├── README.md
├── LICENSE
├── .gitignore
├── training_a_small_language_model.py
└── Training_a_Small_Language_Model.ipynb
/README.md:
--------------------------------------------------------------------------------
1 | # Training-Small-Language-Model
2 | Training Small Language Model
3 |
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 | MIT License
2 |
3 | Copyright (c) 2023 AI Anytime
4 |
5 | Permission is hereby granted, free of charge, to any person obtaining a copy
6 | of this software and associated documentation files (the "Software"), to deal
7 | in the Software without restriction, including without limitation the rights
8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
9 | copies of the Software, and to permit persons to whom the Software is
10 | furnished to do so, subject to the following conditions:
11 |
12 | The above copyright notice and this permission notice shall be included in all
13 | copies or substantial portions of the Software.
14 |
15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
21 | SOFTWARE.
22 |
--------------------------------------------------------------------------------
/.gitignore:
--------------------------------------------------------------------------------
1 | # Byte-compiled / optimized / DLL files
2 | __pycache__/
3 | *.py[cod]
4 | *$py.class
5 |
6 | # C extensions
7 | *.so
8 |
9 | # Distribution / packaging
10 | .Python
11 | build/
12 | develop-eggs/
13 | dist/
14 | downloads/
15 | eggs/
16 | .eggs/
17 | lib/
18 | lib64/
19 | parts/
20 | sdist/
21 | var/
22 | wheels/
23 | share/python-wheels/
24 | *.egg-info/
25 | .installed.cfg
26 | *.egg
27 | MANIFEST
28 |
29 | # PyInstaller
30 | # Usually these files are written by a python script from a template
31 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
32 | *.manifest
33 | *.spec
34 |
35 | # Installer logs
36 | pip-log.txt
37 | pip-delete-this-directory.txt
38 |
39 | # Unit test / coverage reports
40 | htmlcov/
41 | .tox/
42 | .nox/
43 | .coverage
44 | .coverage.*
45 | .cache
46 | nosetests.xml
47 | coverage.xml
48 | *.cover
49 | *.py,cover
50 | .hypothesis/
51 | .pytest_cache/
52 | cover/
53 |
54 | # Translations
55 | *.mo
56 | *.pot
57 |
58 | # Django stuff:
59 | *.log
60 | local_settings.py
61 | db.sqlite3
62 | db.sqlite3-journal
63 |
64 | # Flask stuff:
65 | instance/
66 | .webassets-cache
67 |
68 | # Scrapy stuff:
69 | .scrapy
70 |
71 | # Sphinx documentation
72 | docs/_build/
73 |
74 | # PyBuilder
75 | .pybuilder/
76 | target/
77 |
78 | # Jupyter Notebook
79 | .ipynb_checkpoints
80 |
81 | # IPython
82 | profile_default/
83 | ipython_config.py
84 |
85 | # pyenv
86 | # For a library or package, you might want to ignore these files since the code is
87 | # intended to run in multiple environments; otherwise, check them in:
88 | # .python-version
89 |
90 | # pipenv
91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies
93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not
94 | # install all needed dependencies.
95 | #Pipfile.lock
96 |
97 | # poetry
98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
99 | # This is especially recommended for binary packages to ensure reproducibility, and is more
100 | # commonly ignored for libraries.
101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
102 | #poetry.lock
103 |
104 | # pdm
105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
106 | #pdm.lock
107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
108 | # in version control.
109 | # https://pdm.fming.dev/#use-with-ide
110 | .pdm.toml
111 |
112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
113 | __pypackages__/
114 |
115 | # Celery stuff
116 | celerybeat-schedule
117 | celerybeat.pid
118 |
119 | # SageMath parsed files
120 | *.sage.py
121 |
122 | # Environments
123 | .env
124 | .venv
125 | env/
126 | venv/
127 | ENV/
128 | env.bak/
129 | venv.bak/
130 |
131 | # Spyder project settings
132 | .spyderproject
133 | .spyproject
134 |
135 | # Rope project settings
136 | .ropeproject
137 |
138 | # mkdocs documentation
139 | /site
140 |
141 | # mypy
142 | .mypy_cache/
143 | .dmypy.json
144 | dmypy.json
145 |
146 | # Pyre type checker
147 | .pyre/
148 |
149 | # pytype static type analyzer
150 | .pytype/
151 |
152 | # Cython debug symbols
153 | cython_debug/
154 |
155 | # PyCharm
156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can
157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
158 | # and can be added to the global gitignore or merged into this file. For a more nuclear
159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder.
160 | #.idea/
161 |
--------------------------------------------------------------------------------
/training_a_small_language_model.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | """Training a Small Language Model.ipynb
3 |
4 | Automatically generated by Colaboratory.
5 |
6 | Original file is located at
7 | https://colab.research.google.com/drive/176cjp0TmFiv8rT96OuI51psRKq0gERxh
8 | """
9 |
10 | !pip install torch torchtext transformers sentencepiece pandas tqdm datasets
11 |
12 | from datasets import load_dataset, DatasetDict, Dataset
13 | import pandas as pd
14 | import ast
15 | import datasets
16 | from tqdm import tqdm
17 | import time
18 |
19 | # Load data set from huggingface
20 | data_sample = load_dataset("QuyenAnhDE/Diseases_Symptoms")
21 |
22 | data_sample
23 |
24 | # Convert to a pandas dataframe
25 | updated_data = [{'Name': item['Name'], 'Symptoms': item['Symptoms']} for item in data_sample['train']]
26 | df = pd.DataFrame(updated_data)
27 |
28 | df.head(5)
29 |
30 | # Just extract the Symptoms
31 | df['Symptoms'] = df['Symptoms'].apply(lambda x: ', '.join(x.split(', ')))
32 | display(df.head())
33 |
34 | from transformers import GPT2Tokenizer, GPT2LMHeadModel
35 | import torch
36 | import torch.nn as nn
37 | import torch.optim as optim
38 | from torch.utils.data import Dataset, DataLoader, random_split
39 |
40 | # If you have an NVIDIA GPU attached, use 'cuda'
41 | if torch.cuda.is_available():
42 | device = torch.device('cuda')
43 | else:
44 | # If Apple Silicon, set to 'mps' - otherwise 'cpu' (not advised)
45 | try:
46 | device = torch.device('mps')
47 | except Exception:
48 | device = torch.device('cpu')
49 |
50 | device
51 |
52 | # The tokenizer turns texts to numbers (and vice-versa)
53 | tokenizer = GPT2Tokenizer.from_pretrained('distilgpt2')
54 |
55 | # The transformer
56 | model = GPT2LMHeadModel.from_pretrained('distilgpt2').to(device)
57 |
58 | model
59 |
60 | # Model params
61 | BATCH_SIZE = 8
62 |
63 | df.describe()
64 |
65 | # Dataset Prep
66 | class LanguageDataset(Dataset):
67 | """
68 | An extension of the Dataset object to:
69 | - Make training loop cleaner
70 | - Make ingestion easier from pandas df's
71 | """
72 | def __init__(self, df, tokenizer):
73 | self.labels = df.columns
74 | self.data = df.to_dict(orient='records')
75 | self.tokenizer = tokenizer
76 | x = self.fittest_max_length(df) # Fix here
77 | self.max_length = x
78 |
79 | def __len__(self):
80 | return len(self.data)
81 |
82 | def __getitem__(self, idx):
83 | x = self.data[idx][self.labels[0]]
84 | y = self.data[idx][self.labels[1]]
85 | text = f"{x} | {y}"
86 | tokens = self.tokenizer.encode_plus(text, return_tensors='pt', max_length=128, padding='max_length', truncation=True)
87 | return tokens
88 |
89 | def fittest_max_length(self, df): # Fix here
90 | """
91 | Smallest power of two larger than the longest term in the data set.
92 | Important to set up max length to speed training time.
93 | """
94 | max_length = max(len(max(df[self.labels[0]], key=len)), len(max(df[self.labels[1]], key=len)))
95 | x = 2
96 | while x < max_length: x = x * 2
97 | return x
98 |
99 | # Cast the Huggingface data set as a LanguageDataset we defined above
100 | data_sample = LanguageDataset(df, tokenizer)
101 |
102 | data_sample
103 |
104 | # Create train, valid
105 | train_size = int(0.8 * len(data_sample))
106 | valid_size = len(data_sample) - train_size
107 | train_data, valid_data = random_split(data_sample, [train_size, valid_size])
108 |
109 | # Make the iterators
110 | train_loader = DataLoader(train_data, batch_size=BATCH_SIZE, shuffle=True)
111 | valid_loader = DataLoader(valid_data, batch_size=BATCH_SIZE)
112 |
113 | # Set the number of epochs
114 | num_epochs = 10
115 |
116 | # Training parameters
117 | batch_size = BATCH_SIZE
118 | model_name = 'distilgpt2'
119 | gpu = 0
120 |
121 | # Set the learning rate and loss function
122 | ## CrossEntropyLoss measures how close answers to the truth.
123 | ## More punishing for high confidence wrong answers
124 | criterion = nn.CrossEntropyLoss(ignore_index = tokenizer.pad_token_id)
125 | optimizer = optim.Adam(model.parameters(), lr=5e-4)
126 | tokenizer.pad_token = tokenizer.eos_token
127 |
128 | # Init a results dataframe
129 | results = pd.DataFrame(columns=['epoch', 'transformer', 'batch_size', 'gpu',
130 | 'training_loss', 'validation_loss', 'epoch_duration_sec'])
131 |
132 | # The training loop
133 | for epoch in range(num_epochs):
134 | start_time = time.time() # Start the timer for the epoch
135 |
136 | # Training
137 | ## This line tells the model we're in 'learning mode'
138 | model.train()
139 | epoch_training_loss = 0
140 | train_iterator = tqdm(train_loader, desc=f"Training Epoch {epoch+1}/{num_epochs} Batch Size: {batch_size}, Transformer: {model_name}")
141 | for batch in train_iterator:
142 | optimizer.zero_grad()
143 | inputs = batch['input_ids'].squeeze(1).to(device)
144 | targets = inputs.clone()
145 | outputs = model(input_ids=inputs, labels=targets)
146 | loss = outputs.loss
147 | loss.backward()
148 | optimizer.step()
149 | train_iterator.set_postfix({'Training Loss': loss.item()})
150 | epoch_training_loss += loss.item()
151 | avg_epoch_training_loss = epoch_training_loss / len(train_iterator)
152 |
153 | # Validation
154 | ## This line below tells the model to 'stop learning'
155 | model.eval()
156 | epoch_validation_loss = 0
157 | total_loss = 0
158 | valid_iterator = tqdm(valid_loader, desc=f"Validation Epoch {epoch+1}/{num_epochs}")
159 | with torch.no_grad():
160 | for batch in valid_iterator:
161 | inputs = batch['input_ids'].squeeze(1).to(device)
162 | targets = inputs.clone()
163 | outputs = model(input_ids=inputs, labels=targets)
164 | loss = outputs.loss
165 | total_loss += loss
166 | valid_iterator.set_postfix({'Validation Loss': loss.item()})
167 | epoch_validation_loss += loss.item()
168 |
169 | avg_epoch_validation_loss = epoch_validation_loss / len(valid_loader)
170 |
171 | end_time = time.time() # End the timer for the epoch
172 | epoch_duration_sec = end_time - start_time # Calculate the duration in seconds
173 |
174 | new_row = {'transformer': model_name,
175 | 'batch_size': batch_size,
176 | 'gpu': gpu,
177 | 'epoch': epoch+1,
178 | 'training_loss': avg_epoch_training_loss,
179 | 'validation_loss': avg_epoch_validation_loss,
180 | 'epoch_duration_sec': epoch_duration_sec} # Add epoch_duration to the dataframe
181 |
182 | results.loc[len(results)] = new_row
183 | print(f"Epoch: {epoch+1}, Validation Loss: {total_loss/len(valid_loader)}")
184 |
185 | input_str = "Kidney Failure"
186 | input_ids = tokenizer.encode(input_str, return_tensors='pt').to(device)
187 |
188 | output = model.generate(
189 | input_ids,
190 | max_length=20,
191 | num_return_sequences=1,
192 | do_sample=True,
193 | top_k=8,
194 | top_p=0.95,
195 | temperature=0.5,
196 | repetition_penalty=1.2
197 | )
198 |
199 | decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)
200 | print(decoded_output)
201 |
202 | torch.save(model, 'SmallMedLM.pt')
203 |
204 | torch.save(model, 'drive/My Drive/SmallMedLM.pt')
205 |
206 |
207 |
208 |
--------------------------------------------------------------------------------
/Training_a_Small_Language_Model.ipynb:
--------------------------------------------------------------------------------
1 | {
2 | "nbformat": 4,
3 | "nbformat_minor": 0,
4 | "metadata": {
5 | "colab": {
6 | "provenance": [],
7 | "machine_shape": "hm",
8 | "gpuType": "T4"
9 | },
10 | "kernelspec": {
11 | "name": "python3",
12 | "display_name": "Python 3"
13 | },
14 | "language_info": {
15 | "name": "python"
16 | },
17 | "accelerator": "GPU",
18 | "widgets": {
19 | "application/vnd.jupyter.widget-state+json": {
20 | "909582d0b6014056b113ef9a0a1db740": {
21 | "model_module": "@jupyter-widgets/controls",
22 | "model_name": "HBoxModel",
23 | "model_module_version": "1.5.0",
24 | "state": {
25 | "_dom_classes": [],
26 | "_model_module": "@jupyter-widgets/controls",
27 | "_model_module_version": "1.5.0",
28 | "_model_name": "HBoxModel",
29 | "_view_count": null,
30 | "_view_module": "@jupyter-widgets/controls",
31 | "_view_module_version": "1.5.0",
32 | "_view_name": "HBoxView",
33 | "box_style": "",
34 | "children": [
35 | "IPY_MODEL_6b08d4679ac6461cbe254fe3478091b6",
36 | "IPY_MODEL_9a2502aacbd6489da0f8b6fbadcf079b",
37 | "IPY_MODEL_f6ff0e6cd04047babe24708d21937576"
38 | ],
39 | "layout": "IPY_MODEL_36349f3e29664f0bbdda5c8f7651304e"
40 | }
41 | },
42 | "6b08d4679ac6461cbe254fe3478091b6": {
43 | "model_module": "@jupyter-widgets/controls",
44 | "model_name": "HTMLModel",
45 | "model_module_version": "1.5.0",
46 | "state": {
47 | "_dom_classes": [],
48 | "_model_module": "@jupyter-widgets/controls",
49 | "_model_module_version": "1.5.0",
50 | "_model_name": "HTMLModel",
51 | "_view_count": null,
52 | "_view_module": "@jupyter-widgets/controls",
53 | "_view_module_version": "1.5.0",
54 | "_view_name": "HTMLView",
55 | "description": "",
56 | "description_tooltip": null,
57 | "layout": "IPY_MODEL_59945ccd1da44215b5eaa6226835968c",
58 | "placeholder": "",
59 | "style": "IPY_MODEL_2aed084699344e14b687a38196f3a4dc",
60 | "value": "Downloading readme: 100%"
61 | }
62 | },
63 | "9a2502aacbd6489da0f8b6fbadcf079b": {
64 | "model_module": "@jupyter-widgets/controls",
65 | "model_name": "FloatProgressModel",
66 | "model_module_version": "1.5.0",
67 | "state": {
68 | "_dom_classes": [],
69 | "_model_module": "@jupyter-widgets/controls",
70 | "_model_module_version": "1.5.0",
71 | "_model_name": "FloatProgressModel",
72 | "_view_count": null,
73 | "_view_module": "@jupyter-widgets/controls",
74 | "_view_module_version": "1.5.0",
75 | "_view_name": "ProgressView",
76 | "bar_style": "success",
77 | "description": "",
78 | "description_tooltip": null,
79 | "layout": "IPY_MODEL_97040354aa6047f4b2adfd7d0a255d0e",
80 | "max": 381,
81 | "min": 0,
82 | "orientation": "horizontal",
83 | "style": "IPY_MODEL_4167d18aa99240f09d20b78bb447f302",
84 | "value": 381
85 | }
86 | },
87 | "f6ff0e6cd04047babe24708d21937576": {
88 | "model_module": "@jupyter-widgets/controls",
89 | "model_name": "HTMLModel",
90 | "model_module_version": "1.5.0",
91 | "state": {
92 | "_dom_classes": [],
93 | "_model_module": "@jupyter-widgets/controls",
94 | "_model_module_version": "1.5.0",
95 | "_model_name": "HTMLModel",
96 | "_view_count": null,
97 | "_view_module": "@jupyter-widgets/controls",
98 | "_view_module_version": "1.5.0",
99 | "_view_name": "HTMLView",
100 | "description": "",
101 | "description_tooltip": null,
102 | "layout": "IPY_MODEL_7b8c3ec2b0d7466c89881890686152f3",
103 | "placeholder": "",
104 | "style": "IPY_MODEL_a86181d8ced94aa49b4664f692937ca8",
105 | "value": " 381/381 [00:00<00:00, 4.86kB/s]"
106 | }
107 | },
108 | "36349f3e29664f0bbdda5c8f7651304e": {
109 | "model_module": "@jupyter-widgets/base",
110 | "model_name": "LayoutModel",
111 | "model_module_version": "1.2.0",
112 | "state": {
113 | "_model_module": "@jupyter-widgets/base",
114 | "_model_module_version": "1.2.0",
115 | "_model_name": "LayoutModel",
116 | "_view_count": null,
117 | "_view_module": "@jupyter-widgets/base",
118 | "_view_module_version": "1.2.0",
119 | "_view_name": "LayoutView",
120 | "align_content": null,
121 | "align_items": null,
122 | "align_self": null,
123 | "border": null,
124 | "bottom": null,
125 | "display": null,
126 | "flex": null,
127 | "flex_flow": null,
128 | "grid_area": null,
129 | "grid_auto_columns": null,
130 | "grid_auto_flow": null,
131 | "grid_auto_rows": null,
132 | "grid_column": null,
133 | "grid_gap": null,
134 | "grid_row": null,
135 | "grid_template_areas": null,
136 | "grid_template_columns": null,
137 | "grid_template_rows": null,
138 | "height": null,
139 | "justify_content": null,
140 | "justify_items": null,
141 | "left": null,
142 | "margin": null,
143 | "max_height": null,
144 | "max_width": null,
145 | "min_height": null,
146 | "min_width": null,
147 | "object_fit": null,
148 | "object_position": null,
149 | "order": null,
150 | "overflow": null,
151 | "overflow_x": null,
152 | "overflow_y": null,
153 | "padding": null,
154 | "right": null,
155 | "top": null,
156 | "visibility": null,
157 | "width": null
158 | }
159 | },
160 | "59945ccd1da44215b5eaa6226835968c": {
161 | "model_module": "@jupyter-widgets/base",
162 | "model_name": "LayoutModel",
163 | "model_module_version": "1.2.0",
164 | "state": {
165 | "_model_module": "@jupyter-widgets/base",
166 | "_model_module_version": "1.2.0",
167 | "_model_name": "LayoutModel",
168 | "_view_count": null,
169 | "_view_module": "@jupyter-widgets/base",
170 | "_view_module_version": "1.2.0",
171 | "_view_name": "LayoutView",
172 | "align_content": null,
173 | "align_items": null,
174 | "align_self": null,
175 | "border": null,
176 | "bottom": null,
177 | "display": null,
178 | "flex": null,
179 | "flex_flow": null,
180 | "grid_area": null,
181 | "grid_auto_columns": null,
182 | "grid_auto_flow": null,
183 | "grid_auto_rows": null,
184 | "grid_column": null,
185 | "grid_gap": null,
186 | "grid_row": null,
187 | "grid_template_areas": null,
188 | "grid_template_columns": null,
189 | "grid_template_rows": null,
190 | "height": null,
191 | "justify_content": null,
192 | "justify_items": null,
193 | "left": null,
194 | "margin": null,
195 | "max_height": null,
196 | "max_width": null,
197 | "min_height": null,
198 | "min_width": null,
199 | "object_fit": null,
200 | "object_position": null,
201 | "order": null,
202 | "overflow": null,
203 | "overflow_x": null,
204 | "overflow_y": null,
205 | "padding": null,
206 | "right": null,
207 | "top": null,
208 | "visibility": null,
209 | "width": null
210 | }
211 | },
212 | "2aed084699344e14b687a38196f3a4dc": {
213 | "model_module": "@jupyter-widgets/controls",
214 | "model_name": "DescriptionStyleModel",
215 | "model_module_version": "1.5.0",
216 | "state": {
217 | "_model_module": "@jupyter-widgets/controls",
218 | "_model_module_version": "1.5.0",
219 | "_model_name": "DescriptionStyleModel",
