File size: 26,642 Bytes
97d5a09
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "W030Ll_cpF_H"
      },
      "source": [
        "#Luganda Language Model\n",
        "\n",
        "[Git Notebook: Reference](https://github.com/SunbirdAI/salt/blob/main/notebooks/Train%20Multilingual%20Model.ipynb)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "oLLGScuuP0VX"
      },
      "outputs": [],
      "source": [
        "# from IPython import display\n",
        "# !pip install transformers[torch]\n",
        "# !pip install sacrebleu\n",
        "# !pip install sacremoses\n",
        "# !pip install datasets\n",
        "# !pip install wandb\n",
        "# !pip install sentencepiece\n",
        "# display.clear_output()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "3sVCeJ5ERnr2"
      },
      "outputs": [],
      "source": [
        "import datasets\n",
        "from IPython import display\n",
        "import numpy as np\n",
        "import os\n",
        "import pandas as pd\n",
        "import random\n",
        "import sentencepiece\n",
        "import sacrebleu\n",
        "import sacremoses\n",
        "import tqdm\n",
        "import transformers\n",
        "import torch\n",
        "import wandb"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "JpUFWhV3ab0e"
      },
      "source": [
        "#Dataset\n",
        "\n",
        "Let's start with step 1: loading and preprocessing the data. We'll define a function to load the sentences from the data files and create a tokenized dataset. This involves converting the sentences into sequences of numerical tokens that the model can work with. We'll use the AutoTokenizer class from the transformers library to do this. We'll also truncate or pad the sequences to a fixed length so that they can be batched together. The fixed length is a hyperparameter that you can adjust as needed."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "5cg3u77KQVY3"
      },
      "outputs": [],
      "source": [
        "from transformers import AutoTokenizer\n",
        "from torch.utils.data import Dataset\n",
        "from typing import List\n",
        "import torch\n",
        "\n",
        "class TranslationDataset(Dataset):\n",
        "    def __init__(self, source_sentences: List[str], target_sentences: List[str], tokenizer, max_length=32):\n",
        "        self.source_sentences = source_sentences\n",
        "        self.target_sentences = target_sentences\n",
        "        self.tokenizer = tokenizer\n",
        "        self.max_length = max_length\n",
        "\n",
        "    def __len__(self):\n",
        "        return len(self.source_sentences)\n",
        "\n",
        "    def __getitem__(self, idx):\n",
        "        source_sentence = self.source_sentences[idx]\n",
        "        target_sentence = self.target_sentences[idx]\n",
        "\n",
        "        tokenized_source = self.tokenizer(source_sentence, truncation=True, padding='max_length', max_length=self.max_length, return_tensors=\"pt\")\n",
        "        tokenized_target = self.tokenizer(target_sentence, truncation=True, padding='max_length', max_length=self.max_length, return_tensors=\"pt\")\n",
        "\n",
        "        return tokenized_source, tokenized_target\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "F9S8nBSmQ6xF"
      },
      "outputs": [],
      "source": [
        "# Next, let's define a function to load the sentences from the data files\n",
        "def load_sentences(file_path):\n",
        "    with open(file_path, \"r\") as f:\n",
        "        sentences = f.read().split(\"\\n\")\n",
        "        # Remove any empty sentences\n",
        "        sentences = [sentence for sentence in sentences if sentence]\n",
        "    return sentences\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7icyFvbVasv8"
      },
      "source": [
        "Here we're using the `Helsinki-NLP/opus-mt-lg-en` model as the base for our tokenizer. This model has been pre-trained on a large corpus of Luganda and English text, so it should be a good starting point for our task."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "zvZGxxGfRN_2"
