Upload WiDS_2023_LT.ipynb
Browse files- WiDS_2023_LT.ipynb +1840 -0
WiDS_2023_LT.ipynb
ADDED
@@ -0,0 +1,1840 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"nbformat": 4,
|
3 |
+
"nbformat_minor": 0,
|
4 |
+
"metadata": {
|
5 |
+
"colab": {
|
6 |
+
"provenance": [],
|
7 |
+
"gpuType": "T4"
|
8 |
+
},
|
9 |
+
"kernelspec": {
|
10 |
+
"name": "python3",
|
11 |
+
"display_name": "Python 3"
|
12 |
+
},
|
13 |
+
"language_info": {
|
14 |
+
"name": "python"
|
15 |
+
},
|
16 |
+
"accelerator": "GPU",
|
17 |
+
"widgets": {
|
18 |
+
"application/vnd.jupyter.widget-state+json": {
|
19 |
+
"8c1c7e4a6b8f47149ddca02e551f48a4": {
|
20 |
+
"model_module": "@jupyter-widgets/controls",
|
21 |
+
"model_name": "VBoxModel",
|
22 |
+
"model_module_version": "1.5.0",
|
23 |
+
"state": {
|
24 |
+
"_dom_classes": [],
|
25 |
+
"_model_module": "@jupyter-widgets/controls",
|
26 |
+
"_model_module_version": "1.5.0",
|
27 |
+
"_model_name": "VBoxModel",
|
28 |
+
"_view_count": null,
|
29 |
+
"_view_module": "@jupyter-widgets/controls",
|
30 |
+
"_view_module_version": "1.5.0",
|
31 |
+
"_view_name": "VBoxView",
|
32 |
+
"box_style": "",
|
33 |
+
"children": [
|
34 |
+
"IPY_MODEL_c2463a94b1fb44fa8196e7b61636c3b7",
|
35 |
+
"IPY_MODEL_3040b325f55949fdbdc4caf75e9cd618",
|
36 |
+
"IPY_MODEL_d9de6537b056464baa3dde45e81bbd72",
|
37 |
+
"IPY_MODEL_dc8c33db5e814578a4aa9355132e132a"
|
38 |
+
],
|
39 |
+
"layout": "IPY_MODEL_022ab2bdb55944858b48891baa414d3c"
|
40 |
+
}
|
41 |
+
},
|
42 |
+
"cdbbba5c25e64371a6678a34e1120dc5": {
|
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_5b364ad09e3d4158a728284f583616b3",
|
58 |
+
"placeholder": "",
|
59 |
+
"style": "IPY_MODEL_3e894d7c8a3545c3886c340328d289a2",
|
60 |
+
"value": "<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"
|
61 |
+
}
|
62 |
+
},
|
63 |
+
"70a2cd0297a6456f8a1913c3037a08cd": {
|
64 |
+
"model_module": "@jupyter-widgets/controls",
|
65 |
+
"model_name": "PasswordModel",
|
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": "PasswordModel",
|
72 |
+
"_view_count": null,
|
73 |
+
"_view_module": "@jupyter-widgets/controls",
|
74 |
+
"_view_module_version": "1.5.0",
|
75 |
+
"_view_name": "PasswordView",
|
76 |
+
"continuous_update": true,
|
77 |
+
"description": "Token:",
|
78 |
+
"description_tooltip": null,
|
79 |
+
"disabled": false,
|
80 |
+
"layout": "IPY_MODEL_f1b49e3bd1354e24bc911b2d2c7cfc7d",
|
81 |
+
"placeholder": "",
|
82 |
+
"style": "IPY_MODEL_0c0fa6b93d144ddb8b9a4084dbaee2a4",
|
83 |
+
"value": ""
|
84 |
+
}
|
85 |
+
},
|
86 |
+
"fe8a530f6c91441fb7f48b77e5e673fa": {
|
87 |
+
"model_module": "@jupyter-widgets/controls",
|
88 |
+
"model_name": "CheckboxModel",
|
89 |
+
"model_module_version": "1.5.0",
|
90 |
+
"state": {
|
91 |
+
"_dom_classes": [],
|
92 |
+
"_model_module": "@jupyter-widgets/controls",
|
93 |
+
"_model_module_version": "1.5.0",
|
94 |
+
"_model_name": "CheckboxModel",
|
95 |
+
"_view_count": null,
|
96 |
+
"_view_module": "@jupyter-widgets/controls",
|
97 |
+
"_view_module_version": "1.5.0",
|
98 |
+
"_view_name": "CheckboxView",
|
99 |
+
"description": "Add token as git credential?",
|
100 |
+
"description_tooltip": null,
|
101 |
+
"disabled": false,
|
102 |
+
"indent": true,
|
103 |
+
"layout": "IPY_MODEL_f8bf8d132d774ab89cf258a7027b3557",
|
104 |
+
"style": "IPY_MODEL_5d043f830b7f4981b0597136f1e530ed",
|
105 |
+
"value": true
|
106 |
+
}
|
107 |
+
},
|
108 |
+
"9b84de3ec55a4035bf61621f80b0c374": {
|
109 |
+
"model_module": "@jupyter-widgets/controls",
|
110 |
+
"model_name": "ButtonModel",
|
111 |
+
"model_module_version": "1.5.0",
|
112 |
+
"state": {
|
113 |
+
"_dom_classes": [],
|
114 |
+
"_model_module": "@jupyter-widgets/controls",
|
115 |
+
"_model_module_version": "1.5.0",
|
116 |
+
"_model_name": "ButtonModel",
|
117 |
+
"_view_count": null,
|
118 |
+
"_view_module": "@jupyter-widgets/controls",
|
119 |
+
"_view_module_version": "1.5.0",
|
120 |
+
"_view_name": "ButtonView",
|
121 |
+
"button_style": "",
|
122 |
+
"description": "Login",
|
123 |
+
"disabled": false,
|
124 |
+
"icon": "",
|
125 |
+
"layout": "IPY_MODEL_3f1f2f9baab74de890b2213d4846611d",
|
126 |
+
"style": "IPY_MODEL_f3f7d114085d477692c4933876b8b5cc",
|
127 |
+
"tooltip": ""
|
128 |
+
}
|
129 |
+
},
|
130 |
+
"0f044626ebca4e21b8e05a45dae2341d": {
|
131 |
+
"model_module": "@jupyter-widgets/controls",
|
132 |
+
"model_name": "HTMLModel",
|
133 |
+
"model_module_version": "1.5.0",
|
134 |
+
"state": {
|
135 |
+
"_dom_classes": [],
|
136 |
+
"_model_module": "@jupyter-widgets/controls",
|
137 |
+
"_model_module_version": "1.5.0",
|
138 |
+
"_model_name": "HTMLModel",
|
139 |
+
"_view_count": null,
|
140 |
+
"_view_module": "@jupyter-widgets/controls",
|
141 |
+
"_view_module_version": "1.5.0",
|
142 |
+
"_view_name": "HTMLView",
|
143 |
+
"description": "",
|
144 |
+
"description_tooltip": null,
|
145 |
+
"layout": "IPY_MODEL_a2ceb52d59634de6bf64f41b6f3da3a4",
|
146 |
+
"placeholder": "",
|
147 |
+
"style": "IPY_MODEL_60dc766ea8734e3baa5df22506d8fcf6",
|
148 |
+
"value": "\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"
|
149 |
+
}
|
150 |
+
},
|
151 |
+
"022ab2bdb55944858b48891baa414d3c": {
|
152 |
+
"model_module": "@jupyter-widgets/base",
|
153 |
+
"model_name": "LayoutModel",
|
154 |
+
"model_module_version": "1.2.0",
|
155 |
+
"state": {
|
156 |
+
"_model_module": "@jupyter-widgets/base",
|
157 |
+
"_model_module_version": "1.2.0",
|
158 |
+
"_model_name": "LayoutModel",
|
159 |
+
"_view_count": null,
|
160 |
+
"_view_module": "@jupyter-widgets/base",
|
161 |
+
"_view_module_version": "1.2.0",
|
162 |
+
"_view_name": "LayoutView",
|
163 |
+
"align_content": null,
|
164 |
+
"align_items": "center",
|
165 |
+
"align_self": null,
|
166 |
+
"border": null,
|
167 |
+
"bottom": null,
|
168 |
+
"display": "flex",
|
169 |
+
"flex": null,
|
170 |
+
"flex_flow": "column",
|
171 |
+
"grid_area": null,
|
172 |
+
"grid_auto_columns": null,
|
173 |
+
"grid_auto_flow": null,
|
174 |
+
"grid_auto_rows": null,
|
175 |
+
"grid_column": null,
|
176 |
+
"grid_gap": null,
|
177 |
+
"grid_row": null,
|
178 |
+
"grid_template_areas": null,
|
179 |
+
"grid_template_columns": null,
|
180 |
+
"grid_template_rows": null,
|
181 |
+
"height": null,
|
182 |
+
"justify_content": null,
|
183 |
+
"justify_items": null,
|
184 |
+
"left": null,
|
185 |
+
"margin": null,
|
186 |
+
"max_height": null,
|
187 |
+
"max_width": null,
|
188 |
+
"min_height": null,
|
189 |
+
"min_width": null,
|
190 |
+
"object_fit": null,
|
191 |
+
"object_position": null,
|
192 |
+
"order": null,
|
193 |
+
"overflow": null,
|
194 |
+
"overflow_x": null,
|
195 |
+
"overflow_y": null,
|
196 |
+
"padding": null,
|
197 |
+
"right": null,
|
198 |
+
"top": null,
|
199 |
+
"visibility": null,
|
200 |
+
"width": "50%"
|
201 |
+
}
|
202 |
+
},
|
203 |
+
"5b364ad09e3d4158a728284f583616b3": {
|
204 |
+
"model_module": "@jupyter-widgets/base",
|
205 |
+
"model_name": "LayoutModel",
|
206 |
+
"model_module_version": "1.2.0",
|
207 |
+
"state": {
|
208 |
+
"_model_module": "@jupyter-widgets/base",
|
209 |
+
"_model_module_version": "1.2.0",
|
210 |
+
"_model_name": "LayoutModel",
|
211 |
+
"_view_count": null,
|
212 |
+
"_view_module": "@jupyter-widgets/base",
|
213 |
+
"_view_module_version": "1.2.0",
|
214 |
+
"_view_name": "LayoutView",
|
215 |
+
"align_content": null,
|
216 |
+
"align_items": null,
|
217 |
+
"align_self": null,
|
218 |
+
"border": null,
|
219 |
+
"bottom": null,
|
220 |
+
"display": null,
|
221 |
+
"flex": null,
|
222 |
+
"flex_flow": null,
|
223 |
+
"grid_area": null,
|
224 |
+
"grid_auto_columns": null,
|
225 |
+
"grid_auto_flow": null,
|
226 |
+