220 | "_view_count": null,
221 | "_view_module": "@jupyter-widgets/base",
222 | "_view_module_version": "1.2.0",
223 | "_view_name": "StyleView",
224 | "description_width": ""
225 | }
226 | },
227 | "97040354aa6047f4b2adfd7d0a255d0e": {
228 | "model_module": "@jupyter-widgets/base",
229 | "model_name": "LayoutModel",
230 | "model_module_version": "1.2.0",
231 | "state": {
232 | "_model_module": "@jupyter-widgets/base",
233 | "_model_module_version": "1.2.0",
234 | "_model_name": "LayoutModel",
235 | "_view_count": null,
236 | "_view_module": "@jupyter-widgets/base",
237 | "_view_module_version": "1.2.0",
238 | "_view_name": "LayoutView",
239 | "align_content": null,
240 | "align_items": null,
241 | "align_self": null,
242 | "border": null,
243 | "bottom": null,
244 | "display": null,
245 | "flex": null,
246 | "flex_flow": null,
247 | "grid_area": null,
248 | "grid_auto_columns": null,
249 | "grid_auto_flow": null,
250 | "grid_auto_rows": null,
251 | "grid_column": null,
252 | "grid_gap": null,
253 | "grid_row": null,
254 | "grid_template_areas": null,
255 | "grid_template_columns": null,
256 | "grid_template_rows": null,
257 | "height": null,
258 | "justify_content": null,
259 | "justify_items": null,
260 | "left": null,
261 | "margin": null,
262 | "max_height": null,
263 | "max_width": null,
264 | "min_height": null,
265 | "min_width": null,
266 | "object_fit": null,
267 | "object_position": null,
268 | "order": null,
269 | "overflow": null,
270 | "overflow_x": null,
271 | "overflow_y": null,
272 | "padding": null,
273 | "right": null,
274 | "top": null,
275 | "visibility": null,
276 | "width": null
277 | }
278 | },
279 | "4167d18aa99240f09d20b78bb447f302": {
280 | "model_module": "@jupyter-widgets/controls",
281 | "model_name": "ProgressStyleModel",
282 | "model_module_version": "1.5.0",
283 | "state": {
284 | "_model_module": "@jupyter-widgets/controls",
285 | "_model_module_version": "1.5.0",
286 | "_model_name": "ProgressStyleModel",
287 | "_view_count": null,
288 | "_view_module": "@jupyter-widgets/base",
289 | "_view_module_version": "1.2.0",
290 | "_view_name": "StyleView",
291 | "bar_color": null,
292 | "description_width": ""
293 | }
294 | },
295 | "7b8c3ec2b0d7466c89881890686152f3": {
296 | "model_module": "@jupyter-widgets/base",
297 | "model_name": "LayoutModel",
298 | "model_module_version": "1.2.0",
299 | "state": {
300 | "_model_module": "@jupyter-widgets/base",
301 | "_model_module_version": "1.2.0",
302 | "_model_name": "LayoutModel",
303 | "_view_count": null,
304 | "_view_module": "@jupyter-widgets/base",
305 | "_view_module_version": "1.2.0",
306 | "_view_name": "LayoutView",
307 | "align_content": null,
308 | "align_items": null,
309 | "align_self": null,
310 | "border": null,
311 | "bottom": null,
312 | "display": null,
313 | "flex": null,
314 | "flex_flow": null,
315 | "grid_area": null,
316 | "grid_auto_columns": null,
317 | "grid_auto_flow": null,
318 | "grid_auto_rows": null,
319 | "grid_column": null,
320 | "grid_gap": null,
321 | "grid_row": null,
322 | "grid_template_areas": null,
323 | "grid_template_columns": null,
324 | "grid_template_rows": null,
325 | "height": null,
326 | "justify_content": null,
327 | "justify_items": null,
328 | "left": null,
329 | "margin": null,
330 | "max_height": null,
331 | "max_width": null,
332 | "min_height": null,
333 | "min_width": null,
334 | "object_fit": null,
335 | "object_position": null,
336 | "order": null,
337 | "overflow": null,
338 | "overflow_x": null,
339 | "overflow_y": null,
340 | "padding": null,
341 | "right": null,
342 | "top": null,
343 | "visibility": null,
344 | "width": null
345 | }
346 | },
347 | "a86181d8ced94aa49b4664f692937ca8": {
348 | "model_module": "@jupyter-widgets/controls",
349 | "model_name": "DescriptionStyleModel",
350 | "model_module_version": "1.5.0",
351 | "state": {
352 | "_model_module": "@jupyter-widgets/controls",
353 | "_model_module_version": "1.5.0",
354 | "_model_name": "DescriptionStyleModel",
355 | "_view_count": null,
356 | "_view_module": "@jupyter-widgets/base",
357 | "_view_module_version": "1.2.0",
358 | "_view_name": "StyleView",
359 | "description_width": ""
360 | }
361 | },
362 | "d11ae8b4126d42a8a72dd70b3d093185": {
363 | "model_module": "@jupyter-widgets/controls",
364 | "model_name": "HBoxModel",
365 | "model_module_version": "1.5.0",
366 | "state": {
367 | "_dom_classes": [],
368 | "_model_module": "@jupyter-widgets/controls",
369 | "_model_module_version": "1.5.0",
370 | "_model_name": "HBoxModel",
371 | "_view_count": null,
372 | "_view_module": "@jupyter-widgets/controls",
373 | "_view_module_version": "1.5.0",
374 | "_view_name": "HBoxView",
375 | "box_style": "",
376 | "children": [
377 | "IPY_MODEL_6319e0859d1547f8a586c2409c263519",
378 | "IPY_MODEL_2ce9e1635d34488eb5deee6f1eab48fc",
379 | "IPY_MODEL_44af7e9762b647beae7100e10b0f188f"
380 | ],
381 | "layout": "IPY_MODEL_01062415cb564e54906fa8ad9ff4031b"
382 | }
383 | },
384 | "6319e0859d1547f8a586c2409c263519": {
385 | "model_module": "@jupyter-widgets/controls",
386 | "model_name": "HTMLModel",
387 | "model_module_version": "1.5.0",
388 | "state": {
389 | "_dom_classes": [],
390 | "_model_module": "@jupyter-widgets/controls",
391 | "_model_module_version": "1.5.0",
392 | "_model_name": "HTMLModel",
393 | "_view_count": null,
394 | "_view_module": "@jupyter-widgets/controls",
395 | "_view_module_version": "1.5.0",
396 | "_view_name": "HTMLView",
397 | "description": "",
398 | "description_tooltip": null,
399 | "layout": "IPY_MODEL_3be9d4577dec410cad57443e239347ce",
400 | "placeholder": "",
401 | "style": "IPY_MODEL_9f0b34c9152840ac8f1e853420964173",
402 | "value": "Downloading data: 100%"
403 | }
404 | },
405 | "2ce9e1635d34488eb5deee6f1eab48fc": {
406 | "model_module": "@jupyter-widgets/controls",
407 | "model_name": "FloatProgressModel",
408 | "model_module_version": "1.5.0",
409 | "state": {
410 | "_dom_classes": [],
411 | "_model_module": "@jupyter-widgets/controls",
412 | "_model_module_version": "1.5.0",
413 | "_model_name": "FloatProgressModel",
414 | "_view_count": null,
415 | "_view_module": "@jupyter-widgets/controls",
416 | "_view_module_version": "1.5.0",
417 | "_view_name": "ProgressView",
418 | "bar_style": "success",
419 | "description": "",
420 | "description_tooltip": null,
421 | "layout": "IPY_MODEL_8894905d0d0f4e4a995e8be50b214f39",
422 | "max": 106553,
423 | "min": 0,
424 | "orientation": "horizontal",
425 | "style": "IPY_MODEL_c3b8c945c14e4adeb5031c68fe377ad6",
426 | "value": 106553
427 | }
428 | },
429 | "44af7e9762b647beae7100e10b0f188f": {
430 | "model_module": "@jupyter-widgets/controls",
431 | "model_name": "HTMLModel",
432 | "model_module_version": "1.5.0",
433 | "state": {
434 | "_dom_classes": [],
435 | "_model_module": "@jupyter-widgets/controls",
436 | "_model_module_version": "1.5.0",
437 | "_model_name": "HTMLModel",
438 | "_view_count": null,
439 | "_view_module": "@jupyter-widgets/controls",
440 | "_view_module_version": "1.5.0",
441 | "_view_name": "HTMLView",
442 | "description": "",
443 | "description_tooltip": null,
444 | "layout": "IPY_MODEL_8782c620fea449fd92ea1f8f7ef3c6ed",
445 | "placeholder": "",
446 | "style": "IPY_MODEL_c04efab8b28346ea92e64a1599f1ee17",
447 | "value": " 107k/107k [00:00<00:00, 379kB/s]"
448 | }
449 | },
450 | "01062415cb564e54906fa8ad9ff4031b": {
451 | "model_module": "@jupyter-widgets/base",
452 | "model_name": "LayoutModel",
453 | "model_module_version": "1.2.0",
454 | "state": {
455 | "_model_module": "@jupyter-widgets/base",
456 | "_model_module_version": "1.2.0",
457 | "_model_name": "LayoutModel",
458 | "_view_count": null,
459 | "_view_module": "@jupyter-widgets/base",
460 | "_view_module_version": "1.2.0",
461 | "_view_name": "LayoutView",
462 | "align_content": null,
463 | "align_items": null,
464 | "align_self": null,
465 | "border": null,
466 | "bottom": null,
467 | "display": null,
468 | "flex": null,
469 | "flex_flow": null,
470 | "grid_area": null,
471 | "grid_auto_columns": null,
472 | "grid_auto_flow": null,
473 | "grid_auto_rows": null,
474 | "grid_column": null,
475 | "grid_gap": null,
476 | "grid_row": null,
477 | "grid_template_areas": null,
478 | "grid_template_columns": null,
479 | "grid_template_rows": null,
480 | "height": null,
481 | "justify_content": null,
482 | "justify_items": null,
483 | "left": null,
484 | "margin": null,
485 | "max_height": null,
486 | "max_width": null,
487 | "min_height": null,
488 | "min_width": null,
489 | "object_fit": null,
490 | "object_position": null,
491 | "order": null,
492 | "overflow": null,
493 | "overflow_x": null,
494 | "overflow_y": null,
495 | "padding": null,
496 | "right": null,
497 | "top": null,
498 | "visibility": null,
499 | "width": null
500 | }
501 | },
502 | "3be9d4577dec410cad57443e239347ce": {
503 | "model_module": "@jupyter-widgets/base",
504 | "model_name": "LayoutModel",
505 | "model_module_version": "1.2.0",
506 | "state": {
507 | "_model_module": "@jupyter-widgets/base",
508 | "_model_module_version": "1.2.0",
509 | "_model_name": "LayoutModel",
510 | "_view_count": null,
511 | "_view_module": "@jupyter-widgets/base",
512 | "_view_module_version": "1.2.0",
513 | "_view_name": "LayoutView",
514 | "align_content": null,
515 | "align_items": null,
516 | "align_self": null,
517 | "border": null,
518 | "bottom": null,
519 | "display": null,
520 | "flex": null,
521 | "flex_flow": null,
522 | "grid_area": null,
523 | "grid_auto_columns": null,
524 | "grid_auto_flow": null,
525 | "grid_auto_rows": null,
526 | "grid_column": null,
527 | "grid_gap": null,
528 | "grid_row": null,
529 | "grid_template_areas": null,
530 | "grid_template_columns": null,
531 | "grid_template_rows": null,
532 | "height": null,
533 | "justify_content": null,
534 | "justify_items": null,
535 | "left": null,
536 | "margin": null,
537 | "max_height": null,
538 | "max_width": null,
539 | "min_height": null,
540 | "min_width": null,
541 | "object_fit": null,
542 | "object_position": null,
543 | "order": null,
544 | "overflow": null,
545 | "overflow_x": null,
546 | "overflow_y": null,
547 | "padding": null,
548 | "right": null,
549 | "top": null,
550 | "visibility": null,
551 | "width": null
552 | }
553 | },
554 | "9f0b34c9152840ac8f1e853420964173": {
555 | "model_module": "@jupyter-widgets/controls",
556 | "model_name": "DescriptionStyleModel",
557 | "model_module_version": "1.5.0",
558 | "state": {
559 | "_model_module": "@jupyter-widgets/controls",
560 | "_model_module_version": "1.5.0",
561 | "_model_name": "DescriptionStyleModel",
562 | "_view_count": null,
563 | "_view_module": "@jupyter-widgets/base",
564 | "_view_module_version": "1.2.0",
565 | "_view_name": "StyleView",
566 | "description_width": ""
567 | }
568 | },
569 | "8894905d0d0f4e4a995e8be50b214f39": {
570 | "model_module": "@jupyter-widgets/base",
571 | "model_name": "LayoutModel",
572 | "model_module_version": "1.2.0",
573 | "state": {
574 | "_model_module": "@jupyter-widgets/base",
575 | "_model_module_version": "1.2.0",
576 | "_model_name": "LayoutModel",
577 | "_view_count": null,
578 | "_view_module": "@jupyter-widgets/base",
579 | "_view_module_version": "1.2.0",
580 | "_view_name": "LayoutView",
581 | "align_content": null,
582 | "align_items": null,
583 | "align_self": null,
584 | "border": null,
585 | "bottom": null,
586 | "display": null,
587 | "flex": null,
588 | "flex_flow": null,
589 | "grid_area": null,
590 | "grid_auto_columns": null,
591 | "grid_auto_flow": null,
592 | "grid_auto_rows": null,
593 | "grid_column": null,
594 | "grid_gap": null,
595 | "grid_row": null,
596 | "grid_template_areas": null,
597 | "grid_template_columns": null,
598 | "grid_template_rows": null,
599 | "height": null,
600 | "justify_content": null,
601 | "justify_items": null,
602 | "left": null,
603 | "margin": null,
604 | "max_height": null,
605 | "max_width": null,
606 | "min_height": null,
607 | "min_width": null,
608 | "object_fit": null,
609 | "object_position": null,
610 | "order": null,
611 | "overflow": null,
612 | "overflow_x": null,
613 | "overflow_y": null,
614 | "padding": null,
615 | "right": null,
616 | "top": null,
617 | "visibility": null,
618 | "width": null
619 | }
620 | },
621 | "c3b8c945c14e4adeb5031c68fe377ad6": {
622 | "model_module": "@jupyter-widgets/controls",
623 | "model_name": "ProgressStyleModel",
624 | "model_module_version": "1.5.0",
625 | "state": {
626 | "_model_module": "@jupyter-widgets/controls",
627 | "_model_module_version": "1.5.0",
628 | "_model_name": "ProgressStyleModel",
629 | "_view_count": null,
630 | "_view_module": "@jupyter-widgets/base",
631 | "_view_module_version": "1.2.0",
632 | "_view_name": "StyleView",
633 | "bar_color": null,
634 | "description_width": ""
635 | }
636 | },
637 | "8782c620fea449fd92ea1f8f7ef3c6ed": {
638 | "model_module": "@jupyter-widgets/base",
639 | "model_name": "LayoutModel",
640 | "model_module_version": "1.2.0",
641 | "state": {
642 | "_model_module": "@jupyter-widgets/base",
643 | "_model_module_version": "1.2.0",
644 | "_model_name": "LayoutModel",
645 | "_view_count": null,
646 | "_view_module": "@jupyter-widgets/base",
647 | "_view_module_version": "1.2.0",
648 | "_view_name": "LayoutView",
649 | "align_content": null,
650 | "align_items": null,
651 | "align_self": null,
652 | "border": null,
653 | "bottom": null,
654 | "display": null,
655 | "flex": null,
656 | "flex_flow": null,
657 | "grid_area": null,
658 | "grid_auto_columns": null,
659 | "grid_auto_flow": null,
660 | "grid_auto_rows": null,
661 | "grid_column": null,
662 | "grid_gap": null,
663 | "grid_row": null,
664 | "grid_template_areas": null,
665 | "grid_template_columns": null,
666 | "grid_template_rows": null,
667 | "height": null,
668 | "justify_content": null,
669 | "justify_items": null,
670 | "left": null,
671 | "margin": null,
672 | "max_height": null,
673 | "max_width": null,
674 | "min_height": null,
675 | "min_width": null,
676 | "object_fit": null,
677 | "object_position": null,
678 | "order": null,
679 | "overflow": null,
680 | "overflow_x": null,
681 | "overflow_y": null,
682 | "padding": null,
683 | "right": null,
684 | "top": null,
685 | "visibility": null,
686 | "width": null
687 | }
688 | },
689 | "c04efab8b28346ea92e64a1599f1ee17": {
690 | "model_module": "@jupyter-widgets/controls",
691 | "model_name": "DescriptionStyleModel",
692 | "model_module_version": "1.5.0",
693 | "state": {
694 | "_model_module": "@jupyter-widgets/controls",
695 | "_model_module_version": "1.5.0",
696 | "_model_name": "DescriptionStyleModel",
697 | "_view_count": null,
698 | "_view_module": "@jupyter-widgets/base",
699 | "_view_module_version": "1.2.0",
700 | "_view_name": "StyleView",
701 | "description_width": ""
702 | }
703 | },
704 | "bd60373a16d647d9834a62c2624c9fc2": {
705 | "model_module": "@jupyter-widgets/controls",
706 | "model_name": "HBoxModel",
707 | "model_module_version": "1.5.0",
708 | "state": {
709 | "_dom_classes": [],
710 | "_model_module": "@jupyter-widgets/controls",
711 | "_model_module_version": "1.5.0",
712 | "_model_name": "HBoxModel",
713 | "_view_count": null,
714 | "_view_module": "@jupyter-widgets/controls",
715 | "_view_module_version": "1.5.0",
716 | "_view_name": "HBoxView",
717 | "box_style": "",
718 | "children": [
719 | "IPY_MODEL_8e3fb5977e1c4ccab1181cf41959c132",
720 | "IPY_MODEL_d35466c751474dd688fe7073aec0a71f",
721 | "IPY_MODEL_82e084627ec14d57bf502decdc393b38"
722 | ],
723 | "layout": "IPY_MODEL_df0d6cc9ad9b4597802c6e98614a7f95"
724 | }
725 | },
726 | "8e3fb5977e1c4ccab1181cf41959c132": {
727 | "model_module": "@jupyter-widgets/controls",
728 | "model_name": "HTMLModel",
729 | "model_module_version": "1.5.0",
730 | "state": {
731 | "_dom_classes": [],
732 | "_model_module": "@jupyter-widgets/controls",
733 | "_model_module_version": "1.5.0",
734 | "_model_name": "HTMLModel",
735 | "_view_count": null,
736 | "_view_module": "@jupyter-widgets/controls",
737 | "_view_module_version": "1.5.0",
738 | "_view_name": "HTMLView",
739 | "description": "",
740 | "description_tooltip": null,
741 | "layout": "IPY_MODEL_ef7a60fd80fe4ba8a8224b79f9659644",
742 | "placeholder": "",
743 | "style": "IPY_MODEL_7e912d3befc4448ea114e1fa3aa93119",
744 | "value": "Generating train split: "
745 | }
746 | },
747 | "d35466c751474dd688fe7073aec0a71f": {
748 | "model_module": "@jupyter-widgets/controls",
749 | "model_name": "FloatProgressModel",
750 | "model_module_version": "1.5.0",
751 | "state": {
752 | "_dom_classes": [],
753 | "_model_module": "@jupyter-widgets/controls",
754 | "_model_module_version": "1.5.0",
755 | "_model_name": "FloatProgressModel",
756 | "_view_count": null,
757 | "_view_module": "@jupyter-widgets/controls",
758 | "_view_module_version": "1.5.0",
759 | "_view_name": "ProgressView",
760 | "bar_style": "success",
761 | "description": "",
762 | "description_tooltip": null,
763 | "layout": "IPY_MODEL_ba7aaec1107b40248eb6b76fb09f1fc9",
764 | "max": 1,
765 | "min": 0,
766 | "orientation": "horizontal",
767 | "style": "IPY_MODEL_393fcf7561da4434b07ac6022ee95eeb",
768 | "value": 1
769 | }
770 | },
771 | "82e084627ec14d57bf502decdc393b38": {
772 | "model_module": "@jupyter-widgets/controls",
773 | "model_name": "HTMLModel",
774 | "model_module_version": "1.5.0",
775 | "state": {
776 | "_dom_classes": [],
777 | "_model_module": "@jupyter-widgets/controls",
778 | "_model_module_version": "1.5.0",
779 | "_model_name": "HTMLModel",
780 | "_view_count": null,
781 | "_view_module": "@jupyter-widgets/controls",
782 | "_view_module_version": "1.5.0",
783 | "_view_name": "HTMLView",
784 | "description": "",
785 | "description_tooltip": null,
786 | "layout": "IPY_MODEL_8cc2390d790f46ce880f81da99c3b243",
787 | "placeholder": "",
788 | "style": "IPY_MODEL_cb65ea1de35d439dbb0664329db64b25",
789 | "value": " 400/0 [00:00<00:00, 7601.75 examples/s]"
790 | }
791 | },
792 | "df0d6cc9ad9b4597802c6e98614a7f95": {
793 | "model_module": "@jupyter-widgets/base",
794 | "model_name": "LayoutModel",
795 | "model_module_version": "1.2.0",
796 | "state": {
797 | "_model_module": "@jupyter-widgets/base",
798 | "_model_module_version": "1.2.0",
799 | "_model_name": "LayoutModel",
800 | "_view_count": null,
801 | "_view_module": "@jupyter-widgets/base",
802 | "_view_module_version": "1.2.0",
803 | "_view_name": "LayoutView",
804 | "align_content": null,
805 | "align_items": null,
806 | "align_self": null,
807 | "border": null,
808 | "bottom": null,
809 | "display": null,
810 | "flex": null,
811 | "flex_flow": null,
812 | "grid_area": null,
813 | "grid_auto_columns": null,
814 | "grid_auto_flow": null,
