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: 0.6624
-- Accuracy: 0.8439
-- 1-f1: 0.2273
-- 1-recall: 0.8
-- 1-precision: 0.1325
-- Balanced Acc: 0.8226
+- Loss: 0.5856
+- Accuracy: 0.8921
+- 1-f1: 0.2769
+- 1-recall: 0.72
+- 1-precision: 0.1714
+- Balanced Acc: 0.8086
 
 ## 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
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1   | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
-| 0.7627        | 1.0   | 17   | 0.5292          | 0.8565   | 0.2604 | 0.88     | 0.1528      | 0.8679       |
-| 0.1669        | 2.0   | 34   | 0.6007          | 0.8358   | 0.2099 | 0.76     | 0.1218      | 0.7990       |
-| 0.0427        | 3.0   | 51   | 0.6624          | 0.8439   | 0.2273 | 0.8      | 0.1325      | 0.8226       |
+| 0.072         | 1.0   | 9    | 0.5569          | 0.8519   | 0.2543 | 0.88     | 0.1486      | 0.8655       |
+| 0.0128        | 2.0   | 18   | 0.6338          | 0.8599   | 0.2469 | 0.8      | 0.1460      | 0.8309       |
+| 0.0272        | 3.0   | 27   | 0.5856          | 0.8921   | 0.2769 | 0.72     | 0.1714      | 0.8086       |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5cae3e99c5f5f7bcf7748865e7a8f4fa3013c065df40c458d72f51445b02b8f
+oid sha256:47c0abf548bf22bcb4bc831953aa7bb15bdf12877200624feb1c6318312908e5
 size 669455360

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd82c859e0ed453f75781b2ea020c49b8bca9448c7d66713f40102c7225ae0e2
+oid sha256:a1a47dd5c2a6e6a2f975c4fd8b015a9031eb44a06048a2da136d2f0cf3f0e973
 size 5432