test README

README.md

@@ -10,32 +10,40 @@ model-index:
   - task:
       type: text-classification
     dataset:
-      name: mdk_gov_data_titles_clf
+      name: and-effect/mdk_gov_data_titles_clf
       type: and-effect/mdk_gov_data_titles_clf
     metrics:
-    - type: Accuracy (Bezeichnung)
-      value: 0.7
-    - type: Macro Precision (Bezeichnung)
-      value: 0.5
-    - type: Macro Recall (Bezeichnung)
-      value: 0.61
-    - type: Macro F1(Bezeichnung)
-      value: 0.58
-    - type: Accuracy (Thema)
-      value: 0.92
-    - type: Macro Precision (Thema)
-      value: 0.93
-    - type: Macro Recall (Thema)
-      value: 0.91
-    - type: Macro F1 (Thema)
-      value: 0.9
+    - type: evaluate-metric/accuracy
+      value: '0.7'
+      name: Accuracy Bezeichnung
+    - type: evaluate-metric/precision
+      value: '0.5'
+      name: Precision Bezeichnung
+    - type: evaluate-metric/recall
+      value: '0.61'
+      name: Recall Bezeichnung
+    - type: evaluate-metric/f1
+      value: '0.58'
+      name: F1 Bezeichnung
+    - type: evaluate-metric/accuracy
+      value: '0.92'
+      name: Accuracy Thema
+    - type: evaluate-metric/precision
+      value: '0.93'
+      name: Precision Thema
+    - type: evaluate-metric/recall
+      value: '0.91'
+      name: Recall Thema
+    - type: evaluate-metric/f1
+      value: '0.9'
+      name: F1 Thema
 ---
 
-# Model Card for Musterdatenkatalog Classifier test
+# Model Card for Musterdatenkatalog Classifier
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-
+[More Information Needed]
 
 # Model Details
 
@@ -62,7 +70,7 @@ This model is based on bert-base-german-cased and fine-tuned on and-effect/mdk_g
 
 # Direct Use
 
-[More Information Needed]
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
 ## Get Started with Sentence Transformers
 Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
@@ -146,7 +154,7 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 <!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
-[More Information Needed]
+You can find all information about the training data [here](https://huggingface.co/datasets/and-effect/mdk_gov_data_titles_clf)
 
 ## Training Procedure [optional]
 
@@ -156,6 +164,32 @@ Users (both direct and downstream) should be made aware of the risks, biases and
 
 [More Information Needed]
 
+## Training Parameter
+The model was trained with the parameters:
+
+**DataLoader**:
+`torch.utils.data.dataloader.DataLoader`
+
+**Loss**:
+`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss` 
+
+Hyperparameter:
+```
+{
+    "epochs": [More Information Needed],
+    "evaluation_steps": 0,
+    "evaluator": NoneType,
+    "max_grad_norm": 1,
+    "optimizer_class": <class 'torch.optim.adamw.AdamW'>,
+    "optimizer_params": {'learning rate': 2e-05},
+    "scheduler": WarmupLinear,
+    "steps_per_epoch": null,
+    "warmup_steps": 100,
+    "weight_decay":0.01
+}
+```
+
+
 ### Speeds, Sizes, Times
 
 <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->