815 | "grid_auto_rows": null,
816 | "grid_column": null,
817 | "grid_gap": null,
818 | "grid_row": null,
819 | "grid_template_areas": null,
820 | "grid_template_columns": null,
821 | "grid_template_rows": null,
822 | "height": null,
823 | "justify_content": null,
824 | "justify_items": null,
825 | "left": null,
826 | "margin": null,
827 | "max_height": null,
828 | "max_width": null,
829 | "min_height": null,
830 | "min_width": null,
831 | "object_fit": null,
832 | "object_position": null,
833 | "order": null,
834 | "overflow": null,
835 | "overflow_x": null,
836 | "overflow_y": null,
837 | "padding": null,
838 | "right": null,
839 | "top": null,
840 | "visibility": null,
841 | "width": null
842 | }
843 | },
844 | "ef7a60fd80fe4ba8a8224b79f9659644": {
845 | "model_module": "@jupyter-widgets/base",
846 | "model_name": "LayoutModel",
847 | "model_module_version": "1.2.0",
848 | "state": {
849 | "_model_module": "@jupyter-widgets/base",
850 | "_model_module_version": "1.2.0",
851 | "_model_name": "LayoutModel",
852 | "_view_count": null,
853 | "_view_module": "@jupyter-widgets/base",
854 | "_view_module_version": "1.2.0",
855 | "_view_name": "LayoutView",
856 | "align_content": null,
857 | "align_items": null,
858 | "align_self": null,
859 | "border": null,
860 | "bottom": null,
861 | "display": null,
862 | "flex": null,
863 | "flex_flow": null,
864 | "grid_area": null,
865 | "grid_auto_columns": null,
866 | "grid_auto_flow": null,
867 | "grid_auto_rows": null,
868 | "grid_column": null,
869 | "grid_gap": null,
870 | "grid_row": null,
871 | "grid_template_areas": null,
872 | "grid_template_columns": null,
873 | "grid_template_rows": null,
874 | "height": null,
875 | "justify_content": null,
876 | "justify_items": null,
877 | "left": null,
878 | "margin": null,
879 | "max_height": null,
880 | "max_width": null,
881 | "min_height": null,
882 | "min_width": null,
883 | "object_fit": null,
884 | "object_position": null,
885 | "order": null,
886 | "overflow": null,
887 | "overflow_x": null,
888 | "overflow_y": null,
889 | "padding": null,
890 | "right": null,
891 | "top": null,
892 | "visibility": null,
893 | "width": null
894 | }
895 | },
896 | "7e912d3befc4448ea114e1fa3aa93119": {
897 | "model_module": "@jupyter-widgets/controls",
898 | "model_name": "DescriptionStyleModel",
899 | "model_module_version": "1.5.0",
900 | "state": {
901 | "_model_module": "@jupyter-widgets/controls",
902 | "_model_module_version": "1.5.0",
903 | "_model_name": "DescriptionStyleModel",
904 | "_view_count": null,
905 | "_view_module": "@jupyter-widgets/base",
906 | "_view_module_version": "1.2.0",
907 | "_view_name": "StyleView",
908 | "description_width": ""
909 | }
910 | },
911 | "ba7aaec1107b40248eb6b76fb09f1fc9": {
912 | "model_module": "@jupyter-widgets/base",
913 | "model_name": "LayoutModel",
914 | "model_module_version": "1.2.0",
915 | "state": {
916 | "_model_module": "@jupyter-widgets/base",
917 | "_model_module_version": "1.2.0",
918 | "_model_name": "LayoutModel",
919 | "_view_count": null,
920 | "_view_module": "@jupyter-widgets/base",
921 | "_view_module_version": "1.2.0",
922 | "_view_name": "LayoutView",
923 | "align_content": null,
924 | "align_items": null,
925 | "align_self": null,
926 | "border": null,
927 | "bottom": null,
928 | "display": null,
929 | "flex": null,
930 | "flex_flow": null,
931 | "grid_area": null,
932 | "grid_auto_columns": null,
933 | "grid_auto_flow": null,
934 | "grid_auto_rows": null,
935 | "grid_column": null,
936 | "grid_gap": null,
937 | "grid_row": null,
938 | "grid_template_areas": null,
939 | "grid_template_columns": null,
940 | "grid_template_rows": null,
941 | "height": null,
942 | "justify_content": null,
943 | "justify_items": null,
944 | "left": null,
945 | "margin": null,
946 | "max_height": null,
947 | "max_width": null,
948 | "min_height": null,
949 | "min_width": null,
950 | "object_fit": null,
951 | "object_position": null,
952 | "order": null,
953 | "overflow": null,
954 | "overflow_x": null,
955 | "overflow_y": null,
956 | "padding": null,
957 | "right": null,
958 | "top": null,
959 | "visibility": null,
960 | "width": "20px"
961 | }
962 | },
963 | "393fcf7561da4434b07ac6022ee95eeb": {
964 | "model_module": "@jupyter-widgets/controls",
965 | "model_name": "ProgressStyleModel",
966 | "model_module_version": "1.5.0",
967 | "state": {
968 | "_model_module": "@jupyter-widgets/controls",
969 | "_model_module_version": "1.5.0",
970 | "_model_name": "ProgressStyleModel",
971 | "_view_count": null,
972 | "_view_module": "@jupyter-widgets/base",
973 | "_view_module_version": "1.2.0",
974 | "_view_name": "StyleView",
975 | "bar_color": null,
976 | "description_width": ""
977 | }
978 | },
979 | "8cc2390d790f46ce880f81da99c3b243": {
980 | "model_module": "@jupyter-widgets/base",
981 | "model_name": "LayoutModel",
982 | "model_module_version": "1.2.0",
983 | "state": {
984 | "_model_module": "@jupyter-widgets/base",
985 | "_model_module_version": "1.2.0",
986 | "_model_name": "LayoutModel",
987 | "_view_count": null,
988 | "_view_module": "@jupyter-widgets/base",
989 | "_view_module_version": "1.2.0",
990 | "_view_name": "LayoutView",
991 | "align_content": null,
992 | "align_items": null,
993 | "align_self": null,
994 | "border": null,
995 | "bottom": null,
996 | "display": null,
997 | "flex": null,
998 | "flex_flow": null,
999 | "grid_area": null,
1000 | "grid_auto_columns": null,
1001 | "grid_auto_flow": null,
1002 | "grid_auto_rows": null,
1003 | "grid_column": null,
1004 | "grid_gap": null,
1005 | "grid_row": null,
1006 | "grid_template_areas": null,
1007 | "grid_template_columns": null,
1008 | "grid_template_rows": null,
1009 | "height": null,
1010 | "justify_content": null,
1011 | "justify_items": null,
1012 | "left": null,
1013 | "margin": null,
1014 | "max_height": null,
1015 | "max_width": null,
1016 | "min_height": null,
1017 | "min_width": null,
1018 | "object_fit": null,
1019 | "object_position": null,
1020 | "order": null,
1021 | "overflow": null,
1022 | "overflow_x": null,
1023 | "overflow_y": null,
1024 | "padding": null,
1025 | "right": null,
1026 | "top": null,
1027 | "visibility": null,
1028 | "width": null
1029 | }
1030 | },
1031 | "cb65ea1de35d439dbb0664329db64b25": {
1032 | "model_module": "@jupyter-widgets/controls",
1033 | "model_name": "DescriptionStyleModel",
1034 | "model_module_version": "1.5.0",
1035 | "state": {
1036 | "_model_module": "@jupyter-widgets/controls",
1037 | "_model_module_version": "1.5.0",
1038 | "_model_name": "DescriptionStyleModel",
1039 | "_view_count": null,
1040 | "_view_module": "@jupyter-widgets/base",
1041 | "_view_module_version": "1.2.0",
1042 | "_view_name": "StyleView",
1043 | "description_width": ""
1044 | }
1045 | },
1046 | "ec7fe86bf8f24f6387d541a2801dd4a7": {
1047 | "model_module": "@jupyter-widgets/controls",
1048 | "model_name": "HBoxModel",
1049 | "model_module_version": "1.5.0",
1050 | "state": {
1051 | "_dom_classes": [],
1052 | "_model_module": "@jupyter-widgets/controls",
1053 | "_model_module_version": "1.5.0",
1054 | "_model_name": "HBoxModel",
1055 | "_view_count": null,
1056 | "_view_module": "@jupyter-widgets/controls",
1057 | "_view_module_version": "1.5.0",
1058 | "_view_name": "HBoxView",
1059 | "box_style": "",
1060 | "children": [
1061 | "IPY_MODEL_89e5de0b0b0345b8b1d80adecc11e686",
1062 | "IPY_MODEL_d2ebf5c51f4e4be7b6397f36ea7ea816",
1063 | "IPY_MODEL_76641188f873496a84f24433e930c0c7"
1064 | ],
1065 | "layout": "IPY_MODEL_dc3b7059ab6d44619490a453498994dc"
1066 | }
1067 | },
1068 | "89e5de0b0b0345b8b1d80adecc11e686": {
1069 | "model_module": "@jupyter-widgets/controls",
1070 | "model_name": "HTMLModel",
1071 | "model_module_version": "1.5.0",
1072 | "state": {
1073 | "_dom_classes": [],
1074 | "_model_module": "@jupyter-widgets/controls",
1075 | "_model_module_version": "1.5.0",
1076 | "_model_name": "HTMLModel",
1077 | "_view_count": null,
1078 | "_view_module": "@jupyter-widgets/controls",
1079 | "_view_module_version": "1.5.0",
1080 | "_view_name": "HTMLView",
1081 | "description": "",
1082 | "description_tooltip": null,
1083 | "layout": "IPY_MODEL_e0ab81310bc047fab2b01fd064a7fa45",
1084 | "placeholder": "",
1085 | "style": "IPY_MODEL_2df7b934f04446c69243ad852b1bb66e",
1086 | "value": "vocab.json: 100%"
1087 | }
1088 | },
1089 | "d2ebf5c51f4e4be7b6397f36ea7ea816": {
1090 | "model_module": "@jupyter-widgets/controls",
1091 | "model_name": "FloatProgressModel",
1092 | "model_module_version": "1.5.0",
1093 | "state": {
1094 | "_dom_classes": [],
1095 | "_model_module": "@jupyter-widgets/controls",
1096 | "_model_module_version": "1.5.0",
1097 | "_model_name": "FloatProgressModel",
1098 | "_view_count": null,
1099 | "_view_module": "@jupyter-widgets/controls",
1100 | "_view_module_version": "1.5.0",
1101 | "_view_name": "ProgressView",
1102 | "bar_style": "success",
1103 | "description": "",
1104 | "description_tooltip": null,
1105 | "layout": "IPY_MODEL_ad2e4b0915974802963f70f0e0ef0b4e",
1106 | "max": 1042301,
1107 | "min": 0,
1108 | "orientation": "horizontal",
1109 | "style": "IPY_MODEL_a516e4ccd9844714b9e8738fac138f08",
1110 | "value": 1042301
1111 | }
1112 | },
1113 | "76641188f873496a84f24433e930c0c7": {
1114 | "model_module": "@jupyter-widgets/controls",
1115 | "model_name": "HTMLModel",
1116 | "model_module_version": "1.5.0",
1117 | "state": {
1118 | "_dom_classes": [],
1119 | "_model_module": "@jupyter-widgets/controls",
1120 | "_model_module_version": "1.5.0",
1121 | "_model_name": "HTMLModel",
1122 | "_view_count": null,
1123 | "_view_module": "@jupyter-widgets/controls",
1124 | "_view_module_version": "1.5.0",
1125 | "_view_name": "HTMLView",
1126 | "description": "",
1127 | "description_tooltip": null,
1128 | "layout": "IPY_MODEL_d06613abbcea4ee0b06b2938494b89bc",
1129 | "placeholder": "",
1130 | "style": "IPY_MODEL_69ffd05ad18c4c958dd3da00ecb03861",
1131 | "value": " 1.04M/1.04M [00:00<00:00, 1.06MB/s]"
1132 | }
1133 | },
1134 | "dc3b7059ab6d44619490a453498994dc": {
1135 | "model_module": "@jupyter-widgets/base",
1136 | "model_name": "LayoutModel",
1137 | "model_module_version": "1.2.0",
1138 | "state": {
1139 | "_model_module": "@jupyter-widgets/base",
1140 | "_model_module_version": "1.2.0",
1141 | "_model_name": "LayoutModel",
1142 | "_view_count": null,
1143 | "_view_module": "@jupyter-widgets/base",
1144 | "_view_module_version": "1.2.0",
1145 | "_view_name": "LayoutView",
1146 | "align_content": null,
1147 | "align_items": null,
1148 | "align_self": null,
1149 | "border": null,
1150 | "bottom": null,
1151 | "display": null,
1152 | "flex": null,
1153 | "flex_flow": null,
1154 | "grid_area": null,
1155 | "grid_auto_columns": null,
1156 | "grid_auto_flow": null,
1157 | "grid_auto_rows": null,
1158 | "grid_column": null,
1159 | "grid_gap": null,
1160 | "grid_row": null,
1161 | "grid_template_areas": null,
1162 | "grid_template_columns": null,
1163 | "grid_template_rows": null,
1164 | "height": null,
1165 | "justify_content": null,
1166 | "justify_items": null,
1167 | "left": null,
1168 | "margin": null,
1169 | "max_height": null,
1170 | "max_width": null,
1171 | "min_height": null,
1172 | "min_width": null,
1173 | "object_fit": null,
1174 | "object_position": null,
1175 | "order": null,
1176 | "overflow": null,
1177 | "overflow_x": null,
1178 | "overflow_y": null,
1179 | "padding": null,
1180 | "right": null,
1181 | "top": null,
1182 | "visibility": null,
1183 | "width": null
1184 | }
1185 | },
1186 | "e0ab81310bc047fab2b01fd064a7fa45": {
1187 | "model_module": "@jupyter-widgets/base",
1188 | "model_name": "LayoutModel",
1189 | "model_module_version": "1.2.0",
1190 | "state": {
1191 | "_model_module": "@jupyter-widgets/base",
1192 | "_model_module_version": "1.2.0",
1193 | "_model_name": "LayoutModel",
1194 | "_view_count": null,
1195 | "_view_module": "@jupyter-widgets/base",
1196 | "_view_module_version": "1.2.0",
1197 | "_view_name": "LayoutView",
1198 | "align_content": null,
1199 | "align_items": null,
1200 | "align_self": null,
1201 | "border": null,
1202 | "bottom": null,
1203 | "display": null,
1204 | "flex": null,
1205 | "flex_flow": null,
1206 | "grid_area": null,
1207 | "grid_auto_columns": null,
1208 | "grid_auto_flow": null,
1209 | "grid_auto_rows": null,
1210 | "grid_column": null,
1211 | "grid_gap": null,
1212 | "grid_row": null,
1213 | "grid_template_areas": null,
1214 | "grid_template_columns": null,
1215 | "grid_template_rows": null,
1216 | "height": null,
1217 | "justify_content": null,
1218 | "justify_items": null,
1219 | "left": null,
1220 | "margin": null,
1221 | "max_height": null,
1222 | "max_width": null,
1223 | "min_height": null,
1224 | "min_width": null,
1225 | "object_fit": null,
1226 | "object_position": null,
1227 | "order": null,
1228 | "overflow": null,
1229 | "overflow_x": null,
1230 | "overflow_y": null,
1231 | "padding": null,
1232 | "right": null,
1233 | "top": null,
1234 | "visibility": null,
1235 | "width": null
1236 | }
1237 | },
1238 | "2df7b934f04446c69243ad852b1bb66e": {
1239 | "model_module": "@jupyter-widgets/controls",
1240 | "model_name": "DescriptionStyleModel",
1241 | "model_module_version": "1.5.0",
1242 | "state": {
1243 | "_model_module": "@jupyter-widgets/controls",
1244 | "_model_module_version": "1.5.0",
1245 | "_model_name": "DescriptionStyleModel",
1246 | "_view_count": null,
1247 | "_view_module": "@jupyter-widgets/base",
1248 | "_view_module_version": "1.2.0",
1249 | "_view_name": "StyleView",
1250 | "description_width": ""
1251 | }
1252 | },
1253 | "ad2e4b0915974802963f70f0e0ef0b4e": {
1254 | "model_module": "@jupyter-widgets/base",
1255 | "model_name": "LayoutModel",
1256 | "model_module_version": "1.2.0",
1257 | "state": {
1258 | "_model_module": "@jupyter-widgets/base",
1259 | "_model_module_version": "1.2.0",
1260 | "_model_name": "LayoutModel",
1261 | "_view_count": null,
1262 | "_view_module": "@jupyter-widgets/base",
1263 | "_view_module_version": "1.2.0",
1264 | "_view_name": "LayoutView",
1265 | "align_content": null,
1266 | "align_items": null,
1267 | "align_self": null,
1268 | "border": null,
1269 | "bottom": null,
1270 | "display": null,
1271 | "flex": null,
1272 | "flex_flow": null,
1273 | "grid_area": null,
1274 | "grid_auto_columns": null,
1275 | "grid_auto_flow": null,
1276 | "grid_auto_rows": null,
1277 | "grid_column": null,
1278 | "grid_gap": null,
1279 | "grid_row": null,
1280 | "grid_template_areas": null,
1281 | "grid_template_columns": null,
1282 | "grid_template_rows": null,
1283 | "height": null,
1284 | "justify_content": null,
1285 | "justify_items": null,
1286 | "left": null,
1287 | "margin": null,
1288 | "max_height": null,
1289 | "max_width": null,
1290 | "min_height": null,
1291 | "min_width": null,
1292 | "object_fit": null,
1293 | "object_position": null,
1294 | "order": null,
1295 | "overflow": null,
1296 | "overflow_x": null,
1297 | "overflow_y": null,
1298 | "padding": null,
1299 | "right": null,
1300 | "top": null,
1301 | "visibility": null,
1302 | "width": null
1303 | }
1304 | },
1305 | "a516e4ccd9844714b9e8738fac138f08": {
1306 | "model_module": "@jupyter-widgets/controls",
1307 | "model_name": "ProgressStyleModel",
1308 | "model_module_version": "1.5.0",
1309 | "state": {
1310 | "_model_module": "@jupyter-widgets/controls",
1311 | "_model_module_version": "1.5.0",
1312 | "_model_name": "ProgressStyleModel",
1313 | "_view_count": null,
1314 | "_view_module": "@jupyter-widgets/base",
1315 | "_view_module_version": "1.2.0",
1316 | "_view_name": "StyleView",
1317 | "bar_color": null,
1318 | "description_width": ""
1319 | }
1320 | },
1321 | "d06613abbcea4ee0b06b2938494b89bc": {
1322 | "model_module": "@jupyter-widgets/base",
1323 | "model_name": "LayoutModel",
1324 | "model_module_version": "1.2.0",
1325 | "state": {
1326 | "_model_module": "@jupyter-widgets/base",
1327 | "_model_module_version": "1.2.0",
1328 | "_model_name": "LayoutModel",
1329 | "_view_count": null,
1330 | "_view_module": "@jupyter-widgets/base",
1331 | "_view_module_version": "1.2.0",
1332 | "_view_name": "LayoutView",
1333 | "align_content": null,
1334 | "align_items": null,
1335 | "align_self": null,
1336 | "border": null,
1337 | "bottom": null,
1338 | "display": null,
1339 | "flex": null,
1340 | "flex_flow": null,
1341 | "grid_area": null,
1342 | "grid_auto_columns": null,
1343 | "grid_auto_flow": null,
1344 | "grid_auto_rows": null,
1345 | "grid_column": null,
1346 | "grid_gap": null,
1347 | "grid_row": null,
1348 | "grid_template_areas": null,
1349 | "grid_template_columns": null,
1350 | "grid_template_rows": null,
1351 | "height": null,
1352 | "justify_content": null,
1353 | "justify_items": null,
1354 | "left": null,
1355 | "margin": null,
1356 | "max_height": null,
1357 | "max_width": null,
1358 | "min_height": null,
1359 | "min_width": null,
1360 | "object_fit": null,
1361 | "object_position": null,
1362 | "order": null,
1363 | "overflow": null,
1364 | "overflow_x": null,
1365 | "overflow_y": null,
1366 | "padding": null,
1367 | "right": null,
1368 | "top": null,
1369 | "visibility": null,
1370 | "width": null
1371 | }
1372 | },
1373 | "69ffd05ad18c4c958dd3da00ecb03861": {
1374 | "model_module": "@jupyter-widgets/controls",
1375 | "model_name": "DescriptionStyleModel",
1376 | "model_module_version": "1.5.0",
1377 | "state": {
1378 | "_model_module": "@jupyter-widgets/controls",
1379 | "_model_module_version": "1.5.0",
1380 | "_model_name": "DescriptionStyleModel",
1381 | "_view_count": null,
1382 | "_view_module": "@jupyter-widgets/base",
1383 | "_view_module_version": "1.2.0",
1384 | "_view_name": "StyleView",
1385 | "description_width": ""
1386 | }
1387 | },
1388 | "4ff4e721bc684d3588fc0bf9eef01dc1": {
1389 | "model_module": "@jupyter-widgets/controls",
1390 | "model_name": "HBoxModel",
1391 | "model_module_version": "1.5.0",
1392 | "state": {
1393 | "_dom_classes": [],
1394 | "_model_module": "@jupyter-widgets/controls",
1395 | "_model_module_version": "1.5.0",
1396 | "_model_name": "HBoxModel",
1397 | "_view_count": null,
1398 | "_view_module": "@jupyter-widgets/controls",
1399 | "_view_module_version": "1.5.0",
1400 | "_view_name": "HBoxView",
1401 | "box_style": "",
1402 | "children": [
1403 | "IPY_MODEL_a51c774046d840eba964ae05d44bc121",
1404 | "IPY_MODEL_92c278e987384f9a8211800c54d7d2db",
1405 | "IPY_MODEL_ce8b2c1e2af7468483b0248914da3be9"
1406 | ],
1407 | "layout": "IPY_MODEL_4ed5bcc239e145518de1fef008bb9b26"
1408 | }
1409 | },
1410 | "a51c774046d840eba964ae05d44bc121": {
1411 | "model_module": "@jupyter-widgets/controls",
1412 | "model_name": "HTMLModel",
1413 | "model_module_version": "1.5.0",
