Hugging Face's logo

AnonymousCS
/
populism_classifier_370

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Community
AnonymousCS commited on
Commit
175eeea
·
verified ·
1 Parent(s): 46b26a1

End of training

Browse files
Files changed (3) hide show
  1. README.md +12 -13
  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_english_bert_large_uncased](https://huggingface.co/AnonymousCS/populism_english_bert_large_uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4759
22
- - Accuracy: 0.9492
23
- - 1-f1: 0.675
24
- - 1-recall: 0.8182
25
- - 1-precision: 0.5745
26
- - Balanced Acc: 0.8882
27
 
28
  ## Model description
29
 
@@ -43,8 +43,8 @@ More information needed
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 1e-05
46
- - train_batch_size: 128
47
- - eval_batch_size: 128
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
@@ -55,11 +55,10 @@ 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
- | 0.3183 | 1.0 | 16 | 0.3212 | 0.7988 | 0.3905 | 1.0 | 0.2426 | 0.8925 |
59
- | 0.2097 | 2.0 | 32 | 0.2201 | 0.8652 | 0.4889 | 1.0 | 0.3235 | 0.9280 |
60
- | 0.1279 | 3.0 | 48 | 0.2114 | 0.9414 | 0.6591 | 0.8788 | 0.5273 | 0.9123 |
61
- | 0.0676 | 4.0 | 64 | 0.5225 | 0.9609 | 0.6875 | 0.6667 | 0.7097 | 0.8239 |
62
- | 0.0056 | 5.0 | 80 | 0.4759 | 0.9492 | 0.675 | 0.8182 | 0.5745 | 0.8882 |
63
 
64
 
65
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [AnonymousCS/populism_english_bert_large_uncased](https://huggingface.co/AnonymousCS/populism_english_bert_large_uncased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8051
22
+ - Accuracy: 0.9551
23
+ - 1-f1: 0.6102
24
+ - 1-recall: 0.5455
25
+ - 1-precision: 0.6923
26
+ - Balanced Acc: 0.7644
27
 
28
  ## Model description
29
 
 
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 1e-05
46
+ - train_batch_size: 64
47
+ - eval_batch_size: 64
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
+ | 0.405 | 1.0 | 32 | 0.2995 | 0.8379 | 0.4430 | 1.0 | 0.2845 | 0.9134 |
59
+ | 0.3296 | 2.0 | 64 | 0.4311 | 0.9609 | 0.6970 | 0.6970 | 0.6970 | 0.8380 |
60
+ | 0.1432 | 3.0 | 96 | 0.5666 | 0.9492 | 0.6579 | 0.7576 | 0.5814 | 0.8600 |
61
+ | 0.0227 | 4.0 | 128 | 0.8051 | 0.9551 | 0.6102 | 0.5455 | 0.6923 | 0.7644 |
 
62
 
63
 
64
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6da21d0acd87326797bf01ccad5297cc14752189a8938de262a72a08f4d1c6b3
3
  size 1340622760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea6898fed37e9b799be64e5535577be5bf847bb42f1156121f571e0c9c6e8fd
3
  size 1340622760
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f05b15a85b1918bf07b32bf2d70cedcba4b48f2cbd7b31c7a477412da715d0c
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fae88609307a5d793b8a57f3cdab43ddc3be0e838c7be2e00e4db310066ffc41
3
  size 5432