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: 0.8805
-- Accuracy: 0.7368
-- 1-f1: 0.2953
-- 1-recall: 0.9565
-- 1-precision: 0.1746
-- Balanced Acc: 0.8400
+- Loss: 0.5993
+- Accuracy: 0.8571
+- 1-f1: 0.4242
+- 1-recall: 0.9130
+- 1-precision: 0.2763
+- Balanced Acc: 0.8834
 
 ## 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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
-| 0.1097        | 1.0   | 12   | 0.5220          | 0.8145   | 0.3509 | 0.8696   | 0.2198      | 0.8404       |
-| 0.1248        | 2.0   | 24   | 0.4377          | 0.8521   | 0.4040 | 0.8696   | 0.2632      | 0.8603       |
-| 0.0209        | 3.0   | 36   | 0.8916          | 0.6967   | 0.2754 | 1.0      | 0.1597      | 0.8391       |
-| 0.0083        | 4.0   | 48   | 0.8805          | 0.7368   | 0.2953 | 0.9565   | 0.1746      | 0.8400       |
+| 0.1617        | 1.0   | 6    | 0.5288          | 0.8647   | 0.4375 | 0.9130   | 0.2877      | 0.8874       |
+| 0.3458        | 2.0   | 12   | 0.4557          | 0.8747   | 0.4565 | 0.9130   | 0.3043      | 0.8927       |
+| 0.0434        | 3.0   | 18   | 0.4889          | 0.8471   | 0.4190 | 0.9565   | 0.2683      | 0.8985       |
+| 0.0149        | 4.0   | 24   | 0.4399          | 0.8822   | 0.4719 | 0.9130   | 0.3182      | 0.8967       |
+| 0.0059        | 5.0   | 30   | 0.5142          | 0.8822   | 0.4719 | 0.9130   | 0.3182      | 0.8967       |
+| 0.0021        | 6.0   | 36   | 0.5993          | 0.8571   | 0.4242 | 0.9130   | 0.2763      | 0.8834       |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797feb5127b84692f9e626e17cc2a92419f806f9286288a7407652aee632327e
+oid sha256:b0f2f6afadfa87fa6f8e5a301635380238376efc928f1af8c2d96aa562cbf567
 size 669455360

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f697453e6ac92d847b93b9dab2b717369385f09e184367ce6b6f176984c71dad
+oid sha256:84d8be60d09c04f35ee4600ed18208a3dcc2d6e4691155f4174dddeea1f6e806
 size 5432