Spaces:
Paused
Paused
Update train.py
Browse files
train.py
CHANGED
|
@@ -1,8 +1,3 @@
|
|
| 1 |
-
"""
|
| 2 |
-
Trackmodel - Fine-Tuning Script
|
| 3 |
-
This script downloads a pre-trained model and fine-tunes it on IMDb dataset
|
| 4 |
-
"""
|
| 5 |
-
|
| 6 |
import os
|
| 7 |
import sys
|
| 8 |
from transformers import (
|
|
@@ -11,15 +6,55 @@ from transformers import (
|
|
| 11 |
Trainer,
|
| 12 |
TrainingArguments,
|
| 13 |
)
|
| 14 |
-
from datasets import load_dataset
|
| 15 |
from huggingface_hub import login
|
| 16 |
import torch
|
| 17 |
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
def setup_training():
|
| 24 |
"""Setup and run the fine-tuning process"""
|
| 25 |
|
|
@@ -27,24 +62,27 @@ def setup_training():
|
|
| 27 |
print("π TRACKMODEL - FINE-TUNING STARTED")
|
| 28 |
print("=" * 60)
|
| 29 |
|
| 30 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
print("\nπ Step 1: Loading dataset...")
|
| 32 |
try:
|
| 33 |
-
|
|
|
|
| 34 |
print(f"β
Loaded {len(dataset['train'])} training samples")
|
| 35 |
print(f"β
Loaded {len(dataset['test'])} test samples")
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
# Use a subset for faster training
|
| 41 |
-
print("\nβ‘ Using subset for faster training (500 train, 100 test)")
|
| 42 |
-
try:
|
| 43 |
train_subset = dataset["train"].select(range(500))
|
| 44 |
test_subset = dataset["test"].select(range(100))
|
|
|
|
| 45 |
except Exception as e:
|
| 46 |
-
print(f"β Failed to
|
| 47 |
-
|
|
|
|
| 48 |
|
| 49 |
# 2. Load Model and Tokenizer
|
| 50 |
print("\nπ€ Step 2: Loading pre-trained model...")
|
|
@@ -155,6 +193,7 @@ def setup_training():
|
|
| 155 |
return "./my_finetuned_model"
|
| 156 |
|
| 157 |
|
|
|
|
| 158 |
def push_to_hub():
|
| 159 |
"""Push the fine-tuned model to your Hugging Face profile"""
|
| 160 |
print("\nπ€ Pushing model to Hugging Face Hub...")
|
|
@@ -172,7 +211,8 @@ def push_to_hub():
|
|
| 172 |
model = AutoModelForSequenceClassification.from_pretrained("./my_finetuned_model")
|
| 173 |
tokenizer = AutoTokenizer.from_pretrained("./my_finetuned_model")
|
| 174 |
|
| 175 |
-
|
|
|
|
| 176 |
print(f"π€ Uploading to: https://huggingface.co/{repo_name}")
|
| 177 |
model.push_to_hub(repo_name)
|
| 178 |
tokenizer.push_to_hub(repo_name)
|
|
@@ -181,6 +221,7 @@ def push_to_hub():
|
|
| 181 |
print(f"π https://huggingface.co/{repo_name}")
|
| 182 |
|
| 183 |
|
|
|
|
| 184 |
if __name__ == "__main__":
|
| 185 |
# Train the model
|
| 186 |
model_path = setup_training()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import os
|
| 2 |
import sys
|
| 3 |
from transformers import (
|
|
|
|
| 6 |
Trainer,
|
| 7 |
TrainingArguments,
|
| 8 |
)
|
| 9 |
+
from datasets import load_dataset, Dataset # Added Dataset import for fallback
|
| 10 |
from huggingface_hub import login
|
| 11 |
import torch
|
| 12 |
|
| 13 |
+
# --- Helper function for local dataset (fallback) ---
|
| 14 |
+
def create_local_dataset():
|
| 15 |
+
"""Create a small local dataset for testing if IMDb fails to load."""
|
| 16 |
+
print("\nπ Creating local dataset for testing...")
