rollerhafeezh-amikom commited on
Commit
c3ab726
·
1 Parent(s): 2530a3c
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
 
 
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
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: xlm-roberta-base
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: xlm-roberta-base-fire-classification-silvanus
8
+ results: []
9
+ widget:
10
+ - text: >-
11
+ Kebakaran hutan dan lahan terus terjadi dan semakin meluas di Kota
12
+ Palangkaraya, Kalimantan Tengah (Kalteng) pada hari Rabu, 15 Nopember 2023
13
+ 20.00 WIB. Bahkan kobaran api mulai membakar pondok warga dan mendekati
14
+ permukiman. BZK #RCTINews #SeputariNews #News #Karhutla #KebakaranHutan
15
+ #HutanKalimantan #SILVANUS_Italian_Pilot_Testing
16
+ example_title: Indonesia
17
+ - text: >-
18
+ Wildfire rages for a second day in Evia destroying a Natura 2000 protected
19
+ pine forest. - 5:51 PM Aug 14, 2019
20
+ example_title: English
21
+ - text: >-
22
+ 3 nov 2023 21:57 - Incendio forestal obliga a la evacuación de hasta 850
23
+ personas cerca del pueblo de Montichelvo en Valencia.
24
+ example_title: Spanish
25
+ - text: >-
26
+ Incendi boschivi nell'est del Paese: 2 morti e oltre 50 case distrutte nello
27
+ stato del Queensland.
28
+ example_title: Italian
29
+ - text: >-
30
+ Lesné požiare na Sicílii si vyžiadali dva ľudské životy a evakuáciu hotela
31
+ http://dlvr.it/SwW3sC - 23. septembra 2023 20:57
32
+ example_title: Slovak
33
+ language:
34
+ - id
35
+ - en
36
+ - es
37
+ - it
38
+ - sk
39
+ ---
40
+
41
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
42
+ should probably proofread and complete it, then remove this comment. -->
43
+
44
+ # xlm-roberta-base-fire-classification-silvanus
45
+
46
+ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the Twitter (X) dataset based on the "forest fire" keyword.
47
+ It achieves the following results on the evaluation set:
48
+ - Loss: 0.5255
49
+ - Accuracy: 0.8884
50
+
51
+ ## Model description
52
+
53
+ More information needed
54
+
55
+ ## Intended uses & limitations
56
+
57
+ More information needed
58
+
59
+ ## Training and evaluation data
60
+
61
+ More information needed
62
+
63
+ ## Training procedure
64
+
65
+ ### Training hyperparameters
66
+
67
+ The following hyperparameters were used during training:
68
+ - learning_rate: 3e-05
69
+ - train_batch_size: 8
70
+ - eval_batch_size: 8
71
+ - seed: 42
72
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
+ - lr_scheduler_type: linear
74
+ - num_epochs: 3
75
+
76
+ ### Training results
77
+
78
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
79
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
80
+ | No log | 1.0 | 233 | 0.5431 | 0.8670 |
81
+ | No log | 2.0 | 466 | 0.5125 | 0.8670 |
82
+ | 0.4162 | 3.0 | 699 | 0.5255 | 0.8884 |
83
+
84
+
85
+ ### Framework versions
86
+
87
+ - Transformers 4.35.0
88
+ - Pytorch 2.1.0+cu118
89
+ - Datasets 2.14.6
90
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "Not Fire",
15
+ "1": "Fire"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "Fire": 1,
21
+ "Not Fire": 0
22
+ },
23
+ "layer_norm_eps": 1e-05,
24
+ "max_position_embeddings": 514,
25
+ "model_type": "xlm-roberta",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "output_past": true,
29
+ "pad_token_id": 1,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.35.0",
34
+ "type_vocab_size": 1,
35
+ "use_cache": true,
36
+ "vocab_size": 250002
37
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eecb4badb329c6a0b3fd0f5bb10891a1dfb974b017bc5deff78d451b0c94237
3
+ size 1112205008
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:003498ab0695fbf35aedc8bbbae1e20a6033a1b3914e49c6d2fbe1d54d7d93b9
3
+ size 17082786
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65508f39d381887777d8db4365503bc867eb211340e6a93fc4ee5532d4995fb
3
+ size 4664