sianbrumm/class_classificator_ndc

README.md

@@ -0,0 +1,71 @@
+---
+license: mit
+base_model: dbmdz/bert-base-german-uncased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: class_classificator_results
+  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. -->
+
+# class_classificator_results
+
+This model is a fine-tuned version of [dbmdz/bert-base-german-uncased](https://huggingface.co/dbmdz/bert-base-german-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0045
+- Precision: 0.9378
+- Recall: 0.9378
+- F1: 0.9378
+- Accuracy: 0.9378
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1623        | 1.0   | 2527  | 0.9948          | 0.9213    | 0.9213 | 0.9213 | 0.9213   |
+| 0.1321        | 2.0   | 5054  | 0.9662          | 0.9268    | 0.9268 | 0.9268 | 0.9268   |
+| 0.063         | 3.0   | 7581  | 0.9424          | 0.9330    | 0.9330 | 0.9330 | 0.9330   |
+| 0.0247        | 4.0   | 10108 | 0.9948          | 0.9351    | 0.9351 | 0.9351 | 0.9351   |
+| 0.007         | 5.0   | 12635 | 1.0045          | 0.9378    | 0.9378 | 0.9378 | 0.9378   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,172 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "50181700",
+    "1": "50240300",
+    "2": "50202200",
+    "3": "50221200",
+    "4": "50102100",
+    "5": "50192300",
+    "6": "50340100",
+    "7": "50390100",
+    "8": "50202300",
+    "9": "50202700",
+    "10": "50131800",
+    "11": "50192900",
+    "12": "50193100",
+    "13": "50181900",
+    "14": "50171800",
+    "15": "50182100",
+    "16": "50191500",
+    "17": "50131700",
+    "18": "50101900",
+    "19": "50182200",
+    "20": "50151500",
+    "21": "50161800",
+    "22": "50240100",
+    "23": "50171500",
+    "24": "50192400",
+    "25": "50192100",
+    "26": "50193400",
+    "27": "50221000",
+    "28": "50161500",
+    "29": "50171700",
+    "30": "50290100",
+    "31": "50182000",
+    "32": "50251000",
+    "33": "50132000",
+    "34": "50171900",
+    "35": "50132100",
+    "36": "50193300",
+    "37": "50131900",
+    "38": "50192500",
+    "39": "50172000",
+    "40": "50250800",
+    "41": "50121900",
+    "42": "50132500",
+    "43": "50193800",
+    "44": "50202400",
+    "45": "50193000",
+    "46": "50102000",
+    "47": "50202600",
+    "48": "50260100",
+    "49": "50122100",
+    "50": "50193200",
+    "51": "50202500",
+    "52": "50122500",
+    "53": "50320100",
+    "54": "50230100",
+    "55": "50161900",
+    "56": "50101800",
+    "57": "50182300",
+    "58": "50201700",
+    "59": "50221300",
+    "60": "50151600",
+    "61": "50132200",
+    "62": "50102200",
+    "63": "50251200",
+    "64": "50310100",
+    "65": "50132600",
+    "66": "50270100",
+    "67": "50121500",
+    "68": "50350400",
+    "69": "50193500",
+    "70": "50240200"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "50101800": 56,
+    "50101900": 18,
+    "50102000": 46,
+    "50102100": 4,
+    "50102200": 62,
+    "50121500": 67,
+    "50121900": 41,
+    "50122100": 49,
+    "50122500": 52,
+    "50131700": 17,
+    "50131800": 10,
+    "50131900": 37,
+    "50132000": 33,
+    "50132100": 35,
+    "50132200": 61,
+    "50132500": 42,
+    "50132600": 65,
+    "50151500": 20,
+    "50151600": 60,
+    "50161500": 28,
+    "50161800": 21,
+    "50161900": 55,
+    "50171500": 23,
+    "50171700": 29,
+    "50171800": 14,
+    "50171900": 34,
+    "50172000": 39,
+    "50181700": 0,
+    "50181900": 13,
+    "50182000": 31,
+    "50182100": 15,
+    "50182200": 19,
+    "50182300": 57,
+    "50191500": 16,
+    "50192100": 25,
+    "50192300": 5,
+    "50192400": 24,
+    "50192500": 38,
+    "50192900": 11,
+    "50193000": 45,
+    "50193100": 12,
+    "50193200": 50,
+    "50193300": 36,
+    "50193400": 26,
+    "50193500": 69,
+    "50193800": 43,
+    "50201700": 58,
+    "50202200": 2,
+    "50202300": 8,
+    "50202400": 44,
+    "50202500": 51,
+    "50202600": 47,
+    "50202700": 9,
+    "50221000": 27,
+    "50221200": 3,
+    "50221300": 59,
+    "50230100": 54,
+    "50240100": 22,
+    "50240200": 70,
+    "50240300": 1,
+    "50250800": 40,
+    "50251000": 32,
+    "50251200": 63,
+    "50260100": 48,
+    "50270100": 66,
+    "50290100": 30,
+    "50310100": 64,
+    "50320100": 53,
+    "50340100": 6,
+    "50350400": 68,
+    "50390100": 7
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77ebf4aa9423ae4a37d28296516d64d27a75f71cc02e9d14104672064201deb
+size 439952652

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 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "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 sha256:6b888713ca79cda91207de1ccac2f7e6bd36da0532c9a9481f0a34534d9d3901
+size 4667