1414 | "state": {
1415 | "_dom_classes": [],
1416 | "_model_module": "@jupyter-widgets/controls",
1417 | "_model_module_version": "1.5.0",
1418 | "_model_name": "HTMLModel",
1419 | "_view_count": null,
1420 | "_view_module": "@jupyter-widgets/controls",
1421 | "_view_module_version": "1.5.0",
1422 | "_view_name": "HTMLView",
1423 | "description": "",
1424 | "description_tooltip": null,
1425 | "layout": "IPY_MODEL_479dd0a62eec484a928f39a21b13a5ce",
1426 | "placeholder": "",
1427 | "style": "IPY_MODEL_91efbd33184f4499825677459dc0bdfd",
1428 | "value": "merges.txt: 100%"
1429 | }
1430 | },
1431 | "92c278e987384f9a8211800c54d7d2db": {
1432 | "model_module": "@jupyter-widgets/controls",
1433 | "model_name": "FloatProgressModel",
1434 | "model_module_version": "1.5.0",
1435 | "state": {
1436 | "_dom_classes": [],
1437 | "_model_module": "@jupyter-widgets/controls",
1438 | "_model_module_version": "1.5.0",
1439 | "_model_name": "FloatProgressModel",
1440 | "_view_count": null,
1441 | "_view_module": "@jupyter-widgets/controls",
1442 | "_view_module_version": "1.5.0",
1443 | "_view_name": "ProgressView",
1444 | "bar_style": "success",
1445 | "description": "",
1446 | "description_tooltip": null,
1447 | "layout": "IPY_MODEL_af8dff1656144b30aa37d8e80316f024",
1448 | "max": 456318,
1449 | "min": 0,
1450 | "orientation": "horizontal",
1451 | "style": "IPY_MODEL_b88bdbeefe9444cd8b430e75b6943162",
1452 | "value": 456318
1453 | }
1454 | },
1455 | "ce8b2c1e2af7468483b0248914da3be9": {
1456 | "model_module": "@jupyter-widgets/controls",
1457 | "model_name": "HTMLModel",
1458 | "model_module_version": "1.5.0",
1459 | "state": {
1460 | "_dom_classes": [],
1461 | "_model_module": "@jupyter-widgets/controls",
1462 | "_model_module_version": "1.5.0",
1463 | "_model_name": "HTMLModel",
1464 | "_view_count": null,
1465 | "_view_module": "@jupyter-widgets/controls",
1466 | "_view_module_version": "1.5.0",
1467 | "_view_name": "HTMLView",
1468 | "description": "",
1469 | "description_tooltip": null,
1470 | "layout": "IPY_MODEL_ff2cde47d25749459db552ce4a7d76e8",
1471 | "placeholder": "",
1472 | "style": "IPY_MODEL_fe1f13c138e64a12818be45e287624e1",
1473 | "value": " 456k/456k [00:00<00:00, 938kB/s]"
1474 | }
1475 | },
1476 | "4ed5bcc239e145518de1fef008bb9b26": {
1477 | "model_module": "@jupyter-widgets/base",
1478 | "model_name": "LayoutModel",
1479 | "model_module_version": "1.2.0",
1480 | "state": {
1481 | "_model_module": "@jupyter-widgets/base",
1482 | "_model_module_version": "1.2.0",
1483 | "_model_name": "LayoutModel",
1484 | "_view_count": null,
1485 | "_view_module": "@jupyter-widgets/base",
1486 | "_view_module_version": "1.2.0",
1487 | "_view_name": "LayoutView",
1488 | "align_content": null,
1489 | "align_items": null,
1490 | "align_self": null,
1491 | "border": null,
1492 | "bottom": null,
1493 | "display": null,
1494 | "flex": null,
1495 | "flex_flow": null,
1496 | "grid_area": null,
1497 | "grid_auto_columns": null,
1498 | "grid_auto_flow": null,
1499 | "grid_auto_rows": null,
1500 | "grid_column": null,
1501 | "grid_gap": null,
1502 | "grid_row": null,
1503 | "grid_template_areas": null,
1504 | "grid_template_columns": null,
1505 | "grid_template_rows": null,
1506 | "height": null,
1507 | "justify_content": null,
1508 | "justify_items": null,
1509 | "left": null,
1510 | "margin": null,
1511 | "max_height": null,
1512 | "max_width": null,
1513 | "min_height": null,
1514 | "min_width": null,
1515 | "object_fit": null,
1516 | "object_position": null,
1517 | "order": null,
1518 | "overflow": null,
1519 | "overflow_x": null,
1520 | "overflow_y": null,
1521 | "padding": null,
1522 | "right": null,
1523 | "top": null,
1524 | "visibility": null,
1525 | "width": null
1526 | }
1527 | },
1528 | "479dd0a62eec484a928f39a21b13a5ce": {
1529 | "model_module": "@jupyter-widgets/base",
1530 | "model_name": "LayoutModel",
1531 | "model_module_version": "1.2.0",
1532 | "state": {
1533 | "_model_module": "@jupyter-widgets/base",
1534 | "_model_module_version": "1.2.0",
1535 | "_model_name": "LayoutModel",
1536 | "_view_count": null,
1537 | "_view_module": "@jupyter-widgets/base",
1538 | "_view_module_version": "1.2.0",
1539 | "_view_name": "LayoutView",
1540 | "align_content": null,
1541 | "align_items": null,
1542 | "align_self": null,
1543 | "border": null,
1544 | "bottom": null,
1545 | "display": null,
1546 | "flex": null,
1547 | "flex_flow": null,
1548 | "grid_area": null,
1549 | "grid_auto_columns": null,
1550 | "grid_auto_flow": null,
1551 | "grid_auto_rows": null,
1552 | "grid_column": null,
1553 | "grid_gap": null,
1554 | "grid_row": null,
1555 | "grid_template_areas": null,
1556 | "grid_template_columns": null,
1557 | "grid_template_rows": null,
1558 | "height": null,
1559 | "justify_content": null,
1560 | "justify_items": null,
1561 | "left": null,
1562 | "margin": null,
1563 | "max_height": null,
1564 | "max_width": null,
1565 | "min_height": null,
1566 | "min_width": null,
1567 | "object_fit": null,
1568 | "object_position": null,
1569 | "order": null,
1570 | "overflow": null,
1571 | "overflow_x": null,
1572 | "overflow_y": null,
1573 | "padding": null,
1574 | "right": null,
1575 | "top": null,
1576 | "visibility": null,
1577 | "width": null
1578 | }
1579 | },
1580 | "91efbd33184f4499825677459dc0bdfd": {
1581 | "model_module": "@jupyter-widgets/controls",
1582 | "model_name": "DescriptionStyleModel",
1583 | "model_module_version": "1.5.0",
1584 | "state": {
1585 | "_model_module": "@jupyter-widgets/controls",
1586 | "_model_module_version": "1.5.0",
1587 | "_model_name": "DescriptionStyleModel",
1588 | "_view_count": null,
1589 | "_view_module": "@jupyter-widgets/base",
1590 | "_view_module_version": "1.2.0",
1591 | "_view_name": "StyleView",
1592 | "description_width": ""
1593 | }
1594 | },
1595 | "af8dff1656144b30aa37d8e80316f024": {
1596 | "model_module": "@jupyter-widgets/base",
1597 | "model_name": "LayoutModel",
1598 | "model_module_version": "1.2.0",
1599 | "state": {
1600 | "_model_module": "@jupyter-widgets/base",
1601 | "_model_module_version": "1.2.0",
1602 | "_model_name": "LayoutModel",
1603 | "_view_count": null,
1604 | "_view_module": "@jupyter-widgets/base",
1605 | "_view_module_version": "1.2.0",
1606 | "_view_name": "LayoutView",
1607 | "align_content": null,
1608 | "align_items": null,
1609 | "align_self": null,
1610 | "border": null,
1611 | "bottom": null,
1612 | "display": null,
1613 | "flex": null,
1614 | "flex_flow": null,
1615 | "grid_area": null,
1616 | "grid_auto_columns": null,
1617 | "grid_auto_flow": null,
1618 | "grid_auto_rows": null,
1619 | "grid_column": null,
1620 | "grid_gap": null,
1621 | "grid_row": null,
1622 | "grid_template_areas": null,
1623 | "grid_template_columns": null,
1624 | "grid_template_rows": null,
1625 | "height": null,
1626 | "justify_content": null,
1627 | "justify_items": null,
1628 | "left": null,
1629 | "margin": null,
1630 | "max_height": null,
1631 | "max_width": null,
1632 | "min_height": null,
1633 | "min_width": null,
1634 | "object_fit": null,
1635 | "object_position": null,
1636 | "order": null,
1637 | "overflow": null,
1638 | "overflow_x": null,
1639 | "overflow_y": null,
1640 | "padding": null,
1641 | "right": null,
1642 | "top": null,
1643 | "visibility": null,
1644 | "width": null
1645 | }
1646 | },
1647 | "b88bdbeefe9444cd8b430e75b6943162": {
1648 | "model_module": "@jupyter-widgets/controls",
1649 | "model_name": "ProgressStyleModel",
1650 | "model_module_version": "1.5.0",
1651 | "state": {
1652 | "_model_module": "@jupyter-widgets/controls",
1653 | "_model_module_version": "1.5.0",
1654 | "_model_name": "ProgressStyleModel",
1655 | "_view_count": null,
1656 | "_view_module": "@jupyter-widgets/base",
1657 | "_view_module_version": "1.2.0",
1658 | "_view_name": "StyleView",
1659 | "bar_color": null,
1660 | "description_width": ""
1661 | }
1662 | },
1663 | "ff2cde47d25749459db552ce4a7d76e8": {
1664 | "model_module": "@jupyter-widgets/base",
1665 | "model_name": "LayoutModel",
1666 | "model_module_version": "1.2.0",
1667 | "state": {
1668 | "_model_module": "@jupyter-widgets/base",
1669 | "_model_module_version": "1.2.0",
1670 | "_model_name": "LayoutModel",
1671 | "_view_count": null,
1672 | "_view_module": "@jupyter-widgets/base",
1673 | "_view_module_version": "1.2.0",
1674 | "_view_name": "LayoutView",
1675 | "align_content": null,
1676 | "align_items": null,
1677 | "align_self": null,
1678 | "border": null,
1679 | "bottom": null,
1680 | "display": null,
1681 | "flex": null,
1682 | "flex_flow": null,
1683 | "grid_area": null,
1684 | "grid_auto_columns": null,
1685 | "grid_auto_flow": null,
1686 | "grid_auto_rows": null,
1687 | "grid_column": null,
1688 | "grid_gap": null,
1689 | "grid_row": null,
1690 | "grid_template_areas": null,
1691 | "grid_template_columns": null,
1692 | "grid_template_rows": null,
1693 | "height": null,
1694 | "justify_content": null,
1695 | "justify_items": null,
1696 | "left": null,
1697 | "margin": null,
1698 | "max_height": null,
1699 | "max_width": null,
1700 | "min_height": null,
1701 | "min_width": null,
1702 | "object_fit": null,
1703 | "object_position": null,
1704 | "order": null,
1705 | "overflow": null,
1706 | "overflow_x": null,
1707 | "overflow_y": null,
1708 | "padding": null,
1709 | "right": null,
1710 | "top": null,
1711 | "visibility": null,
1712 | "width": null
1713 | }
1714 | },
1715 | "fe1f13c138e64a12818be45e287624e1": {
1716 | "model_module": "@jupyter-widgets/controls",
1717 | "model_name": "DescriptionStyleModel",
1718 | "model_module_version": "1.5.0",
1719 | "state": {
1720 | "_model_module": "@jupyter-widgets/controls",
1721 | "_model_module_version": "1.5.0",
1722 | "_model_name": "DescriptionStyleModel",
1723 | "_view_count": null,
1724 | "_view_module": "@jupyter-widgets/base",
1725 | "_view_module_version": "1.2.0",
1726 | "_view_name": "StyleView",
1727 | "description_width": ""
1728 | }
1729 | },
1730 | "4ab5fa5d0362442fb891d153a2221269": {
1731 | "model_module": "@jupyter-widgets/controls",
1732 | "model_name": "HBoxModel",
1733 | "model_module_version": "1.5.0",
1734 | "state": {
1735 | "_dom_classes": [],
1736 | "_model_module": "@jupyter-widgets/controls",
1737 | "_model_module_version": "1.5.0",
1738 | "_model_name": "HBoxModel",
1739 | "_view_count": null,
1740 | "_view_module": "@jupyter-widgets/controls",
1741 | "_view_module_version": "1.5.0",
1742 | "_view_name": "HBoxView",
1743 | "box_style": "",
1744 | "children": [
1745 | "IPY_MODEL_3dfce640dbd648049f86bb6f960fba84",
1746 | "IPY_MODEL_047c1c3081184ef8bbd1e55906d6034c",
1747 | "IPY_MODEL_0ddc3a071ee74db4a701fa5c71bde4ab"
1748 | ],
1749 | "layout": "IPY_MODEL_4860d8f28fd4452ea3d78f5d360c8920"
1750 | }
1751 | },
1752 | "3dfce640dbd648049f86bb6f960fba84": {
1753 | "model_module": "@jupyter-widgets/controls",
1754 | "model_name": "HTMLModel",
1755 | "model_module_version": "1.5.0",
1756 | "state": {
1757 | "_dom_classes": [],
1758 | "_model_module": "@jupyter-widgets/controls",
1759 | "_model_module_version": "1.5.0",
1760 | "_model_name": "HTMLModel",
1761 | "_view_count": null,
1762 | "_view_module": "@jupyter-widgets/controls",
1763 | "_view_module_version": "1.5.0",
1764 | "_view_name": "HTMLView",
1765 | "description": "",
1766 | "description_tooltip": null,
1767 | "layout": "IPY_MODEL_a8c102ccd45a4bb9a0366fed028c9c89",
1768 | "placeholder": "",
1769 | "style": "IPY_MODEL_53be2c46b0634ace8157f69dddf502ed",
1770 | "value": "tokenizer.json: 100%"
1771 | }
1772 | },
1773 | "047c1c3081184ef8bbd1e55906d6034c": {
1774 | "model_module": "@jupyter-widgets/controls",
1775 | "model_name": "FloatProgressModel",
1776 | "model_module_version": "1.5.0",
1777 | "state": {
1778 | "_dom_classes": [],
1779 | "_model_module": "@jupyter-widgets/controls",
1780 | "_model_module_version": "1.5.0",
1781 | "_model_name": "FloatProgressModel",
1782 | "_view_count": null,
1783 | "_view_module": "@jupyter-widgets/controls",
1784 | "_view_module_version": "1.5.0",
1785 | "_view_name": "ProgressView",
1786 | "bar_style": "success",
1787 | "description": "",
1788 | "description_tooltip": null,
1789 | "layout": "IPY_MODEL_8aa38554efa847d6b23659bbe3a22fd5",
1790 | "max": 1355256,
1791 | "min": 0,
1792 | "orientation": "horizontal",
1793 | "style": "IPY_MODEL_79ea0ca6be994c05a139b4b3b1d44e41",
1794 | "value": 1355256
1795 | }
1796 | },
1797 | "0ddc3a071ee74db4a701fa5c71bde4ab": {
1798 | "model_module": "@jupyter-widgets/controls",
1799 | "model_name": "HTMLModel",
1800 | "model_module_version": "1.5.0",
1801 | "state": {
1802 | "_dom_classes": [],
1803 | "_model_module": "@jupyter-widgets/controls",
1804 | "_model_module_version": "1.5.0",
1805 | "_model_name": "HTMLModel",
1806 | "_view_count": null,
1807 | "_view_module": "@jupyter-widgets/controls",
1808 | "_view_module_version": "1.5.0",
1809 | "_view_name": "HTMLView",
1810 | "description": "",
1811 | "description_tooltip": null,
1812 | "layout": "IPY_MODEL_a23c7e7a5ac44f1c9fae6db6fb9a380c",
1813 | "placeholder": "",
1814 | "style": "IPY_MODEL_be5a493006c247c6b94a76bfa8cd7717",
1815 | "value": " 1.36M/1.36M [00:00<00:00, 1.39MB/s]"
1816 | }
1817 | },
1818 | "4860d8f28fd4452ea3d78f5d360c8920": {
1819 | "model_module": "@jupyter-widgets/base",
1820 | "model_name": "LayoutModel",
1821 | "model_module_version": "1.2.0",
1822 | "state": {
1823 | "_model_module": "@jupyter-widgets/base",
1824 | "_model_module_version": "1.2.0",
1825 | "_model_name": "LayoutModel",
1826 | "_view_count": null,
1827 | "_view_module": "@jupyter-widgets/base",
1828 | "_view_module_version": "1.2.0",
1829 | "_view_name": "LayoutView",
1830 | "align_content": null,
1831 | "align_items": null,
1832 | "align_self": null,
1833 | "border": null,
1834 | "bottom": null,
1835 | "display": null,
1836 | "flex": null,
1837 | "flex_flow": null,
1838 | "grid_area": null,
1839 | "grid_auto_columns": null,
1840 | "grid_auto_flow": null,
1841 | "grid_auto_rows": null,
1842 | "grid_column": null,
1843 | "grid_gap": null,
1844 | "grid_row": null,
1845 | "grid_template_areas": null,
1846 | "grid_template_columns": null,
1847 | "grid_template_rows": null,
1848 | "height": null,
1849 | "justify_content": null,
1850 | "justify_items": null,
1851 | "left": null,
1852 | "margin": null,
1853 | "max_height": null,
1854 | "max_width": null,
1855 | "min_height": null,
1856 | "min_width": null,
1857 | "object_fit": null,
1858 | "object_position": null,
1859 | "order": null,
1860 | "overflow": null,
1861 | "overflow_x": null,
1862 | "overflow_y": null,
1863 | "padding": null,
1864 | "right": null,
1865 | "top": null,
1866 | "visibility": null,
1867 | "width": null
1868 | }
1869 | },
1870 | "a8c102ccd45a4bb9a0366fed028c9c89": {
1871 | "model_module": "@jupyter-widgets/base",
1872 | "model_name": "LayoutModel",
1873 | "model_module_version": "1.2.0",
1874 | "state": {
1875 | "_model_module": "@jupyter-widgets/base",
1876 | "_model_module_version": "1.2.0",
1877 | "_model_name": "LayoutModel",
1878 | "_view_count": null,
1879 | "_view_module": "@jupyter-widgets/base",
1880 | "_view_module_version": "1.2.0",
1881 | "_view_name": "LayoutView",
1882 | "align_content": null,
1883 | "align_items": null,
1884 | "align_self": null,
1885 | "border": null,
1886 | "bottom": null,
1887 | "display": null,
1888 | "flex": null,
1889 | "flex_flow": null,
1890 | "grid_area": null,
1891 | "grid_auto_columns": null,
1892 | "grid_auto_flow": null,
1893 | "grid_auto_rows": null,
1894 | "grid_column": null,
1895 | "grid_gap": null,
1896 | "grid_row": null,
1897 | "grid_template_areas": null,
1898 | "grid_template_columns": null,
1899 | "grid_template_rows": null,
1900 | "height": null,
1901 | "justify_content": null,
1902 | "justify_items": null,
1903 | "left": null,
1904 | "margin": null,
1905 | "max_height": null,
1906 | "max_width": null,
1907 | "min_height": null,
1908 | "min_width": null,
1909 | "object_fit": null,
1910 | "object_position": null,
1911 | "order": null,
1912 | "overflow": null,
1913 | "overflow_x": null,
1914 | "overflow_y": null,
1915 | "padding": null,
1916 | "right": null,
1917 | "top": null,
1918 | "visibility": null,
1919 | "width": null
1920 | }
1921 | },
1922 | "53be2c46b0634ace8157f69dddf502ed": {
1923 | "model_module": "@jupyter-widgets/controls",
1924 | "model_name": "DescriptionStyleModel",
1925 | "model_module_version": "1.5.0",
1926 | "state": {
1927 | "_model_module": "@jupyter-widgets/controls",
1928 | "_model_module_version": "1.5.0",
1929 | "_model_name": "DescriptionStyleModel",
1930 | "_view_count": null,
1931 | "_view_module": "@jupyter-widgets/base",
1932 | "_view_module_version": "1.2.0",
1933 | "_view_name": "StyleView",
1934 | "description_width": ""
1935 | }
1936 | },
1937 | "8aa38554efa847d6b23659bbe3a22fd5": {
1938 | "model_module": "@jupyter-widgets/base",
1939 | "model_name": "LayoutModel",
1940 | "model_module_version": "1.2.0",
1941 | "state": {
1942 | "_model_module": "@jupyter-widgets/base",
1943 | "_model_module_version": "1.2.0",
1944 | "_model_name": "LayoutModel",
1945 | "_view_count": null,
1946 | "_view_module": "@jupyter-widgets/base",
1947 | "_view_module_version": "1.2.0",
1948 | "_view_name": "LayoutView",
1949 | "align_content": null,
1950 | "align_items": null,
1951 | "align_self": null,
1952 | "border": null,
1953 | "bottom": null,
1954 | "display": null,
1955 | "flex": null,
1956 | "flex_flow": null,
1957 | "grid_area": null,
1958 | "grid_auto_columns": null,
1959 | "grid_auto_flow": null,
1960 | "grid_auto_rows": null,
1961 | "grid_column": null,
1962 | "grid_gap": null,
1963 | "grid_row": null,
1964 | "grid_template_areas": null,
1965 | "grid_template_columns": null,
1966 | "grid_template_rows": null,
1967 | "height": null,
1968 | "justify_content": null,
1969 | "justify_items": null,
1970 | "left": null,
1971 | "margin": null,
1972 | "max_height": null,
1973 | "max_width": null,
1974 | "min_height": null,
1975 | "min_width": null,
1976 | "object_fit": null,
1977 | "object_position": null,
1978 | "order": null,
1979 | "overflow": null,
1980 | "overflow_x": null,
1981 | "overflow_y": null,
1982 | "padding": null,
1983 | "right": null,
1984 | "top": null,
1985 | "visibility": null,
1986 | "width": null
1987 | }
1988 | },
1989 | "79ea0ca6be994c05a139b4b3b1d44e41": {
1990 | "model_module": "@jupyter-widgets/controls",
1991 | "model_name": "ProgressStyleModel",
1992 | "model_module_version": "1.5.0",
1993 | "state": {
1994 | "_model_module": "@jupyter-widgets/controls",
1995 | "_model_module_version": "1.5.0",
1996 | "_model_name": "ProgressStyleModel",
1997 | "_view_count": null,