"grid_auto_rows": null,
|
227 |
+
"grid_column": null,
|
228 |
+
"grid_gap": null,
|
229 |
+
"grid_row": null,
|
230 |
+
"grid_template_areas": null,
|
231 |
+
"grid_template_columns": null,
|
232 |
+
"grid_template_rows": null,
|
233 |
+
"height": null,
|
234 |
+
"justify_content": null,
|
235 |
+
"justify_items": null,
|
236 |
+
"left": null,
|
237 |
+
"margin": null,
|
238 |
+
"max_height": null,
|
239 |
+
"max_width": null,
|
240 |
+
"min_height": null,
|
241 |
+
"min_width": null,
|
242 |
+
"object_fit": null,
|
243 |
+
"object_position": null,
|
244 |
+
"order": null,
|
245 |
+
"overflow": null,
|
246 |
+
"overflow_x": null,
|
247 |
+
"overflow_y": null,
|
248 |
+
"padding": null,
|
249 |
+
"right": null,
|
250 |
+
"top": null,
|
251 |
+
"visibility": null,
|
252 |
+
"width": null
|
253 |
+
}
|
254 |
+
},
|
255 |
+
"3e894d7c8a3545c3886c340328d289a2": {
|
256 |
+
"model_module": "@jupyter-widgets/controls",
|
257 |
+
"model_name": "DescriptionStyleModel",
|
258 |
+
"model_module_version": "1.5.0",
|
259 |
+
"state": {
|
260 |
+
"_model_module": "@jupyter-widgets/controls",
|
261 |
+
"_model_module_version": "1.5.0",
|
262 |
+
"_model_name": "DescriptionStyleModel",
|
263 |
+
"_view_count": null,
|
264 |
+
"_view_module": "@jupyter-widgets/base",
|
265 |
+
"_view_module_version": "1.2.0",
|
266 |
+
"_view_name": "StyleView",
|
267 |
+
"description_width": ""
|
268 |
+
}
|
269 |
+
},
|
270 |
+
"f1b49e3bd1354e24bc911b2d2c7cfc7d": {
|
271 |
+
"model_module": "@jupyter-widgets/base",
|
272 |
+
"model_name": "LayoutModel",
|
273 |
+
"model_module_version": "1.2.0",
|
274 |
+
"state": {
|
275 |
+
"_model_module": "@jupyter-widgets/base",
|
276 |
+
"_model_module_version": "1.2.0",
|
277 |
+
"_model_name": "LayoutModel",
|
278 |
+
"_view_count": null,
|
279 |
+
"_view_module": "@jupyter-widgets/base",
|
280 |
+
"_view_module_version": "1.2.0",
|
281 |
+
"_view_name": "LayoutView",
|
282 |
+
"align_content": null,
|
283 |
+
"align_items": null,
|
284 |
+
"align_self": null,
|
285 |
+
"border": null,
|
286 |
+
"bottom": null,
|
287 |
+
"display": null,
|
288 |
+
"flex": null,
|
289 |
+
"flex_flow": null,
|
290 |
+
"grid_area": null,
|
291 |
+
"grid_auto_columns": null,
|
292 |
+
"grid_auto_flow": null,
|
293 |
+
"grid_auto_rows": null,
|
294 |
+
"grid_column": null,
|
295 |
+
"grid_gap": null,
|
296 |
+
"grid_row": null,
|
297 |
+
"grid_template_areas": null,
|
298 |
+
"grid_template_columns": null,
|
299 |
+
"grid_template_rows": null,
|
300 |
+
"height": null,
|
301 |
+
"justify_content": null,
|
302 |
+
"justify_items": null,
|
303 |
+
"left": null,
|
304 |
+
"margin": null,
|
305 |
+
"max_height": null,
|
306 |
+
"max_width": null,
|
307 |
+
"min_height": null,
|
308 |
+
"min_width": null,
|
309 |
+
"object_fit": null,
|
310 |
+
"object_position": null,
|
311 |
+
"order": null,
|
312 |
+
"overflow": null,
|
313 |
+
"overflow_x": null,
|
314 |
+
"overflow_y": null,
|
315 |
+
"padding": null,
|
316 |
+
"right": null,
|
317 |
+
"top": null,
|
318 |
+
"visibility": null,
|
319 |
+
"width": null
|
320 |
+
}
|
321 |
+
},
|
322 |
+
"0c0fa6b93d144ddb8b9a4084dbaee2a4": {
|
323 |
+
"model_module": "@jupyter-widgets/controls",
|
324 |
+
"model_name": "DescriptionStyleModel",
|
325 |
+
"model_module_version": "1.5.0",
|
326 |
+
"state": {
|
327 |
+
"_model_module": "@jupyter-widgets/controls",
|
328 |
+
"_model_module_version": "1.5.0",
|
329 |
+
"_model_name": "DescriptionStyleModel",
|
330 |
+
"_view_count": null,
|
331 |
+
"_view_module": "@jupyter-widgets/base",
|
332 |
+
"_view_module_version": "1.2.0",
|
333 |
+
"_view_name": "StyleView",
|
334 |
+
"description_width": ""
|
335 |
+
}
|
336 |
+
},
|
337 |
+
"f8bf8d132d774ab89cf258a7027b3557": {
|
338 |
+
"model_module": "@jupyter-widgets/base",
|
339 |
+
"model_name": "LayoutModel",
|
340 |
+
"model_module_version": "1.2.0",
|
341 |
+
"state": {
|
342 |
+
"_model_module": "@jupyter-widgets/base",
|
343 |
+
"_model_module_version": "1.2.0",
|
344 |
+
"_model_name": "LayoutModel",
|
345 |
+
"_view_count": null,
|
346 |
+
"_view_module": "@jupyter-widgets/base",
|
347 |
+
"_view_module_version": "1.2.0",
|
348 |
+
"_view_name": "LayoutView",
|
349 |
+
"align_content": null,
|
350 |
+
"align_items": null,
|
351 |
+
"align_self": null,
|
352 |
+
"border": null,
|
353 |
+
"bottom": null,
|
354 |
+
"display": null,
|
355 |
+
"flex": null,
|
356 |
+
"flex_flow": null,
|
357 |
+
"grid_area": null,
|
358 |
+
"grid_auto_columns": null,
|
359 |
+
"grid_auto_flow": null,
|
360 |
+
"grid_auto_rows": null,
|
361 |
+
"grid_column": null,
|
362 |
+
"grid_gap": null,
|
363 |
+
"grid_row": null,
|
364 |
+
"grid_template_areas": null,
|
365 |
+
"grid_template_columns": null,
|
366 |
+
"grid_template_rows": null,
|
367 |
+
"height": null,
|
368 |
+
"justify_content": null,
|
369 |
+
"justify_items": null,
|
370 |
+
"left": null,
|
371 |
+
"margin": null,
|
372 |
+
"max_height": null,
|
373 |
+
"max_width": null,
|
374 |
+
"min_height": null,
|
375 |
+
"min_width": null,
|
376 |
+
"object_fit": null,
|
377 |
+
"object_position": null,
|
378 |
+
"order": null,
|
379 |
+
"overflow": null,
|
380 |
+
"overflow_x": null,
|
381 |
+
"overflow_y": null,
|
382 |
+
"padding": null,
|
383 |
+
"right": null,
|
384 |
+
"top": null,
|
385 |
+
"visibility": null,
|
386 |
+
"width": null
|
387 |
+
}
|
388 |
+
},
|
389 |
+
"5d043f830b7f4981b0597136f1e530ed": {
|
390 |
+
"model_module": "@jupyter-widgets/controls",
|
391 |
+
"model_name": "DescriptionStyleModel",
|
392 |
+
"model_module_version": "1.5.0",
|
393 |
+
"state": {
|
394 |
+
"_model_module": "@jupyter-widgets/controls",
|
395 |
+
"_model_module_version": "1.5.0",
|
396 |
+
"_model_name": "DescriptionStyleModel",
|
397 |
+
"_view_count": null,
|
398 |
+
"_view_module": "@jupyter-widgets/base",
|
399 |
+
"_view_module_version": "1.2.0",
|
400 |
+
"_view_name": "StyleView",
|
401 |
+
"description_width": ""
|
402 |
+
}
|
403 |
+
},
|
404 |
+
"3f1f2f9baab74de890b2213d4846611d": {
|
405 |
+
"model_module": "@jupyter-widgets/base",
|
406 |
+
"model_name": "LayoutModel",
|
407 |
+
"model_module_version": "1.2.0",
|
408 |
+
"state": {
|
409 |
+
"_model_module": "@jupyter-widgets/base",
|
410 |
+
"_model_module_version": "1.2.0",
|
411 |
+
"_model_name": "LayoutModel",
|
412 |
+
"_view_count": null,
|
413 |
+
"_view_module": "@jupyter-widgets/base",
|
414 |
+
"_view_module_version": "1.2.0",
|
415 |
+
"_view_name": "LayoutView",
|
416 |
+
"align_content": null,
|
417 |
+
"align_items": null,
|
418 |
+
"align_self": null,
|
419 |
+
"border": null,
|
420 |
+
"bottom": null,
|
421 |
+
"display": null,
|
422 |
+
"flex": null,
|
423 |
+
"flex_flow": null,
|
424 |
+
"grid_area": null,
|
425 |
+
"grid_auto_columns": null,
|
426 |
+
"grid_auto_flow": null,
|
427 |
+
"grid_auto_rows": null,
|
428 |
+
"grid_column": null,
|
429 |
+
"grid_gap": null,
|
430 |
+
"grid_row": null,
|
431 |
+
"grid_template_areas": null,
|
432 |
+
"grid_template_columns": null,
|
433 |
+
"grid_template_rows": null,
|
434 |
+
"height": null,
|
435 |
+
"justify_content": null,
|
436 |
+
"justify_items": null,
|
437 |
+
"left": null,
|
438 |
+
"margin": null,
|
439 |
+
"max_height": null,
|
440 |
+
"max_width": null,
|
441 |
+
"min_height": null,
|
442 |
+
"min_width": null,
|
443 |
+
"object_fit": null,
|
444 |
+
"object_position": null,
|
445 |
+
"order": null,
|
446 |
+
"overflow": null,
|
447 |
+
"overflow_x": null,
|
448 |
+
"overflow_y": null,
|
449 |
+
"padding": null,
|
450 |
+
"right": null,
|
451 |
+
"top": null,
|
452 |
+
"visibility": null,
|
453 |
+
"width": null
|
454 |
+
}
|
455 |
+
},
|
456 |
+
"f3f7d114085d477692c4933876b8b5cc": {
