rollerhafeezh-amikom commited on
Commit
6caa151
1 Parent(s): 436c45e

Training complete

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: cahya/distilbert-base-indonesian
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: distilbert-base-indonesian-fire-classification-silvanus
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
+ # distilbert-base-indonesian-fire-classification-silvanus
15
+
16
+ This model is a fine-tuned version of [cahya/distilbert-base-indonesian](https://huggingface.co/cahya/distilbert-base-indonesian) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.1890
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: 8
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 3
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 49 | 0.1673 |
50
+ | No log | 2.0 | 98 | 0.1883 |
51
+ | No log | 3.0 | 147 | 0.1890 |
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.35.0
57
+ - Pytorch 2.1.0+cu118
58
+ - Datasets 2.14.6
59
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cahya/distilbert-base-indonesian",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Not Fire",
13
+ "1": "Fire"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "Fire": 1,
18
+ "Not Fire": 0
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "output_hidden_states": true,
25
+ "pad_token_id": 0,
26
+ "problem_type": "single_label_classification",
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": true,
30
+ "tie_weights_": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.35.0",
33
+ "vocab_size": 32000
34
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee744c83efe5f64064b5eb6a6fd93250987776c45959629f649863dc9c9f50d2
3
+ size 272372984
runs/Jun28_11-12-52_server-cvis/events.out.tfevents.1719547994.server-cvis.3090328.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9cd061e7a9d86b09dc2f844448d9e01f280df5ad2c83bea738d586528e3ec1c
3
+ size 4312
runs/Jun28_11-12-52_server-cvis/events.out.tfevents.1719548048.server-cvis.3090328.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9011614528436e413c636d0f78c010ad3a50e1173621b006d285ed04075c56d8
3
+ size 4136
runs/Jun28_11-12-52_server-cvis/events.out.tfevents.1719548080.server-cvis.3090328.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed88e254a2ae5be5c38ab7c5ef0935039abf837fe1533a14410f015987e06ff
3
+ size 4136
runs/Jun28_11-12-52_server-cvis/events.out.tfevents.1719548111.server-cvis.3090328.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb0d6030d99ff697f931578074909b6759c23250ebe9f808b12adf0f6c91109
3
+ size 5518
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[SEP]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[PAD]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[CLS]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
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": true,
48
+ "full_tokenizer_file": null,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98d1cc9a3239c52edd7331ac4d1e83e59d14257894973865dcc34786b41967f2
3
+ size 4664
vocab.txt ADDED
The diff for this file is too large to render. See raw diff