      },
      "outputs": [],
      "source": [
        "# Initialize the tokenizer\n",
        "tokenizer = AutoTokenizer.from_pretrained(\"Helsinki-NLP/opus-mt-lg-en\")\n",
        "\n",
        "# Load sentences\n",
        "source_sentences = load_sentences(\"train_comb.lug\")\n",
        "target_sentences = load_sentences(\"train_comb.en\")\n",
        "\n",
        "# Create the dataset\n",
        "dataset = TranslationDataset(source_sentences, target_sentences, tokenizer)\n",
        "\n",
        "# Similarly, you can create validation and test datasets\n",
        "\n",
        "valid_source_sentences = load_sentences(\"val.lug\")\n",
        "valid_target_sentences = load_sentences(\"val.en\")\n",
        "\n",
        "vadi_dataset = TranslationDataset(valid_source_sentences, valid_target_sentences, tokenizer)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "g98kVGKKSQhK"
      },
      "outputs": [],
      "source": [
        "from transformers import AutoModelForSeq2SeqLM\n",
        "\n",
        "# Initialize the model\n",
        "model = AutoModelForSeq2SeqLM.from_pretrained(\"Helsinki-NLP/opus-mt-lg-en\")\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "IICfLDein5TM"
      },
      "outputs": [],
      "source": [
        "# def train_model(model, dataloader, val_dataloader, optimizer, num_epochs=10, save_path=\"Models/model.bin\", early_stop=3):\n",
        "#     # Set initial validation loss to positive infinity\n",
        "#     best_val_loss = float(\"inf\")\n",
        "#     # Initialize early stopping counter\n",
        "#     early_stop_counter = 0\n",
        "\n",
        "#     # Training loop\n",
        "#     for epoch in range(num_epochs):\n",
        "#         # Training\n",
        "#         model.train()\n",
        "#         for batch in dataloader:\n",
        "#             optimizer.zero_grad()\n",
        "#             input_ids = batch[0][\"input_ids\"].squeeze().to(\"cuda\")\n",
        "#             attention_mask = batch[0][\"attention_mask\"].squeeze().to(\"cuda\")\n",
        "#             labels = batch[1][\"input_ids\"].squeeze().to(\"cuda\")\n",
        "#             outputs = model(input_ids=input_ids, attention_mask=attention_mask, labels=labels)\n",
        "#             loss = outputs.loss\n",
        "#             loss.backward()\n",
        "#             optimizer.step()\n",
        "\n",
        "#         # Validation\n",
        "#         model.eval()\n",
        "#         total_val_loss = 0\n",
        "#         with torch.no_grad():\n",
        "#             for batch in val_dataloader:\n",
        "#                 input_ids = batch[0][\"input_ids\"].squeeze().to(\"cuda\")\n",
        "#                 attention_mask = batch[0][\"attention_mask\"].squeeze().to(\"cuda\")\n",
        "#                 labels = batch[1][\"input_ids\"].squeeze().to(\"cuda\")\n",
        "#                 outputs = model(input_ids=input_ids, attention_mask=attention_mask, labels=labels)\n",
        "#                 loss = outputs.loss\n",
        "#                 total_val_loss += loss.item()\n",
        "#         avg_val_loss = total_val_loss / len(val_dataloader)\n",
        "#         print(f\"Validation loss at epoch {epoch}: {avg_val_loss}\")\n",
        "\n",
        "#         # If validation loss improved, save the model and reset early stopping counter\n",
        "#         if avg_val_loss < best_val_loss:\n",
        "#             best_val_loss = avg_val_loss\n",
        "#             torch.save(model.state_dict(), save_path)\n",
        "#             early_stop_counter = 0\n",
        "#         # If validation loss did not improve, increment early stopping counter\n",
        "#         else:\n",
        "#             early_stop_counter += 1\n",
        "\n",
        "#         # If early stopping counter reached limit, stop training early\n",
        "#         if early_stop_counter >= early_stop:\n",
        "#             print(\"Early stopping triggered\")\n",