|
457 |
+
"model_module": "@jupyter-widgets/controls",
|
458 |
+
"model_name": "ButtonStyleModel",
|
459 |
+
"model_module_version": "1.5.0",
|
460 |
+
"state": {
|
461 |
+
"_model_module": "@jupyter-widgets/controls",
|
462 |
+
"_model_module_version": "1.5.0",
|
463 |
+
"_model_name": "ButtonStyleModel",
|
464 |
+
"_view_count": null,
|
465 |
+
"_view_module": "@jupyter-widgets/base",
|
466 |
+
"_view_module_version": "1.2.0",
|
467 |
+
"_view_name": "StyleView",
|
468 |
+
"button_color": null,
|
469 |
+
"font_weight": ""
|
470 |
+
}
|
471 |
+
},
|
472 |
+
"a2ceb52d59634de6bf64f41b6f3da3a4": {
|
473 |
+
"model_module": "@jupyter-widgets/base",
|
474 |
+
"model_name": "LayoutModel",
|
475 |
+
"model_module_version": "1.2.0",
|
476 |
+
"state": {
|
477 |
+
"_model_module": "@jupyter-widgets/base",
|
478 |
+
"_model_module_version": "1.2.0",
|
479 |
+
"_model_name": "LayoutModel",
|
480 |
+
"_view_count": null,
|
481 |
+
"_view_module": "@jupyter-widgets/base",
|
482 |
+
"_view_module_version": "1.2.0",
|
483 |
+
"_view_name": "LayoutView",
|
484 |
+
"align_content": null,
|
485 |
+
"align_items": null,
|
486 |
+
"align_self": null,
|
487 |
+
"border": null,
|
488 |
+
"bottom": null,
|
489 |
+
"display": null,
|
490 |
+
"flex": null,
|
491 |
+
"flex_flow": null,
|
492 |
+
"grid_area": null,
|
493 |
+
"grid_auto_columns": null,
|
494 |
+
"grid_auto_flow": null,
|
495 |
+
"grid_auto_rows": null,
|
496 |
+
"grid_column": null,
|
497 |
+
"grid_gap": null,
|
498 |
+
"grid_row": null,
|
499 |
+
"grid_template_areas": null,
|
500 |
+
"grid_template_columns": null,
|
501 |
+
"grid_template_rows": null,
|
502 |
+
"height": null,
|
503 |
+
"justify_content": null,
|
504 |
+
"justify_items": null,
|
505 |
+
"left": null,
|
506 |
+
"margin": null,
|
507 |
+
"max_height": null,
|
508 |
+
"max_width": null,
|
509 |
+
"min_height": null,
|
510 |
+
"min_width": null,
|
511 |
+
"object_fit": null,
|
512 |
+
"object_position": null,
|
513 |
+
"order": null,
|
514 |
+
"overflow": null,
|
515 |
+
"overflow_x": null,
|
516 |
+
"overflow_y": null,
|
517 |
+
"padding": null,
|
518 |
+
"right": null,
|
519 |
+
"top": null,
|
520 |
+
"visibility": null,
|
521 |
+
"width": null
|
522 |
+
}
|
523 |
+
},
|
524 |
+
"60dc766ea8734e3baa5df22506d8fcf6": {
|
525 |
+
"model_module": "@jupyter-widgets/controls",
|
526 |
+
"model_name": "DescriptionStyleModel",
|
527 |
+
"model_module_version": "1.5.0",
|
528 |
+
"state": {
|
529 |
+
"_model_module": "@jupyter-widgets/controls",
|
530 |
+
"_model_module_version": "1.5.0",
|
531 |
+
"_model_name": "DescriptionStyleModel",
|
532 |
+
"_view_count": null,
|
533 |
+
"_view_module": "@jupyter-widgets/base",
|
534 |
+
"_view_module_version": "1.2.0",
|
535 |
+
"_view_name": "StyleView",
|
536 |
+
"description_width": ""
|
537 |
+
}
|
538 |
+
},
|
539 |
+
"ca18786f952c4f3cbdb34b9a4ae5692e": {
|
540 |
+
"model_module": "@jupyter-widgets/controls",
|
541 |
+
"model_name": "LabelModel",
|
542 |
+
"model_module_version": "1.5.0",
|
543 |
+
"state": {
|
544 |
+
"_dom_classes": [],
|
545 |
+
"_model_module": "@jupyter-widgets/controls",
|
546 |
+
"_model_module_version": "1.5.0",
|
547 |
+
"_model_name": "LabelModel",
|
548 |
+
"_view_count": null,
|
549 |
+
"_view_module": "@jupyter-widgets/controls",
|
550 |
+
"_view_module_version": "1.5.0",
|
551 |
+
"_view_name": "LabelView",
|
552 |
+
"description": "",
|
553 |
+
"description_tooltip": null,
|
554 |
+
"layout": "IPY_MODEL_2728eea9f200454d9dc5454385c963a2",
|
555 |
+
"placeholder": "",
|
556 |
+
"style": "IPY_MODEL_109c14c8f5814ecb92f95409e349cfaf",
|
557 |
+
"value": "Connecting..."
|
558 |
+
}
|
559 |
+
},
|
560 |
+
"2728eea9f200454d9dc5454385c963a2": {
|
561 |
+
"model_module": "@jupyter-widgets/base",
|
562 |
+
"model_name": "LayoutModel",
|
563 |
+
"model_module_version": "1.2.0",
|
564 |
+
"state": {
|
565 |
+
"_model_module": "@jupyter-widgets/base",
|
566 |
+
"_model_module_version": "1.2.0",
|
567 |
+
"_model_name": "LayoutModel",
|
568 |
+
"_view_count": null,
|
569 |
+
"_view_module": "@jupyter-widgets/base",
|
570 |
+
"_view_module_version": "1.2.0",
|
571 |
+
"_view_name": "LayoutView",
|
572 |
+
"align_content": null,
|
573 |
+
"align_items": null,
|
574 |
+
"align_self": null,
|
575 |
+
"border": null,
|
576 |
+
"bottom": null,
|
577 |
+
"display": null,
|
578 |
+
"flex": null,
|
579 |
+
"flex_flow": null,
|
580 |
+
"grid_area": null,
|
581 |
+
"grid_auto_columns": null,
|
582 |
+
"grid_auto_flow": null,
|
583 |
+
"grid_auto_rows": null,
|
584 |
+
"grid_column": null,
|
585 |
+
"grid_gap": null,
|
586 |
+
"grid_row": null,
|
587 |
+
"grid_template_areas": null,
|
588 |
+
"grid_template_columns": null,
|
589 |
+
"grid_template_rows": null,
|
590 |
+
"height": null,
|
591 |
+
"justify_content": null,
|
592 |
+
"justify_items": null,
|
593 |
+
"left": null,
|
594 |
+
"margin": null,
|
595 |
+
"max_height": null,
|
596 |
+
"max_width": null,
|
597 |
+
"min_height": null,
|
598 |
+
"min_width": null,
|
599 |
+
"object_fit": null,
|
600 |
+
"object_position": null,
|
601 |
+
"order": null,
|
602 |
+
"overflow": null,
|
603 |
+
"overflow_x": null,
|
604 |
+
"overflow_y": null,
|
605 |
+
"padding": null,
|
606 |
+
"right": null,
|
607 |
+
"top": null,
|
608 |
+
"visibility": null,
|
609 |
+
"width": null
|
610 |
+
}
|
611 |
+
},
|
612 |
+
"109c14c8f5814ecb92f95409e349cfaf": {
|
613 |
+
"model_module": "@jupyter-widgets/controls",
|
614 |
+
"model_name": "DescriptionStyleModel",
|
615 |
+
"model_module_version": "1.5.0",
|
616 |
+
"state": {
|
617 |
+
"_model_module": "@jupyter-widgets/controls",
|
618 |
+
"_model_module_version": "1.5.0",
|
619 |
+
"_model_name": "DescriptionStyleModel",
|
620 |
+
"_view_count": null,
|
621 |
+
"_view_module": "@jupyter-widgets/base",
|
622 |
+
"_view_module_version": "1.2.0",
|
623 |
+
"_view_name": "StyleView",
|
624 |
+
"description_width": ""
|
625 |
+
}
|
626 |
+
},
|
627 |
+
"c2463a94b1fb44fa8196e7b61636c3b7": {
|
628 |
+
"model_module": "@jupyter-widgets/controls",
|
629 |
+
"model_name": "LabelModel",
|
630 |
+
"model_module_version": "1.5.0",
|
631 |
+
"state": {
|
632 |
+
"_dom_classes": [],
|
633 |
+
"_model_module": "@jupyter-widgets/controls",
|
634 |
+
"_model_module_version": "1.5.0",
|
635 |
+
"_model_name": "LabelModel",
|
636 |
+
"_view_count": null,
|
637 |
+
"_view_module": "@jupyter-widgets/controls",
|
638 |
+
"_view_module_version": "1.5.0",
|
639 |
+
"_view_name": "LabelView",
|
640 |
+
"description": "",
|
641 |
+
"description_tooltip": null,
|
642 |
+
"layout": "IPY_MODEL_973a3f8b019c47e5b96cdb867ec5bba2",
|
643 |
+
"placeholder": "",
|
644 |
+
"style": "IPY_MODEL_d327dc625f514fb3977ac2949f092cb4",
|
645 |
+
"value": "Token is valid (permission: write)."
|
646 |
+
}
|
647 |
+
},
|
648 |
+
"3040b325f55949fdbdc4caf75e9cd618": {
|
649 |
+
"model_module": "@jupyter-widgets/controls",
|
650 |
+
"model_name": "LabelModel",
|
651 |
+
"model_module_version": "1.5.0",
|
652 |
+
"state": {
|
653 |
+
"_dom_classes": [],
|
654 |
+
"_model_module": "@jupyter-widgets/controls",
|
655 |
+
"_model_module_version": "1.5.0",
|
656 |
+
"_model_name": "LabelModel",
|
657 |
+
"_view_count": null,
|
658 |
+
"_view_module": "@jupyter-widgets/controls",
|
659 |
+
"_view_module_version": "1.5.0",
|
660 |
+
"_view_name": "LabelView",
|
661 |
+
"description": "",
|
662 |
+
"description_tooltip": null,
|
663 |
+
"layout": "IPY_MODEL_f147b05bc86e4aaabcac45e441ad23ea",
|
664 |
+
"placeholder": "",
|
665 |
+
"style": "IPY_MODEL_4411d82338c244d8aa5a130356f61110",
|
666 |
+
"value": "Your token has been saved in your configured git credential helpers (store)."
