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: 0.4494
-- Accuracy: 0.8878
-- 1-f1: 0.4124
-- 1-recall: 1.0
-- 1-precision: 0.2597
-- Balanced Acc: 0.9416
+- Loss: 0.4623
+- Accuracy: 0.8937
+- 1-f1: 0.4130
+- 1-recall: 0.95
+- 1-precision: 0.2639
+- Balanced Acc: 0.9207
 
 ## 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 +55,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1   | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
-| 0.3074        | 1.0   | 11   | 0.6275          | 0.8484   | 0.3419 | 1.0      | 0.2062      | 0.9211       |
-| 0.3649        | 2.0   | 22   | 0.3886          | 0.9055   | 0.4286 | 0.9      | 0.2812      | 0.9029       |
-| 0.0571        | 3.0   | 33   | 0.4495          | 0.8504   | 0.3448 | 1.0      | 0.2083      | 0.9221       |
-| 0.0474        | 4.0   | 44   | 0.4494          | 0.8878   | 0.4124 | 1.0      | 0.2597      | 0.9416       |
+| 0.0302        | 1.0   | 6    | 0.3907          | 0.8819   | 0.3878 | 0.95     | 0.2436      | 0.9145       |
+| 0.0464        | 2.0   | 12   | 0.3874          | 0.9016   | 0.4186 | 0.9      | 0.2727      | 0.9008       |
+| 0.0545        | 3.0   | 18   | 0.3953          | 0.8878   | 0.4000 | 0.95     | 0.2533      | 0.9176       |
+| 0.0115        | 4.0   | 24   | 0.3764          | 0.9075   | 0.4471 | 0.95     | 0.2923      | 0.9279       |
+| 0.0073        | 5.0   | 30   | 0.4056          | 0.9016   | 0.4318 | 0.95     | 0.2794      | 0.9248       |
+| 0.0023        | 6.0   | 36   | 0.4623          | 0.8937   | 0.4130 | 0.95     | 0.2639      | 0.9207       |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a8cfdbd41a7e8d674ed062cf5bdb8d14dc695aa5e8527195ef516353ac1d973
+oid sha256:ccf072b9836bf653d8b39ecb8e1e8dc337c3ea33eedea0058c3a1911321e4a2d
 size 669455360

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6507f647f3b82faccf223d40cde15f067c46193d1a2775e7fda0d900178300f9
+oid sha256:7aaf4f9af0962115e99f82a4dc3887630747460060eac477b27e6d5f25a96013
 size 5432