End of training

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: distilbert/distilbert-base-german-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: task2_small
+  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. -->
+
+# task2_small
+
+This model is a fine-tuned version of [distilbert/distilbert-base-german-cased](https://huggingface.co/distilbert/distilbert-base-german-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0507
+- Precision: 0.8401
+- Recall: 0.8712
+- F1: 0.8554
+- Accuracy: 0.9894
+
+## 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: 16
+- eval_batch_size: 16
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0329        | 1.0   | 2359  | 0.0386          | 0.8098    | 0.8163 | 0.8130 | 0.9870   |
+| 0.0245        | 2.0   | 4718  | 0.0356          | 0.8210    | 0.8551 | 0.8377 | 0.9888   |
+| 0.0158        | 3.0   | 7077  | 0.0401          | 0.8426    | 0.8551 | 0.8488 | 0.9887   |
+| 0.0118        | 4.0   | 9436  | 0.0417          | 0.8144    | 0.8664 | 0.8396 | 0.9885   |
+| 0.0093        | 5.0   | 11795 | 0.0434          | 0.8470    | 0.8522 | 0.8496 | 0.9889   |
+| 0.0063        | 6.0   | 14154 | 0.0472          | 0.8548    | 0.8580 | 0.8564 | 0.9891   |
+| 0.0054        | 7.0   | 16513 | 0.0484          | 0.8450    | 0.8680 | 0.8564 | 0.9893   |
+| 0.0049        | 8.0   | 18872 | 0.0492          | 0.8398    | 0.8693 | 0.8543 | 0.9894   |
+| 0.0033        | 9.0   | 21231 | 0.0502          | 0.8397    | 0.8709 | 0.8550 | 0.9894   |
+| 0.003         | 10.0  | 23590 | 0.0507          | 0.8401    | 0.8712 | 0.8554 | 0.9894   |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 2.14.4
+- Tokenizers 0.21.2

config.json

@@ -0,0 +1,66 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-DRUG",
+    "2": "I-DRUG",
+    "3": "B-DOSAGE",
+    "4": "I-DOSAGE",
+    "5": "B-FORM",
+    "6": "I-FORM",
+    "7": "B-FREQUENCY",
+    "8": "I-FREQUENCY",
+    "9": "B-DURATION",
+    "10": "I-DURATION",
+    "11": "B-STRENGTH",
+    "12": "I-STRENGTH",
+    "13": "B-REASON",
+    "14": "I-REASON",
+    "15": "B-ROUTE",
+    "16": "I-ROUTE",
+    "17": "B-ACTIVEING",
+    "18": "I-ACTIVEING"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-ACTIVEING": 17,
+    "B-DOSAGE": 3,
+    "B-DRUG": 1,
+    "B-DURATION": 9,
+    "B-FORM": 5,
+    "B-FREQUENCY": 7,
+    "B-REASON": 13,
+    "B-ROUTE": 15,
+    "B-STRENGTH": 11,
+    "I-ACTIVEING": 18,
+    "I-DOSAGE": 4,
+    "I-DRUG": 2,
+    "I-DURATION": 10,
+    "I-FORM": 6,
+    "I-FREQUENCY": 8,
+    "I-REASON": 14,
+    "I-ROUTE": 16,
+    "I-STRENGTH": 12,
+    "O": 0
+  },
+  "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": "4.52.4",
+  "vocab_size": 31102
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71bce057d30c618c7e6c137bb0c1e7f5d74a8320068f942075d3903acac0357a
+size 267304068

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 sha256:6cf1e64d4f84fda186969b2fc56bcb27c63418457bafd8d5240d596a8fa76c50
+size 5304