|
667 |
+
}
|
668 |
+
},
|
669 |
+
"d9de6537b056464baa3dde45e81bbd72": {
|
670 |
+
"model_module": "@jupyter-widgets/controls",
|
671 |
+
"model_name": "LabelModel",
|
672 |
+
"model_module_version": "1.5.0",
|
673 |
+
"state": {
|
674 |
+
"_dom_classes": [],
|
675 |
+
"_model_module": "@jupyter-widgets/controls",
|
676 |
+
"_model_module_version": "1.5.0",
|
677 |
+
"_model_name": "LabelModel",
|
678 |
+
"_view_count": null,
|
679 |
+
"_view_module": "@jupyter-widgets/controls",
|
680 |
+
"_view_module_version": "1.5.0",
|
681 |
+
"_view_name": "LabelView",
|
682 |
+
"description": "",
|
683 |
+
"description_tooltip": null,
|
684 |
+
"layout": "IPY_MODEL_f6a31775093449928d7b6e5306ff0bc7",
|
685 |
+
"placeholder": "",
|
686 |
+
"style": "IPY_MODEL_2ca22edaacc6426b886f554090b2c719",
|
687 |
+
"value": "Your token has been saved to /root/.cache/huggingface/token"
|
688 |
+
}
|
689 |
+
},
|
690 |
+
"dc8c33db5e814578a4aa9355132e132a": {
|
691 |
+
"model_module": "@jupyter-widgets/controls",
|
692 |
+
"model_name": "LabelModel",
|
693 |
+
"model_module_version": "1.5.0",
|
694 |
+
"state": {
|
695 |
+
"_dom_classes": [],
|
696 |
+
"_model_module": "@jupyter-widgets/controls",
|
697 |
+
"_model_module_version": "1.5.0",
|
698 |
+
"_model_name": "LabelModel",
|
699 |
+
"_view_count": null,
|
700 |
+
"_view_module": "@jupyter-widgets/controls",
|
701 |
+
"_view_module_version": "1.5.0",
|
702 |
+
"_view_name": "LabelView",
|
703 |
+
"description": "",
|
704 |
+
"description_tooltip": null,
|
705 |
+
"layout": "IPY_MODEL_626b5f225cee422da0de229fb9ac4622",
|
706 |
+
"placeholder": "",
|
707 |
+
"style": "IPY_MODEL_8c87840632404771a42d21d251deae1e",
|
708 |
+
"value": "Login successful"
|
709 |
+
}
|
710 |
+
},
|
711 |
+
"973a3f8b019c47e5b96cdb867ec5bba2": {
|
712 |
+
"model_module": "@jupyter-widgets/base",
|
713 |
+
"model_name": "LayoutModel",
|
714 |
+
"model_module_version": "1.2.0",
|
715 |
+
"state": {
|
716 |
+
"_model_module": "@jupyter-widgets/base",
|
717 |
+
"_model_module_version": "1.2.0",
|
718 |
+
"_model_name": "LayoutModel",
|
719 |
+
"_view_count": null,
|
720 |
+
"_view_module": "@jupyter-widgets/base",
|
721 |
+
"_view_module_version": "1.2.0",
|
722 |
+
"_view_name": "LayoutView",
|
723 |
+
"align_content": null,
|
724 |
+
"align_items": null,
|
725 |
+
"align_self": null,
|
726 |
+
"border": null,
|
727 |
+
"bottom": null,
|
728 |
+
"display": null,
|
729 |
+
"flex": null,
|
730 |
+
"flex_flow": null,
|
731 |
+
"grid_area": null,
|
732 |
+
"grid_auto_columns": null,
|
733 |
+
"grid_auto_flow": null,
|
734 |
+
"grid_auto_rows": null,
|
735 |
+
"grid_column": null,
|
736 |
+
"grid_gap": null,
|
737 |
+
"grid_row": null,
|
738 |
+
"grid_template_areas": null,
|
739 |
+
"grid_template_columns": null,
|
740 |
+
"grid_template_rows": null,
|
741 |
+
"height": null,
|
742 |
+
"justify_content": null,
|
743 |
+
"justify_items": null,
|
744 |
+
"left": null,
|
745 |
+
"margin": null,
|
746 |
+
"max_height": null,
|
747 |
+
"max_width": null,
|
748 |
+
"min_height": null,
|
749 |
+
"min_width": null,
|
750 |
+
"object_fit": null,
|
751 |
+
"object_position": null,
|
752 |
+
"order": null,
|
753 |
+
"overflow": null,
|
754 |
+
"overflow_x": null,
|
755 |
+
"overflow_y": null,
|
756 |
+
"padding": null,
|
757 |
+
"right": null,
|
758 |
+
"top": null,
|
759 |
+
"visibility": null,
|
760 |
+
"width": null
|
761 |
+
}
|
762 |
+
},
|
763 |
+
"d327dc625f514fb3977ac2949f092cb4": {
|
764 |
+
"model_module": "@jupyter-widgets/controls",
|
765 |
+
"model_name": "DescriptionStyleModel",
|
766 |
+
"model_module_version": "1.5.0",
|
767 |
+
"state": {
|
768 |
+
"_model_module": "@jupyter-widgets/controls",
|
769 |
+
"_model_module_version": "1.5.0",
|
770 |
+
"_model_name": "DescriptionStyleModel",
|
771 |
+
"_view_count": null,
|
772 |
+
"_view_module": "@jupyter-widgets/base",
|
773 |
+
"_view_module_version": "1.2.0",
|
774 |
+
"_view_name": "StyleView",
|
775 |
+
"description_width": ""
|
776 |
+
}
|
777 |
+
},
|
778 |
+
"f147b05bc86e4aaabcac45e441ad23ea": {
|
779 |
+
"model_module": "@jupyter-widgets/base",
|
780 |
+
"model_name": "LayoutModel",
|
781 |
+
"model_module_version": "1.2.0",
|
782 |
+
"state": {
|
783 |
+
"_model_module": "@jupyter-widgets/base",
|
784 |
+
"_model_module_version": "1.2.0",
|
785 |
+
"_model_name": "LayoutModel",
|
786 |
+
"_view_count": null,
|
787 |
+
"_view_module": "@jupyter-widgets/base",
|
788 |
+
"_view_module_version": "1.2.0",
|
789 |
+
"_view_name": "LayoutView",
|
790 |
+
"align_content": null,
|
791 |
+
"align_items": null,
|
792 |
+
"align_self": null,
|
793 |
+
"border": null,
|
794 |
+
"bottom": null,
|
795 |
+
"display": null,
|
796 |
+
"flex": null,
|
797 |
+
"flex_flow": null,
|
798 |
+
"grid_area": null,
|
799 |
+
"grid_auto_columns": null,
|
800 |
+
"grid_auto_flow": null,
|
801 |
+
"grid_auto_rows": null,
|
802 |
+
"grid_column": null,
|
803 |
+
"grid_gap": null,
|
804 |
+
"grid_row": null,
|
805 |
+
"grid_template_areas": null,
|
806 |
+
"grid_template_columns": null,
|
807 |
+
"grid_template_rows": null,
|
808 |
+
"height": null,
|
809 |
+
"justify_content": null,
|
810 |
+
"justify_items": null,
|
811 |
+
"left": null,
|
812 |
+
"margin": null,
|
813 |
+
"max_height": null,
|
814 |
+
"max_width": null,
|
815 |
+
"min_height": null,
|
816 |
+
"min_width": null,
|
817 |
+
"object_fit": null,
|
818 |
+
"object_position": null,
|
819 |
+
"order": null,
|
820 |
+
"overflow": null,
|
821 |
+
"overflow_x": null,
|
822 |
+
"overflow_y": null,
|
823 |
+
"padding": null,
|
824 |
+
"right": null,
|
825 |
+
"top": null,
|
826 |
+
"visibility": null,
|
827 |
+
"width": null
|
828 |
+
}
|
829 |
+
},
|
830 |
+
"4411d82338c244d8aa5a130356f61110": {
|
831 |
+
"model_module": "@jupyter-widgets/controls",
|
832 |
+
"model_name": "DescriptionStyleModel",
|
833 |
+
"model_module_version": "1.5.0",
|
834 |
+
"state": {
|
835 |
+
"_model_module": "@jupyter-widgets/controls",
|
836 |
+
"_model_module_version": "1.5.0",
|
837 |
+
"_model_name": "DescriptionStyleModel",
|
838 |
+
"_view_count": null,
|
839 |
+
"_view_module": "@jupyter-widgets/base",
|
840 |
+
"_view_module_version": "1.2.0",
|
841 |
+
"_view_name": "StyleView",
|
842 |
+
"description_width": ""
|
843 |
+
}
|
844 |
+
},
|
845 |
+
"f6a31775093449928d7b6e5306ff0bc7": {
|
846 |
+
"model_module": "@jupyter-widgets/base",
|
847 |
+
"model_name": "LayoutModel",
|
848 |
+
"model_module_version": "1.2.0",
|
849 |
+
"state": {
|
850 |
+
"_model_module": "@jupyter-widgets/base",
|
851 |
+
"_model_module_version": "1.2.0",
|
852 |
+
"_model_name": "LayoutModel",
|
853 |
+
"_view_count": null,
|
854 |
+
"_view_module": "@jupyter-widgets/base",
|
855 |
+
"_view_module_version": "1.2.0",
|
856 |
+
"_view_name": "LayoutView",
|
857 |
+
"align_content": null,
|
858 |
+
"align_items": null,
|
859 |
+
"align_self": null,
|
860 |
+
"border": null,
|
861 |
+
"bottom": null,
|
862 |
+
"display": null,
|
863 |
+
"flex": null,
|
864 |
+
"flex_flow": null,
|
865 |
+
"grid_area": null,
|
866 |
+
"grid_auto_columns": null,
|
867 |
+
"grid_auto_flow": null,
|
868 |
+
"grid_auto_rows": null,
|
869 |
+
"grid_column": null,
|
870 |
+
"grid_gap": null,
|
871 |
+
"grid_row": null,
|
872 |
+
"grid_template_areas": null,
|
873 |
+
"grid_template_columns": null,
|
874 |
+
"grid_template_rows": null,
|
875 |
+
"height": null,
|
876 |
+
"justify_content": null,
|
877 |
+
"justify_items": null,
|
878 |
+
"left": null,
|
879 |
+
"margin": null,
|
880 |
+
"max_height": null,
|
881 |
+
"max_width": null,
|
882 |
+
"min_height": null,
|
883 |
+
"min_width": null,
|
884 |
+
"object_fit": null,
|
885 |
+
"object_position": null,
|
886 |
+
"order": null,
|
887 |
+
"overflow": null,
|
888 |
+
"overflow_x": null,
|
889 |
+
"overflow_y": null,
|
890 |
+
"padding": null,
|
891 |
+
"right": null,
|
892 |
+
"top": null,
|
893 |
+
"visibility": null,
|
894 |
+
"width": null
|
895 |
+
}
|
896 |
+
},
|
897 |
+
"2ca22edaacc6426b886f554090b2c719": {
|
898 |
+
"model_module": "@jupyter-widgets/controls",
|
899 |
+
"model_name": "DescriptionStyleModel",
|
900 |
+
"model_module_version": "1.5.0",
|
901 |
+
"state": {
|
902 |
+
"_model_module": "@jupyter-widgets/controls",
|
903 |
+
"_model_module_version": "1.5.0",
|
904 |
+
"_model_name": "DescriptionStyleModel",
|
905 |
+
"_view_count": null,
|
906 |
+
"_view_module": "@jupyter-widgets/base",
|
907 |
+
"_view_module_version": "1.2.0",
|
908 |
+
"_view_name": "StyleView",
|
909 |
+
"description_width": ""
|
910 |
+
}
|
911 |
+
},
|
912 |
+
"626b5f225cee422da0de229fb9ac4622": {
|
913 |
+
"model_module": "@jupyter-widgets/base",
|
914 |
+
"model_name": "LayoutModel",
|
915 |
+
"model_module_version": "1.2.0",
|
916 |
+
"state": {
|
917 |
+
"_model_module": "@jupyter-widgets/base",
|
918 |
+
"_model_module_version": "1.2.0",
|
919 |
+
"_model_name": "LayoutModel",
|
920 |
+
"_view_count": null,
|
921 |
+
"_view_module": "@jupyter-widgets/base",
|
922 |
+
"_view_module_version": "1.2.0",
|
923 |
+
"_view_name": "LayoutView",
|
924 |
+
"align_content": null,
|
925 |
+
"align_items": null,
|
926 |
+
"align_self": null,
|
927 |
+
"border": null,
|
928 |
+
"bottom": null,
|
929 |
+
"display": null,
|
930 |
+
"flex": null,
|
931 |
+
"flex_flow": null,
|
932 |
+
"grid_area": null,
|
933 |
+
"grid_auto_columns": null,
|
934 |
+
"grid_auto_flow": null,
|
935 |
+
"grid_auto_rows": null,
|
936 |
+
"grid_column": null,
|
937 |
+
"grid_gap": null,
|
938 |
+
"grid_row": null,
|
939 |
+
"grid_template_areas": null,
|
940 |
+
"grid_template_columns": null,
|
941 |
+
"grid_template_rows": null,
|
942 |
+
"height": null,
|
943 |
+
"justify_content": null,
|
944 |
+
"justify_items": null,
|
945 |
+
"left": null,
|
946 |
+
"margin": null,
|
947 |
+
"max_height": null,
|
948 |
+
"max_width": null,
|
949 |
+
"min_height": null,
|
950 |
+
"min_width": null,
|
951 |
+
"object_fit": null,
|
952 |
+
"object_position": null,
|
953 |
+
"order": null,
|
954 |
+
"overflow": null,
|
955 |
+
"overflow_x": null,
|
956 |
+
"overflow_y": null,
|
957 |
+
"padding": null,
|
958 |
+
"right": null,
|
959 |
+
"top": null,
|
960 |
+
"visibility": null,
|
961 |
+
"width": null
|
962 |
+
}
|
963 |
+
},
|
964 |
+
"8c87840632404771a42d21d251deae1e": {
|
965 |
+
"model_module": "@jupyter-widgets/controls",
|
966 |
+
"model_name": "DescriptionStyleModel",
|
967 |
+
"model_module_version": "1.5.0",
|
968 |
+
"state": {
|
969 |
+
"_model_module": "@jupyter-widgets/controls",
|
970 |
+
"_model_module_version": "1.5.0",
|
971 |
+
"_model_name": "DescriptionStyleModel",
|
972 |
+
"_view_count": null,
|
973 |
+
"_view_module": "@jupyter-widgets/base",
|
974 |
+
"_view_module_version": "1.2.0",
|
975 |
+
"_view_name": "StyleView",
|
976 |
+
"description_width": ""
|
977 |
+
}
|
978 |
+
}
|
979 |
+
}
|
980 |
+
}
|
981 |
+
},
|
982 |
+
"cells": [
|
983 |
+
{
|
984 |
+
"cell_type": "markdown",
|
985 |
+
"source": [
|
986 |
+
"# WiDS 2023: Language Translation Model\n",
|
987 |
+
"This Jupyter notebook contains the code for the language translation model using a pre-trained Transformer based Neural Networks and NLP from Hugging face 🤗. It includes steps for fine-tuning the model on a specific dataset, preprocessing the data, training, and evaluating the model, ultimately providing a user interactive interface for language translation using Gradio."