        "#             break\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vcBedpk3SgSI",
        "outputId": "f52fd995-397e-4836-aa44-1d9e0fc94e35"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/transformers/optimization.py:411: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
            "  warnings.warn(\n"
          ]
        }
      ],
      "source": [
        "from torch.utils.data import DataLoader\n",
        "from transformers import AdamW\n",
        "import torch.nn.functional as F\n",
        "\n",
        "# Create the DataLoader\n",
        "dataloader = DataLoader(dataset, batch_size=32, shuffle=True)\n",
        "val_dataloader = DataLoader(vadi_dataset, batch_size=32, shuffle=True)\n",
        "\n",
        "# Initialize the optimizer\n",
        "optimizer = AdamW(model.parameters(), lr=1e-5)\n",
        "\n",
        "# Move the model to the GPU\n",
        "model = model.to(\"cuda\")\n",
        "\n",
        "def train_model(model, dataloader, val_dataloader, optimizer, num_epochs=100, save_path=\"Models/model.bin\", early_stop=15):\n",
        "    # Set initial validation loss to positive infinity\n",
        "    best_val_loss = float(\"inf\")\n",
        "    # Initialize early stopping counter\n",
        "    early_stop_counter = 0\n",
        "\n",
        "    # Training loop\n",
        "    for epoch in range(num_epochs):\n",
        "        # Training\n",
        "        model.train()\n",
        "        for batch in dataloader:\n",
        "            optimizer.zero_grad()\n",
        "            input_ids = batch[0][\"input_ids\"].squeeze().to(\"cuda\")\n",
        "            attention_mask = batch[0][\"attention_mask\"].squeeze().to(\"cuda\")\n",
        "            labels = batch[1][\"input_ids\"].squeeze().to(\"cuda\")\n",
        "            outputs = model(input_ids=input_ids, attention_mask=attention_mask, labels=labels)\n",
        "            loss = outputs.loss\n",
        "            loss.backward()\n",
        "            optimizer.step()\n",
        "\n",
        "        # Validation\n",
        "        model.eval()\n",
        "        total_val_loss = 0\n",
        "        with torch.no_grad():\n",
        "            for batch in val_dataloader:\n",
        "                input_ids = batch[0][\"input_ids\"].squeeze().to(\"cuda\")\n",
        "                attention_mask = batch[0][\"attention_mask\"].squeeze().to(\"cuda\")\n",
        "                labels = batch[1][\"input_ids\"].squeeze().to(\"cuda\")\n",
        "                outputs = model(input_ids=input_ids, attention_mask=attention_mask, labels=labels)\n",
        "                loss = outputs.loss\n",
        "                total_val_loss += loss.item()\n",
        "        avg_val_loss = total_val_loss / len(val_dataloader)\n",
        "        print(f\"Validation loss at epoch {epoch}: {avg_val_loss}\")\n",
        "\n",
        "        # If validation loss improved, save the model and reset early stopping counter\n",
        "        if avg_val_loss < best_val_loss:\n",
        "            best_val_loss = avg_val_loss\n",
        "            torch.save(model.state_dict(), save_path)\n",
        "            early_stop_counter = 0\n",
        "        # If validation loss did not improve, increment early stopping counter\n",
        "        else:\n",
        "            early_stop_counter += 1\n",
        "\n",
        "        # If early stopping counter reached limit, stop training early\n",
        "        if early_stop_counter >= early_stop:\n",
        "            print(\"Early stopping triggered\")\n",
        "            break\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SGLDovijVFgI",
        "outputId": "80431766-2367-453d-b644-970f0a277c6b"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Validation loss at epoch 0: 1.7545462523319924\n",
            "Validation loss at epoch 1: 1.754554176515387\n",
            "Validation loss at epoch 2: 1.7544680806093438\n",
            "Validation loss at epoch 3: 1.7546287728834522\n",
