Model save

README.md

@@ -16,6 +16,14 @@ should probably proofread and complete it, then remove this comment. -->
 # neobert_test
 
 This model is a fine-tuned version of [chandar-lab/NeoBERT](https://huggingface.co/chandar-lab/NeoBERT) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2391
+- Accuracy Offensive: 0.9441
+- F1 Offensive: 0.9425
+- Accuracy Targeted: 0.9441
+- F1 Targeted: 0.9173
+- Accuracy Stance: 0.9079
+- F1 Stance: 0.8717
 
 ## Model description
 
@@ -42,6 +50,15 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 10
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy Offensive | F1 Offensive | Accuracy Targeted | F1 Targeted | Accuracy Stance | F1 Stance |
+|:-------------:|:-----:|:----:|:---------------:|:------------------:|:------------:|:-----------------:|:-----------:|:---------------:|:---------:|
+| 0.5266        | 1.0   | 1490 | 0.2391          | 0.9441             | 0.9425       | 0.9441            | 0.9173      | 0.9079          | 0.8717    |
+| 0.2303        | 2.0   | 2980 | 0.2468          | 0.9441             | 0.9425       | 0.9441            | 0.9173      | 0.9079          | 0.8717    |
+| 0.2159        | 3.0   | 4470 | 0.2442          | 0.9441             | 0.9425       | 0.9441            | 0.9173      | 0.9079          | 0.8717    |
+
+
 ### Framework versions
 
 - Transformers 4.50.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d989c5eafcb59629a628573f5dadfd14803e85b482d2e235dc740f3f2fc27488
+oid sha256:3db4950a995c5a17ee2b7f842bee8ebd936b72ef03e9f18b09e0c608f3a3376c
 size 95428636