|
988 |
+
],
|
989 |
+
"metadata": {
|
990 |
+
"id": "jd4hr9XpxEAT"
|
991 |
+
}
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"cell_type": "markdown",
|
995 |
+
"source": [
|
996 |
+
"Initially, we establish a connection to the GPU to optimize the execution of our program, leveraging its capacity to efficiently process tasks involving substantial datasets."
|
997 |
+
],
|
998 |
+
"metadata": {
|
999 |
+
"id": "Tn-rAGS7zIPo"
|
1000 |
+
}
|
1001 |
+
},
|
1002 |
+
{
|
1003 |
+
"cell_type": "code",
|
1004 |
+
"source": [
|
1005 |
+
"#checking whether GPU is working or not\n",
|
1006 |
+
"!nvidia-smi"
|
1007 |
+
],
|
1008 |
+
"metadata": {
|
1009 |
+
"colab": {
|
1010 |
+
"base_uri": "https://localhost:8080/"
|
1011 |
+
},
|
1012 |
+
"id": "KrFSyiSTzGAu",
|
1013 |
+
"outputId": "6655d2e5-8c06-45df-9ebc-579726434678"
|
1014 |
+
},
|
1015 |
+
"execution_count": 1,
|
1016 |
+
"outputs": [
|
1017 |
+
{
|
1018 |
+
"output_type": "stream",
|
1019 |
+
"name": "stdout",
|
1020 |
+
"text": [
|
1021 |
+
"Sat Jan 13 08:47:46 2024 \n",
|
1022 |
+
"+---------------------------------------------------------------------------------------+\n",
|
1023 |
+
"| NVIDIA-SMI 535.104.05 Driver Version: 535.104.05 CUDA Version: 12.2 |\n",
|
1024 |
+
"|-----------------------------------------+----------------------+----------------------+\n",
|
1025 |
+
"| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |\n",
|
1026 |
+
"| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |\n",
|
1027 |
+
"| | | MIG M. |\n",
|
1028 |
+
"|=========================================+======================+======================|\n",
|
1029 |
+
"| 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 |\n",
|
1030 |
+
"| N/A 74C P8 13W / 70W | 0MiB / 15360MiB | 0% Default |\n",
|
1031 |
+
"| | | N/A |\n",
|
1032 |
+
"+-----------------------------------------+----------------------+----------------------+\n",
|
1033 |
+
" \n",
|
1034 |
+
"+---------------------------------------------------------------------------------------+\n",
|
1035 |
+
"| Processes: |\n",
|
1036 |
+
"| GPU GI CI PID Type Process name GPU Memory |\n",
|
1037 |
+
"| ID ID Usage |\n",
|
1038 |
+
"|=======================================================================================|\n",
|
1039 |
+
"| No running processes found |\n",
|
1040 |
+
"+---------------------------------------------------------------------------------------+\n"
|
1041 |
+
]
|
1042 |
+
}
|
1043 |
+
]
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"cell_type": "code",
|
1047 |
+
"source": [
|
1048 |
+
"#installing all the necessary libraries\n",
|
1049 |
+
"! pip install -q transformers accelerate sentencepiece gradio datasets evaluate sacrebleu"
|
1050 |
+
],
|
1051 |
+
"metadata": {
|
1052 |
+
"id": "1i5ye3v4zpOM"
|
1053 |
+
},
|
1054 |
+
"execution_count": 2,
|
1055 |
+
"outputs": []
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"cell_type": "markdown",
|
1059 |
+
"source": [
|
1060 |
+
"Importing all the necessary libaries and module."
|
1061 |
+
],
|
1062 |
+
"metadata": {
|
1063 |
+
"id": "2QCou91X0DcV"
|
1064 |
+
}
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"cell_type": "code",
|
1068 |
+
"source": [
|
1069 |
+
"import evaluate\n",
|
1070 |
+
"import numpy as np\n",
|
1071 |
+
"from datasets import load_dataset\n",
|
1072 |
+
"from sklearn.model_selection import train_test_split\n",
|
1073 |
+
"from transformers import pipeline\n",
|
1074 |
+
"from transformers import AutoTokenizer\n",
|
1075 |
+
"from transformers import AutoModelForSeq2SeqLM\n",
|
1076 |
+
"from transformers import DataCollatorForSeq2Seq\n",
|
1077 |
+
"from transformers import Seq2SeqTrainingArguments\n",
|
1078 |
+
"from transformers import Seq2SeqTrainer\n",
|
1079 |
+
"from huggingface_hub import notebook_login"
|
1080 |
+
],
|
1081 |
+
"metadata": {
|
1082 |
+
"id": "jI3MBl6R81Dq"
|
1083 |
+
},
|
1084 |
+
"execution_count": 3,
|
1085 |
+
"outputs": []
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"cell_type": "markdown",
|
1089 |
+
"source": [
|
1090 |
+
"We download the \"kde4\" dataset from Hugging Face, a curated dataset designed for language translation. It's essential to specify the two languages involved in the translation process when obtaining this dataset."
|
1091 |
+
],
|
1092 |
+
"metadata": {
|
1093 |
+
"id": "AVnEuqQdXish"
|
1094 |
+
}
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"cell_type": "code",
|
1098 |
+
"source": [
|
1099 |
+
"raw_datasets = load_dataset(\"kde4\", lang1=\"en\", lang2=\"fr\")\n",
|
1100 |
+
"raw_datasets"
|
1101 |
+
],
|
1102 |
+
"metadata": {
|
1103 |
+
"colab": {
|
1104 |
+
"base_uri": "https://localhost:8080/"
|
1105 |
+
},
|
1106 |
+
"id": "0bazUZj5zvr8",
|
1107 |
+
"outputId": "d94cbfac-9410-4e8f-9145-0245ee86f920"
|
1108 |
+
},
|
1109 |
+
"execution_count": 4,
|
1110 |
+
"outputs": [
|
1111 |
+
{
|
1112 |
+
"output_type": "stream",
|
1113 |
+
"name": "stderr",
|
1114 |
+
"text": [
|
1115 |
+
"/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:88: UserWarning: \n",
|
1116 |
+
"The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
|
1117 |
+
"To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
|
1118 |
+
"You will be able to reuse this secret in all of your notebooks.\n",
|
1119 |
+
"Please note that authentication is recommended but still optional to access public models or datasets.\n",
|
1120 |
+
" warnings.warn(\n",
|
1121 |
+
"/usr/local/lib/python3.10/dist-packages/datasets/load.py:1429: FutureWarning: The repository for kde4 contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/kde4\n",
|
1122 |
+
"You can avoid this message in future by passing the argument `trust_remote_code=True`.\n",
|
1123 |
+
"Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`.\n",
|
1124 |
+
" warnings.warn(\n"
|
1125 |
+
]
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"output_type": "execute_result",
|
1129 |
+
"data": {
|
1130 |
+
"text/plain": [
|
1131 |
+
"DatasetDict({\n",
|
1132 |
+
" train: Dataset({\n",
|
1133 |
+
" features: ['id', 'translation'],\n",
|
1134 |
+
" num_rows: 210173\n",
|
1135 |
+
" })\n",
|
1136 |
+
"})"
|
1137 |
+
]
|
1138 |
+
},
|
1139 |
+
"metadata": {},
|
1140 |
+
"execution_count": 4
|
1141 |
+
}
|
1142 |
+
]
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"cell_type": "markdown",
|
1146 |
+
"source": [
|
1147 |
+
"The dataset initially includes only a training set, but for a comprehensive evaluation of our model's performance, we need both training and testing sets. To achieve this, we employ the train_test_split function, effectively partitioning the dataset into distinct training and testing subsets for subsequent model assessment."
