End of training

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert-base-german-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: distilbert-german-finetuned-ner-v2
+  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. -->
+
+# distilbert-german-finetuned-ner-v2
+
+This model is a fine-tuned version of [distilbert-base-german-cased](https://huggingface.co/distilbert-base-german-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0016
+- Precision: 0.9985
+- Recall: 0.9982
+- F1: 0.9983
+- Accuracy: 0.9995
+
+## 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 | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.041         | 1.0   | 1000 | 0.0077          | 0.9919    | 0.9934 | 0.9926 | 0.9980   |
+| 0.0068        | 2.0   | 2000 | 0.0041          | 0.9969    | 0.9971 | 0.9970 | 0.9989   |
+| 0.0032        | 3.0   | 3000 | 0.0016          | 0.9985    | 0.9982 | 0.9983 | 0.9995   |
+
+
+### Framework versions
+
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.2

config.json

@@ -0,0 +1,58 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "0",
+    "1": "B-DAT",
+    "2": "I-DAT",
+    "3": "B-TIM",
+    "4": "I-TIM",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-DUR",
+    "8": "I-DUR",
+    "9": "B-MON",
+    "10": "I-MON",
+    "11": "B-URL",
+    "12": "I-URL",
+    "13": "B-TYP",
+    "14": "I-TYP"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "B-DAT": 1,
+    "B-DUR": 7,
+    "B-LOC": 5,
+    "B-MON": 9,
+    "B-TIM": 3,
+    "B-TYP": 13,
+    "B-URL": 11,
+    "I-DAT": 2,
+    "I-DUR": 8,
+    "I-LOC": 6,
+    "I-MON": 10,
+    "I-TIM": 4,
+    "I-TYP": 14,
+    "I-URL": 12
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "vocab_size": 31102
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ae4878c095c4a857b9e02109b780d268e18d26e9dca3c670a0a17135b75a31
+size 267291764

runs/Jul08_08-17-01_b668b40c9a7b/events.out.tfevents.1751962630.b668b40c9a7b.267.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34c0c4a16399bab98a1eea32d0a9f2f9282b3f9be0ab6907be17feac30d0de6
+size 8598

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
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54df6c63c3cb74b68a7c4dd5475ed5d40616031439a2aae87f3886ff235198b2
+size 5368