,
+        6.002602778582934,
+        5.495873220255017,
+        5.041820852088422,
+        4.739296629925965,
+        4.417383114813492,
+        4.152467428450565,
+        3.7957898891304596
+    ],
+    "train_ndcg": [
+        0.8197692561558241,
+        0.9231711810932137,
+        0.9376293856843534,
+        0.9425875070204298,
+        0.9503919912445276,
+        0.9540359039393911,
+        0.9593489245668667,
+        0.9625757746151086,
+        0.9665195502410056
+    ],
+    "val_loss": [
+        182.59727460997445,
+        115.0690230414981,
+        127.87416275909969,
+        70.06721037910098,
+        80.27486997558957,
+        59.44625475293114,
+        55.08135130291893,
+        55.871143658955894,
+        6659.085475047429
+    ],
+    "val_rmse": [
+        12.557709290761498,
+        9.918567012807063,
+        9.48277149453734,
+        7.70885356906008,
+        8.371686730469683,
+        6.979592169329438,
+        6.689580094676087,
+        6.870983494561128,
+        13.458319354048012
+    ],
+    "val_mae": [
+        7.897627572218577,
+        6.56597325915382,
+        6.200662170137678,
+        5.50618282244319,
+        5.874495851142066,
+        5.199094084047136,
+        4.840447388944172,
+        5.065636995292845,
+        5.93146392986888
+    ],
+    "val_ndcg": [
+        0.9034571490649667,
+        0.9252599633875347,
+        0.9298035546338984,
+        0.9361445135658696,
+        0.9352943633816072,
+        0.9418964138520616,
+        0.9416976965786445,
+        0.9426969763423715,
+        0.9398589121798674
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_010732.json

@@ -0,0 +1,83 @@
+{
+    "train_loss": [
+        692.2268594424168,
+        155.58579151731894,
+        91.02494073715381,
+        62.284806612625864,
+        47.696007902716595,
+        38.79570380175977,
+        32.10595765445017
+    ],
+    "train_rmse": [
+        22.40536726075939,
+        11.802893998549271,
+        9.076339798846956,
+        7.597033458710151,
+        6.689866192745471,
+        6.0580873553579595,
+        5.513845330073774
+    ],
+    "train_mae": [
+        13.051485515691345,
+        7.651320030299294,
+        6.286715831749469,
+        5.468741066692657,
+        4.908279659856692,
+        4.434657849154426,
+        3.9721677486713114
+    ],
+    "train_ndcg": [
+        0.8087768409661309,
+        0.9128060766827535,
+        0.93383413372955,
+        0.947167278855171,
+        0.9551643581645003,
+        0.9637041410196174,
+        0.9702560895854987
+    ],
+    "val_loss": [
+        651.0634523192448,
+        133.79051945529767,
+        106.96319920696429,
+        85.06644299350567,
+        64.02761468175632,
+        73.5220956830836,
+        78.7099423735889
+    ],
+    "val_rmse": [
+        13.131415164476463,
+        10.055183463157267,
+        8.756330566095277,
+        8.131971300432767,
+        7.268484960466997,
+        7.782613046313818,
+        8.050298634841678
+    ],
+    "val_mae": [
+        8.55465096430992,
+        7.276789544233635,
+        6.283327481995768,
+        5.751810121536255,
+        5.33152237080816,
+        5.470134524445036,
+        5.669236395252285
+    ],
+    "val_ndcg": [
+        0.4010162910418724,
+        0.4096747400155708,
+        0.41334134856266763,
+        0.4137950132142252,
+        0.4159794373298759,
+        0.41582945051477915,
+        0.4164658988589671
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_011443.json