|
1148 |
+
],
|
1149 |
+
"metadata": {
|
1150 |
+
"id": "7lCOOlj_0zAD"
|
1151 |
+
}
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"cell_type": "code",
|
1155 |
+
"source": [
|
1156 |
+
"split_datasets= raw_datasets[\"train\"].train_test_split(test_size=0.2, seed=20)\n",
|
1157 |
+
"split_datasets"
|
1158 |
+
],
|
1159 |
+
"metadata": {
|
1160 |
+
"colab": {
|
1161 |
+
"base_uri": "https://localhost:8080/"
|
1162 |
+
},
|
1163 |
+
"id": "qbrDvPe_0x5A",
|
1164 |
+
"outputId": "29166139-473f-4bc0-bc0c-8b39f36f6621"
|
1165 |
+
},
|
1166 |
+
"execution_count": 5,
|
1167 |
+
"outputs": [
|
1168 |
+
{
|
1169 |
+
"output_type": "execute_result",
|
1170 |
+
"data": {
|
1171 |
+
"text/plain": [
|
1172 |
+
"DatasetDict({\n",
|
1173 |
+
" train: Dataset({\n",
|
1174 |
+
" features: ['id', 'translation'],\n",
|
1175 |
+
" num_rows: 168138\n",
|
1176 |
+
" })\n",
|
1177 |
+
" test: Dataset({\n",
|
1178 |
+
" features: ['id', 'translation'],\n",
|
1179 |
+
" num_rows: 42035\n",
|
1180 |
+
" })\n",
|
1181 |
+
"})"
|
1182 |
+
]
|
1183 |
+
},
|
1184 |
+
"metadata": {},
|
1185 |
+
"execution_count": 5
|
1186 |
+
}
|
1187 |
+
]
|
1188 |
+
},
|
1189 |
+
{
|
1190 |
+
"cell_type": "code",
|
1191 |
+
"source": [
|
1192 |
+
"split_datasets[\"train\"][45][\"translation\"]"
|
1193 |
+
],
|
1194 |
+
"metadata": {
|
1195 |
+
"colab": {
|
1196 |
+
"base_uri": "https://localhost:8080/"
|
1197 |
+
},
|
1198 |
+
"id": "5r2LDjjU1pAI",
|
1199 |
+
"outputId": "b2720a51-63b2-4595-d6df-0221ad52d4bf"
|
1200 |
+
},
|
1201 |
+
"execution_count": 6,
|
1202 |
+
"outputs": [
|
1203 |
+
{
|
1204 |
+
"output_type": "execute_result",
|
1205 |
+
"data": {
|
1206 |
+
"text/plain": [
|
1207 |
+
"{'en': 'If you choose the wrong settings here your articles could be unreadable or not sendable at all, so please be careful with these settings.',\n",
|
1208 |
+
" 'fr': 'Si vous choisissez ici les mauvais paramètres, vos articles peuvent devenir illisibles ou vous ne pourrez pas du tout les envoyer. Veuillez donc être prudent avec ces paramètres.'}"
|
1209 |
+
]
|
1210 |
+
},
|
1211 |
+
"metadata": {},
|
1212 |
+
"execution_count": 6
|
1213 |
+
}
|
1214 |
+
]
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"cell_type": "markdown",
|
1218 |
+
"source": [
|
1219 |
+
"We will utilize a pre-trained model available on HuggingFace, specifically the Helsinki-NLP/opus-mt-en-fr model. This model has been pre-trained to facilitate translation tasks from English to French, and we will leverage its capabilities for our language translation project."
|
1220 |
+
],
|
1221 |
+
"metadata": {
|
1222 |
+
"id": "pD-XEIQ41v2I"
|
1223 |
+
}
|
1224 |
+
},
|
1225 |
+
{
|
1226 |
+
"cell_type": "code",
|
1227 |
+
"source": [
|
1228 |
+
"model=\"Helsinki-NLP/opus-mt-en-fr\"\n",
|
1229 |
+
"translator=pipeline(\"translation\", model=model)\n",
|
1230 |
+
"translator(\"If you choose the wrong settings here your articles could be unreadable or not sendable at all, so please be careful with these settings.\")"
|
1231 |
+
],
|
1232 |
+
"metadata": {
|
1233 |
+
"colab": {
|
1234 |
+
"base_uri": "https://localhost:8080/"
|
1235 |
+
},
|
1236 |
+
"id": "5QM1qTcQ2CT4",
|
1237 |
+
"outputId": "1eac8925-afe8-45cd-f263-fc9c900829a0"
|
1238 |
+
},
|
1239 |
+
"execution_count": 7,
|
1240 |
+
"outputs": [
|
1241 |
+
{
|
1242 |
+
"output_type": "stream",
|
1243 |
+
"name": "stderr",
|
1244 |
+
"text": [
|
1245 |
+
"/usr/local/lib/python3.10/dist-packages/transformers/models/marian/tokenization_marian.py:197: UserWarning: Recommended: pip install sacremoses.\n",
|
1246 |
+
" warnings.warn(\"Recommended: pip install sacremoses.\")\n"
|
1247 |
+
]
|
1248 |
+
},
|
1249 |
+
{
|
1250 |
+
"output_type": "execute_result",
|
1251 |
+
"data": {
|
1252 |
+
"text/plain": [
|
1253 |
+
"[{'translation_text': \"Si vous choisissez les mauvais paramètres ici, vos articles pourraient être illisibles ou ne pas être envoyés du tout, alors s'il vous plaît soyez prudent avec ces paramètres.\"}]"
|
1254 |
+
]
|
1255 |
+
},
|
1256 |
+
"metadata": {},
|
1257 |
+
"execution_count": 7
|
1258 |
+
}
|
1259 |
+
]
|
1260 |
+
},
|
1261 |
+
{
|
1262 |
+
"cell_type": "markdown",
|
1263 |
+
"source": [
|
1264 |
+
"The initial results from the pre-trained model demonstrate reasonably accurate translations. Further refinement through fine-tuning is expected to enhance the translation quality even more.\n",
|
1265 |
+
"\n",
|
1266 |
+
"Next, we employ the AutoTokenizer to apply the same tokenization scheme used in the pre-trained model to process the dataset."
|
1267 |
+
],
|
1268 |
+
"metadata": {
|
1269 |
+
"id": "fxdJGwXv2WXt"
|
1270 |
+
}
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"cell_type": "code",
|
1274 |
+
"source": [
|
1275 |
+
"tokenizer=AutoTokenizer.from_pretrained(model, return_tensors=\"pt\")"
|
1276 |
+
],
|
1277 |
+
"metadata": {
|
1278 |
+
"id": "2mh8dVZU2F_f"
|
1279 |
+
},
|
1280 |
+
"execution_count": 8,
|
1281 |
+
"outputs": []
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"cell_type": "code",
|
1285 |
+
"source": [
|
1286 |
+
"def pre_processtext(text):\n",
|
1287 |
+
" inputs=[sample['en'] for sample in text['translation']]\n",
|
1288 |
+
" output=[sample['fr'] for sample in text['translation']]\n",
|
1289 |
+
" tokenized_text=tokenizer(inputs, text_target=output, max_length=128, truncation=True) #(text_target because if not done it will tokenize the french sentence according to english and so the labels will then not be correct)\n",
|
1290 |
+
" return tokenized_text"
|
1291 |
+
],
|
1292 |
+
"metadata": {
|
1293 |
+
"id": "UTXFIklN2fNN"
|
1294 |
+
},
|
1295 |
+
"execution_count": 9,
|
1296 |
+
"outputs": []
|
1297 |
+
},
|
1298 |
+
{
|
1299 |
+
"cell_type": "code",
|
1300 |
+
"source": [
|
1301 |
+
"tokenized_datasets=split_datasets.map(\n",
|
1302 |
+
" pre_processtext,\n",
|
1303 |
+
" batched=True,\n",
|
1304 |
+
" remove_columns=split_datasets[\"train\"].column_names #(to remove extra columns)\n",
|
1305 |
+
")"
|
1306 |
+
],
|
1307 |
+
"metadata": {
|
1308 |
+
"id": "9GZsxyhl2hUV"
|
1309 |
+
},
|
1310 |
+
"execution_count": 10,
|
1311 |
+
"outputs": []
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"cell_type": "markdown",
|
1315 |
+
"source": [
|
1316 |
+
"Following preprocessing, the next step involves selecting a model for training, and in this case, the choice is the AutoModelForSeq2SeqLM."
|
1317 |
+
],
|
1318 |
+
"metadata": {
|
1319 |
+
"id": "jVfmONpU2s2B"
|
1320 |
+
}
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"cell_type": "code",
|
1324 |
+
"source": [
|
1325 |
+
"model_1= AutoModelForSeq2SeqLM.from_pretrained(model)"
|
1326 |
+
],
|
1327 |
+
"metadata": {
|
1328 |
+
"id": "SjRCrAz62k6x"
|
1329 |
+
},
|
1330 |
+
"execution_count": 11,
|
1331 |
+
"outputs": []
|
1332 |
+
},
|
1333 |
+
{
|
1334 |
+
"cell_type": "markdown",
|
1335 |
+
"source": [
|
1336 |
+
"The data collator plays a crucial role, facilitating dynamic padding, appending -100 to short sentences for length matching, and incorporating a start-of-sentence token, visible in decoder_input_ids."
|
1337 |
+
],
|
1338 |
+
"metadata": {
|
1339 |
+
"id": "gClhwDls2wzq"
|
1340 |
+
}
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"cell_type": "code",
|
1344 |
+
"source": [
|
1345 |
+
"data_collator=DataCollatorForSeq2Seq(tokenizer,model=model_1)"
|
1346 |
+
],
|
1347 |
+
"metadata": {
|
1348 |
+
"id": "LwPGf4Xk25Ae"
|
1349 |
+
},
|
1350 |
+
"execution_count": 12,
|
1351 |
+
"outputs": []
|
1352 |
+
},
|
1353 |
+
{
|
1354 |
+
"cell_type": "code",
|
1355 |
+
"source": [
|
1356 |
+
"batch = data_collator([tokenized_datasets[\"train\"][i] for i in range(1,3)])\n",
|
1357 |
+
"print(batch.keys())\n",
|
1358 |
+
"print(batch['labels'])\n",
|
1359 |
+
"batch['decoder_input_ids']"
|
1360 |
+
],
|
1361 |
+
"metadata": {
|
1362 |
+
"colab": {
|
1363 |
+
"base_uri": "https://localhost:8080/"
|
1364 |
+
},
|
1365 |
+
"id": "tw6WhfZ_27aY",
|
1366 |
+
"outputId": "44512578-ae13-435f-84a1-def8441b4e42"
|
1367 |
+
},
|
1368 |
+
"execution_count": 13,
|
1369 |
+
"outputs": [
|
1370 |
+
{
|
1371 |
+
"output_type": "stream",
|
1372 |
+
"name": "stdout",
|
1373 |
+
"text": [
|
1374 |
+
"dict_keys(['input_ids', 'attention_mask', 'labels', 'decoder_input_ids'])\n",
|
1375 |
+
"tensor([[25966, 19, 540, 8, 669, 33355, 24, 11106, 37, 583,\n",
|
1376 |
+
" 583, 9507, 10571, 3, 49, 19015, 3, 49, 1937, 74,\n",
|
1377 |
+
" 2635, 973, 529, 13518, 74, 102, 0],\n",
|
1378 |
+
" [14743, 301, 548, 0, -100, -100, -100, -100, -100, -100,\n",
|
1379 |
+
" -100, -100, -100, -100, -100, -100, -100, -100, -100, -100,\n",
|
1380 |
+
" -100, -100, -100, -100, -100, -100, -100]])\n"
|
1381 |
+
]
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"output_type": "execute_result",
|
1385 |
+
"data": {
|
1386 |
+
"text/plain": [
|
1387 |
+
"tensor([[59513, 25966, 19, 540, 8, 669, 33355, 24, 11106, 37,\n",
|
1388 |
+
" 583, 583, 9507, 10571, 3, 49, 19015, 3, 49, 1937,\n",
|
1389 |
+
" 74, 2635, 973, 529, 13518, 74, 102],\n",
|
1390 |
+
" [59513, 14743, 301, 548, 0, 59513, 59513, 59513, 59513, 59513,\n",
|
1391 |
+
" 59513, 59513, 59513, 59513, 59513, 59513, 59513, 59513, 59513, 59513,\n",
|
1392 |
+
" 59513, 59513, 59513, 59513, 59513, 59513, 59513]])"
|
1393 |
+
]
|
1394 |
+
},
|
1395 |
+
"metadata": {},
|
1396 |
+
"execution_count": 13
|
1397 |
+
}
|
1398 |
+
]
|
1399 |
+
},
|
1400 |
+
{
|
1401 |
+
"cell_type": "markdown",
|
1402 |
+
"source": [
|
1403 |
+
"To assess our model, we employ the sacrebleu score, which focuses on word matching between translations and references. This metric doesn't scrutinize grammatical correctness but penalizes repetitive words not present in the original translation."