|
| 17 |
+
|
| 18 |
+
# Sample data (repeated to reach ~500 samples)
|
| 19 |
+
train_texts = [
|
| 20 |
+
"I loved this movie, it was amazing!",
|
| 21 |
+
"The acting was terrible and boring.",
|
| 22 |
+
"Great film, highly recommend it.",
|
| 23 |
+
"Waste of time, don't watch it.",
|
| 24 |
+
"Fantastic story and characters!",
|
| 25 |
+
"Poorly made and disappointing.",
|
| 26 |
+
"Excellent cinematography!",
|
| 27 |
+
"The plot made no sense at all.",
|
| 28 |
+
"Brilliant performance by the lead actor.",
|
| 29 |
+
"I fell asleep halfway through.",
|
| 30 |
+
] * 50 # 10 * 50 = 500 samples
|
| 31 |
+
|
| 32 |
+
train_labels = [1, 0, 1, 0, 1, 0, 1, 0, 1, 0] * 50 # 1=positive, 0=negative
|
| 33 |
+
|
| 34 |
+
test_texts = [
|
| 35 |
+
"Pretty good movie overall.",
|
| 36 |
+
"Not worth the ticket price.",
|
| 37 |
+
"Enjoyable with some flaws.",
|
| 38 |
+
"Complete disaster.",
|
| 39 |
+
"Decent watch for a rainy day.",
|
| 40 |
+
] * 20 # 5 * 20 = 100 samples
|
| 41 |
+
|
| 42 |
+
test_labels = [1, 0, 1, 0, 1] * 20
|
| 43 |
+
|
| 44 |
+
train_dataset = Dataset.from_dict({
|
| 45 |
+
'text': train_texts,
|
| 46 |
+
'label': train_labels
|
| 47 |
+
})
|
| 48 |
+
test_dataset = Dataset.from_dict({
|
| 49 |
+
'text': test_texts,
|
| 50 |
+
'label': test_labels
|
| 51 |
+
})
|
| 52 |
+
|
| 53 |
+
print(f"β
Created local dataset: {len(train_dataset)} train, {len(test_dataset)} test")
|
| 54 |
+
return train_dataset, test_dataset
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
# --- Main Training Function (FIXED) ---
|
| 58 |
def setup_training():
|
| 59 |
"""Setup and run the fine-tuning process"""
|
| 60 |
|
|
|
|
| 62 |
print("π TRACKMODEL - FINE-TUNING STARTED")
|
| 63 |
print("=" * 60)
|
| 64 |
|
| 65 |
+
print(f"β
PyTorch version: {torch.__version__}")
|
| 66 |
+
print(f"β
Transformers version: {__import__('transformers').__version__}")
|
| 67 |
+
print(f"β
Datasets version: {__import__('datasets').__version__}")
|
| 68 |
+
|
| 69 |
+
# 1. Load Dataset - FIXED with trust_remote_code=True
|
| 70 |
print("\nπ Step 1: Loading dataset...")
|
| 71 |
try:
|
| 72 |
+
# The key fix is adding trust_remote_code=True
|
| 73 |
+
dataset = load_dataset("imdb", trust_remote_code=True)
|
| 74 |
print(f"β
Loaded {len(dataset['train'])} training samples")
|
| 75 |
print(f"β
Loaded {len(dataset['test'])} test samples")
|
| 76 |
+
|
| 77 |
+
# Use a subset for faster training
|
| 78 |
+
print("\nβ‘ Using subset for faster training (500 train, 100 test)")
|
|
|
|
|
|
|
|
|
|
|
|
|
| 79 |
train_subset = dataset["train"].select(range(500))
|
| 80 |
test_subset = dataset["test"].select(range(100))
|
| 81 |
+
|
| 82 |
except Exception as e:
|
| 83 |
+
print(f"β Failed to load IMDb dataset: {str(e)}")
|
| 84 |
+
print("π‘ Falling back to local dataset...")
|
| 85 |
+
train_subset, test_subset = create_local_dataset()
|
| 86 |
|
| 87 |
# 2. Load Model and Tokenizer
|
| 88 |
print("\nπ€ Step 2: Loading pre-trained model...")
|
|
|
|
| 193 |
return "./my_finetuned_model"
|
| 194 |
|
| 195 |
|
| 196 |
+
# --- Push to Hugging Face Hub (Unchanged) ---
|
| 197 |
def push_to_hub():
|
| 198 |
"""Push the fine-tuned model to your Hugging Face profile"""
|
| 199 |
print("\nπ€ Pushing model to Hugging Face Hub...")
|
|
|
|
| 211 |
model = AutoModelForSequenceClassification.from_pretrained("./my_finetuned_model")
|
| 212 |
tokenizer = AutoTokenizer.from_pretrained("./my_finetuned_model")
|
| 213 |
|
| 214 |
+
# Change this to your own Hugging Face username if needed
|
| 215 |
+
repo_name = "Surajnitp/sentiment-trackmodel"
|
| 216 |
print(f"π€ Uploading to: https://huggingface.co/{repo_name}")
|
| 217 |
model.push_to_hub(repo_name)
|
| 218 |
tokenizer.push_to_hub(repo_name)
|
|
|
|
| 221 |
print(f"π https://huggingface.co/{repo_name}")
|
| 222 |
|
| 223 |
|
| 224 |
+
# --- Main Execution ---
|
| 225 |
if __name__ == "__main__":
|
| 226 |
# Train the model
|
| 227 |
model_path = setup_training()
|