@@ -0,0 +1,128 @@
+{
+    "train_loss": [
+        747.3488913914265,
+        145.96466789430784,
+        86.39479489572196,
+        64.20039664960068,
+        51.28491067993187,
+        43.607586832167584,
+        36.55425032472504,
+        31.25288286166373,
+        28.14833299431719,
+        23.908967951859353,
+        21.428236955666915,
+        18.679253836012848
+    ],
+    "train_rmse": [
+        23.184188219227416,
+        11.45168295735762,
+        8.8864819143681,
+        7.723792975325597,
+        6.940280548097029,
+        6.405828542767508,
+        5.8662402382937495,
+        5.424234613831899,
+        5.121161785708606,
+        4.746361522360717,
+        4.497774703122681,
+        4.185096451859765
+    ],
+    "train_mae": [
+        13.71706475349751,
+        7.50529452007684,
+        6.259701011606435,
+        5.580138392729756,
+        5.098060473476977,
+        4.688325964576545,
+        4.2858362388397175,
+        3.895885395327106,
+        3.616349921198012,
+        3.3526823201047744,
+        3.12058784901161,
+        2.8688033105189272
+    ],
+    "train_ndcg": [
+        0.8063238421107257,
+        0.9175900664511593,
+        0.9312679269883151,
+        0.9422594188664545,
+        0.9506532769981296,
+        0.9590009508558491,
+        0.9641841692742881,
+        0.9713488008390174,
+        0.9751414411810461,
+        0.9765989279195032,
+        0.9805166315373598,
+        0.984279945949016
+    ],
+    "val_loss": [
+        184.07673564455402,
+        108.30949287983908,
+        90.20219907618281,
+        473.1458847216706,
+        72.058516757168,
+        68.01195372823459,
+        67.81648602841506,
+        58.370672943342974,
+        61.947438388795995,
+        52.14976073023099,
+        63.069723879401366,
+        54.61616339754703
+    ],
+    "val_rmse": [
+        11.634516435881071,
+        9.221781411128266,
+        8.318100175119454,
+        9.578305728731655,
+        7.4885203644097045,
+        7.3712299298358985,
+        7.198502113314191,
+        6.9242316173129375,
+        6.918810462818225,
+        6.618950349174297,
+        7.152791654657651,
+        6.622356772554203
+    ],
+    "val_mae": [
+        8.255931179559052,
+        6.688144994137892,
+        5.8846641960428725,
+        6.175251124510124,
+        5.329085095249005,
+        5.345389533398756,
+        5.003653562246863,
+        5.040316158977907,
+        4.728284999861646,
+        4.580177233112392,
+        4.811583769499366,
+        4.467982399997426
+    ],
+    "val_ndcg": [
+        0.40758441028310294,
+        0.4145419465961741,
+        0.41645416679667,
+        0.4170703012551834,
+        0.4193937687731501,
+        0.41901908401233046,
+        0.41975115822322334,
+        0.4202720586933307,
+        0.42026146952785665,
+        0.4205170225741258,
+        0.42038892685477414,
+        0.4204279004637875
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_012344.json

