MercuraTech/reranker-de-50k-classifier

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: mit
+base_model: bert-base-german-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: classifier-de
+  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-de
+
+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: 0.3460
+- Accuracy: 0.8811
+- Precision: 0.5353
+- Recall: 0.2849
+- F1: 0.3719
+
+## 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     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.2897        | 0.2569 | 500  | 0.3390          | 0.8773   | 0.5747    | 0.0282 | 0.0537 |
+| 0.2437        | 0.5139 | 1000 | 0.3320          | 0.8789   | 0.5347    | 0.1568 | 0.2425 |
+| 0.2292        | 0.7708 | 1500 | 0.3317          | 0.8826   | 0.5760    | 0.1901 | 0.2859 |
+| 0.1915        | 1.0277 | 2000 | 0.3557          | 0.8820   | 0.5583    | 0.2164 | 0.3119 |
+| 0.2146        | 1.2847 | 2500 | 0.3390          | 0.8837   | 0.5757    | 0.2250 | 0.3236 |
+| 0.2222        | 1.5416 | 3000 | 0.3298          | 0.8811   | 0.5358    | 0.2819 | 0.3694 |
+| 0.1861        | 1.7986 | 3500 | 0.3338          | 0.8823   | 0.5501    | 0.2620 | 0.3549 |
+| 0.1789        | 2.0555 | 4000 | 0.3460          | 0.8811   | 0.5353    | 0.2849 | 0.3719 |
+| 0.1739        | 2.3124 | 4500 | 0.3614          | 0.8850   | 0.5863    | 0.2368 | 0.3373 |
+| 0.1899        | 2.5694 | 5000 | 0.3487          | 0.8844   | 0.5716    | 0.2578 | 0.3554 |
+| 0.1692        | 2.8263 | 5500 | 0.3484          | 0.8847   | 0.5728    | 0.2653 | 0.3626 |
+
+
+### 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 sha256:03fece0c1929ae3527fd08ecbd9dc587021180b7b058840f4fa780614dc2a7e2
+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 sha256:942b6983ad5cb346bd57734eabf8386f36c32573124b63c31e8aab22a87316de
+size 5649