            "Validation loss at epoch 4: 1.7545841932296753\n",
            "Validation loss at epoch 5: 1.754523749499358\n",
            "Validation loss at epoch 6: 1.7545043581215911\n",
            "Validation loss at epoch 7: 1.754460991815079\n",
            "Validation loss at epoch 8: 1.7544717650080837\n",
            "Validation loss at epoch 9: 1.754521275675574\n",
            "Validation loss at epoch 10: 1.7546228022538415\n",
            "Validation loss at epoch 11: 1.7545199015343835\n",
            "Validation loss at epoch 12: 1.7544237670972365\n",
            "Validation loss at epoch 13: 1.7543645856916443\n",
            "Validation loss at epoch 14: 1.7545291823010112\n",
            "Validation loss at epoch 15: 1.7544125946917275\n",
            "Validation loss at epoch 16: 1.7545219927795173\n",
            "Validation loss at epoch 17: 1.7544939120610554\n",
            "Validation loss at epoch 18: 1.7546383881753729\n",
            "Validation loss at epoch 19: 1.7544449724892313\n",
            "Validation loss at epoch 20: 1.7543920389441556\n",
            "Validation loss at epoch 21: 1.754468938176946\n",
            "Validation loss at epoch 22: 1.7544591380644214\n",
            "Validation loss at epoch 23: 1.7544086173523303\n",
            "Validation loss at epoch 24: 1.7543756333432456\n",
            "Validation loss at epoch 25: 1.7544627235841381\n",
            "Validation loss at epoch 26: 1.7545039237931717\n",
            "Validation loss at epoch 27: 1.7544716698254725\n",
            "Validation loss at epoch 28: 1.7545381793680117\n",
            "Validation loss at epoch 29: 1.7545897045800851\n",
            "Validation loss at epoch 30: 1.7545358460078868\n",
            "Validation loss at epoch 31: 1.7544444235720376\n",
            "Validation loss at epoch 32: 1.754581522571948\n",
            "Validation loss at epoch 33: 1.7545249785563743\n",
            "Validation loss at epoch 34: 1.754526928413746\n",
            "Validation loss at epoch 35: 1.7544997089592986\n",
            "Validation loss at epoch 36: 1.754356905471447\n",
            "Validation loss at epoch 37: 1.7544961908991024\n",
            "Validation loss at epoch 38: 1.7544016745663429\n",
            "Validation loss at epoch 39: 1.7544285225313763\n",
            "Validation loss at epoch 40: 1.7543853114741716\n",
            "Validation loss at epoch 41: 1.7544597156288089\n",
            "Validation loss at epoch 42: 1.7544455519018247\n",
            "Validation loss at epoch 43: 1.7545130761094796\n",
            "Validation loss at epoch 44: 1.7544649515965187\n",
            "Validation loss at epoch 45: 1.7544141277786374\n",
            "Validation loss at epoch 46: 1.7543530149977336\n",
            "Validation loss at epoch 47: 1.754479126412739\n",
            "Validation loss at epoch 48: 1.754434443259424\n",
            "Validation loss at epoch 49: 1.7545662998229035\n",
            "Validation loss at epoch 50: 1.7544944332551586\n",
            "Validation loss at epoch 51: 1.7544685287993083\n",
            "Validation loss at epoch 52: 1.754468088002168\n",
            "Validation loss at epoch 53: 1.754519222318664\n",
            "Validation loss at epoch 54: 1.7544778945834139\n",
            "Validation loss at epoch 55: 1.754462572031243\n",
            "Validation loss at epoch 56: 1.7544783483179964\n",
            "Validation loss at epoch 57: 1.75440527856812\n",
            "Validation loss at epoch 58: 1.7543795145759287\n",
            "Validation loss at epoch 59: 1.7547633232072342\n",
            "Validation loss at epoch 60: 1.7543582971705947\n",
            "Validation loss at epoch 61: 1.7546772864437843\n",
            "Validation loss at epoch 62: 1.75445248175037\n",
            "Validation loss at epoch 63: 1.7546141766762549\n",
            "Validation loss at epoch 64: 1.7545681397120159\n",
            "Validation loss at epoch 65: 1.7544179286143577\n",
            "Validation loss at epoch 66: 1.7545378984406936\n",
            "Validation loss at epoch 67: 1.7545608402222626\n",
