Upload 12 files

README.md

@@ -1,3 +1,54 @@
 ---
 license: apache-2.0
+language:
+- tr
+pipeline_tag: token-classification
+widget:
+  - text: >-
+      Lütfen yardım Akevler mahallesi Rüzgar sokak Tuncay apartmanı zemin kat Antakya akrabalarım göçük altında #hatay #Afad
+    example_title: Örnek
 ---
+## deprem-ner
+
+Bu model depremde enkaz altında kalan kişilerin bildirimlerinden sokak, il, ilçe gibi bilgileri çekmeye çalıştık. 
+
+Örnek girdiler:
+- "Lütfen yardım Akevler mahallesi Rüzgar sokak Tuncay apartmanı zemin kat Antakya akrabalarım göçük altında #hatay #Afad"
+- "MARAȘA'ta arkadaşimizdan haber alamıyoruz ACIL yardım Penta Park konutları 1. Blok en üst kat 11. Kat \n\n@AFADBaskanlik #kahramanmaraş\nACİL"
+
+Verdiği çıktılar:
+
+```
+[
+  {
+    "entity_group": "mahalle",
+    "score": 0.8160411715507507,
+    "word": "Akevler mahallesi",
+    "start": 14,
+    "end": 31
+  },
+  {
+    "entity_group": "sokak",
+    "score": 0.940501868724823,
+    "word": "Rüzgar sokak",
+    "start": 32,
+    "end": 44
+  },
+  {
+    "entity_group": "Apartman/Site",
+    "score": 0.8081040978431702,
+    "word": "Tuncay apartmanı",
+    "start": 45,
+    "end": 61
+  },
+  {
+    "entity_group": "ilce",
+    "score": 0.854024350643158,
+    "word": "Antakya",
+    "start": 72,
+    "end": 79
+  }
+]
+```
+### Değerlendirme
+Bu modeli Hugging Face Hub'daki diğer modellerle karşılaştırdık, örnek 30 input'ta sonuçları [bu repository'de](https://huggingface.co/datasets/deprem-ml/butun_model_benchmarklari) bulabilirsiniz.

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "dbmdz/bert-base-turkish-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-no",
+    "2": "I-no",
+    "3": "B-mahalle",
+    "4": "I-mahalle",
+    "5": "B-ad-soyad",
+    "6": "I-ad-soyad",
+    "7": "B-kat",
+    "8": "I-kat",
+    "9": "B-ilce",
+    "10": "I-ilce",
+    "11": "B-sokak",
+    "12": "I-sokak",
+    "13": "B-dis kapi no",
+    "14": "I-dis kapi no",
+    "15": "B-Apartman/Site",
+    "16": "I-Apartman/Site",
+    "17": "B-ic kapi no",
+    "18": "I-ic kapi no",
+    "19": "B-il",
+    "20": "I-il"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Apartman/Site": 15,
+    "B-ad-soyad": 5,
+    "B-dis kapi no": 13,
+    "B-ic kapi no": 17,
+    "B-il": 19,
+    "B-ilce": 9,
+    "B-kat": 7,
+    "B-mahalle": 3,
+    "B-no": 1,
+    "B-sokak": 11,
+    "I-Apartman/Site": 16,
+    "I-ad-soyad": 6,
+    "I-dis kapi no": 14,
+    "I-ic kapi no": 18,
+    "I-il": 20,
+    "I-ilce": 10,
+    "I-kat": 8,
+    "I-mahalle": 4,
+    "I-no": 2,
+    "I-sokak": 12,
+    "O": 0
+  },
+  "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": "4.26.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a25b72c7fe7d98472edde90c27c723e24d5a35e049ff3c4c9d844bc1900623
+size 880454149

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf391d9593e46a28c72c354fddec4bf0c32ff3b82d906b7e304ac5434e56ee76
+size 440240941

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac24378e997ab22750b8358348a530a7f4bf8bb32d223518d36949b7ee3c384
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e3b8f60b042b392ad355e090a5de17a747f9b059d9c9d85983e3b19120b529f
+size 627

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 +1,17 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "name_or_path": "dbmdz/bert-base-turkish-cased",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.23053854703903198,
+  "best_model_checkpoint": "address_detection_model/checkpoint-240",
+  "epoch": 5.0,
+  "global_step": 240,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8829663962920047,
+      "eval_f1": 0.4565916398713826,
+      "eval_loss": 0.41948696970939636,
+      "eval_precision": 0.4152046783625731,
+      "eval_recall": 0.5071428571428571,
+      "eval_runtime": 62.0598,
+      "eval_samples_per_second": 3.094,
+      "eval_steps_per_second": 0.193,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9248744689069138,
+      "eval_f1": 0.66,
+      "eval_loss": 0.2642114460468292,
+      "eval_precision": 0.61875,
+      "eval_recall": 0.7071428571428572,
+      "eval_runtime": 65.1672,
+      "eval_samples_per_second": 2.946,
+      "eval_steps_per_second": 0.184,
+      "step": 96
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9341444573194283,
+      "eval_f1": 0.729036729036729,
+      "eval_loss": 0.23378442227840424,
+      "eval_precision": 0.7079407806191117,
+      "eval_recall": 0.7514285714285714,
+      "eval_runtime": 61.439,
+      "eval_samples_per_second": 3.125,
+      "eval_steps_per_second": 0.195,
+      "step": 144
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9351100811123986,
+      "eval_f1": 0.729036729036729,
+      "eval_loss": 0.2325739860534668,
+      "eval_precision": 0.7079407806191117,
+      "eval_recall": 0.7514285714285714,
+      "eval_runtime": 63.6313,
+      "eval_samples_per_second": 3.017,
+      "eval_steps_per_second": 0.189,
+      "step": 192
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9351100811123986,
+      "eval_f1": 0.7285318559556787,
+      "eval_loss": 0.23053854703903198,
+      "eval_precision": 0.706989247311828,
+      "eval_recall": 0.7514285714285714,
+      "eval_runtime": 61.6163,
+      "eval_samples_per_second": 3.116,
+      "eval_steps_per_second": 0.195,
+      "step": 240
+    }
+  ],
+  "max_steps": 240,
+  "num_train_epochs": 5,
+  "total_flos": 180264480845040.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ddf6899b7a894e80bcf4bec04a3e161773f940e7c3de5b36d8e7471570b4220
+size 3515