arincon/ia-detection-bert-tiny
Browse files- README.md +95 -0
- logs/events.out.tfevents.1698523599.b35e6e2f6525.1480.0 +2 -2
- logs/events.out.tfevents.1698524027.b35e6e2f6525.1480.2 +3 -0
- pytorch_model.bin +1 -1
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- autextification2023
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
- f1
|
10 |
+
- precision
|
11 |
+
- recall
|
12 |
+
model-index:
|
13 |
+
- name: ia-detection-bert-tiny
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Text Classification
|
17 |
+
type: text-classification
|
18 |
+
dataset:
|
19 |
+
name: autextification2023
|
20 |
+
type: autextification2023
|
21 |
+
config: detection_en
|
22 |
+
split: train
|
23 |
+
args: detection_en
|
24 |
+
metrics:
|
25 |
+
- name: Accuracy
|
26 |
+
type: accuracy
|
27 |
+
value: 0.699019787467937
|
28 |
+
- name: F1
|
29 |
+
type: f1
|
30 |
+
value: 0.7522153927372828
|
31 |
+
- name: Precision
|
32 |
+
type: precision
|
33 |
+
value: 0.6506621436492922
|
34 |
+
- name: Recall
|
35 |
+
type: recall
|
36 |
+
value: 0.891331546023235
|
37 |
+
---
|
38 |
+
|
39 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
40 |
+
should probably proofread and complete it, then remove this comment. -->
|
41 |
+
|
42 |
+
# ia-detection-bert-tiny
|
43 |
+
|
44 |
+
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the autextification2023 dataset.
|
45 |
+
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.9775
|
47 |
+
- Accuracy: 0.6990
|
48 |
+
- F1: 0.7522
|
49 |
+
- Precision: 0.6507
|
50 |
+
- Recall: 0.8913
|
51 |
+
|
52 |
+
## Model description
|
53 |
+
|
54 |
+
More information needed
|
55 |
+
|
56 |
+
## Intended uses & limitations
|
57 |
+
|
58 |
+
More information needed
|
59 |
+
|
60 |
+
## Training and evaluation data
|
61 |
+
|
62 |
+
More information needed
|
63 |
+
|
64 |
+
## Training procedure
|
65 |
+
|
66 |
+
### Training hyperparameters
|
67 |
+
|
68 |
+
The following hyperparameters were used during training:
|
69 |
+
- learning_rate: 0.0001
|
70 |
+
- train_batch_size: 8
|
71 |
+
- eval_batch_size: 8
|
72 |
+
- seed: 42
|
73 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
74 |
+
- lr_scheduler_type: linear
|
75 |
+
- lr_scheduler_warmup_steps: 500
|
76 |
+
- num_epochs: 10
|
77 |
+
|
78 |
+
### Training results
|
79 |
+
|
80 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
81 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
82 |
+
| 0.3606 | 1.0 | 3808 | 0.4135 | 0.8068 | 0.8126 | 0.7795 | 0.8486 |
|
83 |
+
| 0.39 | 2.0 | 7616 | 0.4197 | 0.8213 | 0.8147 | 0.8344 | 0.7959 |
|
84 |
+
| 0.386 | 3.0 | 11424 | 0.5145 | 0.8210 | 0.8249 | 0.7977 | 0.8540 |
|
85 |
+
| 0.277 | 4.0 | 15232 | 0.7962 | 0.8080 | 0.7887 | 0.8633 | 0.7259 |
|
86 |
+
| 0.1913 | 5.0 | 19040 | 0.8833 | 0.8115 | 0.8001 | 0.8396 | 0.7642 |
|
87 |
+
| 0.2053 | 6.0 | 22848 | 0.9313 | 0.8180 | 0.8070 | 0.8468 | 0.7708 |
|
88 |
+
|
89 |
+
|
90 |
+
### Framework versions
|
91 |
+
|
92 |
+
- Transformers 4.26.1
|
93 |
+
- Pytorch 2.1.0+cu118
|
94 |
+
- Datasets 2.14.6
|
95 |
+
- Tokenizers 0.13.3
|
logs/events.out.tfevents.1698523599.b35e6e2f6525.1480.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20094746a924d03679b008d4a17a23676f4864e8038ebfa06fde13a5bfbbf066
|
3 |
+
size 367668
|
logs/events.out.tfevents.1698524027.b35e6e2f6525.1480.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77e8db4054309371ae01b825ad324ba7c68984cd38317fd1d39f7dc8c28758b7
|
3 |
+
size 569
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17563052
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a51670f65b6528ae3f35b555eb4e856488265c5ad232b9c4865de837db35f928
|
3 |
size 17563052
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"name_or_path": "prajjwal1/bert-tiny",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|