gender-play-gysbert-5a2

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: GroNLP/bert-base-dutch-cased
+license: mit
+base_model: emanjavacas/GysBERT
 tags:
 - generated_from_trainer
 metrics:
@@ -14,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-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.
+This model is a fine-tuned version of [emanjavacas/GysBERT](https://huggingface.co/emanjavacas/GysBERT) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8171
-- Accuracy: 0.6389
+- Loss: 0.6985
+- Accuracy: 0.5045
 
 ## Model description
 
@@ -48,8 +49,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.6804        | 1.1111 | 100  | 0.7366          | 0.5583   |
-| 0.4936        | 2.2222 | 200  | 0.8171          | 0.6389   |
+| 0.7111        | 0.9091 | 100  | 0.7119          | 0.5      |
+| 0.7086        | 1.8182 | 200  | 0.7008          | 0.5023   |
+| 0.6918        | 2.7273 | 300  | 0.6985          | 0.5045   |
 
 
 ### Framework versions

config.json

@@ -1,11 +1,10 @@
 {
-  "_name_or_path": "GroNLP/bert-base-dutch-cased",
+  "_name_or_path": "emanjavacas/GysBERT",
   "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,
@@ -16,12 +15,12 @@
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 3,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30073
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a900606628aa6d9dfb0e8c725df8ba2343b34cf2d31d1f074e340fa382a21a
-size 436579312
+oid sha256:74c79641fa5535e8b7ed30ae4ad14eaa2fd0b8acef411ba7b8aa6724b014c67a
+size 437958648