Pushing of the new best model checkpoint

README.md

@@ -0,0 +1,101 @@
+---
+library_name: transformers
+license: mit
+base_model: dbmdz/bert-base-turkish-cased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: turkish-medical-question-answering
+  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. -->
+
+# turkish-medical-question-answering
+
+This model is a fine-tuned version of [dbmdz/bert-base-turkish-cased](https://huggingface.co/dbmdz/bert-base-turkish-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2864
+- Exact Match: 55.1899
+- F1: 75.1246
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 64
+- 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: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Exact Match | F1      |
+|:-------------:|:------:|:----:|:---------------:|:-----------:|:-------:|
+| 5.9451        | 0.1166 | 50   | 5.9731          | 0.0         | 5.7871  |
+| 5.8483        | 0.2331 | 100  | 5.8315          | 0.0         | 5.9124  |
+| 5.6758        | 0.3497 | 150  | 5.6207          | 0.2519      | 6.2966  |
+| 5.4079        | 0.4662 | 200  | 5.3396          | 0.2584      | 6.1159  |
+| 5.1136        | 0.5828 | 250  | 5.0135          | 0.2755      | 7.7324  |
+| 4.7974        | 0.6993 | 300  | 4.6818          | 1.2531      | 9.4001  |
+| 4.4412        | 0.8159 | 350  | 4.3335          | 1.5656      | 10.9210 |
+| 4.1566        | 0.9324 | 400  | 3.8584          | 7.0281      | 22.6904 |
+| 3.599         | 1.0490 | 450  | 2.8534          | 23.4628     | 48.7349 |
+| 3.0347        | 1.1655 | 500  | 2.4007          | 28.9362     | 53.4749 |
+| 2.7626        | 1.2821 | 550  | 2.2064          | 33.4711     | 57.0427 |
+| 2.5741        | 1.3986 | 600  | 2.0689          | 37.3297     | 60.0019 |
+| 2.3917        | 1.5152 | 650  | 1.9761          | 38.6968     | 61.5842 |
+| 2.3607        | 1.6317 | 700  | 1.9137          | 41.5344     | 63.5713 |
+| 2.2972        | 1.7483 | 750  | 1.8294          | 44.0210     | 65.5393 |
+| 2.1214        | 1.8648 | 800  | 1.7721          | 44.7028     | 65.9376 |
+| 2.1775        | 1.9814 | 850  | 1.7058          | 46.1538     | 66.8453 |
+| 1.9282        | 2.0979 | 900  | 1.6579          | 46.7784     | 67.7813 |
+| 1.9428        | 2.2145 | 950  | 1.6366          | 46.8912     | 68.5467 |
+| 1.8639        | 2.3310 | 1000 | 1.5751          | 49.4819     | 70.2320 |
+| 1.8969        | 2.4476 | 1050 | 1.5519          | 48.9610     | 70.3424 |
+| 1.7348        | 2.5641 | 1100 | 1.5173          | 50.4505     | 71.1044 |
+| 1.7847        | 2.6807 | 1150 | 1.4999          | 50.5762     | 71.6186 |
+| 1.7822        | 2.7972 | 1200 | 1.4566          | 53.0691     | 72.0005 |
+| 1.7989        | 2.9138 | 1250 | 1.4300          | 51.6005     | 72.0121 |
+| 1.7683        | 3.0303 | 1300 | 1.4319          | 52.0305     | 72.2366 |
+| 1.5444        | 3.1469 | 1350 | 1.4277          | 51.7903     | 72.0603 |
+| 1.5121        | 3.2634 | 1400 | 1.3861          | 53.6122     | 73.3486 |
+| 1.6294        | 3.3800 | 1450 | 1.3830          | 52.6718     | 73.2456 |
+| 1.514         | 3.4965 | 1500 | 1.3456          | 53.7389     | 73.4757 |
+| 1.3778        | 3.6131 | 1550 | 1.3644          | 53.2319     | 73.5271 |
+| 1.4502        | 3.7296 | 1600 | 1.3491          | 53.6030     | 73.8642 |
+| 1.5388        | 3.8462 | 1650 | 1.3611          | 53.0380     | 73.1390 |
+| 1.5244        | 3.9627 | 1700 | 1.3143          | 53.3587     | 74.0002 |
+| 1.3127        | 4.0793 | 1750 | 1.3191          | 54.4767     | 74.6247 |
+| 1.3819        | 4.1958 | 1800 | 1.2864          | 55.1899     | 75.1246 |
+| 1.307         | 4.3124 | 1850 | 1.3762          | 54.1401     | 74.4158 |
+| 1.2792        | 4.4289 | 1900 | 1.3156          | 53.4943     | 75.0122 |
+| 1.289         | 4.5455 | 1950 | 1.2809          | 55.0063     | 74.6137 |
+
+
+### Framework versions
+
+- Transformers 4.48.0.dev0
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "dbmdz/bert-base-turkish-cased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.2,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.2,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "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:bcf1e97fa80acd7e34110f7b2f17b6e5d5379d27f978a4ab8bd983bc57efe492
+size 440136504

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 +1,59 @@
+{
+  "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": false,
+  "extra_special_tokens": {},
+  "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 sha256:50dffc91e032cee9e5d4246dabf7dbb61430bf79c9d7fd4829fbf092223f251b
+size 5432