gender-play-gysbert-4b

README.md

@@ -1,6 +1,5 @@
 ---
-license: mit
-base_model: emanjavacas/GysBERT
+base_model: GroNLP/bert-base-dutch-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [emanjavacas/GysBERT](https://huggingface.co/emanjavacas/GysBERT) on an unknown dataset.
+This model is a fine-tuned version of [GroNLP/bert-base-dutch-cased](https://huggingface.co/GroNLP/bert-base-dutch-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6299
-- Accuracy: 0.6589
+- Loss: 0.9758
+- Accuracy: 0.6464
 
 ## Model description
 
@@ -49,14 +48,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.7228        | 0.7143 | 100  | 0.6931          | 0.4875   |
-| 0.7043        | 1.4286 | 200  | 0.6834          | 0.5357   |
-| 0.6531        | 2.1429 | 300  | 0.6321          | 0.6482   |
-| 0.5927        | 2.8571 | 400  | 0.6299          | 0.6589   |
+| 0.6817        | 0.7143 | 100  | 0.6938          | 0.5696   |
+| 0.5836        | 1.4286 | 200  | 0.7187          | 0.6286   |
+| 0.4291        | 2.1429 | 300  | 0.8203          | 0.6625   |
+| 0.2009        | 2.8571 | 400  | 0.9758          | 0.6464   |
 
 
 ### Framework versions
 
-- Transformers 4.41.1
+- Transformers 4.41.2
 - Pytorch 2.3.0+cu121
 - Tokenizers 0.19.1

config.json

@@ -1,10 +1,11 @@
 {
-  "_name_or_path": "emanjavacas/GysBERT",
+  "_name_or_path": "GroNLP/bert-base-dutch-cased",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -15,12 +16,12 @@
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "pad_token_id": 3,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.41.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30073
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0294e5461fbfb174835f4e5191f3f4eb59b4801a9fbff17d30ad23011e8d7d3c
-size 437958648
+oid sha256:4b07394ba5d96ca47525d8f544181e8ab4d5e5a78db69e872439b7fd1bb42bf1
+size 436579312