syafiqfaray
commited on
Commit
•
f6dcc17
1
Parent(s):
f8799d1
End of training
Browse files- README.md +46 -0
- added_tokens.json +10 -0
- config.json +42 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +121 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: spanemo-id-ta
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# spanemo-id-ta
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
+
|
16 |
+
## Model description
|
17 |
+
|
18 |
+
More information needed
|
19 |
+
|
20 |
+
## Intended uses & limitations
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Training and evaluation data
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training procedure
|
29 |
+
|
30 |
+
### Training hyperparameters
|
31 |
+
|
32 |
+
The following hyperparameters were used during training:
|
33 |
+
- learning_rate: 2e-05
|
34 |
+
- train_batch_size: 64
|
35 |
+
- eval_batch_size: 64
|
36 |
+
- seed: 42
|
37 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
38 |
+
- lr_scheduler_type: linear
|
39 |
+
- num_epochs: 30
|
40 |
+
|
41 |
+
### Framework versions
|
42 |
+
|
43 |
+
- Transformers 4.41.0.dev0
|
44 |
+
- Pytorch 2.1.2
|
45 |
+
- Datasets 2.19.1.dev0
|
46 |
+
- Tokenizers 0.19.1
|
added_tokens.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Antisipasi": 31929,
|
3 |
+
"Bahagia": 31926,
|
4 |
+
"Jijik": 31928,
|
5 |
+
"Marah": 31930,
|
6 |
+
"Percaya": 31923,
|
7 |
+
"Sedih": 31925,
|
8 |
+
"Takut": 31927,
|
9 |
+
"Terkejut": 31924
|
10 |
+
}
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SpanEmo"
|
4 |
+
],
|
5 |
+
"embedding_vocab_size": 31931,
|
6 |
+
"id2label": {
|
7 |
+
"0": "Percaya",
|
8 |
+
"1": "Terkejut",
|
9 |
+
"2": "Sedih",
|
10 |
+
"3": "Bahagia",
|
11 |
+
"4": "Takut",
|
12 |
+
"5": "Jijik",
|
13 |
+
"6": "Antisipasi",
|
14 |
+
"7": "Marah"
|
15 |
+
},
|
16 |
+
"inter_loss_factor": 0,
|
17 |
+
"label2id": {
|
18 |
+
"Antisipasi": 6,
|
19 |
+
"Bahagia": 3,
|
20 |
+
"Jijik": 5,
|
21 |
+
"Marah": 7,
|
22 |
+
"Percaya": 0,
|
23 |
+
"Sedih": 2,
|
24 |
+
"Takut": 4,
|
25 |
+
"Terkejut": 1
|
26 |
+
},
|
27 |
+
"label_idxs": [
|
28 |
+
1,
|
29 |
+
2,
|
30 |
+
3,
|
31 |
+
4,
|
32 |
+
5,
|
33 |
+
6,
|
34 |
+
7,
|
35 |
+
8
|
36 |
+
],
|
37 |
+
"model_type": "spanemo",
|
38 |
+
"output_dropout": 0.1,
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.41.0.dev0",
|
41 |
+
"zlpr_loss_factor": 0
|
42 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e90116d600bcbdb5e23a47ea83b61bedec86677ef439440d1935eb98884d2639
|
3 |
+
size 444647172
|
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 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[MASK]",
|
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": "[SEP]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"31923": {
|
44 |
+
"content": "Percaya",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"31924": {
|
52 |
+
"content": "Terkejut",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": false
|
58 |
+
},
|
59 |
+
"31925": {
|
60 |
+
"content": "Sedih",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": false
|
66 |
+
},
|
67 |
+
"31926": {
|
68 |
+
"content": "Bahagia",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": true,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": false
|
74 |
+
},
|
75 |
+
"31927": {
|
76 |
+
"content": "Takut",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": true,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": false
|
82 |
+
},
|
83 |
+
"31928": {
|
84 |
+
"content": "Jijik",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": true,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": false
|
90 |
+
},
|
91 |
+
"31929": {
|
92 |
+
"content": "Antisipasi",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": true,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": false
|
98 |
+
},
|
99 |
+
"31930": {
|
100 |
+
"content": "Marah",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": true,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": false
|
106 |
+
}
|
107 |
+
},
|
108 |
+
"clean_up_tokenization_spaces": true,
|
109 |
+
"cls_token": "[CLS]",
|
110 |
+
"do_basic_tokenize": true,
|
111 |
+
"do_lower_case": true,
|
112 |
+
"mask_token": "[MASK]",
|
113 |
+
"model_max_length": 1000000000000000019884624838656,
|
114 |
+
"never_split": null,
|
115 |
+
"pad_token": "[PAD]",
|
116 |
+
"sep_token": "[SEP]",
|
117 |
+
"strip_accents": null,
|
118 |
+
"tokenize_chinese_chars": true,
|
119 |
+
"tokenizer_class": "BertTokenizer",
|
120 |
+
"unk_token": "[UNK]"
|
121 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9dff8c6408140dba6a2479f645e93269918bd1f4cf616996f863cffdad318bf
|
3 |
+
size 5048
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|