@@ -0,0 +1,173 @@
+{
+    "train_loss": [
+        722.9548574494639,
+        146.40175312147647,
+        85.42187348865056,
+        60.501964287049205,
+        46.8718575875736,
+        38.23729195854751,
+        32.00270525638162,
+        26.729942461018066,
+        22.60702768967524,
+        19.945530043153997,
+        17.704082511092764,
+        15.55396806561653,
+        14.22020652518511,
+        13.117395714470662,
+        11.661882876147967,
+        10.93010081454299,
+        10.063436130786494
+    ],
+    "train_rmse": [
+        22.846375160921244,
+        11.488120501193247,
+        8.85727562168705,
+        7.5123279911361145,
+        6.651862302193106,
+        6.015104275769991,
+        5.503403441923615,
+        5.023545856386948,
+        4.613676628631371,
+        4.327437248494172,
+        4.075261877032907,
+        3.8140716091468234,
+        3.6273248958625297,
+        3.482522223257597,
+        3.287567164428574,
+        3.185012855283296,
+        3.0444534353048933
+    ],
+    "train_mae": [
+        13.455125815125879,
+        7.575254692258543,
+        6.217654748671619,
+        5.466741007241498,
+        4.886993498122006,
+        4.304617277270738,
+        3.8304975337284195,
+        3.4418799343885462,
+        3.1144455406895495,
+        2.875781349587387,
+        2.696398690086946,
+        2.517050676865752,
+        2.362347985756228,
+        2.2487000726870052,
+        2.1161791984940574,
+        2.028291983956984,
+        1.9097916470079657
+    ],
+    "train_ndcg": [
+        0.8235555761219006,
+        0.9166275169964688,
+        0.9388797100663986,
+        0.9502400709809965,
+        0.9563324356631079,
+        0.9658247269606572,
+        0.9723488926175283,
+        0.9765766591078493,
+        0.9812312149752246,
+        0.9848286770812783,
+        0.985791131575843,
+        0.9877286714969774,
+        0.9889362170413147,
+        0.9895972986556061,
+        0.9907311449930506,
+        0.9918896107196452,
+        0.9920450084862912
+    ],
+    "val_loss": [
+        167.6522611874253,
+        124.15631333251498,
+        88.2374712104228,
+        77.93126045340922,
+        96.88929993216671,
+        62.72705197120781,
+        81.45877939338115,
+        56.441899389295436,
+        55.19662875559793,
+        55.066983817940326,
+        51.7734276614972,
+        74.40411837421246,
+        51.016412199789016,
+        51.02640529177082,
+        48.52456700766265,
+        52.53771702922992,
+        49.43981172220031
+    ],
+    "val_rmse": [
+        11.189840606415867,
+        9.58600997111548,
+        8.292045612260651,
+        7.99427763195157,
+        7.6412259979978945,
+        7.274987733142102,
+        7.713936945366049,
+        6.845516443905154,
+        6.897868368615047,
+        6.99134984579161,
+        6.809175488282247,
+        7.420135492837055,
+        6.766768687883562,
+        6.770783006127933,
+        6.4910948027873525,
+        6.757588578758839,
+        6.594931427040444
+    ],
+    "val_mae": [
+        7.976505904411202,
+        6.769147197524114,
+        5.974825873303769,
+        5.764017573399331,
+        5.348576226874964,
+        5.293500059754101,
+        5.225544199303015,
+        4.757777753160961,
+        4.790411420366658,
+        4.871365610165382,
+        4.69525331347736,
+        5.044188578804927,
+        4.645911375444327,
+        4.551653947047333,
+        4.403688052163195,
+        4.524548444107397,
+        4.412602953412639
+    ],
+    "val_ndcg": [
+        0.3854664285681141,
+        0.3970626523245626,
+        0.3993091859034638,
+        0.40061406377536146,
+        0.40129871381752524,
+        0.40149890638109464,
+        0.4004063760166738,
+        0.40111275430935533,
+        0.40202835949499216,
+        0.40123411852922014,
+        0.4020480241348494,
+        0.4016766359112156,
+        0.4013568968025606,
+        0.40230912454982304,
+        0.40139322908066993,
+        0.4017819784915269,
+        0.40200455873759827
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_021315.json

@@ -0,0 +1,74 @@
+{
+    "train_loss": [
+        708.2152493528861,
+        146.5171740804705,
+        85.76771927449666,
+        63.229462375028355,
+        49.763298486221004,
+        42.55385646791579
+    ],
+    "train_rmse": [
+        22.764913456014224,
+        11.484859694358866,
+        8.869339527044579,
+        7.658590551511417,
+        6.847131576050916,
+        6.3402288735225705
+    ],
+    "train_mae": [
+        13.560497156802713,
+        7.479677234504363,
+        6.2542528368983366,
+        5.5760266296537715,
+        5.116533957282672,
+        4.754307395224254
+    ],
+    "train_ndcg": [
+        0.8192471829406456,
+        0.921438950547271,
+        0.9353899640254426,
+        0.9402380620196873,
+        0.9492815241629371,
+        0.9570066111914874
+    ],
+    "val_loss": [
+        161.44745741317521,
+        109.14599984581791,
+        90.46889235368415,
+        87.12105213136816,
+        466.9354229471577,
+        1302.5879631554903
+    ],
+    "val_rmse": [
+        10.559003265112123,
+        9.104435882279088,
+        8.444436996559249,
+        8.23822649753548,
+        9.129098270401919,
+        11.23793314526776
+    ],
+    "val_mae": [
+        7.498428307718306,
+        6.650554202919576,
+        6.160198556131391,
+        5.933253830582348,
+        5.8467706381385005,
+        6.12841546784586
+    ],
+    "val_ndcg": [
+        0.40186114240048537,
+        0.4085635163890782,
+        0.41129920856276553,
+        0.4130042755781715,
+        0.41324490735779945,
+        0.41233258656601407
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_021913.json

