End of training

README.md

@@ -18,12 +18,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.8012
-- Accuracy: 0.6986
-- 1-f1: 0.4793
+- Loss: 0.6123
+- Accuracy: 0.7368
+- 1-f1: 0.5133
 - 1-recall: 1.0
-- 1-precision: 0.3152
-- Balanced Acc: 0.825
+- 1-precision: 0.3452
+- Balanced Acc: 0.8472
 
 ## Model description
 
@@ -42,9 +42,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
@@ -55,12 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1   | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
-| 0.3022        | 1.0   | 9    | 1.9260          | 0.2919   | 0.2816 | 1.0      | 0.1638      | 0.5889       |
-| 0.1907        | 2.0   | 18   | 1.1305          | 0.3493   | 0.2990 | 1.0      | 0.1758      | 0.6222       |
-| 0.071         | 3.0   | 27   | 0.7778          | 0.6459   | 0.4308 | 0.9655   | 0.2772      | 0.7800       |
-| 0.2102        | 4.0   | 36   | 0.7717          | 0.6842   | 0.4590 | 0.9655   | 0.3011      | 0.8022       |
-| 0.0285        | 5.0   | 45   | 0.8266          | 0.6699   | 0.4567 | 1.0      | 0.2959      | 0.8083       |
-| 0.0302        | 6.0   | 54   | 0.8012          | 0.6986   | 0.4793 | 1.0      | 0.3152      | 0.825        |
+| 0.1185        | 1.0   | 5    | 1.0444          | 0.6316   | 0.4296 | 1.0      | 0.2736      | 0.7861       |
+| 0.0433        | 2.0   | 10   | 0.4482          | 0.8086   | 0.5918 | 1.0      | 0.4203      | 0.8889       |
+| 0.012         | 3.0   | 15   | 0.3738          | 0.8373   | 0.6136 | 0.9310   | 0.4576      | 0.8766       |
+| 0.0211        | 4.0   | 20   | 0.4960          | 0.7751   | 0.5524 | 1.0      | 0.3816      | 0.8694       |
+| 0.0395        | 5.0   | 25   | 0.6123          | 0.7368   | 0.5133 | 1.0      | 0.3452      | 0.8472       |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa3451c1daf4b413149069e20d02310f3bc6bf2b60f88e1ceceddf0268c51565
+oid sha256:4aae883fb18fd054559fda2a97141fd62912bfe39360a8df82e6597d2c60fcbd
 size 669455360

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6569d6d2c2a8d11e9f7dc3ecf854cc7f91c000175732dd295e8ca3e690f4295
+oid sha256:be3ae79a56ed77baac8ad3f0dab19937dbf10c44318c8c8903623eedef90d923
 size 5432