            "Validation loss at epoch 68: 1.7545665456343067\n",
            "Validation loss at epoch 69: 1.7544571272162504\n",
            "Validation loss at epoch 70: 1.75438537523728\n",
            "Validation loss at epoch 71: 1.754475281220074\n",
            "Validation loss at epoch 72: 1.7544309556946274\n",
            "Validation loss at epoch 73: 1.7544244287549988\n",
            "Validation loss at epoch 74: 1.754499077796936\n",
            "Validation loss at epoch 75: 1.7544040023818497\n",
            "Validation loss at epoch 76: 1.7544351991756941\n",
            "Validation loss at epoch 77: 1.754511554111806\n",
            "Validation loss at epoch 78: 1.7543873029161794\n",
            "Validation loss at epoch 79: 1.7544674688531448\n",
            "Validation loss at epoch 80: 1.7544794553934142\n",
            "Validation loss at epoch 81: 1.7544126473655997\n",
            "Validation loss at epoch 82: 1.7543944314468738\n",
            "Validation loss at epoch 83: 1.7545764122822487\n",
            "Validation loss at epoch 84: 1.754630867824998\n",
            "Validation loss at epoch 85: 1.754439910252889\n",
            "Validation loss at epoch 86: 1.7544531914614891\n",
            "Validation loss at epoch 87: 1.754458603008773\n",
            "Validation loss at epoch 88: 1.7545876179554665\n",
            "Validation loss at epoch 89: 1.7544927439948386\n",
            "Validation loss at epoch 90: 1.7544405303260153\n",
            "Validation loss at epoch 91: 1.7544977942178415\n",
            "Validation loss at epoch 92: 1.7545225269110627\n",
            "Validation loss at epoch 93: 1.7544962186221928\n",
            "Validation loss at epoch 94: 1.7546170672705008\n",
            "Validation loss at epoch 95: 1.7544567150663035\n",
            "Validation loss at epoch 96: 1.7544416161470635\n",
            "Validation loss at epoch 97: 1.7545978921328405\n",
            "Validation loss at epoch 98: 1.7546191123104835\n",
            "Validation loss at epoch 99: 1.7544194071791892\n"
          ]
        }
      ],
      "source": [
        "# Train the model\n",
        "train_model(model, dataloader, val_dataloader, optimizer)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "P-3KwjtCZ0C2"
      },
      "source": [
        "# BLUE Score\n",
        "The Bilingual Evaluation Understudy (BLEU) score is a metric used to measure the quality of machine-generated translations. It compares the machine-generated translations to one or more reference translations. The BLEU score is a number between 0 and 100.\n",
        "\n",
        "1. A score of 0 means that the machine-generated translations do not match the reference translations at all.\n",
        "2. A score of 100 means that the machine-generated translations perfectly match the reference translations.\n",
        "\n",
        "The BLEU score takes into account the precision of n-grams in the machine-generated translations. It also includes a brevity penalty for translations that are too short, as these may not fully capture the meaning of the reference translations.\n",
        "\n",
        "Here are some general guidelines for interpreting BLEU scores:\n",
        "\n",
        "- A BLEU score in the range of 10-19 is considered to be equivalent to a translation done by a human with elementary proficiency in the target language, with some fluency errors.\n",
        "- A score in the range of 20-29 is roughly equivalent to a translation done by a human with intermediate proficiency in the target language, with minimal fluency errors.\n",
        "- A score in the range of 30-40 is equivalent to a translation done by a human with advanced proficiency in the target language, with few to no fluency errors.\n",
        "- A score in the range of 40-50 is equivalent to a translation done by a professional human translator.\n",
        "- A score above 50 is typically considered to be equivalent to a high-quality, professional human translation.\n",
        "\n",