1998 | "_view_module": "@jupyter-widgets/base",
1999 | "_view_module_version": "1.2.0",
2000 | "_view_name": "StyleView",
2001 | "bar_color": null,
2002 | "description_width": ""
2003 | }
2004 | },
2005 | "a23c7e7a5ac44f1c9fae6db6fb9a380c": {
2006 | "model_module": "@jupyter-widgets/base",
2007 | "model_name": "LayoutModel",
2008 | "model_module_version": "1.2.0",
2009 | "state": {
2010 | "_model_module": "@jupyter-widgets/base",
2011 | "_model_module_version": "1.2.0",
2012 | "_model_name": "LayoutModel",
2013 | "_view_count": null,
2014 | "_view_module": "@jupyter-widgets/base",
2015 | "_view_module_version": "1.2.0",
2016 | "_view_name": "LayoutView",
2017 | "align_content": null,
2018 | "align_items": null,
2019 | "align_self": null,
2020 | "border": null,
2021 | "bottom": null,
2022 | "display": null,
2023 | "flex": null,
2024 | "flex_flow": null,
2025 | "grid_area": null,
2026 | "grid_auto_columns": null,
2027 | "grid_auto_flow": null,
2028 | "grid_auto_rows": null,
2029 | "grid_column": null,
2030 | "grid_gap": null,
2031 | "grid_row": null,
2032 | "grid_template_areas": null,
2033 | "grid_template_columns": null,
2034 | "grid_template_rows": null,
2035 | "height": null,
2036 | "justify_content": null,
2037 | "justify_items": null,
2038 | "left": null,
2039 | "margin": null,
2040 | "max_height": null,
2041 | "max_width": null,
2042 | "min_height": null,
2043 | "min_width": null,
2044 | "object_fit": null,
2045 | "object_position": null,
2046 | "order": null,
2047 | "overflow": null,
2048 | "overflow_x": null,
2049 | "overflow_y": null,
2050 | "padding": null,
2051 | "right": null,
2052 | "top": null,
2053 | "visibility": null,
2054 | "width": null
2055 | }
2056 | },
2057 | "be5a493006c247c6b94a76bfa8cd7717": {
2058 | "model_module": "@jupyter-widgets/controls",
2059 | "model_name": "DescriptionStyleModel",
2060 | "model_module_version": "1.5.0",
2061 | "state": {
2062 | "_model_module": "@jupyter-widgets/controls",
2063 | "_model_module_version": "1.5.0",
2064 | "_model_name": "DescriptionStyleModel",
2065 | "_view_count": null,
2066 | "_view_module": "@jupyter-widgets/base",
2067 | "_view_module_version": "1.2.0",
2068 | "_view_name": "StyleView",
2069 | "description_width": ""
2070 | }
2071 | },
2072 | "8aa16db0c6804e789acc16ecda32fe5e": {
2073 | "model_module": "@jupyter-widgets/controls",
2074 | "model_name": "HBoxModel",
2075 | "model_module_version": "1.5.0",
2076 | "state": {
2077 | "_dom_classes": [],
2078 | "_model_module": "@jupyter-widgets/controls",
2079 | "_model_module_version": "1.5.0",
2080 | "_model_name": "HBoxModel",
2081 | "_view_count": null,
2082 | "_view_module": "@jupyter-widgets/controls",
2083 | "_view_module_version": "1.5.0",
2084 | "_view_name": "HBoxView",
2085 | "box_style": "",
2086 | "children": [
2087 | "IPY_MODEL_a898f936e23a4c8785e9de322f72c248",
2088 | "IPY_MODEL_5fc6d2a6dde041e0a128e8eb550d9b10",
2089 | "IPY_MODEL_5784196f1f3046b0b47370f2603c6f77"
2090 | ],
2091 | "layout": "IPY_MODEL_bdbd732073334dc0bde296c4fb3673c5"
2092 | }
2093 | },
2094 | "a898f936e23a4c8785e9de322f72c248": {
2095 | "model_module": "@jupyter-widgets/controls",
2096 | "model_name": "HTMLModel",
2097 | "model_module_version": "1.5.0",
2098 | "state": {
2099 | "_dom_classes": [],
2100 | "_model_module": "@jupyter-widgets/controls",
2101 | "_model_module_version": "1.5.0",
2102 | "_model_name": "HTMLModel",
2103 | "_view_count": null,
2104 | "_view_module": "@jupyter-widgets/controls",
2105 | "_view_module_version": "1.5.0",
2106 | "_view_name": "HTMLView",
2107 | "description": "",
2108 | "description_tooltip": null,
2109 | "layout": "IPY_MODEL_7c498217462d4c20bc892641e1437d4d",
2110 | "placeholder": "",
2111 | "style": "IPY_MODEL_735689422d2648d8941ca86b240f8fec",
2112 | "value": "config.json: 100%"
2113 | }
2114 | },
2115 | "5fc6d2a6dde041e0a128e8eb550d9b10": {
2116 | "model_module": "@jupyter-widgets/controls",
2117 | "model_name": "FloatProgressModel",
2118 | "model_module_version": "1.5.0",
2119 | "state": {
2120 | "_dom_classes": [],
2121 | "_model_module": "@jupyter-widgets/controls",
2122 | "_model_module_version": "1.5.0",
2123 | "_model_name": "FloatProgressModel",
2124 | "_view_count": null,
2125 | "_view_module": "@jupyter-widgets/controls",
2126 | "_view_module_version": "1.5.0",
2127 | "_view_name": "ProgressView",
2128 | "bar_style": "success",
2129 | "description": "",
2130 | "description_tooltip": null,
2131 | "layout": "IPY_MODEL_250afadc3f5b4effad629a23e08a18d7",
2132 | "max": 762,
2133 | "min": 0,
2134 | "orientation": "horizontal",
2135 | "style": "IPY_MODEL_d9bd3ade496c480697a94ff869e27be6",
2136 | "value": 762
2137 | }
2138 | },
2139 | "5784196f1f3046b0b47370f2603c6f77": {
2140 | "model_module": "@jupyter-widgets/controls",
2141 | "model_name": "HTMLModel",
2142 | "model_module_version": "1.5.0",
2143 | "state": {
2144 | "_dom_classes": [],
2145 | "_model_module": "@jupyter-widgets/controls",
2146 | "_model_module_version": "1.5.0",
2147 | "_model_name": "HTMLModel",
2148 | "_view_count": null,
2149 | "_view_module": "@jupyter-widgets/controls",
2150 | "_view_module_version": "1.5.0",
2151 | "_view_name": "HTMLView",
2152 | "description": "",
2153 | "description_tooltip": null,
2154 | "layout": "IPY_MODEL_1338c901f2d049c88a98d2ea31b3fe46",
2155 | "placeholder": "",
2156 | "style": "IPY_MODEL_4ef7ad4d6dde4af9876bb5fe43efa56a",
2157 | "value": " 762/762 [00:00<00:00, 63.3kB/s]"
2158 | }
2159 | },
2160 | "bdbd732073334dc0bde296c4fb3673c5": {
2161 | "model_module": "@jupyter-widgets/base",
2162 | "model_name": "LayoutModel",
2163 | "model_module_version": "1.2.0",
2164 | "state": {
2165 | "_model_module": "@jupyter-widgets/base",
2166 | "_model_module_version": "1.2.0",
2167 | "_model_name": "LayoutModel",
2168 | "_view_count": null,
2169 | "_view_module": "@jupyter-widgets/base",
2170 | "_view_module_version": "1.2.0",
2171 | "_view_name": "LayoutView",
2172 | "align_content": null,
2173 | "align_items": null,
2174 | "align_self": null,
2175 | "border": null,
2176 | "bottom": null,
2177 | "display": null,
2178 | "flex": null,
2179 | "flex_flow": null,
2180 | "grid_area": null,
2181 | "grid_auto_columns": null,
2182 | "grid_auto_flow": null,
2183 | "grid_auto_rows": null,
2184 | "grid_column": null,
2185 | "grid_gap": null,
2186 | "grid_row": null,
2187 | "grid_template_areas": null,
2188 | "grid_template_columns": null,
2189 | "grid_template_rows": null,
2190 | "height": null,
2191 | "justify_content": null,
2192 | "justify_items": null,
2193 | "left": null,
2194 | "margin": null,
2195 | "max_height": null,
2196 | "max_width": null,
2197 | "min_height": null,
2198 | "min_width": null,
2199 | "object_fit": null,
2200 | "object_position": null,
2201 | "order": null,
2202 | "overflow": null,
2203 | "overflow_x": null,
2204 | "overflow_y": null,
2205 | "padding": null,
2206 | "right": null,
2207 | "top": null,
2208 | "visibility": null,
2209 | "width": null
2210 | }
2211 | },
2212 | "7c498217462d4c20bc892641e1437d4d": {
2213 | "model_module": "@jupyter-widgets/base",
2214 | "model_name": "LayoutModel",
2215 | "model_module_version": "1.2.0",
2216 | "state": {
2217 | "_model_module": "@jupyter-widgets/base",
2218 | "_model_module_version": "1.2.0",
2219 | "_model_name": "LayoutModel",
2220 | "_view_count": null,
2221 | "_view_module": "@jupyter-widgets/base",
2222 | "_view_module_version": "1.2.0",
2223 | "_view_name": "LayoutView",
2224 | "align_content": null,
2225 | "align_items": null,
2226 | "align_self": null,
2227 | "border": null,
2228 | "bottom": null,
2229 | "display": null,
2230 | "flex": null,
2231 | "flex_flow": null,
2232 | "grid_area": null,
2233 | "grid_auto_columns": null,
2234 | "grid_auto_flow": null,
2235 | "grid_auto_rows": null,
2236 | "grid_column": null,
2237 | "grid_gap": null,
2238 | "grid_row": null,
2239 | "grid_template_areas": null,
2240 | "grid_template_columns": null,
2241 | "grid_template_rows": null,
2242 | "height": null,
2243 | "justify_content": null,
2244 | "justify_items": null,
2245 | "left": null,
2246 | "margin": null,
2247 | "max_height": null,
2248 | "max_width": null,
2249 | "min_height": null,
2250 | "min_width": null,
2251 | "object_fit": null,
2252 | "object_position": null,
2253 | "order": null,
2254 | "overflow": null,
2255 | "overflow_x": null,
2256 | "overflow_y": null,
2257 | "padding": null,
2258 | "right": null,
2259 | "top": null,
2260 | "visibility": null,
2261 | "width": null
2262 | }
2263 | },
2264 | "735689422d2648d8941ca86b240f8fec": {
2265 | "model_module": "@jupyter-widgets/controls",
2266 | "model_name": "DescriptionStyleModel",
2267 | "model_module_version": "1.5.0",
2268 | "state": {
2269 | "_model_module": "@jupyter-widgets/controls",
2270 | "_model_module_version": "1.5.0",
2271 | "_model_name": "DescriptionStyleModel",
2272 | "_view_count": null,
2273 | "_view_module": "@jupyter-widgets/base",
2274 | "_view_module_version": "1.2.0",
2275 | "_view_name": "StyleView",
2276 | "description_width": ""
2277 | }
2278 | },
2279 | "250afadc3f5b4effad629a23e08a18d7": {
2280 | "model_module": "@jupyter-widgets/base",
2281 | "model_name": "LayoutModel",
2282 | "model_module_version": "1.2.0",
2283 | "state": {
2284 | "_model_module": "@jupyter-widgets/base",
2285 | "_model_module_version": "1.2.0",
2286 | "_model_name": "LayoutModel",
2287 | "_view_count": null,
2288 | "_view_module": "@jupyter-widgets/base",
2289 | "_view_module_version": "1.2.0",
2290 | "_view_name": "LayoutView",
2291 | "align_content": null,
2292 | "align_items": null,
2293 | "align_self": null,
2294 | "border": null,
2295 | "bottom": null,
2296 | "display": null,
2297 | "flex": null,
2298 | "flex_flow": null,
2299 | "grid_area": null,
2300 | "grid_auto_columns": null,
2301 | "grid_auto_flow": null,
2302 | "grid_auto_rows": null,
2303 | "grid_column": null,
2304 | "grid_gap": null,
2305 | "grid_row": null,
2306 | "grid_template_areas": null,
2307 | "grid_template_columns": null,
2308 | "grid_template_rows": null,
2309 | "height": null,
2310 | "justify_content": null,
2311 | "justify_items": null,
2312 | "left": null,
2313 | "margin": null,
2314 | "max_height": null,
2315 | "max_width": null,
2316 | "min_height": null,
2317 | "min_width": null,
2318 | "object_fit": null,
2319 | "object_position": null,
2320 | "order": null,
2321 | "overflow": null,
2322 | "overflow_x": null,
2323 | "overflow_y": null,
2324 | "padding": null,
2325 | "right": null,
2326 | "top": null,
2327 | "visibility": null,
2328 | "width": null
2329 | }
2330 | },
2331 | "d9bd3ade496c480697a94ff869e27be6": {
2332 | "model_module": "@jupyter-widgets/controls",
2333 | "model_name": "ProgressStyleModel",
2334 | "model_module_version": "1.5.0",
2335 | "state": {
2336 | "_model_module": "@jupyter-widgets/controls",
2337 | "_model_module_version": "1.5.0",
2338 | "_model_name": "ProgressStyleModel",
2339 | "_view_count": null,
2340 | "_view_module": "@jupyter-widgets/base",
2341 | "_view_module_version": "1.2.0",
2342 | "_view_name": "StyleView",
2343 | "bar_color": null,
2344 | "description_width": ""
2345 | }
2346 | },
2347 | "1338c901f2d049c88a98d2ea31b3fe46": {
2348 | "model_module": "@jupyter-widgets/base",
2349 | "model_name": "LayoutModel",
2350 | "model_module_version": "1.2.0",
2351 | "state": {
2352 | "_model_module": "@jupyter-widgets/base",
2353 | "_model_module_version": "1.2.0",
2354 | "_model_name": "LayoutModel",
2355 | "_view_count": null,
2356 | "_view_module": "@jupyter-widgets/base",
2357 | "_view_module_version": "1.2.0",
2358 | "_view_name": "LayoutView",
2359 | "align_content": null,
2360 | "align_items": null,
2361 | "align_self": null,
2362 | "border": null,
2363 | "bottom": null,
2364 | "display": null,
2365 | "flex": null,
2366 | "flex_flow": null,
2367 | "grid_area": null,
2368 | "grid_auto_columns": null,
2369 | "grid_auto_flow": null,
2370 | "grid_auto_rows": null,
2371 | "grid_column": null,
2372 | "grid_gap": null,
2373 | "grid_row": null,
2374 | "grid_template_areas": null,
2375 | "grid_template_columns": null,
2376 | "grid_template_rows": null,
2377 | "height": null,
2378 | "justify_content": null,
2379 | "justify_items": null,
2380 | "left": null,
2381 | "margin": null,
2382 | "max_height": null,
2383 | "max_width": null,
2384 | "min_height": null,
2385 | "min_width": null,
2386 | "object_fit": null,
2387 | "object_position": null,
2388 | "order": null,
2389 | "overflow": null,
2390 | "overflow_x": null,
2391 | "overflow_y": null,
2392 | "padding": null,
2393 | "right": null,
2394 | "top": null,
2395 | "visibility": null,
2396 | "width": null
2397 | }
2398 | },
2399 | "4ef7ad4d6dde4af9876bb5fe43efa56a": {
2400 | "model_module": "@jupyter-widgets/controls",
2401 | "model_name": "DescriptionStyleModel",
2402 | "model_module_version": "1.5.0",
2403 | "state": {
2404 | "_model_module": "@jupyter-widgets/controls",
2405 | "_model_module_version": "1.5.0",
2406 | "_model_name": "DescriptionStyleModel",
2407 | "_view_count": null,
2408 | "_view_module": "@jupyter-widgets/base",
2409 | "_view_module_version": "1.2.0",
2410 | "_view_name": "StyleView",
2411 | "description_width": ""
2412 | }
2413 | },
2414 | "53e702e5171c40b7b257df00043bd869": {
2415 | "model_module": "@jupyter-widgets/controls",
2416 | "model_name": "HBoxModel",
2417 | "model_module_version": "1.5.0",
2418 | "state": {
2419 | "_dom_classes": [],
2420 | "_model_module": "@jupyter-widgets/controls",
2421 | "_model_module_version": "1.5.0",
2422 | "_model_name": "HBoxModel",
2423 | "_view_count": null,
2424 | "_view_module": "@jupyter-widgets/controls",
2425 | "_view_module_version": "1.5.0",
2426 | "_view_name": "HBoxView",
2427 | "box_style": "",
2428 | "children": [
2429 | "IPY_MODEL_e0e15cb7f0b94a4ab4553b398fa345bd",
2430 | "IPY_MODEL_8972d3a55d1f43ddbad6d4a2543598f6",
2431 | "IPY_MODEL_1434fedfd0c349f5925292e4d7df1b03"
2432 | ],
2433 | "layout": "IPY_MODEL_447946a3f9ca45c6874540d292ed27c3"
2434 | }
2435 | },
2436 | "e0e15cb7f0b94a4ab4553b398fa345bd": {
2437 | "model_module": "@jupyter-widgets/controls",
2438 | "model_name": "HTMLModel",
2439 | "model_module_version": "1.5.0",
2440 | "state": {
2441 | "_dom_classes": [],
2442 | "_model_module": "@jupyter-widgets/controls",
2443 | "_model_module_version": "1.5.0",
2444 | "_model_name": "HTMLModel",
2445 | "_view_count": null,
2446 | "_view_module": "@jupyter-widgets/controls",
2447 | "_view_module_version": "1.5.0",
2448 | "_view_name": "HTMLView",
2449 | "description": "",
2450 | "description_tooltip": null,
2451 | "layout": "IPY_MODEL_46945285c25749079dcb3945fef79f23",
2452 | "placeholder": "",
2453 | "style": "IPY_MODEL_07b35023dc9f46168345187a02aabf46",
2454 | "value": "model.safetensors: 100%"
2455 | }
2456 | },
2457 | "8972d3a55d1f43ddbad6d4a2543598f6": {
2458 | "model_module": "@jupyter-widgets/controls",
2459 | "model_name": "FloatProgressModel",
2460 | "model_module_version": "1.5.0",
2461 | "state": {
2462 | "_dom_classes": [],
2463 | "_model_module": "@jupyter-widgets/controls",
2464 | "_model_module_version": "1.5.0",
2465 | "_model_name": "FloatProgressModel",
2466 | "_view_count": null,
2467 | "_view_module": "@jupyter-widgets/controls",
2468 | "_view_module_version": "1.5.0",
2469 | "_view_name": "ProgressView",
2470 | "bar_style": "success",
2471 | "description": "",
2472 | "description_tooltip": null,
2473 | "layout": "IPY_MODEL_97fabf4a49954879bd24d482a8b7088b",
2474 | "max": 352824413,
2475 | "min": 0,
2476 | "orientation": "horizontal",
2477 | "style": "IPY_MODEL_5c08a4c88c7a4873bbcd1e2bfc53ec83",
2478 | "value": 352824413
2479 | }
2480 | },
2481 | "1434fedfd0c349f5925292e4d7df1b03": {
2482 | "model_module": "@jupyter-widgets/controls",
2483 | "model_name": "HTMLModel",
2484 | "model_module_version": "1.5.0",
2485 | "state": {
2486 | "_dom_classes": [],
2487 | "_model_module": "@jupyter-widgets/controls",
2488 | "_model_module_version": "1.5.0",
2489 | "_model_name": "HTMLModel",
2490 | "_view_count": null,
2491 | "_view_module": "@jupyter-widgets/controls",
2492 | "_view_module_version": "1.5.0",
2493 | "_view_name": "HTMLView",
2494 | "description": "",
2495 | "description_tooltip": null,
2496 | "layout": "IPY_MODEL_f7e099183e73426ea945ddee509106ce",
2497 | "placeholder": "",
2498 | "style": "IPY_MODEL_24c1fecb5f244f3ea91cc67a8942e9e7",
2499 | "value": " 353M/353M [00:01<00:00, 236MB/s]"
2500 | }
2501 | },
2502 | "447946a3f9ca45c6874540d292ed27c3": {
2503 | "model_module": "@jupyter-widgets/base",
2504 | "model_name": "LayoutModel",
2505 | "model_module_version": "1.2.0",
2506 | "state": {
2507 | "_model_module": "@jupyter-widgets/base",
2508 | "_model_module_version": "1.2.0",
2509 | "_model_name": "LayoutModel",
2510 | "_view_count": null,
2511 | "_view_module": "@jupyter-widgets/base",
2512 | "_view_module_version": "1.2.0",
2513 | "_view_name": "LayoutView",
2514 | "align_content": null,
2515 | "align_items": null,
2516 | "align_self": null,
2517 | "border": null,
2518 | "bottom": null,
2519 | "display": null,
2520 | "flex": null,
2521 | "flex_flow": null,
2522 | "grid_area": null,
2523 | "grid_auto_columns": null,
2524 | "grid_auto_flow": null,
2525 | "grid_auto_rows": null,
2526 | "grid_column": null,
2527 | "grid_gap": null,
2528 | "grid_row": null,
2529 | "grid_template_areas": null,
2530 | "grid_template_columns": null,
2531 | "grid_template_rows": null,
2532 | "height": null,
2533 | "justify_content": null,
2534 | "justify_items": null,
2535 | "left": null,
2536 | "margin": null,
2537 | "max_height": null,
2538 | "max_width": null,
2539 | "min_height": null,
2540 | "min_width": null,
2541 | "object_fit": null,
2542 | "object_position": null,
2543 | "order": null,
2544 | "overflow": null,
2545 | "overflow_x": null,
2546 | "overflow_y": null,
2547 | "padding": null,
2548 | "right": null,
2549 | "top": null,
2550 | "visibility": null,
2551 | "width": null
2552 | }
2553 | },
2554 | "46945285c25749079dcb3945fef79f23": {
2555 | "model_module": "@jupyter-widgets/base",
2556 | "model_name": "LayoutModel",
2557 | "model_module_version": "1.2.0",
2558 | "state": {
2559 | "_model_module": "@jupyter-widgets/base",
2560 | "_model_module_version": "1.2.0",
2561 | "_model_name": "LayoutModel",
2562 | "_view_count": null,
2563 | "_view_module": "@jupyter-widgets/base",
2564 | "_view_module_version": "1.2.0",
2565 | "_view_name": "LayoutView",
2566 | "align_content": null,
2567 | "align_items": null,
2568 | "align_self": null,
2569 | "border": null,
2570 | "bottom": null,
2571 | "display": null,
2572 | "flex": null,
2573 | "flex_flow": null,
2574 | "grid_area": null,
2575 | "grid_auto_columns": null,
