Training in progress, epoch 1

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+base_model: mschiesser/ner-bert-german
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: ner-bert-german-addresses-finetuned
+  results: []
+---
+
+<!-- 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-bert-german-addresses-finetuned
+
+This model is a fine-tuned version of [mschiesser/ner-bert-german](https://huggingface.co/mschiesser/ner-bert-german) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0
+- Precision: 1.0
+- Recall: 1.0
+- F1: 1.0
+- Accuracy: 1.0
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:---:|:--------:|
+| 0.0           | 1.0   | 37824  | 0.0000          | 1.0       | 1.0    | 1.0 | 1.0      |
+| 0.0           | 2.0   | 75648  | 0.0000          | 1.0       | 1.0    | 1.0 | 1.0      |
+| 0.0           | 3.0   | 113472 | 0.0             | 1.0       | 1.0    | 1.0 | 1.0      |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.4.0+cu118
+- Datasets 2.21.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "mschiesser/ner-bert-german",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-GEMEINDE",
+    "2": "I-GEMEINDE",
+    "3": "B-STRASSENNAME",
+    "4": "I-STRASSENNAME",
+    "5": "B-HAUSNUMMER",
+    "6": "I-HAUSNUMMER",
+    "7": "B-POSTLEITZAHL",
+    "8": "I-POSTLEITZAHL"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-GEMEINDE": 1,
+    "B-HAUSNUMMER": 5,
+    "B-POSTLEITZAHL": 7,
+    "B-STRASSENNAME": 3,
+    "I-GEMEINDE": 2,
+    "I-HAUSNUMMER": 6,
+    "I-POSTLEITZAHL": 8,
+    "I-STRASSENNAME": 4,
+    "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,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7034f7013cc00b82474c60cac3e7ba177efb2b57d5dadb109eb990a87a6e934
+size 709102436

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "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 sha256:90aae417c0cd49fcf3558eb1e15fe888f8f37613d7223303f3f17fbfeb5ca7ce
+size 4728