Hugging Face's logo

YagiASAFAS
/
MyPoliBERT-ver03

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
YagiASAFAS commited on
Commit
0efbf92
·
verified ·
1 Parent(s): 4cbf781

MyPoliBERT Ver. Up

Browse files
Files changed (2) hide show
  1. README.md +93 -3
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,3 +1,93 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: bert-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: MyPoliBERT-ver03
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # MyPoliBERT-ver03
16
+
17
+ This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2655
20
+ - Democracy F1: 0.9312
21
+ - Democracy Accuracy: 0.9318
22
+ - Economy F1: 0.9143
23
+ - Economy Accuracy: 0.9151
24
+ - Race F1: 0.9449
25
+ - Race Accuracy: 0.9456
26
+ - Leadership F1: 0.8488
27
+ - Leadership Accuracy: 0.8494
28
+ - Development F1: 0.8710
29
+ - Development Accuracy: 0.8748
30
+ - Corruption F1: 0.9420
31
+ - Corruption Accuracy: 0.9441
32
+ - Instability F1: 0.9164
33
+ - Instability Accuracy: 0.9198
34
+ - Safety F1: 0.9042
35
+ - Safety Accuracy: 0.9032
36
+ - Administration F1: 0.8831
37
+ - Administration Accuracy: 0.8891
38
+ - Education F1: 0.9565
39
+ - Education Accuracy: 0.9567
40
+ - Religion F1: 0.9426
41
+ - Religion Accuracy: 0.9424
42
+ - Environment F1: 0.9745
43
+ - Environment Accuracy: 0.9746
44
+ - Overall F1: 0.9191
45
+ - Overall Accuracy: 0.9206
46
+
47
+ ## Model description
48
+
49
+ More information needed
50
+
51
+ ## Intended uses & limitations
52
+
53
+ More information needed
54
+
55
+ ## Training and evaluation data
56
+
57
+ More information needed
58
+
59
+ ## Training procedure
60
+
61
+ ### Training hyperparameters
62
+
63
+ The following hyperparameters were used during training:
64
+ - learning_rate: 3e-05
65
+ - train_batch_size: 16
66
+ - eval_batch_size: 16
67
+ - seed: 42
68
+ - gradient_accumulation_steps: 2
69
+ - total_train_batch_size: 32
70
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
71
+ - lr_scheduler_type: linear
72
+ - num_epochs: 16
73
+ - mixed_precision_training: Native AMP
74
+
75
+ ### Training results
76
+
77
+ | Training Loss | Epoch | Step | Validation Loss | Democracy F1 | Democracy Accuracy | Economy F1 | Economy Accuracy | Race F1 | Race Accuracy | Leadership F1 | Leadership Accuracy | Development F1 | Development Accuracy | Corruption F1 | Corruption Accuracy | Instability F1 | Instability Accuracy | Safety F1 | Safety Accuracy | Administration F1 | Administration Accuracy | Education F1 | Education Accuracy | Religion F1 | Religion Accuracy | Environment F1 | Environment Accuracy | Overall F1 | Overall Accuracy |
78
+ |:-------------:|:-----:|:----:|:---------------:|:------------:|:------------------:|:----------:|:----------------:|:-------:|:-------------:|:-------------:|:-------------------:|:--------------:|:--------------------:|:-------------:|:-------------------:|:--------------:|:--------------------:|:---------:|:---------------:|:-----------------:|:-----------------------:|:------------:|:------------------:|:-----------:|:-----------------:|:--------------:|:--------------------:|:----------:|:----------------:|
79
+ | 0.448 | 1.0 | 674 | 0.2781 | 0.8973 | 0.9201 | 0.8952 | 0.9062 | 0.9346 | 0.9385 | 0.8199 | 0.8340 | 0.8462 | 0.8672 | 0.9210 | 0.9302 | 0.8873 | 0.9084 | 0.8869 | 0.8947 | 0.8307 | 0.8700 | 0.9344 | 0.9467 | 0.9219 | 0.9304 | 0.9565 | 0.9619 | 0.8943 | 0.9090 |
80
+ | 0.2646 | 2.0 | 1348 | 0.2372 | 0.9232 | 0.9335 | 0.9111 | 0.9144 | 0.9438 | 0.9467 | 0.8406 | 0.8403 | 0.8669 | 0.8739 | 0.9385 | 0.9424 | 0.9222 | 0.9278 | 0.9038 | 0.9081 | 0.8724 | 0.8869 | 0.9543 | 0.9580 | 0.9380 | 0.9409 | 0.9732 | 0.9734 | 0.9157 | 0.9205 |
81
+ | 0.1696 | 3.0 | 2022 | 0.2291 | 0.9277 | 0.9333 | 0.9132 | 0.9177 | 0.9441 | 0.9469 | 0.8465 | 0.8503 | 0.8768 | 0.8847 | 0.9423 | 0.9454 | 0.9219 | 0.9255 | 0.9104 | 0.9114 | 0.8806 | 0.8919 | 0.9592 | 0.9597 | 0.9407 | 0.9419 | 0.9753 | 0.9766 | 0.9199 | 0.9238 |
82
+ | 0.1309 | 4.0 | 2696 | 0.2374 | 0.9290 | 0.9344 | 0.9168 | 0.9175 | 0.9441 | 0.9452 | 0.8454 | 0.8470 | 0.8733 | 0.8804 | 0.9433 | 0.9465 | 0.9215 | 0.9233 | 0.9101 | 0.9096 | 0.8762 | 0.8758 | 0.9577 | 0.9597 | 0.9389 | 0.9408 | 0.9740 | 0.9740 | 0.9192 | 0.9212 |
83
+ | 0.1085 | 5.0 | 3370 | 0.2414 | 0.9314 | 0.9346 | 0.9166 | 0.9175 | 0.9419 | 0.9452 | 0.8492 | 0.8459 | 0.8747 | 0.8808 | 0.9435 | 0.9463 | 0.9218 | 0.9257 | 0.9070 | 0.9083 | 0.8862 | 0.8921 | 0.9574 | 0.9588 | 0.9420 | 0.9426 | 0.9732 | 0.9736 | 0.9204 | 0.9226 |
84
+ | 0.0759 | 6.0 | 4044 | 0.2556 | 0.9311 | 0.9313 | 0.9153 | 0.9162 | 0.9465 | 0.9473 | 0.8492 | 0.8511 | 0.8743 | 0.8810 | 0.9431 | 0.9447 | 0.9185 | 0.9205 | 0.9049 | 0.9034 | 0.8797 | 0.8886 | 0.9588 | 0.9601 | 0.9419 | 0.9421 | 0.9753 | 0.9757 | 0.9199 | 0.9218 |
85
+ | 0.0618 | 7.0 | 4718 | 0.2655 | 0.9312 | 0.9318 | 0.9143 | 0.9151 | 0.9449 | 0.9456 | 0.8488 | 0.8494 | 0.8710 | 0.8748 | 0.9420 | 0.9441 | 0.9164 | 0.9198 | 0.9042 | 0.9032 | 0.8831 | 0.8891 | 0.9565 | 0.9567 | 0.9426 | 0.9424 | 0.9745 | 0.9746 | 0.9191 | 0.9206 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.48.2
91
+ - Pytorch 2.5.1+cu124
92
+ - Datasets 3.2.0
93
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:239459ee5e26bfb60ee18a2ddd2b19f03414d3a5ab527beb9d4cd2508e4f07d2
3
  size 438100144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc069e386a6deb789edc1a12057f57b654519f5f9fe6868369fcde2f08a30b74
3
  size 438100144