@@ -0,0 +1,92 @@
+{
+    "train_loss": [
+        732.8318314612847,
+        141.73860721431444,
+        84.18782035622515,
+        63.14002042105164,
+        50.55775786621344,
+        44.19075770018437,
+        37.73816345875792,
+        34.06126776375461
+    ],
+    "train_rmse": [
+        22.99165184330979,
+        11.323542329528655,
+        8.814999768566919,
+        7.657488695076422,
+        6.889741401117676,
+        6.445235970464815,
+        5.984314805835451,
+        5.662435650372836
+    ],
+    "train_mae": [
+        13.584246410372723,
+        7.424672826534781,
+        6.1922993643948,
+        5.566740326422021,
+        5.093327478475763,
+        4.778021319042488,
+        4.4446718904667595,
+        4.133069074536723
+    ],
+    "train_ndcg": [
+        0.8110227949946529,
+        0.9211597838804204,
+        0.937679745028765,
+        0.9412411521505384,
+        0.9503305667344984,
+        0.9545676151792712,
+        0.9600524606546241,
+        0.967420418263372
+    ],
+    "val_loss": [
+        160.6261031933685,
+        128.34096046846304,
+        85.32431740974313,
+        80.64392247128842,
+        67.0554843091253,
+        66.06501499147558,
+        1049.1388928541496,
+        69.18329388205684
+    ],
+    "val_rmse": [
+        10.805885756804322,
+        9.089829880151473,
+        8.07756226301517,
+        7.707812207446884,
+        6.890123732031058,
+        7.136241044110198,
+        9.04072006674995,
+        7.161699365254218
+    ],
+    "val_mae": [
+        7.704081655616191,
+        6.686001412548236,
+        5.980107501015734,
+        5.5615818735378895,
+        5.153203635429269,
+        5.337269631428505,
+        5.525877652951141,
+        5.073120658789108
+    ],
+    "val_ndcg": [
+        0.40463845373979257,
+        0.41194865721375196,
+        0.41457322889299536,
+        0.4161684600274954,
+        0.4162150126784595,
+        0.4159772846236158,
+        0.41703249518551044,
+        0.4172478131393888
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_024710.json

@@ -0,0 +1,128 @@
+{
+    "train_loss": [
+        698.9571214965068,
+        159.28611053398424,
+        94.177260281347,
+        68.67736714058977,
+        52.19162373831238,
+        43.988458228876915,
+        38.1462167963508,
+        33.081662080108096,
+        28.3430894199283,
+        24.18672723535106,
+        20.909505849814042,
+        18.01416439347698
+    ],
+    "train_rmse": [
+        22.664169959178874,
+        11.85711222954263,
+        9.258804724471577,
+        7.915980144950924,
+        6.947577161715384,
+        6.403177358387431,
+        5.9451505323781495,
+        5.515501669518754,
+        5.114904968799297,
+        4.701472378918194,
+        4.367025956447108,
+        4.040677529004106
+    ],
+    "train_mae": [
+        13.043204946781469,
+        7.643941563220946,
+        6.423641862221134,
+        5.645208807290714,
+        5.099023518765302,
+        4.734131901365683,
+        4.364591504674602,
+        4.010108899678465,
+        3.6647100993463404,
+        3.291041061983258,
+        2.980214517983685,
+        2.6817004160706546
+    ],
+    "train_ndcg": [
+        0.8104183176939972,
+        0.9130722236575433,
+        0.9314459845273463,
+        0.9441268801844948,
+        0.9525130322791463,
+        0.9570151019154243,
+        0.9625859918257832,
+        0.9686254831149206,
+        0.974737417795838,
+        0.9780842145714321,
+        0.9821972065313793,
+        0.9857209688073401
+    ],
+    "val_loss": [
+        172.88161589494393,
+        426.1052271003154,
+        112.51207539714984,
+        72.3706546854617,
+        294.6680413772811,
+        62.068981108024936,
+        58.63476648473028,
+        56.30721573900821,
+        59.38546958467854,
+        53.21272474545152,
+        27868.435395572436,
+        1104.9548586503784
+    ],
+    "val_rmse": [
+        11.102760222063104,
+        10.900741960806847,
+        8.854496686646492,
+        7.612281812653077,
+        9.060998067683073,
+        6.995194889772411,
+        7.0915024895963485,
+        6.86413349464537,
+        7.045319108247602,
+        6.5340257952496295,
+        29.066774280978127,
+        9.589615194488836
+    ],
+    "val_mae": [
+        7.9578251155454724,
+        7.149700511391483,
+        6.4138230003527745,
+        5.7778721852089046,
+        5.830743086515968,
+        5.309667143892886,
+        5.423977222015608,
+        5.078170818357325,
+        5.1515387592031,
+        4.622512403886709,
+        8.53286396104898,
+        5.080765780406212
+    ],
+    "val_ndcg": [
+        0.3995119698012053,
+        0.4074448676474059,
+        0.41436846994642,
+        0.41535265410124367,
+        0.415723830995275,
+        0.4158541956944252,
+        0.4157818028286322,
+        0.4167915175210184,
+        0.4170165019248849,
+        0.4162059310656875,
+        0.4151763634895211,
+        0.41661322686209606
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_030507.json