        "It's important to note that while the BLEU score is a useful metric, it does not capture all aspects of translation quality. For example, it does not measure the grammatical correctness of the translations, and it may not accurately reflect the quality of translations for languages with complex grammar or sentence structure. Therefore, it's a good idea to use other evaluation methods in addition to the BLEU score when assessing the quality of machine translations."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gpiRWBrmVcGK",
        "outputId": "bdb3fe7c-7659-462a-95e0-da74f63f64f6"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "BLEU score: 62.538661494402014\n"
          ]
        }
      ],
      "source": [
        "from transformers import AutoTokenizer\n",
        "from torch.utils.data import DataLoader\n",
        "from sacrebleu import corpus_bleu\n",
        "\n",
        "# Create the test dataset and DataLoader\n",
        "test_source_sentences = load_sentences(\"test.lug\")\n",
        "test_target_sentences = load_sentences(\"test.en\")\n",
        "test_dataset = TranslationDataset(test_source_sentences, test_target_sentences, tokenizer)\n",
        "test_dataloader = DataLoader(test_dataset, batch_size=32)\n",
        "\n",
        "# Evaluate the model\n",
        "model.eval()\n",
        "model.to(\"cuda\")\n",
        "\n",
        "predictions = []\n",
        "actuals = []\n",
        "\n",
        "with torch.no_grad():\n",
        "    for batch in test_dataloader:\n",
        "        input_ids = batch[0][\"input_ids\"].squeeze().to(\"cuda\")\n",
        "        attention_mask = batch[0][\"attention_mask\"].squeeze().to(\"cuda\")\n",
        "        labels = batch[1][\"input_ids\"].squeeze().to(\"cuda\")\n",
        "        outputs = model.generate(input_ids=input_ids, attention_mask=attention_mask)\n",
        "\n",
        "        # Convert output tokens to sentences\n",
        "        pred_sentences = [tokenizer.decode(tokens) for tokens in outputs]\n",
        "        actual_sentences = [tokenizer.decode(tokens) for tokens in labels]\n",
        "        predictions.extend(pred_sentences)\n",
        "        actuals.extend(actual_sentences)\n",
        "\n",
        "# Compute BLEU score\n",
        "bleu_score = corpus_bleu(predictions, [actuals]).score\n",
        "print(f\"BLEU score: {bleu_score}\")\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "iIWT_hi8dRNU"
      },
      "source": [
        "Load the saved model: You can load the saved model using the load_state_dict method. You'll need to initialize the model architecture first, and then load the saved parameters into it."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "FeoE1M2mdQwD"
      },
      "outputs": [],
      "source": [
        "model = AutoModelForSeq2SeqLM.from_pretrained(\"Helsinki-NLP/opus-mt-lg-en\")\n",
        "model.load_state_dict(torch.load(\"Models/model.bin\"))\n",
        "model = model.to(\"cuda\")  # if you're using a GPU\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uadyysKRdYrw"
      },
      "source": [
        "# Translate a new sentence:\n",
        "\n",
        "To translate a new sentence, you'll need to tokenize the sentence, feed it to the model, and then decode the model's output back into a sentence."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ma7Lcd6ndVIo",
        "outputId": "ec311303-ebc0-4c15-e9b5-a3e29d8665fc"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "<pad> How do you know?</s>\n"
          ]
        }
      ],
      "source": [
        "sentence = \"Oli otya?\"\n",
        "# Tokenize the sentence\n",
        "tokenized_sentence = tokenizer(sentence, return_tensors=\"pt\")\n",
        "tokenized_sentence = tokenized_sentence.to(\"cuda\")  # if you're using a GPU\n",
        "# Generate the translation\n",
        "translated_tokens = model.generate(**tokenized_sentence)\n",
        "# Decode the translation\n",
        "translation = tokenizer.decode(translated_tokens[0])\n",
        "print(translation)\n"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}