Hugging Face's logo

AnonymousCS
/
populism_classifier_bsample_181

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
AnonymousCS commited on
Commit
0875a20
·
verified ·
1 Parent(s): 8ecd24a

End of training

Browse files
Files changed (3) hide show
  1. README.md +15 -12
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,12 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [AnonymousCS/populism_multilingual_bert_uncased_v2](https://huggingface.co/AnonymousCS/populism_multilingual_bert_uncased_v2) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6965
22
- - Accuracy: 0.6870
23
- - 1-f1: 0.2379
24
- - 1-recall: 0.8649
25
- - 1-precision: 0.1379
26
- - Balanced Acc: 0.7706
27
 
28
  ## Model description
29
 
@@ -42,9 +42,9 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 3e-05
46
- - train_batch_size: 16
47
- - eval_batch_size: 16
48
  - seed: 42
49
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
@@ -55,9 +55,12 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
58
- | 0.1149 | 1.0 | 18 | 0.6490 | 0.7588 | 0.2818 | 0.8378 | 0.1694 | 0.7959 |
59
- | 0.0428 | 2.0 | 36 | 1.1044 | 0.6550 | 0.2207 | 0.8649 | 0.1265 | 0.7536 |
60
- | 0.6395 | 3.0 | 54 | 0.6965 | 0.6870 | 0.2379 | 0.8649 | 0.1379 | 0.7706 |
 
 
 
61
 
62
 
63
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [AnonymousCS/populism_multilingual_bert_uncased_v2](https://huggingface.co/AnonymousCS/populism_multilingual_bert_uncased_v2) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8742
22
+ - Accuracy: 0.8427
23
+ - 1-f1: 0.3355
24
+ - 1-recall: 0.7027
25
+ - 1-precision: 0.2203
26
+ - Balanced Acc: 0.7769
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 1e-05
46
+ - train_batch_size: 32
47
+ - eval_batch_size: 32
48
  - seed: 42
49
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: linear
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
57
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
58
+ | 0.1663 | 1.0 | 9 | 1.0609 | 0.7435 | 0.2632 | 0.8108 | 0.1571 | 0.7751 |
59
+ | 0.2964 | 2.0 | 18 | 0.7859 | 0.8061 | 0.3060 | 0.7568 | 0.1918 | 0.7829 |
60
+ | 0.0629 | 3.0 | 27 | 0.7313 | 0.7695 | 0.2911 | 0.8378 | 0.1761 | 0.8016 |
61
+ | 0.0174 | 4.0 | 36 | 0.7297 | 0.8336 | 0.3313 | 0.7297 | 0.2143 | 0.7848 |
62
+ | 0.0657 | 5.0 | 45 | 0.9259 | 0.7893 | 0.31 | 0.8378 | 0.1902 | 0.8121 |
63
+ | 0.0357 | 6.0 | 54 | 0.8742 | 0.8427 | 0.3355 | 0.7027 | 0.2203 | 0.7769 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb139213fd4ed62dac05cbdcbef04b901984d030e42428e4bac3129e257ce051
3
  size 669455360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab4cc33721c384f847429076862841899161814277cdcb247f0bd798a6ce65c
3
  size 669455360
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8987cd055a5da61f980085ede3eeb8bb9f8193024bedda44a9b4d67e6b0be320
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac1394fed6a3a3037eedec2197540b17e7b77c78c30d5d95f6853765ba4df2d
3
  size 5432