Upload README.md

README.md

@@ -1,22 +1,50 @@
 ---
+language:
+- de
 license: mit
-tags:
-- generated_from_keras_callback
+datasets:
+- germeval_14
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
-- name: HuggingAlex1247/distilbert-base-german-europeana-cased-germeval_14
-  results: []
+- name: distilbert-base-german-europeana-cased-germeval_14
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: germeval_14
+      type: germeval_14
+      args: default
+    metrics:
+    - name: precision
+      type: precision
+      value: 0.7437097717963721
+    - name: recall
+      type: recall
+      value: 0.7571485305798252
+    - name: f1
+      type: f1
+      value: 0.7503689855357669
+    - name: accuracy
+      type: accuracy
+      value: 0.9541357066185896
 ---
 
-<!-- This model card has been generated automatically according to the information Keras had access to. You should
-probably proofread and complete it, then remove this comment. -->
+<!-- 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. -->
 
-# HuggingAlex1247/distilbert-base-german-europeana-cased-germeval_14
+# distilbert-base-german-europeana-cased-germeval_14
 
-This model is a fine-tuned version of [dbmdz/distilbert-base-german-europeana-cased](https://huggingface.co/dbmdz/distilbert-base-german-europeana-cased) on an unknown dataset.
+This model is a fine-tuned version of [dbmdz/distilbert-base-german-europeana-cased](https://huggingface.co/dbmdz/distilbert-base-german-europeana-cased) on the germeval_14 dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.0433
-- Validation Loss: 0.1874
-- Epoch: 9
+- precision: 0.7437
+- recall: 0.7571
+- f1: 0.7504
+- accuracy: 0.9541
 
 ## Model description
 
@@ -35,28 +63,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 25500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
-- training_precision: float32
-
-### Training results
-
-| Train Loss | Validation Loss | Epoch |
-|:----------:|:---------------:|:-----:|
-| 0.3609     | 0.2115          | 0     |
-| 0.1889     | 0.1810          | 1     |
-| 0.1430     | 0.1729          | 2     |
-| 0.1115     | 0.1647          | 3     |
-| 0.0887     | 0.1715          | 4     |
-| 0.0726     | 0.1754          | 5     |
-| 0.0607     | 0.1790          | 6     |
-| 0.0528     | 0.1838          | 7     |
-| 0.0473     | 0.1853          | 8     |
-| 0.0433     | 0.1874          | 9     |
-
+- num_train_epochs: 10
+- train_batch_size: 8
+- eval_batch_size: 8
+- learning_rate: 1e-05
+- weight_decay_rate: 0.01
+- num_warmup_steps: 0
+- fp16: True
 
 ### Framework versions
 
 - Transformers 4.17.0
-- TensorFlow 2.6.2
 - Datasets 1.18.0
 - Tokenizers 0.11.6