Hugging Face's logo

nadika
/
nepali_complaints_classification_muril

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
Community
nadika commited on
Commit
02d82d4
·
verified ·
1 Parent(s): b9b5ceb

Model trained- 1st iteration

Browse files
Files changed (8) hide show
  1. README.md +61 -0
  2. config.json +59 -0
  3. gitattributes +35 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +37 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +65 -0
  8. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ base_model: google/muril-base-cased
6
+ model-index:
7
+ - name: nepali_complaints_classification_muril
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # nepali_complaints_classification_muril
15
+
16
+ This model is a fine-tuned version of [google/muril-base-cased](https://huggingface.co/google/muril-base-cased) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.2424
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 1000
44
+ - num_epochs: 4
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | 0.916 | 1.0 | 2244 | 0.7103 |
51
+ | 0.2725 | 2.0 | 4488 | 0.3206 |
52
+ | 0.1678 | 3.0 | 6732 | 0.2685 |
53
+ | 0.204 | 4.0 | 8976 | 0.2424 |
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.38.2
59
+ - Pytorch 2.1.0+cu121
60
+ - Datasets 2.18.0
61
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./my_muril_model",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "\u0905\u0930\u094d\u0925 \u0938\u092c\u0928\u094d\u0927\u0940",
14
+ "1": "\u0905\u0930\u094d\u0925\u093f\u0915 \u0905\u0928\u093f\u092f\u092e\u093f\u0924\u0924\u093e \u0924\u0925\u093e \u092d\u094d\u0930\u0937\u094d\u091f\u093e\u091a\u093e\u0930 \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940",
15
+ "2": "\u0915\u0930\u094d\u092e\u091a\u093e\u0930\u0940 \u0938\u092e\u094d\u0935\u0928\u094d\u0927\u0940",
16
+ "3": "\u0916\u093e\u0928\u0947\u092a\u093e\u0928\u0940",
17
+ "4": "\u0928\u093f\u0930\u094d\u092e\u093e\u0923 \u0915\u093e\u0930\u094d\u092f \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940",
18
+ "5": "\u092a\u093e\u0930\u094d\u0915\u093f\u0919\u094d\u0917 \u0924\u0925\u093e \u092e\u0947\u091f\u094d\u0930\u094b \u092a\u0941\u0932\u093f\u0938",
19
+ "6": "\u092a\u094d\u0930\u093e\u0915\u0943\u0924\u093f\u0915 \u0936\u094d\u0930\u094b\u0924/\u0938\u093e\u0927\u0928 \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940",
20
+ "7": "\u092b\u094b\u0939\u094b\u0930\u092e\u0948\u0932\u093e \u0935\u094d\u092f\u0935\u0938\u094d\u0925\u093e\u092a\u0928",
21
+ "8": "\u0932\u093e\u0917\u0941 \u092a\u0926\u093e\u0930\u094d\u0925 \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940",
22
+ "9": "\u0935\u0947\u092c\u0938\u093e\u0907\u091f \u0924\u0925\u093e \u0905\u092d\u093f\u0932\u0947\u0916 \u0935\u094d\u092f\u0935\u0938\u094d\u0925\u093e\u092a\u0928 \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940",
23
+ "10": "\u0936\u093e\u0928\u094d\u0924\u093f \u0938\u0941\u0930\u0915\u094d\u0937\u093e",
24
+ "11": "\u0938\u0942\u091a\u0928\u093e \u0924\u0925\u093e \u0938\u0902\u091a\u093e\u0930",
25
+ "12": "\u0938\u094b\u0927\u092a\u0941\u091b, \u0938\u0941\u091d\u093e\u0935, \u092a\u094d\u0930\u0936\u0902\u0938\u093e \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940",
26
+ "13": "\u0938\u094d\u0935\u093e\u0938\u094d\u0925\u094d\u092f\u0938\u0901\u0917 \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "\u0905\u0930\u094d\u0925 \u0938\u092c\u0928\u094d\u0927\u0940": 0,
32
+ "\u0905\u0930\u094d\u0925\u093f\u0915 \u0905\u0928\u093f\u092f\u092e\u093f\u0924\u0924\u093e \u0924\u0925\u093e \u092d\u094d\u0930\u0937\u094d\u091f\u093e\u091a\u093e\u0930 \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940": 1,
33
+ "\u0915\u0930\u094d\u092e\u091a\u093e\u0930\u0940 \u0938\u092e\u094d\u0935\u0928\u094d\u0927\u0940": 2,
34
+ "\u0916\u093e\u0928\u0947\u092a\u093e\u0928\u0940": 3,
35
+ "\u0928\u093f\u0930\u094d\u092e\u093e\u0923 \u0915\u093e\u0930\u094d\u092f \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940": 4,
36
+ "\u092a\u093e\u0930\u094d\u0915\u093f\u0919\u094d\u0917 \u0924\u0925\u093e \u092e\u0947\u091f\u094d\u0930\u094b \u092a\u0941\u0932\u093f\u0938": 5,
37
+ "\u092a\u094d\u0930\u093e\u0915\u0943\u0924\u093f\u0915 \u0936\u094d\u0930\u094b\u0924/\u0938\u093e\u0927\u0928 \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940": 6,
38
+ "\u092b\u094b\u0939\u094b\u0930\u092e\u0948\u0932\u093e \u0935\u094d\u092f\u0935\u0938\u094d\u0925\u093e\u092a\u0928": 7,
39
+ "\u0932\u093e\u0917\u0941 \u092a\u0926\u093e\u0930\u094d\u0925 \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940": 8,
40
+ "\u0935\u0947\u092c\u0938\u093e\u0907\u091f \u0924\u0925\u093e \u0905\u092d\u093f\u0932\u0947\u0916 \u0935\u094d\u092f\u0935\u0938\u094d\u0925\u093e\u092a\u0928 \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940": 9,
41
+ "\u0936\u093e\u0928\u094d\u0924\u093f \u0938\u0941\u0930\u0915\u094d\u0937\u093e": 10,
42
+ "\u0938\u0942\u091a\u0928\u093e \u0924\u0925\u093e \u0938\u0902\u091a\u093e\u0930": 11,
43
+ "\u0938\u094b\u0927\u092a\u0941\u091b, \u0938\u0941\u091d\u093e\u0935, \u092a\u094d\u0930\u0936\u0902\u0938\u093e \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940": 12,
44
+ "\u0938\u094d\u0935\u093e\u0938\u094d\u0925\u094d\u092f\u0938\u0901\u0917 \u0938\u092e\u094d\u092c\u0928\u094d\u0927\u0940": 13
45
+ },
46
+ "layer_norm_eps": 1e-12,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "bert",
49
+ "num_attention_heads": 12,
50
+ "num_hidden_layers": 12,
51
+ "pad_token_id": 0,
52
+ "position_embedding_type": "absolute",
53
+ "problem_type": "single_label_classification",
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.38.2",
56
+ "type_vocab_size": 2,
57
+ "use_cache": true,
58
+ "vocab_size": 197285
59
+ }
gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df455c7d66c16aab4867aed166c7f635f3c5aaca93378644ad23caee2536b2a5
3
+ size 950291512
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "103": {
20
+ "content": "[MASK]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "104": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "105": {
36
+ "content": "[SEP]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "lowercase": false,
49
+ "mask_token": "[MASK]",
50
+ "max_length": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": false,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff