owusu/DS-LLM-TEMPLATE-FINETUNING
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

added style mimicking piepelines

Browse Source
This commit is contained in:
OwusuBlessing
2025-08-13 21:17:01 +01:00
parent fd54d4be39
commit 710d074b47
31 changed files with 3816 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files
configs/classification/emotion.yaml
+26 -26
View File
@@ -1,6 +1,6 @@
# Comprehensive Classification Configuration
# This file defines all parameters for emotion classification using the dair-ai/emotion dataset
# Organized by level: data processing, model, training, and inference
# Organized by level: task, data processing, model, training, and inference
# Task Configuration
task:
@@ -15,9 +15,9 @@ data:
data_format: "jsonl" # Data format: "jsonl", "csv", "json" (for custom data)
# Field Mapping
input_field: "text" # Field name containing input text
label_field: "label" # Field name containing labels
id_field: null # Optional ID field name
input_field: "text" # Field name containing input text to be classified
label_field: "label" # Field name containing classification labels
id_field: null # Optional ID field name for tracking individual samples
# Processing Parameters
max_samples: 1000 # Maximum samples to process (null for all samples)
@@ -26,54 +26,54 @@ data:
test_split: 0.1 # Test split ratio (0.0 to 1.0)
# Text Preprocessing
clean_text: true # Clean and normalize text
remove_special_chars: false # Remove special characters from text
lowercase: true # Convert text to lowercase
clean_text: true # Clean and normalize text (remove extra spaces, normalize quotes, etc.)
remove_special_chars: false # Remove special characters from text (keep for emotion analysis)
lowercase: true # Convert text to lowercase (standard for BERT models)
min_length: 10 # Minimum text length (filter out shorter texts)
max_length: 1000 # Maximum text length (truncate longer texts)
# Label Processing
label_encoding: "auto" # Label encoding: "auto", "numeric", "string"
multilabel: false # Enable multilabel classification
label_separator: "," # Separator for multilabel datasets
multilabel: false # Enable multilabel classification (false for single emotion per text)
label_separator: "," # Separator for multilabel datasets (comma-separated labels)
# Output Configuration
output_format: "classification" # Output format: "classification", "instruction", "conversation", "qa"
output_dir: "./data/processed/classification/emotion" # Specific output directory for this dataset
output_dir: "./data/processed/classification/emotion" # Output directory for processed data and splits
# HuggingFace Specific
hf_split: "train" # HuggingFace dataset split to use
hf_cache_dir: null # HuggingFace cache directory (null for default)
hf_split: "train" # HuggingFace dataset split to use as base
hf_cache_dir: null # HuggingFace cache directory (null for default ~/.cache/huggingface)
# Split Configuration (Advanced)
test_split_from: "train" # Source for test split: "train", "use_test_if_available", "use_val_if_available"
val_split_from: "train" # Source for validation split: "train", "use_val_if_available"
# Custom Data Specific
encoding: "utf-8" # File encoding for custom data
delimiter: "," # Delimiter for CSV files
encoding: "utf-8" # File encoding for custom data files
delimiter: "," # Delimiter for CSV files (comma for standard CSV)
# Model Configuration
model:
name: "bert-base-uncased" # Model name from HuggingFace Hub
max_length: 512 # Maximum sequence length for tokenization
num_labels: 6 # Number of classification labels
name: "bert-base-uncased" # Model name from HuggingFace Hub (good for text classification)
max_length: 512 # Maximum sequence length for tokenization (BERT limit)
num_labels: 6 # Number of classification labels (emotion categories)
# Training Configuration
training:
num_epochs: 3 # Number of training epochs
batch_size: 16 # Training batch size
learning_rate: 2e-5 # Learning rate (typical range: 1e-5 to 5e-5)
weight_decay: 0.01 # Weight decay for optimizer (typical range: 0.01 to 0.1)
num_epochs: 3 # Number of training epochs (adjust based on dataset size)
batch_size: 16 # Training batch size (adjust based on GPU memory)
learning_rate: 2e-5 # Learning rate (typical range: 1e-5 to 5e-5 for fine-tuning)
weight_decay: 0.01 # Weight decay for optimizer (prevents overfitting)
lr_scheduler_type: "linear" # Scheduler type: "linear", "cosine", "polynomial"
warmup_ratio: 0.1 # Warmup ratio for scheduler (0.0 to 1.0)
data_dir: "./data/processed/classification/emotion" # Directory containing train/validation/test JSONL files
output_dir: "./results/classification/emotion_model" # Output directory for saved model
output_dir: "./results/classification/emotion_model" # Output directory for saved model and checkpoints
# Inference Configuration
inference:
model_path: "./results/classification/emotion_model" # Path to saved model directory
device: "auto" # Device: "auto", "cuda", "cpu"
batch_size: 32 # Batch size for inference
return_probabilities: true # Return all class probabilities
return_top_k: 3 # Return top K predictions
device: "auto" # Device: "auto", "cuda", "cpu" (auto detects best available)
batch_size: 32 # Batch size for inference (can be larger than training)
return_probabilities: true # Return all class probabilities (not just top prediction)
return_top_k: 3 # Return top K predictions (useful for confidence analysis)