peterkros commited on
Commit
0b4c6c4
·
1 Parent(s): f0b48bb

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +11 -41
app.py CHANGED
@@ -206,7 +206,7 @@ markdown_text = """
206
  markdown_text_file_upload = """
207
  - Trained with ~1500 rows of data on bert-base-uncased, English.
208
  - Upload CSV ONLY and name your column with budget line item as **text**.
209
- - Added RAG (Retrieval-augmented generation) to feed context into classifier using preceing lines of budget.
210
  - Accuracy of the model is ~88%.
211
  """
212
  html_table = """
@@ -226,50 +226,20 @@ html_table = """
226
  input for subsequent second-level classification. The project
227
  is conducted with an exclusive focus on academic and research
228
  objectives.
 
 
 
 
 
 
 
 
229
  Detailed metrics of the training process are as follows:
230
  <code>TrainOutput(global_step=395, training_loss=1.1497593360611156,
231
  metrics={'train_runtime': 650.0119, 'train_samples_per_second':
232
  9.638, 'train_steps_per_second': 0.608, 'total_flos': 1648509163714560.0,
233
  'train_loss': 1.1497593360611156, 'epoch': 5.0})</code>.
234
  </p>
235
- <table style="margin-left: auto; margin-right: auto;">
236
- <tr>
237
- <th>Epoch</th>
238
- <th>Training Loss</th>
239
- <th>Validation Loss</th>
240
- <th>Accuracy</th>
241
- </tr>
242
- <tr>
243
- <td>1</td>
244
- <td>No log</td>
245
- <td>2.095209</td>
246
- <td>0.340764</td>
247
- </tr>
248
- <tr>
249
- <td>2</td>
250
- <td>No log</td>
251
- <td>1.419945</td>
252
- <td>0.662420</td>
253
- </tr>
254
- <tr>
255
- <td>3</td>
256
- <td>No log</td>
257
- <td>0.683810</td>
258
- <td>0.850318</td>
259
- </tr>
260
- <tr>
261
- <td>4</td>
262
- <td>No log</td>
263
- <td>0.460408</td>
264
- <td>0.872611</td>
265
- </tr>
266
- <tr>
267
- <td>5</td>
268
- <td>No log</td>
269
- <td>0.422096</td>
270
- <td>0.888535</td>
271
- </tr>
272
- </table>
273
  </div>
274
  """
275
  # First interface for single line input
@@ -277,7 +247,7 @@ iface1 = gr.Interface(
277
  fn=predict,
278
  inputs=gr.components.Textbox(lines=1, placeholder="Enter Budget line here...", label="Budget Input"),
279
  outputs=gr.components.Label(label="Classification Output"),
280
- title="COFOG AutoClassification",
281
  description=markdown_text,
282
  article=html_table,
283
  allow_flagging="manual", # Enables flagging
@@ -294,7 +264,7 @@ iface2 = gr.Interface(
294
  outputs=gr.components.DataFrame(label="Classification Results"),
295
  description=markdown_text_file_upload,
296
  article=html_table,
297
- title="Batch Classification"
298
  )
299
 
300
  # Combine the interfaces in a tabbed interface
 
206
  markdown_text_file_upload = """
207
  - Trained with ~1500 rows of data on bert-base-uncased, English.
208
  - Upload CSV ONLY and name your column with budget line item as **text**.
209
+ - Using RAG (Retrieval-augmented generation) aproach to feed context into classifier using preceding lines of budget.
210
  - Accuracy of the model is ~88%.
211
  """
212
  html_table = """
 
226
  input for subsequent second-level classification. The project
227
  is conducted with an exclusive focus on academic and research
228
  objectives.
229
+
230
+ For batch prediction we integrated Retriever-Augmented Generator (RAG)
231
+ approach. This approach enriches the prediction process
232
+ by incorporating contextual information from up to 5 preceding
233
+ lines in the dataset, significantly enhancing the model's
234
+ ability to understand and classify each entry in the context
235
+ of related data.
236
+
237
  Detailed metrics of the training process are as follows:
238
  <code>TrainOutput(global_step=395, training_loss=1.1497593360611156,
239
  metrics={'train_runtime': 650.0119, 'train_samples_per_second':
240
  9.638, 'train_steps_per_second': 0.608, 'total_flos': 1648509163714560.0,
241
  'train_loss': 1.1497593360611156, 'epoch': 5.0})</code>.
242
  </p>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
243
  </div>
244
  """
245
  # First interface for single line input
 
247
  fn=predict,
248
  inputs=gr.components.Textbox(lines=1, placeholder="Enter Budget line here...", label="Budget Input"),
249
  outputs=gr.components.Label(label="Classification Output"),
250
+ title="COFOG AutoClassification - Single Line",
251
  description=markdown_text,
252
  article=html_table,
253
  allow_flagging="manual", # Enables flagging
 
264
  outputs=gr.components.DataFrame(label="Classification Results"),
265
  description=markdown_text_file_upload,
266
  article=html_table,
267
+ title="COFOG AutoClassification - Batch Classification"
268
  )
269
 
270
  # Combine the interfaces in a tabbed interface