2576 | "grid_auto_flow": null,
2577 | "grid_auto_rows": null,
2578 | "grid_column": null,
2579 | "grid_gap": null,
2580 | "grid_row": null,
2581 | "grid_template_areas": null,
2582 | "grid_template_columns": null,
2583 | "grid_template_rows": null,
2584 | "height": null,
2585 | "justify_content": null,
2586 | "justify_items": null,
2587 | "left": null,
2588 | "margin": null,
2589 | "max_height": null,
2590 | "max_width": null,
2591 | "min_height": null,
2592 | "min_width": null,
2593 | "object_fit": null,
2594 | "object_position": null,
2595 | "order": null,
2596 | "overflow": null,
2597 | "overflow_x": null,
2598 | "overflow_y": null,
2599 | "padding": null,
2600 | "right": null,
2601 | "top": null,
2602 | "visibility": null,
2603 | "width": null
2604 | }
2605 | },
2606 | "07b35023dc9f46168345187a02aabf46": {
2607 | "model_module": "@jupyter-widgets/controls",
2608 | "model_name": "DescriptionStyleModel",
2609 | "model_module_version": "1.5.0",
2610 | "state": {
2611 | "_model_module": "@jupyter-widgets/controls",
2612 | "_model_module_version": "1.5.0",
2613 | "_model_name": "DescriptionStyleModel",
2614 | "_view_count": null,
2615 | "_view_module": "@jupyter-widgets/base",
2616 | "_view_module_version": "1.2.0",
2617 | "_view_name": "StyleView",
2618 | "description_width": ""
2619 | }
2620 | },
2621 | "97fabf4a49954879bd24d482a8b7088b": {
2622 | "model_module": "@jupyter-widgets/base",
2623 | "model_name": "LayoutModel",
2624 | "model_module_version": "1.2.0",
2625 | "state": {
2626 | "_model_module": "@jupyter-widgets/base",
2627 | "_model_module_version": "1.2.0",
2628 | "_model_name": "LayoutModel",
2629 | "_view_count": null,
2630 | "_view_module": "@jupyter-widgets/base",
2631 | "_view_module_version": "1.2.0",
2632 | "_view_name": "LayoutView",
2633 | "align_content": null,
2634 | "align_items": null,
2635 | "align_self": null,
2636 | "border": null,
2637 | "bottom": null,
2638 | "display": null,
2639 | "flex": null,
2640 | "flex_flow": null,
2641 | "grid_area": null,
2642 | "grid_auto_columns": null,
2643 | "grid_auto_flow": null,
2644 | "grid_auto_rows": null,
2645 | "grid_column": null,
2646 | "grid_gap": null,
2647 | "grid_row": null,
2648 | "grid_template_areas": null,
2649 | "grid_template_columns": null,
2650 | "grid_template_rows": null,
2651 | "height": null,
2652 | "justify_content": null,
2653 | "justify_items": null,
2654 | "left": null,
2655 | "margin": null,
2656 | "max_height": null,
2657 | "max_width": null,
2658 | "min_height": null,
2659 | "min_width": null,
2660 | "object_fit": null,
2661 | "object_position": null,
2662 | "order": null,
2663 | "overflow": null,
2664 | "overflow_x": null,
2665 | "overflow_y": null,
2666 | "padding": null,
2667 | "right": null,
2668 | "top": null,
2669 | "visibility": null,
2670 | "width": null
2671 | }
2672 | },
2673 | "5c08a4c88c7a4873bbcd1e2bfc53ec83": {
2674 | "model_module": "@jupyter-widgets/controls",
2675 | "model_name": "ProgressStyleModel",
2676 | "model_module_version": "1.5.0",
2677 | "state": {
2678 | "_model_module": "@jupyter-widgets/controls",
2679 | "_model_module_version": "1.5.0",
2680 | "_model_name": "ProgressStyleModel",
2681 | "_view_count": null,
2682 | "_view_module": "@jupyter-widgets/base",
2683 | "_view_module_version": "1.2.0",
2684 | "_view_name": "StyleView",
2685 | "bar_color": null,
2686 | "description_width": ""
2687 | }
2688 | },
2689 | "f7e099183e73426ea945ddee509106ce": {
2690 | "model_module": "@jupyter-widgets/base",
2691 | "model_name": "LayoutModel",
2692 | "model_module_version": "1.2.0",
2693 | "state": {
2694 | "_model_module": "@jupyter-widgets/base",
2695 | "_model_module_version": "1.2.0",
2696 | "_model_name": "LayoutModel",
2697 | "_view_count": null,
2698 | "_view_module": "@jupyter-widgets/base",
2699 | "_view_module_version": "1.2.0",
2700 | "_view_name": "LayoutView",
2701 | "align_content": null,
2702 | "align_items": null,
2703 | "align_self": null,
2704 | "border": null,
2705 | "bottom": null,
2706 | "display": null,
2707 | "flex": null,
2708 | "flex_flow": null,
2709 | "grid_area": null,
2710 | "grid_auto_columns": null,
2711 | "grid_auto_flow": null,
2712 | "grid_auto_rows": null,
2713 | "grid_column": null,
2714 | "grid_gap": null,
2715 | "grid_row": null,
2716 | "grid_template_areas": null,
2717 | "grid_template_columns": null,
2718 | "grid_template_rows": null,
2719 | "height": null,
2720 | "justify_content": null,
2721 | "justify_items": null,
2722 | "left": null,
2723 | "margin": null,
2724 | "max_height": null,
2725 | "max_width": null,
2726 | "min_height": null,
2727 | "min_width": null,
2728 | "object_fit": null,
2729 | "object_position": null,
2730 | "order": null,
2731 | "overflow": null,
2732 | "overflow_x": null,
2733 | "overflow_y": null,
2734 | "padding": null,
2735 | "right": null,
2736 | "top": null,
2737 | "visibility": null,
2738 | "width": null
2739 | }
2740 | },
2741 | "24c1fecb5f244f3ea91cc67a8942e9e7": {
2742 | "model_module": "@jupyter-widgets/controls",
2743 | "model_name": "DescriptionStyleModel",
2744 | "model_module_version": "1.5.0",
2745 | "state": {
2746 | "_model_module": "@jupyter-widgets/controls",
2747 | "_model_module_version": "1.5.0",
2748 | "_model_name": "DescriptionStyleModel",
2749 | "_view_count": null,
2750 | "_view_module": "@jupyter-widgets/base",
2751 | "_view_module_version": "1.2.0",
2752 | "_view_name": "StyleView",
2753 | "description_width": ""
2754 | }
2755 | },
2756 | "9ed7a6cf110c4d559166c1174e635aef": {
2757 | "model_module": "@jupyter-widgets/controls",
2758 | "model_name": "HBoxModel",
2759 | "model_module_version": "1.5.0",
2760 | "state": {
2761 | "_dom_classes": [],
2762 | "_model_module": "@jupyter-widgets/controls",
2763 | "_model_module_version": "1.5.0",
2764 | "_model_name": "HBoxModel",
2765 | "_view_count": null,
2766 | "_view_module": "@jupyter-widgets/controls",
2767 | "_view_module_version": "1.5.0",
2768 | "_view_name": "HBoxView",
2769 | "box_style": "",
2770 | "children": [
2771 | "IPY_MODEL_74b378012a2e46268df9de6eee525a39",
2772 | "IPY_MODEL_379423052eed4c03a9f73f6f93a5563a",
2773 | "IPY_MODEL_a84ffe146af54101b04048a700012ac5"
2774 | ],
2775 | "layout": "IPY_MODEL_b5ed1581833f4cd18df6b618ee6dcb6d"
2776 | }
2777 | },
2778 | "74b378012a2e46268df9de6eee525a39": {
2779 | "model_module": "@jupyter-widgets/controls",
2780 | "model_name": "HTMLModel",
2781 | "model_module_version": "1.5.0",
2782 | "state": {
2783 | "_dom_classes": [],
2784 | "_model_module": "@jupyter-widgets/controls",
2785 | "_model_module_version": "1.5.0",
2786 | "_model_name": "HTMLModel",
2787 | "_view_count": null,
2788 | "_view_module": "@jupyter-widgets/controls",
2789 | "_view_module_version": "1.5.0",
2790 | "_view_name": "HTMLView",
2791 | "description": "",
2792 | "description_tooltip": null,
2793 | "layout": "IPY_MODEL_57dd8a572c6b4098a932d09d3f6887a1",
2794 | "placeholder": "",
2795 | "style": "IPY_MODEL_8777bc937048458f9f2c5bcdc229be0d",
2796 | "value": "generation_config.json: 100%"
2797 | }
2798 | },
2799 | "379423052eed4c03a9f73f6f93a5563a": {
2800 | "model_module": "@jupyter-widgets/controls",
2801 | "model_name": "FloatProgressModel",
2802 | "model_module_version": "1.5.0",
2803 | "state": {
2804 | "_dom_classes": [],
2805 | "_model_module": "@jupyter-widgets/controls",
2806 | "_model_module_version": "1.5.0",
2807 | "_model_name": "FloatProgressModel",
2808 | "_view_count": null,
2809 | "_view_module": "@jupyter-widgets/controls",
2810 | "_view_module_version": "1.5.0",
2811 | "_view_name": "ProgressView",
2812 | "bar_style": "success",
2813 | "description": "",
2814 | "description_tooltip": null,
2815 | "layout": "IPY_MODEL_64bb5ff3353d439b8ad3044832f8ad0e",
2816 | "max": 124,
2817 | "min": 0,
2818 | "orientation": "horizontal",
2819 | "style": "IPY_MODEL_fedf4812a5a2401080ca6ac779172cee",
2820 | "value": 124
2821 | }
2822 | },
2823 | "a84ffe146af54101b04048a700012ac5": {
2824 | "model_module": "@jupyter-widgets/controls",
2825 | "model_name": "HTMLModel",
2826 | "model_module_version": "1.5.0",
2827 | "state": {
2828 | "_dom_classes": [],
2829 | "_model_module": "@jupyter-widgets/controls",
2830 | "_model_module_version": "1.5.0",
2831 | "_model_name": "HTMLModel",
2832 | "_view_count": null,
2833 | "_view_module": "@jupyter-widgets/controls",
2834 | "_view_module_version": "1.5.0",
2835 | "_view_name": "HTMLView",
2836 | "description": "",
2837 | "description_tooltip": null,
2838 | "layout": "IPY_MODEL_229b7b51aa904bd895a95b212b6a610e",
2839 | "placeholder": "",
2840 | "style": "IPY_MODEL_66168d105bd340f7af008e996f5e24ae",
2841 | "value": " 124/124 [00:00<00:00, 7.34kB/s]"
2842 | }
2843 | },
2844 | "b5ed1581833f4cd18df6b618ee6dcb6d": {
2845 | "model_module": "@jupyter-widgets/base",
2846 | "model_name": "LayoutModel",
2847 | "model_module_version": "1.2.0",
2848 | "state": {
2849 | "_model_module": "@jupyter-widgets/base",
2850 | "_model_module_version": "1.2.0",
2851 | "_model_name": "LayoutModel",
2852 | "_view_count": null,
2853 | "_view_module": "@jupyter-widgets/base",
2854 | "_view_module_version": "1.2.0",
2855 | "_view_name": "LayoutView",
2856 | "align_content": null,
2857 | "align_items": null,
2858 | "align_self": null,
2859 | "border": null,
2860 | "bottom": null,
2861 | "display": null,
2862 | "flex": null,
2863 | "flex_flow": null,
2864 | "grid_area": null,
2865 | "grid_auto_columns": null,
2866 | "grid_auto_flow": null,
2867 | "grid_auto_rows": null,
2868 | "grid_column": null,
2869 | "grid_gap": null,
2870 | "grid_row": null,
2871 | "grid_template_areas": null,
2872 | "grid_template_columns": null,
2873 | "grid_template_rows": null,
2874 | "height": null,
2875 | "justify_content": null,
2876 | "justify_items": null,
2877 | "left": null,
2878 | "margin": null,
2879 | "max_height": null,
2880 | "max_width": null,
2881 | "min_height": null,
2882 | "min_width": null,
2883 | "object_fit": null,
2884 | "object_position": null,
2885 | "order": null,
2886 | "overflow": null,
2887 | "overflow_x": null,
2888 | "overflow_y": null,
2889 | "padding": null,
2890 | "right": null,
2891 | "top": null,
2892 | "visibility": null,
2893 | "width": null
2894 | }
2895 | },
2896 | "57dd8a572c6b4098a932d09d3f6887a1": {
2897 | "model_module": "@jupyter-widgets/base",
2898 | "model_name": "LayoutModel",
2899 | "model_module_version": "1.2.0",
2900 | "state": {
2901 | "_model_module": "@jupyter-widgets/base",
2902 | "_model_module_version": "1.2.0",
2903 | "_model_name": "LayoutModel",
2904 | "_view_count": null,
2905 | "_view_module": "@jupyter-widgets/base",
2906 | "_view_module_version": "1.2.0",
2907 | "_view_name": "LayoutView",
2908 | "align_content": null,
2909 | "align_items": null,
2910 | "align_self": null,
2911 | "border": null,
2912 | "bottom": null,
2913 | "display": null,
2914 | "flex": null,
2915 | "flex_flow": null,
2916 | "grid_area": null,
2917 | "grid_auto_columns": null,
2918 | "grid_auto_flow": null,
2919 | "grid_auto_rows": null,
2920 | "grid_column": null,
2921 | "grid_gap": null,
2922 | "grid_row": null,
2923 | "grid_template_areas": null,
2924 | "grid_template_columns": null,
2925 | "grid_template_rows": null,
2926 | "height": null,
2927 | "justify_content": null,
2928 | "justify_items": null,
2929 | "left": null,
2930 | "margin": null,
2931 | "max_height": null,
2932 | "max_width": null,
2933 | "min_height": null,
2934 | "min_width": null,
2935 | "object_fit": null,
2936 | "object_position": null,
2937 | "order": null,
2938 | "overflow": null,
2939 | "overflow_x": null,
2940 | "overflow_y": null,
2941 | "padding": null,
2942 | "right": null,
2943 | "top": null,
2944 | "visibility": null,
2945 | "width": null
2946 | }
2947 | },
2948 | "8777bc937048458f9f2c5bcdc229be0d": {
2949 | "model_module": "@jupyter-widgets/controls",
2950 | "model_name": "DescriptionStyleModel",
2951 | "model_module_version": "1.5.0",
2952 | "state": {
2953 | "_model_module": "@jupyter-widgets/controls",
2954 | "_model_module_version": "1.5.0",
2955 | "_model_name": "DescriptionStyleModel",
2956 | "_view_count": null,
2957 | "_view_module": "@jupyter-widgets/base",
2958 | "_view_module_version": "1.2.0",
2959 | "_view_name": "StyleView",
2960 | "description_width": ""
2961 | }
2962 | },
2963 | "64bb5ff3353d439b8ad3044832f8ad0e": {
2964 | "model_module": "@jupyter-widgets/base",
2965 | "model_name": "LayoutModel",
2966 | "model_module_version": "1.2.0",
2967 | "state": {
2968 | "_model_module": "@jupyter-widgets/base",
2969 | "_model_module_version": "1.2.0",
2970 | "_model_name": "LayoutModel",
2971 | "_view_count": null,
2972 | "_view_module": "@jupyter-widgets/base",
2973 | "_view_module_version": "1.2.0",
2974 | "_view_name": "LayoutView",
2975 | "align_content": null,
2976 | "align_items": null,
2977 | "align_self": null,
2978 | "border": null,
2979 | "bottom": null,
2980 | "display": null,
2981 | "flex": null,
2982 | "flex_flow": null,
2983 | "grid_area": null,
2984 | "grid_auto_columns": null,
2985 | "grid_auto_flow": null,
2986 | "grid_auto_rows": null,
2987 | "grid_column": null,
2988 | "grid_gap": null,
2989 | "grid_row": null,
2990 | "grid_template_areas": null,
2991 | "grid_template_columns": null,
2992 | "grid_template_rows": null,
2993 | "height": null,
2994 | "justify_content": null,
2995 | "justify_items": null,
2996 | "left": null,
2997 | "margin": null,
2998 | "max_height": null,
2999 | "max_width": null,
3000 | "min_height": null,
3001 | "min_width": null,
3002 | "object_fit": null,
3003 | "object_position": null,
3004 | "order": null,
3005 | "overflow": null,
3006 | "overflow_x": null,
3007 | "overflow_y": null,
3008 | "padding": null,
3009 | "right": null,
3010 | "top": null,
3011 | "visibility": null,
3012 | "width": null
3013 | }
3014 | },
3015 | "fedf4812a5a2401080ca6ac779172cee": {
3016 | "model_module": "@jupyter-widgets/controls",
3017 | "model_name": "ProgressStyleModel",
3018 | "model_module_version": "1.5.0",
3019 | "state": {
3020 | "_model_module": "@jupyter-widgets/controls",
3021 | "_model_module_version": "1.5.0",
3022 | "_model_name": "ProgressStyleModel",
3023 | "_view_count": null,
3024 | "_view_module": "@jupyter-widgets/base",
3025 | "_view_module_version": "1.2.0",
3026 | "_view_name": "StyleView",
3027 | "bar_color": null,
3028 | "description_width": ""
3029 | }
3030 | },
3031 | "229b7b51aa904bd895a95b212b6a610e": {
3032 | "model_module": "@jupyter-widgets/base",
3033 | "model_name": "LayoutModel",
3034 | "model_module_version": "1.2.0",
3035 | "state": {
3036 | "_model_module": "@jupyter-widgets/base",
3037 | "_model_module_version": "1.2.0",
3038 | "_model_name": "LayoutModel",
3039 | "_view_count": null,
3040 | "_view_module": "@jupyter-widgets/base",
3041 | "_view_module_version": "1.2.0",
3042 | "_view_name": "LayoutView",
3043 | "align_content": null,
3044 | "align_items": null,
3045 | "align_self": null,
3046 | "border": null,
3047 | "bottom": null,
3048 | "display": null,
3049 | "flex": null,
3050 | "flex_flow": null,
3051 | "grid_area": null,
3052 | "grid_auto_columns": null,
3053 | "grid_auto_flow": null,
3054 | "grid_auto_rows": null,
3055 | "grid_column": null,
3056 | "grid_gap": null,
3057 | "grid_row": null,
3058 | "grid_template_areas": null,
3059 | "grid_template_columns": null,
3060 | "grid_template_rows": null,
3061 | "height": null,
3062 | "justify_content": null,
3063 | "justify_items": null,
3064 | "left": null,
3065 | "margin": null,
3066 | "max_height": null,
3067 | "max_width": null,
3068 | "min_height": null,
3069 | "min_width": null,
3070 | "object_fit": null,
3071 | "object_position": null,
3072 | "order": null,
3073 | "overflow": null,
3074 | "overflow_x": null,
3075 | "overflow_y": null,
3076 | "padding": null,
3077 | "right": null,
3078 | "top": null,
3079 | "visibility": null,
3080 | "width": null
3081 | }
3082 | },
3083 | "66168d105bd340f7af008e996f5e24ae": {
3084 | "model_module": "@jupyter-widgets/controls",
3085 | "model_name": "DescriptionStyleModel",
3086 | "model_module_version": "1.5.0",
3087 | "state": {
3088 | "_model_module": "@jupyter-widgets/controls",
3089 | "_model_module_version": "1.5.0",
3090 | "_model_name": "DescriptionStyleModel",
3091 | "_view_count": null,
3092 | "_view_module": "@jupyter-widgets/base",
3093 | "_view_module_version": "1.2.0",
3094 | "_view_name": "StyleView",
3095 | "description_width": ""
3096 | }
3097 | }
3098 | }
3099 | }
3100 | },
3101 | "cells": [
3102 | {
3103 | "cell_type": "code",
3104 | "execution_count": null,
3105 | "metadata": {
3106 | "colab": {
3107 | "base_uri": "https://localhost:8080/"
3108 | },
3109 | "id": "Jrl-l6buT6bT",
3110 | "outputId": "272f22ad-bff3-43b9-da32-4f9302ba2c56"
3111 | },
3112 | "outputs": [
3113 | {
3114 | "output_type": "stream",
3115 | "name": "stdout",
3116 | "text": [
3117 | "Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (2.1.0+cu121)\n",
3118 | "Requirement already satisfied: torchtext in /usr/local/lib/python3.10/dist-packages (0.16.0)\n",
3119 | "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.35.2)\n",
3120 | "Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (0.1.99)\n",
3121 | "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (1.5.3)\n",
3122 | "Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (4.66.1)\n",
3123 | "Collecting datasets\n",
3124 | " Downloading datasets-2.16.0-py3-none-any.whl (507 kB)\n",
3125 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m507.1/507.1 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
3126 | "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch) (3.13.1)\n",
3127 | "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch) (4.5.0)\n",
3128 | "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch) (1.12)\n",
3129 | "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch) (3.2.1)\n",
3130 | "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch) (3.1.2)\n",
3131 | "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch) (2023.6.0)\n",
3132 | "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch) (2.1.0)\n",
3133 | "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from torchtext) (2.31.0)\n",
3134 | "Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from torchtext) (1.23.5)\n",
3135 | "Requirement already satisfied: torchdata==0.7.0 in /usr/local/lib/python3.10/dist-packages (from torchtext) (0.7.0)\n",
3136 | "Requirement already satisfied: urllib3>=1.25 in /usr/local/lib/python3.10/dist-packages (from torchdata==0.7.0->torchtext) (2.0.7)\n",
3137 | "Requirement already satisfied: huggingface-hub<1.0,>=0.16.4 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.19.4)\n",
