MercuraTech/reranker-de-all-classifier_2

README.md

@@ -0,0 +1,99 @@
+---
+library_name: transformers
+license: mit
+base_model: bert-base-german-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: classifier-de2
+  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. -->
+
+# classifier-de2
+
+This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3294
+- Accuracy: 0.8826
+- Precision: 0.5399
+- Recall: 0.3576
+- F1: 0.4302
+
+## 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: 1.5e-05
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.2757        | 0.0923 | 900   | 0.3526          | 0.8732   | 0.4426    | 0.0879 | 0.1466 |
+| 0.2537        | 0.1845 | 1800  | 0.3498          | 0.8739   | 0.4782    | 0.1823 | 0.2640 |
+| 0.2242        | 0.2768 | 2700  | 0.3381          | 0.8815   | 0.5739    | 0.1712 | 0.2637 |
+| 0.2061        | 0.3690 | 3600  | 0.3430          | 0.8763   | 0.5022    | 0.2519 | 0.3355 |
+| 0.1914        | 0.4613 | 4500  | 0.3435          | 0.8784   | 0.5202    | 0.2482 | 0.3360 |
+| 0.1798        | 0.5535 | 5400  | 0.3240          | 0.8817   | 0.5554    | 0.2291 | 0.3243 |
+| 0.1899        | 0.6458 | 6300  | 0.3206          | 0.8768   | 0.5052    | 0.3153 | 0.3883 |
+| 0.1761        | 0.7380 | 7200  | 0.3340          | 0.8846   | 0.5955    | 0.2170 | 0.3181 |
+| 0.189         | 0.8303 | 8100  | 0.3241          | 0.8860   | 0.6141    | 0.2160 | 0.3196 |
+| 0.1644        | 0.9225 | 9000  | 0.3278          | 0.8861   | 0.6105    | 0.2251 | 0.3289 |
+| 0.1582        | 1.0148 | 9900  | 0.3437          | 0.8847   | 0.5773    | 0.2633 | 0.3616 |
+| 0.1511        | 1.1070 | 10800 | 0.3187          | 0.8836   | 0.5556    | 0.3076 | 0.3960 |
+| 0.1602        | 1.1993 | 11700 | 0.3198          | 0.8860   | 0.5858    | 0.2764 | 0.3756 |
+| 0.149         | 1.2915 | 12600 | 0.3244          | 0.8842   | 0.5635    | 0.2945 | 0.3868 |
+| 0.1512        | 1.3838 | 13500 | 0.3281          | 0.8863   | 0.5792    | 0.3040 | 0.3987 |
+| 0.1463        | 1.4760 | 14400 | 0.3228          | 0.8869   | 0.5947    | 0.2753 | 0.3763 |
+| 0.1372        | 1.5683 | 15300 | 0.3300          | 0.8872   | 0.5869    | 0.3048 | 0.4012 |
+| 0.1545        | 1.6605 | 16200 | 0.3229          | 0.8866   | 0.5807    | 0.3086 | 0.4030 |
+| 0.1755        | 1.7528 | 17100 | 0.3070          | 0.8854   | 0.5652    | 0.3280 | 0.4151 |
+| 0.1403        | 1.8450 | 18000 | 0.3212          | 0.8877   | 0.5995    | 0.2836 | 0.3851 |
+| 0.1425        | 1.9373 | 18900 | 0.3179          | 0.8861   | 0.5722    | 0.3235 | 0.4133 |
+| 0.1271        | 2.0295 | 19800 | 0.3483          | 0.8843   | 0.5545    | 0.3411 | 0.4224 |
+| 0.1235        | 2.1218 | 20700 | 0.3362          | 0.8858   | 0.5685    | 0.3294 | 0.4171 |
+| 0.1324        | 2.2140 | 21600 | 0.3294          | 0.8826   | 0.5399    | 0.3576 | 0.4302 |
+| 0.1236        | 2.3063 | 22500 | 0.3345          | 0.8859   | 0.5712    | 0.3214 | 0.4113 |
+| 0.1264        | 2.3985 | 23400 | 0.3575          | 0.8876   | 0.5879    | 0.3141 | 0.4094 |
+| 0.1157        | 2.4908 | 24300 | 0.3405          | 0.8872   | 0.5863    | 0.3058 | 0.4020 |
+| 0.1261        | 2.5830 | 25200 | 0.3372          | 0.8874   | 0.5853    | 0.3165 | 0.4109 |
+| 0.1346        | 2.6753 | 26100 | 0.3398          | 0.8863   | 0.5747    | 0.3205 | 0.4115 |
+| 0.1099        | 2.7675 | 27000 | 0.3492          | 0.8872   | 0.5843    | 0.3122 | 0.4070 |
+| 0.1295        | 2.8598 | 27900 | 0.3374          | 0.8871   | 0.5813    | 0.3191 | 0.4120 |
+| 0.1259        | 2.9520 | 28800 | 0.3410          | 0.8875   | 0.5863    | 0.3152 | 0.4100 |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.7.0+cu126
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "4.51.3",
+  "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 sha256:7f5eabf03779d706f947963d0fcdf2042d96604d5bcb7b94517d666695715493
+size 436355056

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 sha256:9604bbb1bef454773450efc3c7ca64fd12f387ef5baffccc8394aacfc56c142b
+size 5649