Update README.md

README.md

@@ -6,40 +6,40 @@ tags:
 model-index:
 - name: bert-mapa-german
   results: []
+language:
+- de
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
 # bert-mapa-german
 
-This model is a fine-tuned version of [google-bert/bert-base-german-cased](https://huggingface.co/google-bert/bert-base-german-cased) on the None dataset.
-It achieves the following results on the evaluation set:
+This model is a fine-tuned version of [google-bert/bert-base-german-cased](https://huggingface.co/google-bert/bert-base-german-cased) on the MAPA german dataset.
+It's purpose is to discern private information within German texts.
+
+It achieves the following results on the test set:
+
+| Category      | Precision  | Recall     | F1         | Number |
+|---------------|------------|------------|------------|--------|
+| Address       | 0.5882     | 0.6667     | 0.625      | 15     |
+| Age           | 0.0        | 0.0        | 0.0        | 3      |
+| Amount        | 1.0        | 1.0        | 1.0        | 1      |
+| Date          | 0.9455     | 0.9455     | 0.9455     | 55     |
+| Name          | 0.7        | 0.9545     | 0.8077     | 22     |
+| Organisation  | 0.5405     | 0.6452     | 0.5882     | 31     |
+| Person        | 0.5385     | 0.5        | 0.5185     | 14     |
+| Role          | 0.0        | 0.0        | 0.0        | 1      |
+| Overall       | 0.7255     | 0.7817     | 0.7525     |        |
+
 - Loss: 0.0325
-- Address: {'precision': 0.5882352941176471, 'recall': 0.6666666666666666, 'f1': 0.625, 'number': 15}
-- Age: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}
-- Amount: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1}
-- Date: {'precision': 0.9454545454545454, 'recall': 0.9454545454545454, 'f1': 0.9454545454545454, 'number': 55}
-- Name: {'precision': 0.7, 'recall': 0.9545454545454546, 'f1': 0.8076923076923077, 'number': 22}
-- Organisation: {'precision': 0.5405405405405406, 'recall': 0.6451612903225806, 'f1': 0.588235294117647, 'number': 31}
-- Person: {'precision': 0.5384615384615384, 'recall': 0.5, 'f1': 0.5185185185185186, 'number': 14}
-- Role: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1}
-- Overall Precision: 0.7255
-- Overall Recall: 0.7817
-- Overall F1: 0.7525
 - Overall Accuracy: 0.9912
 
-## Model description
-
-More information needed
 
 ## Intended uses & limitations
 
-More information needed
+This model is engineered for the purpose of discerning private information within German texts. Its training corpus comprises only 1744 example sentences, thereby leading to a higher frequency of errors in its predictions.
 
 ## Training and evaluation data
 
-More information needed
+Random split of the MAPA german dataset into 80% train, 10% valdiation and 10% test.
 
 ## Training procedure
 
@@ -56,12 +56,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Address                                                                                    | Amount                                                    | Date                                                                                                    | Marital status                                            | Name                                                                                                    | Organisation                                                                               | Person                                                                                                  | Profession                                                | Role                                                      | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:------------------------------------------------------------------------------------------:|:---------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------:|:---------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| No log        | 1.0   | 218  | 0.0607          | {'precision': 0.5882352941176471, 'recall': 0.6666666666666666, 'f1': 0.625, 'number': 15} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.851063829787234, 'recall': 0.9090909090909091, 'f1': 0.8791208791208791, 'number': 44}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.76, 'recall': 0.9047619047619048, 'f1': 0.8260869565217391, 'number': 21}               | {'precision': 0.4915254237288136, 'recall': 0.725, 'f1': 0.5858585858585859, 'number': 40} | {'precision': 0.5, 'recall': 0.6153846153846154, 'f1': 0.5517241379310345, 'number': 13}                | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | 0.6527            | 0.7786         | 0.7101     | 0.9859           |
-| No log        | 2.0   | 436  | 0.0479          | {'precision': 0.65, 'recall': 0.8666666666666667, 'f1': 0.7428571428571429, 'number': 15}  | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.8958333333333334, 'recall': 0.9772727272727273, 'f1': 0.9347826086956522, 'number': 44} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.6774193548387096, 'recall': 1.0, 'f1': 0.8076923076923077, 'number': 21}                | {'precision': 0.5897435897435898, 'recall': 0.575, 'f1': 0.5822784810126582, 'number': 40} | {'precision': 0.7857142857142857, 'recall': 0.8461538461538461, 'f1': 0.8148148148148148, 'number': 13} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | 0.7355            | 0.8143         | 0.7729     | 0.9896           |
-| 0.116         | 3.0   | 654  | 0.0414          | {'precision': 0.65, 'recall': 0.8666666666666667, 'f1': 0.7428571428571429, 'number': 15}  | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.8958333333333334, 'recall': 0.9772727272727273, 'f1': 0.9347826086956522, 'number': 44} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.7407407407407407, 'recall': 0.9523809523809523, 'f1': 0.8333333333333334, 'number': 21} | {'precision': 0.725, 'recall': 0.725, 'f1': 0.7250000000000001, 'number': 40}              | {'precision': 0.6666666666666666, 'recall': 0.7692307692307693, 'f1': 0.7142857142857142, 'number': 13} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | 0.7712            | 0.8429         | 0.8055     | 0.9908           |
-| 0.116         | 4.0   | 872  | 0.0421          | {'precision': 0.65, 'recall': 0.8666666666666667, 'f1': 0.7428571428571429, 'number': 15}  | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 3} | {'precision': 0.8958333333333334, 'recall': 0.9772727272727273, 'f1': 0.9347826086956522, 'number': 44} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.8, 'recall': 0.9523809523809523, 'f1': 0.8695652173913043, 'number': 21}                | {'precision': 0.6818181818181818, 'recall': 0.75, 'f1': 0.7142857142857143, 'number': 40}  | {'precision': 0.8571428571428571, 'recall': 0.9230769230769231, 'f1': 0.888888888888889, 'number': 13}  | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | 0.7857            | 0.8643         | 0.8231     | 0.9917           |
+| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| No log        | 1.0   | 218  | 0.0607          | 0.6527            | 0.7786         | 0.7101     | 0.9859           |
+| No log        | 2.0   | 436  | 0.0479          | 0.7355            | 0.8143         | 0.7729     | 0.9896           |
+| 0.116         | 3.0   | 654  | 0.0414          | 0.7712            | 0.8429         | 0.8055     | 0.9908           |
+| 0.116         | 4.0   | 872  | 0.0421          | 0.7857            | 0.8643         | 0.8231     | 0.9917           |
 
 
 ### Framework versions
@@ -69,4 +69,4 @@ The following hyperparameters were used during training:
 - Transformers 4.40.0
 - Pytorch 2.1.0+cu121
 - Datasets 2.19.0
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1