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: 1.1394
-- Accuracy: 0.6418
-- 1-f1: 0.3425
+- Loss: 0.7925
+- Accuracy: 0.7463
+- 1-f1: 0.4237
 - 1-recall: 1.0
-- 1-precision: 0.2066
-- Balanced Acc: 0.8025
+- 1-precision: 0.2688
+- Balanced Acc: 0.8601
 
 ## 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
@@ -55,10 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1   | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
-| 0.0768        | 1.0   | 8    | 1.1451          | 0.5522   | 0.2941 | 1.0      | 0.1724      | 0.7531       |
-| 0.0282        | 2.0   | 16   | 0.4035          | 0.8396   | 0.5057 | 0.88     | 0.3548      | 0.8577       |
-| 0.0461        | 3.0   | 24   | 0.9247          | 0.6791   | 0.3676 | 1.0      | 0.2252      | 0.8230       |
-| 0.0032        | 4.0   | 32   | 1.1394          | 0.6418   | 0.3425 | 1.0      | 0.2066      | 0.8025       |
+| 0.1843        | 1.0   | 4    | 0.5074          | 0.8134   | 0.5    | 1.0      | 0.3333      | 0.8971       |
+| 0.0175        | 2.0   | 8    | 0.6357          | 0.7612   | 0.4386 | 1.0      | 0.2809      | 0.8683       |
+| 0.0233        | 3.0   | 12   | 0.4706          | 0.8209   | 0.5    | 0.96     | 0.3380      | 0.8833       |
+| 0.0038        | 4.0   | 16   | 0.5882          | 0.7948   | 0.4762 | 1.0      | 0.3125      | 0.8868       |
+| 0.0182        | 5.0   | 20   | 0.7925          | 0.7463   | 0.4237 | 1.0      | 0.2688      | 0.8601       |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a126cedc7f726c396c31231a7251add6125a64c333e0773f17d644aa583be20
+oid sha256:76336d286bc392f6b4e32d43eeb7063429edcc77f061db4eb8fb2e950f4c1e2d
 size 669455360

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e50f63132e4b4871593b1b4d8c759c4bdc3dde70764392345085f55222272cf3
+oid sha256:b258c1ceb01301795e453bd58b25b81e0d09ba142ac5d106025d7801dab9c811
 size 5432