@@ -0,0 +1,47 @@
+{
+    "train_loss": [
+        735.3264224940579,
+        151.60405352153023,
+        89.78745444698775
+    ],
+    "train_rmse": [
+        23.047277585501725,
+        11.651142931361225,
+        9.012670799733398
+    ],
+    "train_mae": [
+        13.923379173734634,
+        7.57802535029291,
+        6.274760499474182
+    ],
+    "train_ndcg": [
+        0.8126091989344285,
+        0.9122520486161368,
+        0.9342558337535495
+    ],
+    "val_loss": [
+        11324.795474004033,
+        504789.3357626616,
+        60333.76644566095
+    ],
+    "val_rmse": [
+        24.241182599915337,
+        77.56569549417645,
+        27.3166621065554
+    ],
+    "val_mae": [
+        10.046802049608372,
+        22.964381659920537,
+        9.750387768247235
+    ],
+    "val_ndcg": [
+        0.40520864476018875,
+        0.41310783446724736,
+        0.4158413812295714
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001
+    ]
+}

metrics/training_metrics_20250104_030726.json

@@ -0,0 +1,65 @@
+{
+    "train_loss": [
+        707.4203591421525,
+        151.07523157776427,
+        84.22673951021498,
+        58.70951760002176,
+        48.33882554846971
+    ],
+    "train_rmse": [
+        22.78345383665935,
+        11.619997248790062,
+        8.761896087930726,
+        7.343267081961219,
+        6.71071821741142
+    ],
+    "train_mae": [
+        13.44424786720817,
+        7.635795480551517,
+        6.188227196430608,
+        5.423829537705755,
+        5.011434268203576
+    ],
+    "train_ndcg": [
+        0.8127191672971037,
+        0.9208593445206151,
+        0.937281206661948,
+        0.948826389427591,
+        0.9551151390392625
+    ],
+    "val_loss": [
+        227.13909398833317,
+        91.5767605084092,
+        91.0302365459613,
+        103.32767609553551,
+        141.4468235556759
+    ],
+    "val_rmse": [
+        12.660615976782926,
+        8.360802165435022,
+        8.298719194047607,
+        7.70032410250077,
+        8.050560559871839
+    ],
+    "val_mae": [
+        8.709459909752233,
+        6.094283602130947,
+        5.971917348121529,
+        5.656715124044846,
+        5.366701940991986
+    ],
+    "val_ndcg": [
+        0.382423224377988,
+        0.3980416394881348,
+        0.3991476348976591,
+        0.4011840544529815,
+        0.40102315963204227
+    ],
+    "lr": [
+        0.001,
+        0.001,
+        0.001,
+        0.001,
+        0.001
+    ]
+}