OK!

README.md

@@ -0,0 +1,78 @@
+---
+license: mit
+base_model: dbmdz/bert-base-turkish-uncased
+tags:
+- generated_from_trainer
+datasets:
+- turkish-wiki_ner
+metrics:
+- f1
+model-index:
+- name: bert-base-turkish-uncased-ner
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: turkish-wiki_ner
+      type: turkish-wiki_ner
+      config: turkish-WikiNER
+      split: validation
+      args: turkish-WikiNER
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.7821495486288537
+---
+
+<!-- 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. -->
+
+# bert-base-turkish-uncased-ner
+
+This model is a fine-tuned version of [dbmdz/bert-base-turkish-uncased](https://huggingface.co/dbmdz/bert-base-turkish-uncased) on the turkish-wiki_ner dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2603
+- F1: 0.7821
+
+## 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
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.4           | 1.0   | 1186 | 0.2502          | 0.7703 |
+| 0.2227        | 2.0   | 2372 | 0.2439          | 0.7740 |
+| 0.1738        | 3.0   | 3558 | 0.2511          | 0.7783 |
+| 0.1474        | 4.0   | 4744 | 0.2603          | 0.7821 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "dbmdz/bert-base-turkish-uncased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "I-LANGUAGE",
+    "1": "I-MONEY",
+    "2": "B-ORDINAL",
+    "3": "I-DATE",
+    "4": "I-FAC",
+    "5": "I-EVENT",
+    "6": "I-GPE",
+    "7": "B-LAW",
+    "8": "I-QUANTITY",
+    "9": "B-FAC",
+    "10": "I-PERSON",
+    "11": "B-GPE",
+    "12": "I-LOC",
+    "13": "I-LAW",
+    "14": "B-WORK_OF_ART",
+    "15": "B-QUANTITY",
+    "16": "I-ORDINAL",
+    "17": "B-ORG",
+    "18": "I-WORK_OF_ART",
+    "19": "B-TIME",
+    "20": "B-CARDINAL",
+    "21": "I-ORG",
+    "22": "I-CARDINAL",
+    "23": "I-NORP",
+    "24": "B-DATE",
+    "25": "B-TITLE",
+    "26": "B-EVENT",
+    "27": "B-PERCENT",
+    "28": "B-LOC",
+    "29": "B-NORP",
+    "30": "B-LANGUAGE",
+    "31": "I-PERCENT",
+    "32": "I-TITLE",
+    "33": "B-PRODUCT",
+    "34": "B-MONEY",
+    "35": "I-TIME",
+    "36": "B-PERSON",
+    "37": "O",
+    "38": "I-PRODUCT"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-CARDINAL": 20,
+    "B-DATE": 24,
+    "B-EVENT": 26,
+    "B-FAC": 9,
+    "B-GPE": 11,
+    "B-LANGUAGE": 30,
+    "B-LAW": 7,
+    "B-LOC": 28,
+    "B-MONEY": 34,
+    "B-NORP": 29,
+    "B-ORDINAL": 2,
+    "B-ORG": 17,
+    "B-PERCENT": 27,
+    "B-PERSON": 36,
+    "B-PRODUCT": 33,
+    "B-QUANTITY": 15,
+    "B-TIME": 19,
+    "B-TITLE": 25,
+    "B-WORK_OF_ART": 14,
+    "I-CARDINAL": 22,
+    "I-DATE": 3,
+    "I-EVENT": 5,
+    "I-FAC": 4,
+    "I-GPE": 6,
+    "I-LANGUAGE": 0,
+    "I-LAW": 13,
+    "I-LOC": 12,
+    "I-MONEY": 1,
+    "I-NORP": 23,
+    "I-ORDINAL": 16,
+    "I-ORG": 21,
+    "I-PERCENT": 31,
+    "I-PERSON": 10,
+    "I-PRODUCT": 38,
+    "I-QUANTITY": 8,
+    "I-TIME": 35,
+    "I-TITLE": 32,
+    "I-WORK_OF_ART": 18,
+    "O": 37
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68b04704f2a76772b9154bc27d68aad96ea9831d29f40995d3eee0502afac514
+size 440250324

runs/Jun06_22-04-29_b18afc294261/events.out.tfevents.1717711486.b18afc294261.1365.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e15089467e9101ac7b60293a25344d1cce83873b440e08c5ac529b89a8f7643
+size 8844

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
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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 sha256:056740c31f89d3044a5e49ebf773b6c4bca3b49675412b55796c0aa7a1f4946c
+size 5112