|
1404 |
+
],
|
1405 |
+
"metadata": {
|
1406 |
+
"id": "FRw8bbhb3Ed7"
|
1407 |
+
}
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"cell_type": "code",
|
1411 |
+
"source": [
|
1412 |
+
"metric_evaluate= evaluate.load(\"sacrebleu\")"
|
1413 |
+
],
|
1414 |
+
"metadata": {
|
1415 |
+
"id": "ofoatdSx29pn"
|
1416 |
+
},
|
1417 |
+
"execution_count": 14,
|
1418 |
+
"outputs": []
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"cell_type": "code",
|
1422 |
+
"source": [
|
1423 |
+
"def compute_metrics(eval):\n",
|
1424 |
+
" preds, labels= eval\n",
|
1425 |
+
" if isinstance(preds, tuple): #if model returns more than the prediction logits\n",
|
1426 |
+
" preds=preds[0]\n",
|
1427 |
+
" decoded_preds= tokenizer.batch_decode(preds, skip_special_tokens=True)\n",
|
1428 |
+
"\n",
|
1429 |
+
" labels=np.where(labels != -100, labels,tokenizer.pad_token_id) #replacing -100 as we will not be able to decode them\n",
|
1430 |
+
" decoded_labels=tokenizer.batch_decode(labels, skip_special_tokens=True)\n",
|
1431 |
+
"\n",
|
1432 |
+
" decoded_preds=[pred.strip() for pred in decoded_preds]\n",
|
1433 |
+
" decoded_labels=[[label.strip()] for label in decoded_labels] #references should be list of list of sentences\n",
|
1434 |
+
"\n",
|
1435 |
+
" result=metric_evaluate.compute(predictions=decoded_preds, references=decoded_labels)\n",
|
1436 |
+
" return {\"bleu\": result[\"score\"]}"
|
1437 |
+
],
|
1438 |
+
"metadata": {
|
1439 |
+
"id": "73eZuhyD3KSx"
|
1440 |
+
},
|
1441 |
+
"execution_count": 15,
|
1442 |
+
"outputs": []
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"cell_type": "markdown",
|
1446 |
+
"source": [
|
1447 |
+
"To preserve my model, I'll utilize the Hugging Face repository. Let's proceed by logging into the Hugging Face platform."
|
1448 |
+
],
|
1449 |
+
"metadata": {
|
1450 |
+
"id": "Rjiji2Zh3Pd-"
|
1451 |
+
}
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"cell_type": "code",
|
1455 |
+
"source": [
|
1456 |
+
"notebook_login()"
|
1457 |
+
],
|
1458 |
+
"metadata": {
|
1459 |
+
"colab": {
|
1460 |
+
"base_uri": "https://localhost:8080/",
|
1461 |
+
"height": 145,
|
1462 |
+
"referenced_widgets": [
|
1463 |
+
"8c1c7e4a6b8f47149ddca02e551f48a4",
|
1464 |
+
"cdbbba5c25e64371a6678a34e1120dc5",
|
1465 |
+
"70a2cd0297a6456f8a1913c3037a08cd",
|
1466 |
+
"fe8a530f6c91441fb7f48b77e5e673fa",
|
1467 |
+
"9b84de3ec55a4035bf61621f80b0c374",
|
1468 |
+
"0f044626ebca4e21b8e05a45dae2341d",
|
1469 |
+
"022ab2bdb55944858b48891baa414d3c",
|
1470 |
+
"5b364ad09e3d4158a728284f583616b3",
|
1471 |
+
"3e894d7c8a3545c3886c340328d289a2",
|
1472 |
+
"f1b49e3bd1354e24bc911b2d2c7cfc7d",
|
1473 |
+
"0c0fa6b93d144ddb8b9a4084dbaee2a4",
|
1474 |
+
"f8bf8d132d774ab89cf258a7027b3557",
|
1475 |
+
"5d043f830b7f4981b0597136f1e530ed",
|
1476 |
+
"3f1f2f9baab74de890b2213d4846611d",
|
1477 |
+
"f3f7d114085d477692c4933876b8b5cc",
|
1478 |
+
"a2ceb52d59634de6bf64f41b6f3da3a4",
|
1479 |
+
"60dc766ea8734e3baa5df22506d8fcf6",
|
1480 |
+
"ca18786f952c4f3cbdb34b9a4ae5692e",
|
1481 |
+
"2728eea9f200454d9dc5454385c963a2",
|
1482 |
+
"109c14c8f5814ecb92f95409e349cfaf",
|
1483 |
+
"c2463a94b1fb44fa8196e7b61636c3b7",
|
1484 |
+
"3040b325f55949fdbdc4caf75e9cd618",
|
1485 |
+
"d9de6537b056464baa3dde45e81bbd72",
|
1486 |
+
"dc8c33db5e814578a4aa9355132e132a",
|
1487 |
+
"973a3f8b019c47e5b96cdb867ec5bba2",
|
1488 |
+
"d327dc625f514fb3977ac2949f092cb4",
|
1489 |
+
"f147b05bc86e4aaabcac45e441ad23ea",
|
1490 |
+
"4411d82338c244d8aa5a130356f61110",
|
1491 |
+
"f6a31775093449928d7b6e5306ff0bc7",
|
1492 |
+
"2ca22edaacc6426b886f554090b2c719",
|
1493 |
+
"626b5f225cee422da0de229fb9ac4622",
|
1494 |
+
"8c87840632404771a42d21d251deae1e"
|
1495 |
+
]
|
1496 |
+
},
|
1497 |
+
"id": "Rbk3-DTU3OuC",
|
1498 |
+
"outputId": "653cd2e8-4fb9-4495-9fe5-3d99673ac6cd"
|
1499 |
+
},
|
1500 |
+
"execution_count": 16,
|
1501 |
+
"outputs": [
|
1502 |
+
{
|
1503 |
+
"output_type": "display_data",
|
1504 |
+
"data": {
|
1505 |
+
"text/plain": [
|
1506 |
+
"VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
|
1507 |
+
],
|
1508 |
+
"application/vnd.jupyter.widget-view+json": {
|
1509 |
+
"version_major": 2,
|
1510 |
+
"version_minor": 0,
|
1511 |
+
"model_id": "8c1c7e4a6b8f47149ddca02e551f48a4"
|
1512 |
+
}
|
1513 |
+
},
|
1514 |
+
"metadata": {}
|
1515 |
+
}
|
1516 |
+
]
|
1517 |
+
},
|
1518 |
+
{
|
1519 |
+
"cell_type": "markdown",
|
1520 |
+
"source": [
|
1521 |
+
"To fine-tune and train our dataset using a pre-trained model, we'll leverage the Seq2SeqTrainingArguments and Seq2SeqTrainer, configuring the relevant parameters to ensure the model's effectiveness can be assessed."
|
1522 |
+
],
|
1523 |
+
"metadata": {
|
1524 |
+
"id": "HbOell3-3sas"
|
1525 |
+
}
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"cell_type": "code",
|
1529 |
+
"source": [
|
1530 |
+
"arg= Seq2SeqTrainingArguments(\n",
|
1531 |
+
" f\"eng-to-fra-model\",\n",
|
1532 |
+
" evaluation_strategy=\"no\",\n",
|
1533 |
+
" save_strategy=\"epoch\",\n",
|
1534 |
+
" learning_rate=3e-5,\n",
|
1535 |
+
" per_device_train_batch_size=32,\n",
|
1536 |
+
" per_device_eval_batch_size=64,\n",
|
1537 |
+
" weight_decay=0.01,\n",
|
1538 |
+
" save_total_limit=3,\n",
|
1539 |
+
" num_train_epochs=3,\n",
|
1540 |
+
" predict_with_generate=True,\n",
|
1541 |
+
" fp16=True,\n",
|
1542 |
+
" push_to_hub=True #(for saving my model onto huggingface repository)\n",
|
1543 |
+
")"
|
1544 |
+
],
|
1545 |
+
"metadata": {
|
1546 |
+
"id": "q2TnvOTs3YFi"
|
1547 |
+
},
|
1548 |
+
"execution_count": 17,
|
1549 |
+
"outputs": []
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"cell_type": "code",
|
1553 |
+
"source": [
|
1554 |
+
"trainer = Seq2SeqTrainer(\n",
|
1555 |
+
" model=model_1,\n",
|
1556 |
+
" args=arg,\n",
|
1557 |
+
" train_dataset=tokenized_datasets[\"train\"],\n",
|
1558 |
+
" eval_dataset=tokenized_datasets[\"test\"],\n",
|
1559 |
+
" data_collator=data_collator,\n",
|
1560 |
+
" tokenizer=tokenizer,\n",
|
1561 |
+
" compute_metrics=compute_metrics\n",
|
1562 |
+
")"
|
1563 |
+
],
|
1564 |
+
"metadata": {
|
1565 |
+
"id": "ZfCpHJbf3wer"
|
1566 |
+
},
|
1567 |
+
"execution_count": 18,
|
1568 |
+
"outputs": []
|
1569 |
+
},
|
1570 |
+
{
|
1571 |
+
"cell_type": "code",
|
1572 |
+
"source": [
|
1573 |
+
"#training starts form here\n",
|
1574 |
+
"trainer.train()"
|
1575 |
+
],
|
1576 |
+
"metadata": {
|
1577 |
+
"id": "uWTZe5Lg3zZQ",
|
1578 |
+
"colab": {
|
1579 |
+
"base_uri": "https://localhost:8080/",
|
1580 |
+
"height": 1000
|
1581 |
+
},
|
1582 |
+
"outputId": "15725474-e67d-4517-9993-bcf181026b11"
|
1583 |
+
},
|
1584 |
+
"execution_count": 19,
|
1585 |
+
"outputs": [
|
1586 |
+
{
|
1587 |
+
"output_type": "display_data",
|
1588 |
+
"data": {
|
1589 |
+
"text/plain": [
|
1590 |
+
"<IPython.core.display.HTML object>"
|
1591 |
+
],
|
1592 |
+
"text/html": [
|
1593 |
+
"\n",
|
1594 |
+
" <div>\n",
|
1595 |
+
" \n",
|
1596 |
+
" <progress value='15765' max='15765' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
|
1597 |
+
" [15765/15765 49:09, Epoch 3/3]\n",
|
1598 |
+
" </div>\n",
|
1599 |
+
" <table border=\"1\" class=\"dataframe\">\n",
|
1600 |
+
" <thead>\n",
|
1601 |
+
" <tr style=\"text-align: left;\">\n",
|
1602 |
+
" <th>Step</th>\n",
|
1603 |
+
" <th>Training Loss</th>\n",
|
1604 |
+
" </tr>\n",
|
1605 |
+
" </thead>\n",
|
1606 |
+
" <tbody>\n",
|