3138 | "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (23.2)\n",
3139 | "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n",
3140 | "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.6.3)\n",
3141 | "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.0)\n",
3142 | "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.1)\n",
3143 | "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2.8.2)\n",
3144 | "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2023.3.post1)\n",
3145 | "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (10.0.1)\n",
3146 | "Collecting pyarrow-hotfix (from datasets)\n",
3147 | " Downloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n",
3148 | "Collecting dill<0.3.8,>=0.3.0 (from datasets)\n",
3149 | " Downloading dill-0.3.7-py3-none-any.whl (115 kB)\n",
3150 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m15.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
3151 | "\u001b[?25hRequirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets) (3.4.1)\n",
3152 | "Collecting multiprocess (from datasets)\n",
3153 | " Downloading multiprocess-0.70.15-py310-none-any.whl (134 kB)\n",
3154 | "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m17.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
3155 | "\u001b[?25hRequirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.1)\n",
3156 | "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.1.0)\n",
3157 | "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.4)\n",
3158 | "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n",
3159 | "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n",
3160 | "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n",
3161 | "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n",
3162 | "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas) (1.16.0)\n",
3163 | "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->torchtext) (3.3.2)\n",
3164 | "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->torchtext) (3.6)\n",
3165 | "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->torchtext) (2023.11.17)\n",
3166 | "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch) (2.1.3)\n",
3167 | "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch) (1.3.0)\n",
3168 | "Installing collected packages: pyarrow-hotfix, dill, multiprocess, datasets\n",
3169 | "Successfully installed datasets-2.16.0 dill-0.3.7 multiprocess-0.70.15 pyarrow-hotfix-0.6\n"
3170 | ]
3171 | }
3172 | ],
3173 | "source": [
3174 | "!pip install torch torchtext transformers sentencepiece pandas tqdm datasets"
3175 | ]
3176 | },
3177 | {
3178 | "cell_type": "code",
3179 | "source": [
3180 | "from datasets import load_dataset, DatasetDict, Dataset\n",
3181 | "import pandas as pd\n",
3182 | "import ast\n",
3183 | "import datasets\n",
3184 | "from tqdm import tqdm\n",
3185 | "import time"
3186 | ],
3187 | "metadata": {
3188 | "id": "veBWZ4_6ZzNF"
3189 | },
3190 | "execution_count": null,
3191 | "outputs": []
3192 | },
3193 | {
3194 | "cell_type": "code",
3195 | "source": [
3196 | "# Load data set from huggingface\n",
3197 | "data_sample = load_dataset(\"QuyenAnhDE/Diseases_Symptoms\")"
3198 | ],
3199 | "metadata": {
3200 | "colab": {
3201 | "base_uri": "https://localhost:8080/",
3202 | "height": 168,
3203 | "referenced_widgets": [
3204 | "909582d0b6014056b113ef9a0a1db740",
3205 | "6b08d4679ac6461cbe254fe3478091b6",
3206 | "9a2502aacbd6489da0f8b6fbadcf079b",
3207 | "f6ff0e6cd04047babe24708d21937576",
3208 | "36349f3e29664f0bbdda5c8f7651304e",
3209 | "59945ccd1da44215b5eaa6226835968c",
3210 | "2aed084699344e14b687a38196f3a4dc",
3211 | "97040354aa6047f4b2adfd7d0a255d0e",
3212 | "4167d18aa99240f09d20b78bb447f302",
3213 | "7b8c3ec2b0d7466c89881890686152f3",
3214 | "a86181d8ced94aa49b4664f692937ca8",
3215 | "d11ae8b4126d42a8a72dd70b3d093185",
3216 | "6319e0859d1547f8a586c2409c263519",
3217 | "2ce9e1635d34488eb5deee6f1eab48fc",
3218 | "44af7e9762b647beae7100e10b0f188f",
3219 | "01062415cb564e54906fa8ad9ff4031b",
3220 | "3be9d4577dec410cad57443e239347ce",
3221 | "9f0b34c9152840ac8f1e853420964173",
3222 | "8894905d0d0f4e4a995e8be50b214f39",
3223 | "c3b8c945c14e4adeb5031c68fe377ad6",
3224 | "8782c620fea449fd92ea1f8f7ef3c6ed",
3225 | "c04efab8b28346ea92e64a1599f1ee17",
3226 | "bd60373a16d647d9834a62c2624c9fc2",
3227 | "8e3fb5977e1c4ccab1181cf41959c132",
3228 | "d35466c751474dd688fe7073aec0a71f",
3229 | "82e084627ec14d57bf502decdc393b38",
3230 | "df0d6cc9ad9b4597802c6e98614a7f95",
3231 | "ef7a60fd80fe4ba8a8224b79f9659644",
3232 | "7e912d3befc4448ea114e1fa3aa93119",
3233 | "ba7aaec1107b40248eb6b76fb09f1fc9",
3234 | "393fcf7561da4434b07ac6022ee95eeb",
3235 | "8cc2390d790f46ce880f81da99c3b243",
3236 | "cb65ea1de35d439dbb0664329db64b25"
3237 | ]
3238 | },
3239 | "id": "vup_3Q1jZ60E",
3240 | "outputId": "d6611e5c-1fdf-43ba-b8c9-e9af9211b932"
3241 | },
3242 | "execution_count": null,
3243 | "outputs": [
3244 | {
3245 | "output_type": "display_data",
3246 | "data": {
3247 | "text/plain": [
3248 | "Downloading readme: 0%| | 0.00/381 [00:00, ?B/s]"
3249 | ],
3250 | "application/vnd.jupyter.widget-view+json": {
3251 | "version_major": 2,
3252 | "version_minor": 0,
3253 | "model_id": "909582d0b6014056b113ef9a0a1db740"
3254 | }
3255 | },
3256 | "metadata": {}
3257 | },
3258 | {
3259 | "output_type": "stream",
3260 | "name": "stderr",
3261 | "text": [
3262 | "/usr/local/lib/python3.10/dist-packages/huggingface_hub/repocard.py:105: UserWarning: Repo card metadata block was not found. Setting CardData to empty.\n",
3263 | " warnings.warn(\"Repo card metadata block was not found. Setting CardData to empty.\")\n"
3264 | ]
3265 | },
3266 | {
3267 | "output_type": "display_data",
3268 | "data": {
3269 | "text/plain": [
3270 | "Downloading data: 0%| | 0.00/107k [00:00, ?B/s]"
3271 | ],
3272 | "application/vnd.jupyter.widget-view+json": {
3273 | "version_major": 2,
3274 | "version_minor": 0,
3275 | "model_id": "d11ae8b4126d42a8a72dd70b3d093185"
3276 | }
3277 | },
3278 | "metadata": {}
3279 | },
3280 | {
3281 | "output_type": "display_data",
3282 | "data": {
3283 | "text/plain": [
3284 | "Generating train split: 0 examples [00:00, ? examples/s]"
3285 | ],
3286 | "application/vnd.jupyter.widget-view+json": {
3287 | "version_major": 2,
3288 | "version_minor": 0,
3289 | "model_id": "bd60373a16d647d9834a62c2624c9fc2"
3290 | }
3291 | },
3292 | "metadata": {}
3293 | }
3294 | ]
3295 | },
3296 | {
3297 | "cell_type": "code",
3298 | "source": [
3299 | "data_sample"
3300 | ],
3301 | "metadata": {
3302 | "colab": {
3303 | "base_uri": "https://localhost:8080/"
3304 | },
3305 | "id": "JAvb29N9Z62N",
3306 | "outputId": "c6fedf47-fd85-4854-d89e-12b7fef58ba5"
3307 | },
3308 | "execution_count": null,
3309 | "outputs": [
3310 | {
3311 | "output_type": "execute_result",
3312 | "data": {
3313 | "text/plain": [
3314 | "DatasetDict({\n",
3315 | " train: Dataset({\n",
3316 | " features: ['Code', 'Name', 'Symptoms', 'Treatments'],\n",
3317 | " num_rows: 400\n",
3318 | " })\n",
3319 | "})"
3320 | ]
3321 | },
3322 | "metadata": {},
3323 | "execution_count": 8
3324 | }
3325 | ]
3326 | },
3327 | {
3328 | "cell_type": "code",
3329 | "source": [
3330 | "# Convert to a pandas dataframe\n",
3331 | "updated_data = [{'Name': item['Name'], 'Symptoms': item['Symptoms']} for item in data_sample['train']]\n",
3332 | "df = pd.DataFrame(updated_data)"
3333 | ],
3334 | "metadata": {
3335 | "id": "m21_P13gZ64a"
3336 | },
3337 | "execution_count": null,
3338 | "outputs": []
3339 | },
3340 | {
3341 | "cell_type": "code",
3342 | "source": [
3343 | "df.head(5)"
3344 | ],
3345 | "metadata": {
3346 | "colab": {
3347 | "base_uri": "https://localhost:8080/",
3348 | "height": 206
3349 | },
3350 | "id": "7QiFNklKbJyC",
3351 | "outputId": "eb43216d-4336-422a-ba1e-473c522a8aec"
3352 | },
3353 | "execution_count": null,
3354 | "outputs": [
3355 | {
3356 | "output_type": "execute_result",
3357 | "data": {
3358 | "text/plain": [
3359 | " Name \\\n",
3360 | "0 Panic disorder \n",
3361 | "1 Vocal cord polyp \n",
3362 | "2 Turner syndrome \n",
3363 | "3 Cryptorchidism \n",
3364 | "4 Ethylene glycol poisoning-1 \n",
3365 | "\n",
3366 | " Symptoms \n",
3367 | "0 Palpitations, Sweating, Trembling, Shortness o... \n",
3368 | "1 Hoarseness, Vocal Changes, Vocal Fatigue \n",
3369 | "2 Short stature, Gonadal dysgenesis, Webbed neck... \n",
3370 | "3 Absence or undescended testicle(s), empty scro... \n",
3371 | "4 Nausea, vomiting, abdominal pain, General mala... "
3372 | ],
3373 | "text/html": [
3374 | "\n",
3375 | "
\n",
3376 | "
\n",
3377 | "\n",
3390 | "
\n",
3391 | " \n",
3392 | " \n",
3393 | " | \n",
3394 | " Name | \n",
3395 | " Symptoms | \n",
3396 | "
\n",
3397 | " \n",
3398 | " \n",
3399 | " \n",
3400 | " | 0 | \n",
3401 | " Panic disorder | \n",
3402 | " Palpitations, Sweating, Trembling, Shortness o... | \n",
3403 | "
\n",
3404 | " \n",
3405 | " | 1 | \n",
3406 | " Vocal cord polyp | \n",
3407 | " Hoarseness, Vocal Changes, Vocal Fatigue | \n",
3408 | "
\n",
3409 | " \n",
3410 | " | 2 | \n",
3411 | " Turner syndrome | \n",
3412 | " Short stature, Gonadal dysgenesis, Webbed neck... | \n",
3413 | "
\n",
3414 | " \n",
3415 | " | 3 | \n",
3416 | " Cryptorchidism | \n",
3417 | " Absence or undescended testicle(s), empty scro... | \n",
3418 | "
\n",
3419 | " \n",
3420 | " | 4 | \n",
3421 | " Ethylene glycol poisoning-1 | \n",
3422 | " Nausea, vomiting, abdominal pain, General mala... | \n",
3423 | "
\n",
3424 | " \n",
3425 | "
\n",
3426 | "
\n",
3427 | "
\n",
3635 | "
\n"
3636 | ]
3637 | },
3638 | "metadata": {},
3639 | "execution_count": 15
3640 | }
3641 | ]
3642 | },
3643 | {
3644 | "cell_type": "code",
3645 | "source": [
3646 | "# Just extract the Symptoms\n",
3647 | "df['Symptoms'] = df['Symptoms'].apply(lambda x: ', '.join(x.split(', ')))\n",
3648 | "display(df.head())"
3649 | ],
3650 | "metadata": {
3651 | "colab": {
3652 | "base_uri": "https://localhost:8080/",
3653 | "height": 206
3654 | },
3655 | "id": "LmMrE9qdZ66o",
3656 | "outputId": "cbb7cdef-b6e8-4aad-d577-df954fde34ef"
3657 | },
3658 | "execution_count": null,
3659 | "outputs": [
3660 | {
3661 | "output_type": "display_data",
3662 | "data": {
3663 | "text/plain": [
3664 | " Name \\\n",
3665 | "0 Panic disorder \n",
3666 | "1 Vocal cord polyp \n",
3667 | "2 Turner syndrome \n",
3668 | "3 Cryptorchidism \n",
3669 | "4 Ethylene glycol poisoning-1 \n",
3670 | "\n",
3671 | " Symptoms \n",
3672 | "0 Palpitations, Sweating, Trembling, Shortness o... \n",
3673 | "1 Hoarseness, Vocal Changes, Vocal Fatigue \n",
3674 | "2 Short stature, Gonadal dysgenesis, Webbed neck... \n",
3675 | "3 Absence or undescended testicle(s), empty scro... \n",
3676 | "4 Nausea, vomiting, abdominal pain, General mala... "
3677 | ],
3678 | "text/html": [
3679 | "\n",
3680 | " \n",
3681 | "
\n",
3682 | "\n",
3695 | "
\n",
3696 | " \n",
3697 | " \n",
3698 | " | \n",
3699 | " Name | \n",
3700 | " Symptoms | \n",
3701 | "
\n",
3702 | " \n",
3703 | " \n",
3704 | " \n",
3705 | " | 0 | \n",
3706 | " Panic disorder | \n",
3707 | " Palpitations, Sweating, Trembling, Shortness o... | \n",
3708 | "
\n",
3709 | " \n",
3710 | " | 1 | \n",
3711 | " Vocal cord polyp | \n",
3712 | " Hoarseness, Vocal Changes, Vocal Fatigue | \n",
3713 | "
\n",
3714 | " \n",
3715 | " | 2 | \n",
3716 | " Turner syndrome | \n",
3717 | " Short stature, Gonadal dysgenesis, Webbed neck... | \n",
3718 | "
\n",
3719 | " \n",
3720 | " | 3 | \n",
3721 | " Cryptorchidism | \n",
3722 | " Absence or undescended testicle(s), empty scro... | \n",
3723 | "
\n",
3724 | " \n",
3725 | " | 4 | \n",
3726 | " Ethylene glycol poisoning-1 | \n",
3727 | " Nausea, vomiting, abdominal pain, General mala... | \n",
3728 | "
\n",
3729 | " \n",
3730 | "
\n",
3731 | "
\n",
3732 | "
\n",
3940 | "
\n"
3941 | ]
3942 | },
3943 | "metadata": {}
3944 | }
3945 | ]
3946 | },
3947 | {
3948 | "cell_type": "code",
3949 | "source": [
3950 | "from transformers import GPT2Tokenizer, GPT2LMHeadModel\n",
3951 | "import torch\n",
3952 | "import torch.nn as nn\n",
3953 | "import torch.optim as optim\n",
3954 | "from torch.utils.data import Dataset, DataLoader, random_split"
3955 | ],
3956 | "metadata": {
3957 | "id": "tp47z0HkZ68-"
3958 | },
3959 | "execution_count": null,
3960 | "outputs": []
3961 | },
3962 | {
3963 | "cell_type": "code",
3964 | "source": [
3965 | "# If you have an NVIDIA GPU attached, use 'cuda'\n",
3966 | "if torch.cuda.is_available():\n",
3967 | " device = torch.device('cuda')\n",
3968 | "else:\n",
3969 | " # If Apple Silicon, set to 'mps' - otherwise 'cpu' (not advised)\n",
3970 | " try:\n",
3971 | " device = torch.device('mps')\n",
3972 | " except Exception:\n",
3973 | " device = torch.device('cpu')"
3974 | ],
3975 | "metadata": {
3976 | "id": "UudM36y5Z6_G"
3977 | },
3978 | "execution_count": null,
3979 | "outputs": []
3980 | },
3981 | {
3982 | "cell_type": "code",
3983 | "source": [
3984 | "device"
3985 | ],
3986 | "metadata": {
3987 | "colab": {
3988 | "base_uri": "https://localhost:8080/"
3989 | },
3990 | "id": "qKDArW3SZ7BW",
3991 | "outputId": "f9ae22d0-f893-480f-9f9e-65d09ef783f1"
3992 | },
3993 | "execution_count": null,
3994 | "outputs": [
3995 | {
3996 | "output_type": "execute_result",
3997 | "data": {
3998 | "text/plain": [
3999 | "device(type='cuda')"
4000 | ]
4001 | },
4002 | "metadata": {},
4003 | "execution_count": 20
4004 | }
4005 | ]
4006 | },
4007 | {
4008 | "cell_type": "code",
4009 | "source": [
4010 | "# The tokenizer turns texts to numbers (and vice-versa)\n",
4011 | "tokenizer = GPT2Tokenizer.from_pretrained('distilgpt2')\n",
4012 | "\n",
4013 | "# The transformer\n",
4014 | "model = GPT2LMHeadModel.from_pretrained('distilgpt2').to(device)"
4015 | ],
4016 | "metadata": {
4017 | "colab": {
4018 | "base_uri": "https://localhost:8080/",
4019 | "height": 209,
4020 | "referenced_widgets": [
4021 | "ec7fe86bf8f24f6387d541a2801dd4a7",
4022 | "89e5de0b0b0345b8b1d80adecc11e686",
4023 | "d2ebf5c51f4e4be7b6397f36ea7ea816",
4024 | "76641188f873496a84f24433e930c0c7",
4025 | "dc3b7059ab6d44619490a453498994dc",
4026 | "e0ab81310bc047fab2b01fd064a7fa45",
4027 | "2df7b934f04446c69243ad852b1bb66e",
4028 | "ad2e4b0915974802963f70f0e0ef0b4e",
4029 | "a516e4ccd9844714b9e8738fac138f08",
4030 | "d06613abbcea4ee0b06b2938494b89bc",
4031 | "69ffd05ad18c4c958dd3da00ecb03861",
4032 | "4ff4e721bc684d3588fc0bf9eef01dc1",
4033 | "a51c774046d840eba964ae05d44bc121",
4034 | "92c278e987384f9a8211800c54d7d2db",
4035 | "ce8b2c1e2af7468483b0248914da3be9",
4036 | "4ed5bcc239e145518de1fef008bb9b26",
4037 | "479dd0a62eec484a928f39a21b13a5ce",
4038 | "91efbd33184f4499825677459dc0bdfd",
4039 | "af8dff1656144b30aa37d8e80316f024",
4040 | "b88bdbeefe9444cd8b430e75b6943162",
4041 | "ff2cde47d25749459db552ce4a7d76e8",
4042 | "fe1f13c138e64a12818be45e287624e1",
4043 | "4ab5fa5d0362442fb891d153a2221269",
4044 | "3dfce640dbd648049f86bb6f960fba84",
4045 | "047c1c3081184ef8bbd1e55906d6034c",
4046 | "0ddc3a071ee74db4a701fa5c71bde4ab",
4047 | "4860d8f28fd4452ea3d78f5d360c8920",
4048 | "a8c102ccd45a4bb9a0366fed028c9c89",
4049 | "53be2c46b0634ace8157f69dddf502ed",
4050 | "8aa38554efa847d6b23659bbe3a22fd5",
4051 | "79ea0ca6be994c05a139b4b3b1d44e41",
4052 | "a23c7e7a5ac44f1c9fae6db6fb9a380c",
4053 | "be5a493006c247c6b94a76bfa8cd7717",
4054 | "8aa16db0c6804e789acc16ecda32fe5e",
4055 | "a898f936e23a4c8785e9de322f72c248",
4056 | "5fc6d2a6dde041e0a128e8eb550d9b10",
4057 | "5784196f1f3046b0b47370f2603c6f77",
4058 | "bdbd732073334dc0bde296c4fb3673c5",
4059 | "7c498217462d4c20bc892641e1437d4d",
4060 | "735689422d2648d8941ca86b240f8fec",
4061 | "250afadc3f5b4effad629a23e08a18d7",
4062 | "d9bd3ade496c480697a94ff869e27be6",
4063 | "1338c901f2d049c88a98d2ea31b3fe46",
4064 | "4ef7ad4d6dde4af9876bb5fe43efa56a",
4065 | "53e702e5171c40b7b257df00043bd869",
4066 | "e0e15cb7f0b94a4ab4553b398fa345bd",
4067 | "8972d3a55d1f43ddbad6d4a2543598f6",
4068 | "1434fedfd0c349f5925292e4d7df1b03",
4069 | "447946a3f9ca45c6874540d292ed27c3",
4070 | "46945285c25749079dcb3945fef79f23",
4071 | "07b35023dc9f46168345187a02aabf46",
4072 | "97fabf4a49954879bd24d482a8b7088b",
4073 | "5c08a4c88c7a4873bbcd1e2bfc53ec83",
4074 | "f7e099183e73426ea945ddee509106ce",
4075 | "24c1fecb5f244f3ea91cc67a8942e9e7",
4076 | "9ed7a6cf110c4d559166c1174e635aef",
4077 | "74b378012a2e46268df9de6eee525a39",
4078 | "379423052eed4c03a9f73f6f93a5563a",
4079 | "a84ffe146af54101b04048a700012ac5",
4080 | "b5ed1581833f4cd18df6b618ee6dcb6d",
4081 | "57dd8a572c6b4098a932d09d3f6887a1",
4082 | "8777bc937048458f9f2c5bcdc229be0d",
4083 | "64bb5ff3353d439b8ad3044832f8ad0e",
4084 | "fedf4812a5a2401080ca6ac779172cee",
4085 | "229b7b51aa904bd895a95b212b6a610e",
4086 | "66168d105bd340f7af008e996f5e24ae"
4087 | ]
4088 | },
4089 | "id": "0I1Wz-EuZ7Do",
4090 | "outputId": "97133506-e964-4c24-973a-58d49c152b65"
4091 | },
4092 | "execution_count": null,
4093 | "outputs": [
4094 | {
4095 | "output_type": "display_data",
4096 | "data": {
4097 | "text/plain": [
4098 | "vocab.json: 0%| | 0.00/1.04M [00:00, ?B/s]"
4099 | ],
4100 | "application/vnd.jupyter.widget-view+json": {
4101 | "version_major": 2,
4102 | "version_minor": 0,
4103 | "model_id": "ec7fe86bf8f24f6387d541a2801dd4a7"
4104 | }
4105 | },
4106 | "metadata": {}
4107 | },
4108 | {
4109 | "output_type": "display_data",
4110 | "data": {
4111 | "text/plain": [
4112 | "merges.txt: 0%| | 0.00/456k [00:00, ?B/s]"
4113 | ],
4114 | "application/vnd.jupyter.widget-view+json": {
4115 | "version_major": 2,
4116 | "version_minor": 0,
4117 | "model_id": "4ff4e721bc684d3588fc0bf9eef01dc1"
4118 | }
4119 | },
4120 | "metadata": {}
4121 | },
4122 | {
4123 | "output_type": "display_data",
4124 | "data": {
4125 | "text/plain": [
4126 | "tokenizer.json: 0%| | 0.00/1.36M [00:00, ?B/s]"
4127 | ],
4128 | "application/vnd.jupyter.widget-view+json": {
4129 | "version_major": 2,
4130 | "version_minor": 0,
4131 | "model_id": "4ab5fa5d0362442fb891d153a2221269"
4132 | }
4133 | },
4134 | "metadata": {}
4135 | },
4136 | {
4137 | "output_type": "display_data",
4138 | "data": {
4139 | "text/plain": [
4140 | "config.json: 0%| | 0.00/762 [00:00, ?B/s]"
4141 | ],
4142 | "application/vnd.jupyter.widget-view+json": {
4143 | "version_major": 2,
4144 | "version_minor": 0,
4145 | "model_id": "8aa16db0c6804e789acc16ecda32fe5e"
4146 | }
4147 | },
4148 | "metadata": {}
4149 | },
4150 | {
4151 | "output_type": "display_data",
4152 | "data": {
4153 | "text/plain": [
4154 | "model.safetensors: 0%| | 0.00/353M [00:00, ?B/s]"
4155 | ],
4156 | "application/vnd.jupyter.widget-view+json": {
4157 | "version_major": 2,
4158 | "version_minor": 0,
4159 | "model_id": "53e702e5171c40b7b257df00043bd869"
4160 | }
