End of training

README.md

@@ -3,6 +3,9 @@ license: mit
 base_model: DTAI-KULeuven/robbert-2023-dutch-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
+- f1
 model-index:
 - name: thesis_RobBERT
   results: []
@@ -14,6 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
 # thesis_RobBERT
 
 This model is a fine-tuned version of [DTAI-KULeuven/robbert-2023-dutch-base](https://huggingface.co/DTAI-KULeuven/robbert-2023-dutch-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.6461
+- Accuracy: 0.1827
+- F1: 0.0891
 
 ## Model description
 
@@ -41,6 +48,13 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 1
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 5.1293        | 1.0   | 489  | 4.6461          | 0.1827   | 0.0891 |
+
+
 ### Framework versions
 
 - Transformers 4.38.2

config.json

@@ -1060,6 +1060,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "sep_token_id": 3,
   "tokenizer_class": "RobertaTokenizerFast",
   "torch_dtype": "float32",

logs/events.out.tfevents.1712935702.3abc3077e426.695.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f88e7cc24e31e457b0317e0bce3c8e40a9923fb7495f62e1b569895681becc
+size 39004

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:618a5f8b4411a549b5f723409cb88d35271b9fcfaf5576678e81ecf7d33f9eab
+oid sha256:f9561bd48219abe9dbb177b06722dfc1669a68b38c71d9d61396bd413eeeaf98
 size 499382884