1607 |
+
" <tr>\n",
|
1608 |
+
" <td>500</td>\n",
|
1609 |
+
" <td>1.365200</td>\n",
|
1610 |
+
" </tr>\n",
|
1611 |
+
" <tr>\n",
|
1612 |
+
" <td>1000</td>\n",
|
1613 |
+
" <td>1.226200</td>\n",
|
1614 |
+
" </tr>\n",
|
1615 |
+
" <tr>\n",
|
1616 |
+
" <td>1500</td>\n",
|
1617 |
+
" <td>1.156000</td>\n",
|
1618 |
+
" </tr>\n",
|
1619 |
+
" <tr>\n",
|
1620 |
+
" <td>2000</td>\n",
|
1621 |
+
" <td>1.108600</td>\n",
|
1622 |
+
" </tr>\n",
|
1623 |
+
" <tr>\n",
|
1624 |
+
" <td>2500</td>\n",
|
1625 |
+
" <td>1.084900</td>\n",
|
1626 |
+
" </tr>\n",
|
1627 |
+
" <tr>\n",
|
1628 |
+
" <td>3000</td>\n",
|
1629 |
+
" <td>1.033100</td>\n",
|
1630 |
+
" </tr>\n",
|
1631 |
+
" <tr>\n",
|
1632 |
+
" <td>3500</td>\n",
|
1633 |
+
" <td>1.020700</td>\n",
|
1634 |
+
" </tr>\n",
|
1635 |
+
" <tr>\n",
|
1636 |
+
" <td>4000</td>\n",
|
1637 |
+
" <td>1.009600</td>\n",
|
1638 |
+
" </tr>\n",
|
1639 |
+
" <tr>\n",
|
1640 |
+
" <td>4500</td>\n",
|
1641 |
+
" <td>0.994900</td>\n",
|
1642 |
+
" </tr>\n",
|
1643 |
+
" <tr>\n",
|
1644 |
+
" <td>5000</td>\n",
|
1645 |
+
" <td>0.972800</td>\n",
|
1646 |
+
" </tr>\n",
|
1647 |
+
" <tr>\n",
|
1648 |
+
" <td>5500</td>\n",
|
1649 |
+
" <td>0.921200</td>\n",
|
1650 |
+
" </tr>\n",
|
1651 |
+
" <tr>\n",
|
1652 |
+
" <td>6000</td>\n",
|
1653 |
+
" <td>0.869000</td>\n",
|
1654 |
+
" </tr>\n",
|
1655 |
+
" <tr>\n",
|
1656 |
+
" <td>6500</td>\n",
|
1657 |
+
" <td>0.847500</td>\n",
|
1658 |
+
" </tr>\n",
|
1659 |
+
" <tr>\n",
|
1660 |
+
" <td>7000</td>\n",
|
1661 |
+
" <td>0.862500</td>\n",
|
1662 |
+
" </tr>\n",
|
1663 |
+
" <tr>\n",
|
1664 |
+
" <td>7500</td>\n",
|
1665 |
+
" <td>0.847000</td>\n",
|
1666 |
+
" </tr>\n",
|
1667 |
+
" <tr>\n",
|
1668 |
+
" <td>8000</td>\n",
|
1669 |
+
" <td>0.845800</td>\n",
|
1670 |
+
" </tr>\n",
|
1671 |
+
" <tr>\n",
|
1672 |
+
" <td>8500</td>\n",
|
1673 |
+
" <td>0.854900</td>\n",
|
1674 |
+
" </tr>\n",
|
1675 |
+
" <tr>\n",
|
1676 |
+
" <td>9000</td>\n",
|
1677 |
+
" <td>0.845700</td>\n",
|
1678 |
+
" </tr>\n",
|
1679 |
+
" <tr>\n",
|
1680 |
+
" <td>9500</td>\n",
|
1681 |
+
" <td>0.847800</td>\n",
|
1682 |
+
" </tr>\n",
|
1683 |
+
" <tr>\n",
|
1684 |
+
" <td>10000</td>\n",
|
1685 |
+
" <td>0.848000</td>\n",
|
1686 |
+
" </tr>\n",
|
1687 |
+
" <tr>\n",
|
1688 |
+
" <td>10500</td>\n",
|
1689 |
+
" <td>0.834000</td>\n",
|
1690 |
+
" </tr>\n",
|
1691 |
+
" <tr>\n",
|
1692 |
+
" <td>11000</td>\n",
|
1693 |
+
" <td>0.762500</td>\n",
|
1694 |
+
" </tr>\n",
|
1695 |
+
" <tr>\n",
|
1696 |
+
" <td>11500</td>\n",
|
1697 |
+
" <td>0.764200</td>\n",
|
1698 |
+
" </tr>\n",
|
1699 |
+
" <tr>\n",
|
1700 |
+
" <td>12000</td>\n",
|
1701 |
+
" <td>0.767400</td>\n",
|
1702 |
+
" </tr>\n",
|
1703 |
+
" <tr>\n",
|
1704 |
+
" <td>12500</td>\n",
|
1705 |
+
" <td>0.765000</td>\n",
|
1706 |
+
" </tr>\n",
|
1707 |
+
" <tr>\n",
|
1708 |
+
" <td>13000</td>\n",
|
1709 |
+
" <td>0.770000</td>\n",
|
1710 |
+
" </tr>\n",
|
1711 |
+
" <tr>\n",
|
1712 |
+
" <td>13500</td>\n",
|
1713 |
+
" <td>0.757100</td>\n",
|
1714 |
+
" </tr>\n",
|
1715 |
+
" <tr>\n",
|
1716 |
+
" <td>14000</td>\n",
|
1717 |
+
" <td>0.756700</td>\n",
|
1718 |
+
" </tr>\n",
|
1719 |
+
" <tr>\n",
|
1720 |
+
" <td>14500</td>\n",
|
1721 |
+
" <td>0.762700</td>\n",
|
1722 |
+
" </tr>\n",
|
1723 |
+
" <tr>\n",
|
1724 |
+
" <td>15000</td>\n",
|
1725 |
+
" <td>0.766800</td>\n",
|
1726 |
+
" </tr>\n",
|
1727 |
+
" <tr>\n",
|
1728 |
+
" <td>15500</td>\n",
|
1729 |
+
" <td>0.751000</td>\n",
|
1730 |
+
" </tr>\n",
|
1731 |
+
" </tbody>\n",
|
1732 |
+
"</table><p>"
|
1733 |
+
]
|
1734 |
+
},
|
1735 |
+
"metadata": {}
|
1736 |
+
},
|
1737 |
+
{
|
1738 |
+
"output_type": "execute_result",
|
1739 |
+
"data": {
|
1740 |
+
"text/plain": [
|
1741 |
+
"TrainOutput(global_step=15765, training_loss=0.9012604572793396, metrics={'train_runtime': 2950.8187, 'train_samples_per_second': 170.94, 'train_steps_per_second': 5.343, 'total_flos': 1.008207288336384e+16, 'train_loss': 0.9012604572793396, 'epoch': 3.0})"
|
1742 |
+
]
|
1743 |
+
},
|
1744 |
+
"metadata": {},
|
1745 |
+
"execution_count": 19
|
1746 |
+
}
|
1747 |
+
]
|
1748 |
+
},
|
1749 |
+
{
|
1750 |
+
"cell_type": "code",
|
1751 |
+
"source": [
|
1752 |
+
"trainer.push_to_hub(tags=\"translation\", commit_message=\"Training complete\") #To save the latest model onto the repository"
|
1753 |
+
],
|
1754 |
+
"metadata": {
|
1755 |
+
"colab": {
|
1756 |
+
"base_uri": "https://localhost:8080/",
|
1757 |
+
"height": 52
|
1758 |
+
},
|
1759 |
+
"id": "TnYcoiFLzU_f",
|
1760 |
+
"outputId": "b4080bed-d2f9-4e91-be88-0ae88d4a325e"
|
1761 |
+
},
|
1762 |
+
"execution_count": 20,
|
1763 |
+
"outputs": [
|
1764 |
+
{
|
1765 |
+
"output_type": "execute_result",
|
1766 |
+
"data": {
|
1767 |
+
"text/plain": [
|
1768 |
+
"CommitInfo(commit_url='https://huggingface.co/rajbhirud/eng-to-fra-model/commit/7dc6032cdedafc309f004b8d65493fbfe40fd5b7', commit_message='Training complete', commit_description='', oid='7dc6032cdedafc309f004b8d65493fbfe40fd5b7', pr_url=None, pr_revision=None, pr_num=None)"
|
1769 |
+
],
|
1770 |
+
"application/vnd.google.colaboratory.intrinsic+json": {
|
1771 |
+
"type": "string"
|
1772 |
+
}
|
1773 |
+
},
|
1774 |
+
"metadata": {},
|
1775 |
+
"execution_count": 20
|
1776 |
+
}
|
1777 |
+
]
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"cell_type": "code",
|
1781 |
+
"source": [
|
1782 |
+
"# we can check the score of our model through the following code\n",
|
1783 |
+
"trainer.evaluate(max_length=128)"
|
1784 |
+
],
|
1785 |
+
"metadata": {
|
1786 |
+
"colab": {
|
1787 |
+
"base_uri": "https://localhost:8080/",
|
1788 |
+
"height": 141
|
1789 |
+
},
|
1790 |
+
"id": "mhf4dB0pzlA_",
|
1791 |
+
"outputId": "f92c5300-8f61-4f04-8a36-62d31028c467"
|
1792 |
+
},
|
1793 |
+
"execution_count": 21,
|
1794 |
+
"outputs": [
|
1795 |
+
{
|
1796 |
+
"output_type": "display_data",
|
1797 |
+
"data": {
|
1798 |
+
"text/plain": [
|
1799 |
+
"<IPython.core.display.HTML object>"
|
1800 |
+
],
|
1801 |
+
"text/html": [
|
1802 |
+
"\n",
|
1803 |
+
" <div>\n",
|
1804 |
+
" \n",
|
1805 |
+
" <progress value='657' max='657' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
|
1806 |
+
" [657/657 45:14]\n",
|
1807 |
+
" </div>\n",
|
1808 |
+
" "
|
1809 |
+
]
|
1810 |
+
},
|
1811 |
+
"metadata": {}
|
1812 |
+
},
|
1813 |
+
{
|
1814 |
+
"output_type": "execute_result",
|
1815 |
+
"data": {
|
1816 |
+
"text/plain": [
|
1817 |
+
"{'eval_loss': 0.8449926376342773,\n",
|
1818 |
+
" 'eval_bleu': 53.45040267621567,\n",
|
1819 |
+
" 'eval_runtime': 3010.6388,\n",
|
1820 |
+
" 'eval_samples_per_second': 13.962,\n",
|
1821 |
+
" 'eval_steps_per_second': 0.218,\n",
|
1822 |
+
" 'epoch': 3.0}"
|
1823 |
+
]
|
1824 |
+
},
|
1825 |
+
"metadata": {},
|
1826 |
+
"execution_count": 21
|
1827 |
+
}
|
1828 |
+
]
|
1829 |
+
},
|
1830 |
+
{
|
1831 |
+
"cell_type": "markdown",
|
1832 |
+
"source": [
|
1833 |
+
"To observe the model's performance interactively, particularly in language translation, we can leverage Gradio. A ready-to-use script, \"gradio_eng_to_fra.py\", has been provided in the repository. Executing this file enables seamless integration with the Gradio interface, offering users an intuitive platform for language translation without the need for extensive coding."
|
1834 |
+
],
|
1835 |
+
"metadata": {
|
1836 |
+
"id": "qtHmvt340FXh"
|
1837 |
+
}
|
1838 |
+
}
|
1839 |
+
]
|
1840 |
+
}
|