4161 | },
4162 | "metadata": {}
4163 | },
4164 | {
4165 | "output_type": "display_data",
4166 | "data": {
4167 | "text/plain": [
4168 | "generation_config.json: 0%| | 0.00/124 [00:00, ?B/s]"
4169 | ],
4170 | "application/vnd.jupyter.widget-view+json": {
4171 | "version_major": 2,
4172 | "version_minor": 0,
4173 | "model_id": "9ed7a6cf110c4d559166c1174e635aef"
4174 | }
4175 | },
4176 | "metadata": {}
4177 | }
4178 | ]
4179 | },
4180 | {
4181 | "cell_type": "code",
4182 | "source": [
4183 | "model"
4184 | ],
4185 | "metadata": {
4186 | "colab": {
4187 | "base_uri": "https://localhost:8080/"
4188 | },
4189 | "id": "8bezI4T5Z7F0",
4190 | "outputId": "b5009022-bacf-4fd8-a890-bf618d9ac2a9"
4191 | },
4192 | "execution_count": null,
4193 | "outputs": [
4194 | {
4195 | "output_type": "execute_result",
4196 | "data": {
4197 | "text/plain": [
4198 | "GPT2LMHeadModel(\n",
4199 | " (transformer): GPT2Model(\n",
4200 | " (wte): Embedding(50257, 768)\n",
4201 | " (wpe): Embedding(1024, 768)\n",
4202 | " (drop): Dropout(p=0.1, inplace=False)\n",
4203 | " (h): ModuleList(\n",
4204 | " (0-5): 6 x GPT2Block(\n",
4205 | " (ln_1): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
4206 | " (attn): GPT2Attention(\n",
4207 | " (c_attn): Conv1D()\n",
4208 | " (c_proj): Conv1D()\n",
4209 | " (attn_dropout): Dropout(p=0.1, inplace=False)\n",
4210 | " (resid_dropout): Dropout(p=0.1, inplace=False)\n",
4211 | " )\n",
4212 | " (ln_2): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
4213 | " (mlp): GPT2MLP(\n",
4214 | " (c_fc): Conv1D()\n",
4215 | " (c_proj): Conv1D()\n",
4216 | " (act): NewGELUActivation()\n",
4217 | " (dropout): Dropout(p=0.1, inplace=False)\n",
4218 | " )\n",
4219 | " )\n",
4220 | " )\n",
4221 | " (ln_f): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
4222 | " )\n",
4223 | " (lm_head): Linear(in_features=768, out_features=50257, bias=False)\n",
4224 | ")"
4225 | ]
4226 | },
4227 | "metadata": {},
4228 | "execution_count": 22
4229 | }
4230 | ]
4231 | },
4232 | {
4233 | "cell_type": "code",
4234 | "source": [
4235 | "# Model params\n",
4236 | "BATCH_SIZE = 8"
4237 | ],
4238 | "metadata": {
4239 | "id": "dvflNT0NZ7JP"
4240 | },
4241 | "execution_count": null,
4242 | "outputs": []
4243 | },
4244 | {
4245 | "cell_type": "code",
4246 | "source": [
4247 | "df.describe()"
4248 | ],
4249 | "metadata": {
4250 | "colab": {
4251 | "base_uri": "https://localhost:8080/",
4252 | "height": 175
4253 | },
4254 | "id": "aRekizA8c9Tf",
4255 | "outputId": "3d8fc919-c49a-48eb-9bfa-286d0946354f"
4256 | },
4257 | "execution_count": null,
4258 | "outputs": [
4259 | {
4260 | "output_type": "execute_result",
4261 | "data": {
4262 | "text/plain": [
4263 | " Name Symptoms\n",
4264 | "count 400 400\n",
4265 | "unique 392 395\n",
4266 | "top Sciatica Swelling, pain, dry mouth, bad taste\n",
4267 | "freq 3 3"
4268 | ],
4269 | "text/html": [
4270 | "\n",
4271 | " \n",
4272 | "
\n",
4273 | "\n",
4286 | "
\n",
4287 | " \n",
4288 | " \n",
4289 | " | \n",
4290 | " Name | \n",
4291 | " Symptoms | \n",
4292 | "
\n",
4293 | " \n",
4294 | " \n",
4295 | " \n",
4296 | " | count | \n",
4297 | " 400 | \n",
4298 | " 400 | \n",
4299 | "
\n",
4300 | " \n",
4301 | " | unique | \n",
4302 | " 392 | \n",
4303 | " 395 | \n",
4304 | "
\n",
4305 | " \n",
4306 | " | top | \n",
4307 | " Sciatica | \n",
4308 | " Swelling, pain, dry mouth, bad taste | \n",
4309 | "
\n",
4310 | " \n",
4311 | " | freq | \n",
4312 | " 3 | \n",
4313 | " 3 | \n",
4314 | "
\n",
4315 | " \n",
4316 | "
\n",
4317 | "
\n",
4318 | "
\n",
4526 | "
\n"
4527 | ]
4528 | },
4529 | "metadata": {},
4530 | "execution_count": 24
4531 | }
4532 | ]
4533 | },
4534 | {
4535 | "cell_type": "code",
4536 | "source": [
4537 | "# Dataset Prep\n",
4538 | "class LanguageDataset(Dataset):\n",
4539 | " \"\"\"\n",
4540 | " An extension of the Dataset object to:\n",
4541 | " - Make training loop cleaner\n",
4542 | " - Make ingestion easier from pandas df's\n",
4543 | " \"\"\"\n",
4544 | " def __init__(self, df, tokenizer):\n",
4545 | " self.labels = df.columns\n",
4546 | " self.data = df.to_dict(orient='records')\n",
4547 | " self.tokenizer = tokenizer\n",
4548 | " x = self.fittest_max_length(df) # Fix here\n",
4549 | " self.max_length = x\n",
4550 | "\n",
4551 | " def __len__(self):\n",
4552 | " return len(self.data)\n",
4553 | "\n",
4554 | " def __getitem__(self, idx):\n",
4555 | " x = self.data[idx][self.labels[0]]\n",
4556 | " y = self.data[idx][self.labels[1]]\n",
4557 | " text = f\"{x} | {y}\"\n",
4558 | " tokens = self.tokenizer.encode_plus(text, return_tensors='pt', max_length=128, padding='max_length', truncation=True)\n",
4559 | " return tokens\n",
4560 | "\n",
4561 | " def fittest_max_length(self, df): # Fix here\n",
4562 | " \"\"\"\n",
4563 | " Smallest power of two larger than the longest term in the data set.\n",
4564 | " Important to set up max length to speed training time.\n",
4565 | " \"\"\"\n",
4566 | " max_length = max(len(max(df[self.labels[0]], key=len)), len(max(df[self.labels[1]], key=len)))\n",
4567 | " x = 2\n",
4568 | " while x < max_length: x = x * 2\n",
4569 | " return x\n",
4570 | "\n",
4571 | "# Cast the Huggingface data set as a LanguageDataset we defined above\n",
4572 | "data_sample = LanguageDataset(df, tokenizer)\n"
4573 | ],
4574 | "metadata": {
4575 | "id": "lw70elXsc9ZL"
4576 | },
4577 | "execution_count": null,
4578 | "outputs": []
4579 | },
4580 | {
4581 | "cell_type": "code",
4582 | "source": [
4583 | "data_sample"
4584 | ],
4585 | "metadata": {
4586 | "colab": {
4587 | "base_uri": "https://localhost:8080/"
4588 | },
4589 | "id": "H3Mu1wmRc9b5",
4590 | "outputId": "eae0559d-7bfd-47b6-dc14-f41b3ed01891"
4591 | },
4592 | "execution_count": null,
4593 | "outputs": [
4594 | {
4595 | "output_type": "execute_result",
4596 | "data": {
4597 | "text/plain": [
4598 | "<__main__.LanguageDataset at 0x7c9e40196230>"
4599 | ]
4600 | },
4601 | "metadata": {},
4602 | "execution_count": 29
4603 | }
4604 | ]
4605 | },
4606 | {
4607 | "cell_type": "code",
4608 | "source": [
4609 | "# Create train, valid\n",
4610 | "train_size = int(0.8 * len(data_sample))\n",
4611 | "valid_size = len(data_sample) - train_size\n",
4612 | "train_data, valid_data = random_split(data_sample, [train_size, valid_size])"
4613 | ],
4614 | "metadata": {
4615 | "id": "fWs2iOdAc9dv"
4616 | },
4617 | "execution_count": null,
4618 | "outputs": []
4619 | },
4620 | {
4621 | "cell_type": "code",
4622 | "source": [
4623 | "# Make the iterators\n",
4624 | "train_loader = DataLoader(train_data, batch_size=BATCH_SIZE, shuffle=True)\n",
4625 | "valid_loader = DataLoader(valid_data, batch_size=BATCH_SIZE)"
4626 | ],
4627 | "metadata": {
4628 | "id": "4ECz4JD1c9gh"
4629 | },
4630 | "execution_count": null,
4631 | "outputs": []
4632 | },
4633 | {
4634 | "cell_type": "code",
4635 | "source": [
4636 | "# Set the number of epochs\n",
4637 | "num_epochs = 10"
4638 | ],
4639 | "metadata": {
4640 | "id": "U0NxSiIuc9j3"
4641 | },
4642 | "execution_count": null,
4643 | "outputs": []
4644 | },
4645 | {
4646 | "cell_type": "code",
4647 | "source": [
4648 | "# Training parameters\n",
4649 | "batch_size = BATCH_SIZE\n",
4650 | "model_name = 'distilgpt2'\n",
4651 | "gpu = 0"
4652 | ],
4653 | "metadata": {
4654 | "id": "AOfoBQALe5iI"
4655 | },
4656 | "execution_count": null,
4657 | "outputs": []
4658 | },
4659 | {
4660 | "cell_type": "code",
4661 | "source": [
4662 | "# Set the learning rate and loss function\n",
4663 | "## CrossEntropyLoss measures how close answers to the truth.\n",
4664 | "## More punishing for high confidence wrong answers\n",
4665 | "criterion = nn.CrossEntropyLoss(ignore_index = tokenizer.pad_token_id)\n",
4666 | "optimizer = optim.Adam(model.parameters(), lr=5e-4)\n",
4667 | "tokenizer.pad_token = tokenizer.eos_token"
4668 | ],
4669 | "metadata": {
4670 | "id": "jgv7BrEse5kv"
4671 | },
4672 | "execution_count": null,
4673 | "outputs": []
4674 | },
4675 | {
4676 | "cell_type": "code",
4677 | "source": [
4678 | "# Init a results dataframe\n",
4679 | "results = pd.DataFrame(columns=['epoch', 'transformer', 'batch_size', 'gpu',\n",
4680 | " 'training_loss', 'validation_loss', 'epoch_duration_sec'])"
4681 | ],
4682 | "metadata": {
4683 | "id": "hsrgomD-e5nL"
4684 | },
4685 | "execution_count": null,
4686 | "outputs": []
4687 | },
4688 | {
4689 | "cell_type": "code",
4690 | "source": [
4691 | "# The training loop\n",
4692 | "for epoch in range(num_epochs):\n",
4693 | " start_time = time.time() # Start the timer for the epoch\n",
4694 | "\n",
4695 | " # Training\n",
4696 | " ## This line tells the model we're in 'learning mode'\n",
4697 | " model.train()\n",
4698 | " epoch_training_loss = 0\n",
4699 | " train_iterator = tqdm(train_loader, desc=f\"Training Epoch {epoch+1}/{num_epochs} Batch Size: {batch_size}, Transformer: {model_name}\")\n",
4700 | " for batch in train_iterator:\n",
4701 | " optimizer.zero_grad()\n",
4702 | " inputs = batch['input_ids'].squeeze(1).to(device)\n",
4703 | " targets = inputs.clone()\n",
4704 | " outputs = model(input_ids=inputs, labels=targets)\n",
4705 | " loss = outputs.loss\n",
4706 | " loss.backward()\n",
4707 | " optimizer.step()\n",
4708 | " train_iterator.set_postfix({'Training Loss': loss.item()})\n",
4709 | " epoch_training_loss += loss.item()\n",
4710 | " avg_epoch_training_loss = epoch_training_loss / len(train_iterator)\n",
4711 | "\n",
4712 | " # Validation\n",
4713 | " ## This line below tells the model to 'stop learning'\n",
4714 | " model.eval()\n",
4715 | " epoch_validation_loss = 0\n",
4716 | " total_loss = 0\n",
4717 | " valid_iterator = tqdm(valid_loader, desc=f\"Validation Epoch {epoch+1}/{num_epochs}\")\n",
4718 | " with torch.no_grad():\n",
4719 | " for batch in valid_iterator:\n",
4720 | " inputs = batch['input_ids'].squeeze(1).to(device)\n",
4721 | " targets = inputs.clone()\n",
4722 | " outputs = model(input_ids=inputs, labels=targets)\n",
4723 | " loss = outputs.loss\n",
4724 | " total_loss += loss\n",
4725 | " valid_iterator.set_postfix({'Validation Loss': loss.item()})\n",
4726 | " epoch_validation_loss += loss.item()\n",
4727 | "\n",
4728 | " avg_epoch_validation_loss = epoch_validation_loss / len(valid_loader)\n",
4729 | "\n",
4730 | " end_time = time.time() # End the timer for the epoch\n",
4731 | " epoch_duration_sec = end_time - start_time # Calculate the duration in seconds\n",
4732 | "\n",
4733 | " new_row = {'transformer': model_name,\n",
4734 | " 'batch_size': batch_size,\n",
4735 | " 'gpu': gpu,\n",
4736 | " 'epoch': epoch+1,\n",
4737 | " 'training_loss': avg_epoch_training_loss,\n",
4738 | " 'validation_loss': avg_epoch_validation_loss,\n",
4739 | " 'epoch_duration_sec': epoch_duration_sec} # Add epoch_duration to the dataframe\n",
4740 | "\n",
4741 | " results.loc[len(results)] = new_row\n",
4742 | " print(f\"Epoch: {epoch+1}, Validation Loss: {total_loss/len(valid_loader)}\")"
4743 | ],
4744 | "metadata": {
4745 | "colab": {
4746 | "base_uri": "https://localhost:8080/"
4747 | },
4748 | "id": "v1lSK_1Re5qi",
4749 | "outputId": "c63455fa-0212-4186-dbcd-474c296b2585"
4750 | },
4751 | "execution_count": null,
4752 | "outputs": [
4753 | {
4754 | "output_type": "stream",
4755 | "name": "stderr",
4756 | "text": [
4757 | "Training Epoch 1/10 Batch Size: 8, Transformer: distilgpt2: 100%|██████████| 40/40 [00:07<00:00, 5.17it/s, Training Loss=0.365]\n",
4758 | "Validation Epoch 1/10: 100%|██████████| 10/10 [00:00<00:00, 17.85it/s, Validation Loss=0.619]\n"
4759 | ]
4760 | },
4761 | {
4762 | "output_type": "stream",
4763 | "name": "stdout",
4764 | "text": [
4765 | "Epoch: 1, Validation Loss: 0.6991834044456482\n"
4766 | ]
4767 | },
4768 | {
4769 | "output_type": "stream",
4770 | "name": "stderr",
4771 | "text": [
4772 | "Training Epoch 2/10 Batch Size: 8, Transformer: distilgpt2: 100%|██████████| 40/40 [00:07<00:00, 5.07it/s, Training Loss=0.319]\n",
4773 | "Validation Epoch 2/10: 100%|██████████| 10/10 [00:00<00:00, 17.46it/s, Validation Loss=0.683]\n"
4774 | ]
4775 | },
4776 | {
4777 | "output_type": "stream",
4778 | "name": "stdout",
4779 | "text": [
4780 | "Epoch: 2, Validation Loss: 0.7609376907348633\n"
4781 | ]
4782 | },
4783 | {
4784 | "output_type": "stream",
4785 | "name": "stderr",
4786 | "text": [
4787 | "Training Epoch 3/10 Batch Size: 8, Transformer: distilgpt2: 100%|██████████| 40/40 [00:08<00:00, 4.98it/s, Training Loss=0.259]\n",
4788 | "Validation Epoch 3/10: 100%|██████████| 10/10 [00:00<00:00, 17.42it/s, Validation Loss=0.713]\n"
4789 | ]
4790 | },
4791 | {
4792 | "output_type": "stream",
4793 | "name": "stdout",
4794 | "text": [
4795 | "Epoch: 3, Validation Loss: 0.8256472945213318\n"
4796 | ]
4797 | },
4798 | {
4799 | "output_type": "stream",
4800 | "name": "stderr",
4801 | "text": [
4802 | "Training Epoch 4/10 Batch Size: 8, Transformer: distilgpt2: 100%|██████████| 40/40 [00:07<00:00, 5.02it/s, Training Loss=0.258]\n",
4803 | "Validation Epoch 4/10: 100%|██████████| 10/10 [00:00<00:00, 17.60it/s, Validation Loss=0.77]\n"
4804 | ]
4805 | },
4806 | {
4807 | "output_type": "stream",
4808 | "name": "stdout",
4809 | "text": [
4810 | "Epoch: 4, Validation Loss: 0.8827103972434998\n"
4811 | ]
4812 | },
4813 | {
4814 | "output_type": "stream",
4815 | "name": "stderr",
4816 | "text": [
4817 | "Training Epoch 5/10 Batch Size: 8, Transformer: distilgpt2: 100%|██████████| 40/40 [00:07<00:00, 5.13it/s, Training Loss=0.167]\n",
4818 | "Validation Epoch 5/10: 100%|██████████| 10/10 [00:00<00:00, 17.80it/s, Validation Loss=0.799]\n"
4819 | ]
4820 | },
4821 | {
4822 | "output_type": "stream",
4823 | "name": "stdout",
4824 | "text": [
4825 | "Epoch: 5, Validation Loss: 0.9266298413276672\n"
4826 | ]
4827 | },
4828 | {
4829 | "output_type": "stream",
4830 | "name": "stderr",
4831 | "text": [
4832 | "Training Epoch 6/10 Batch Size: 8, Transformer: distilgpt2: 100%|██████████| 40/40 [00:07<00:00, 5.18it/s, Training Loss=0.196]\n",
4833 | "Validation Epoch 6/10: 100%|██████████| 10/10 [00:00<00:00, 17.98it/s, Validation Loss=0.798]\n"
4834 | ]
4835 | },
4836 | {
4837 | "output_type": "stream",
4838 | "name": "stdout",
4839 | "text": [
4840 | "Epoch: 6, Validation Loss: 0.9501779675483704\n"
4841 | ]
4842 | },
4843 | {
4844 | "output_type": "stream",
4845 | "name": "stderr",
4846 | "text": [
4847 | "Training Epoch 7/10 Batch Size: 8, Transformer: distilgpt2: 100%|██████████| 40/40 [00:07<00:00, 5.22it/s, Training Loss=0.0849]\n",
4848 | "Validation Epoch 7/10: 100%|██████████| 10/10 [00:00<00:00, 17.94it/s, Validation Loss=0.925]\n"
4849 | ]
4850 | },
4851 | {
4852 | "output_type": "stream",
4853 | "name": "stdout",
4854 | "text": [
4855 | "Epoch: 7, Validation Loss: 1.0285433530807495\n"
4856 | ]
4857 | },
4858 | {
4859 | "output_type": "stream",
4860 | "name": "stderr",
4861 | "text": [
4862 | "Training Epoch 8/10 Batch Size: 8, Transformer: distilgpt2: 100%|██████████| 40/40 [00:07<00:00, 5.24it/s, Training Loss=0.0743]\n",
4863 | "Validation Epoch 8/10: 100%|██████████| 10/10 [00:00<00:00, 17.94it/s, Validation Loss=0.841]\n"
4864 | ]
4865 | },
4866 | {
4867 | "output_type": "stream",
4868 | "name": "stdout",
4869 | "text": [
4870 | "Epoch: 8, Validation Loss: 1.005602240562439\n"
4871 | ]
4872 | },
4873 | {
4874 | "output_type": "stream",
4875 | "name": "stderr",
4876 | "text": [
4877 | "Training Epoch 9/10 Batch Size: 8, Transformer: distilgpt2: 100%|██████████| 40/40 [00:07<00:00, 5.22it/s, Training Loss=0.074]\n",
4878 | "Validation Epoch 9/10: 100%|██████████| 10/10 [00:00<00:00, 17.78it/s, Validation Loss=0.865]\n"
4879 | ]
4880 | },
4881 | {
4882 | "output_type": "stream",
4883 | "name": "stdout",
4884 | "text": [
4885 | "Epoch: 9, Validation Loss: 1.039918065071106\n"
4886 | ]
4887 | },
4888 | {
4889 | "output_type": "stream",
4890 | "name": "stderr",
4891 | "text": [
4892 | "Training Epoch 10/10 Batch Size: 8, Transformer: distilgpt2: 100%|██████████| 40/40 [00:07<00:00, 5.20it/s, Training Loss=0.0684]\n",
4893 | "Validation Epoch 10/10: 100%|██████████| 10/10 [00:00<00:00, 18.05it/s, Validation Loss=0.906]"
4894 | ]
4895 | },
4896 | {
4897 | "output_type": "stream",
4898 | "name": "stdout",
4899 | "text": [
4900 | "Epoch: 10, Validation Loss: 1.0768476724624634\n"
4901 | ]
4902 | },
4903 | {
4904 | "output_type": "stream",
4905 | "name": "stderr",
4906 | "text": [
4907 | "\n"
4908 | ]
4909 | }
4910 | ]
4911 | },
4912 | {
4913 | "cell_type": "code",
4914 | "source": [
4915 | "input_str = \"Kidney Failure\"\n",
4916 | "input_ids = tokenizer.encode(input_str, return_tensors='pt').to(device)\n",
4917 | "\n",
4918 | "output = model.generate(\n",
4919 | " input_ids,\n",
4920 | " max_length=20,\n",
4921 | " num_return_sequences=1,\n",
4922 | " do_sample=True,\n",
4923 | " top_k=8,\n",
4924 | " top_p=0.95,\n",
4925 | " temperature=0.5,\n",
4926 | " repetition_penalty=1.2\n",
4927 | ")\n",
4928 | "\n",
4929 | "decoded_output = tokenizer.decode(output[0], skip_special_tokens=True)\n",
4930 | "print(decoded_output)"
4931 | ],
4932 | "metadata": {
4933 | "colab": {
4934 | "base_uri": "https://localhost:8080/"
4935 | },
4936 | "id": "kdFB-15HfByw",
4937 | "outputId": "4172d404-506a-4310-d646-38041fcf42e7"
4938 | },
4939 | "execution_count": null,
4940 | "outputs": [
4941 | {
4942 | "output_type": "stream",
4943 | "name": "stderr",
4944 | "text": [
4945 | "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
4946 | "Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.\n"
4947 | ]
4948 | },
4949 | {
4950 | "output_type": "stream",
4951 | "name": "stdout",
4952 | "text": [
4953 | "Kidney Failure | Decreased urine output, fluid retention, fatigue, shortness of breath, nausea\n"
4954 | ]
4955 | }
4956 | ]
4957 | },
4958 | {
4959 | "cell_type": "code",
4960 | "source": [
4961 | "torch.save(model, 'SmallMedLM.pt')"
4962 | ],
4963 | "metadata": {
4964 | "id": "wYx0GjubfB06"
4965 | },
4966 | "execution_count": null,
4967 | "outputs": []
4968 | },
4969 | {
4970 | "cell_type": "code",
4971 | "source": [
4972 | "torch.save(model, 'drive/My Drive/SmallMedLM.pt')"
4973 | ],
4974 | "metadata": {
4975 | "id": "hUHvYtrqfB3f"
4976 | },
4977 | "execution_count": null,
4978 | "outputs": []
4979 | },
4980 | {
4981 | "cell_type": "code",
4982 | "source": [],
4983 | "metadata": {
4984 | "id": "NbMjEZcMfB51"
4985 | },
4986 | "execution_count": null,
4987 | "outputs": []
4988 | },
4989 | {
4990 | "cell_type": "code",
4991 | "source": [],
4992 | "metadata": {
4993 | "id": "A8AZHT6KfB9V"
4994 | },
4995 | "execution_count": null,
4996 | "outputs": []
4997 | }
4998 | ]
4999 | }
--------------------------------------------------------------------------------