Training completed!

README.md

@@ -0,0 +1,93 @@
+---
+library_name: transformers
+license: mit
+base_model: bert-base-german-cased
+tags:
+- generated_from_trainer
+datasets:
+- germeval_14
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: ner_model
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: germeval_14
+      type: germeval_14
+      config: germeval_14
+      split: test
+      args: germeval_14
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9703112769708805
+    - name: F1
+      type: f1
+      value: 0.8348410033576931
+    - name: Precision
+      type: precision
+      value: 0.8311310366525091
+    - name: Recall
+      type: recall
+      value: 0.8385842393460836
+---
+
+<!-- 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. -->
+
+# ner_model
+
+This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on the germeval_14 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1446
+- Accuracy: 0.9703
+- F1: 0.8348
+- Precision: 0.8311
+- Recall: 0.8386
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.1274        | 1.0   | 3000 | 0.1132          | 0.9671   | 0.8144 | 0.8031    | 0.8260 |
+| 0.065         | 2.0   | 6000 | 0.1382          | 0.9690   | 0.8301 | 0.8452    | 0.8155 |
+| 0.0365        | 3.0   | 9000 | 0.1446          | 0.9703   | 0.8348 | 0.8311    | 0.8386 |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,79 @@
+{
+  "_name_or_path": "bert-base-german-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-LOC",
+    "2": "I-LOC",
+    "3": "B-LOCderiv",
+    "4": "I-LOCderiv",
+    "5": "B-LOCpart",
+    "6": "I-LOCpart",
+    "7": "B-ORG",
+    "8": "I-ORG",
+    "9": "B-ORGderiv",
+    "10": "I-ORGderiv",
+    "11": "B-ORGpart",
+    "12": "I-ORGpart",
+    "13": "B-OTH",
+    "14": "I-OTH",
+    "15": "B-OTHderiv",
+    "16": "I-OTHderiv",
+    "17": "B-OTHpart",
+    "18": "I-OTHpart",
+    "19": "B-PER",
+    "20": "I-PER",
+    "21": "B-PERderiv",
+    "22": "I-PERderiv",
+    "23": "B-PERpart",
+    "24": "I-PERpart"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 1,
+    "B-LOCderiv": 3,
+    "B-LOCpart": 5,
+    "B-ORG": 7,
+    "B-ORGderiv": 9,
+    "B-ORGpart": 11,
+    "B-OTH": 13,
+    "B-OTHderiv": 15,
+    "B-OTHpart": 17,
+    "B-PER": 19,
+    "B-PERderiv": 21,
+    "B-PERpart": 23,
+    "I-LOC": 2,
+    "I-LOCderiv": 4,
+    "I-LOCpart": 6,
+    "I-ORG": 8,
+    "I-ORGderiv": 10,
+    "I-ORGpart": 12,
+    "I-OTH": 14,
+    "I-OTHderiv": 16,
+    "I-OTHpart": 18,
+    "I-PER": 20,
+    "I-PERderiv": 22,
+    "I-PERpart": 24,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8b1467cb78f6348a57e68e880135b6f870eefc947258765c788be60efed255
+size 434063252

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2508f21ac071b9e6eaad33d0741cdd5e2952b5c8ecaaefbc06e64c1772eebe
+size 5304