Spaces:
Runtime error
Runtime error
File size: 6,943 Bytes
8673e1c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | """
DocuMint Train - Gradio UI for LoRA Training
"""
import os
import threading
import gradio as gr
from train import train, get_status, authenticate
# ============ GLOBAL STATE ============
training_thread = None
# ============ HANDLERS ============
def start_training(dataset_name: str, epochs: int, batch_size: int, learning_rate: float):
"""Start training in background thread."""
global training_thread
if training_thread and training_thread.is_alive():
return "⚠️ Training already in progress!"
def run():
train(
dataset_name=dataset_name if dataset_name.strip() else None,
epochs=int(epochs),
batch_size=int(batch_size),
learning_rate=float(learning_rate)
)
training_thread = threading.Thread(target=run, daemon=True)
training_thread.start()
return "🚀 Training started! Check status below."
def refresh_status():
"""Get formatted training status."""
status = get_status()
output = "## 📊 Training Status\n\n"
output += f"**Status:** {'🔄 Training' if status['is_training'] else '⏸️ Idle'}\n"
output += f"**Message:** {status['message']}\n\n"
if status['is_training'] or status['progress'] > 0:
output += f"**Progress:** {status['progress']:.1f}%\n"
output += f"**Step:** {status['current_step']} / {status['total_steps']}\n"
output += f"**Loss:** {status['loss']:.4f}\n"
# Progress bar
bar_len = 30
filled = int(bar_len * status['progress'] / 100)
bar = "█" * filled + "░" * (bar_len - filled)
output += f"\n`[{bar}]`"
return output
def check_auth():
"""Check HuggingFace authentication."""
if os.environ.get("HF_TOKEN"):
return "✅ HF_TOKEN is set"
return "❌ HF_TOKEN not found - set it in Space secrets!"
# ============ GRADIO UI ============
with gr.Blocks(
title="DocuMint Train - LoRA Training",
theme=gr.themes.Soft(primary_hue="orange")
) as demo:
gr.Markdown("""
# 🏆 DocuMint Train
### LoRA Fine-tuning for Qwen2-0.5B
Train custom LoRA adapters for document processing tasks.
""")
with gr.Row():
auth_status = gr.Textbox(label="Authentication", value=check_auth(), interactive=False)
with gr.Tabs():
# Training Tab
with gr.Tab("🎯 Train"):
with gr.Row():
with gr.Column():
dataset_input = gr.Textbox(
label="Dataset",
placeholder="Leave empty for himu1780/DocuMint-Data",
info="HuggingFace dataset name or empty for default"
)
epochs_input = gr.Slider(
minimum=1, maximum=10, value=3, step=1,
label="Epochs"
)
batch_input = gr.Slider(
minimum=1, maximum=4, value=1, step=1,
label="Batch Size",
info="Keep low for CPU training"
)
lr_input = gr.Number(
value=2e-4,
label="Learning Rate"
)
train_btn = gr.Button("🚀 Start Training", variant="primary", size="lg")
with gr.Column():
train_output = gr.Textbox(label="Output", interactive=False, lines=3)
status_display = gr.Markdown()
refresh_btn = gr.Button("🔄 Refresh Status")
train_btn.click(
fn=start_training,
inputs=[dataset_input, epochs_input, batch_input, lr_input],
outputs=train_output
)
refresh_btn.click(fn=refresh_status, outputs=status_display)
demo.load(fn=refresh_status, outputs=status_display)
# Config Tab
with gr.Tab("⚙️ Configuration"):
gr.Markdown("""
## Model Configuration
| Setting | Value |
|---------|-------|
| Base Model | `Qwen/Qwen2-0.5B-Instruct` |
| Output Repo | `himu1780/DocuMint-Models` |
| Data Repo | `himu1780/DocuMint-Data` |
## LoRA Configuration
| Setting | Value |
|---------|-------|
| Rank (r) | 8 |
| Alpha | 16 |
| Dropout | 0.05 |
| Target Modules | q_proj, k_proj, v_proj, o_proj |
## Training Settings
| Setting | Value |
|---------|-------|
| Max Length | 512 tokens |
| Gradient Accumulation | 4 |
| Warmup Steps | 100 |
| Scheduler | Cosine |
""")
# Help Tab
with gr.Tab("❓ Help"):
gr.Markdown("""
## How to Use
### 1. Set HF_TOKEN
Add your HuggingFace token as a Space secret named `HF_TOKEN`.
### 2. Prepare Dataset
Upload your dataset to `himu1780/DocuMint-Data` with one of these formats:
**Instruction Format (Alpaca-style):**
```json
{"instruction": "Summarize this document", "output": "Summary here..."}
```
**Q&A Format:**
```json
{"question": "What is in this document?", "answer": "The document contains..."}
```
**Plain Text:**
```json
{"text": "Document text here..."}
```
### 3. Start Training
- Leave dataset empty to use DocuMint-Data
- Or specify any HuggingFace dataset name
- Click "Start Training"
- Monitor progress with "Refresh Status"
### 4. Use Trained Model
After training, LoRA adapters will be saved to `himu1780/DocuMint-Models`.
The main DocuMint app will automatically load these adapters!
""")
gr.Markdown("""
---
<center>
**DocuMint Train** | [DocuMint](https://huggingface.co/spaces/himu1780/DocuMint) | [Models](https://huggingface.co/himu1780/DocuMint-Models)
</center>
""")
# ============ LAUNCH ============
if __name__ == "__main__":
demo.launch(server_name="0.0.0.0", server_port=7860)
|