Pushing of the new best model checkpoint

README.md

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+license: mit
+base_model: dbmdz/bert-base-turkish-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: turkish-sentiment
+  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-sentiment
+
+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: 0.0957
+- Accuracy: 0.9657
+- F1 Macro: 0.9398
+- F1 Weighted: 0.9653
+- Precision: 0.9651
+- Recall: 0.9657
+
+## 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: 3e-05
+- train_batch_size: 64
+- eval_batch_size: 128
+- 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: 600
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted | Precision | Recall |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------:|:------:|
+| 0.6035        | 0.0290 | 200  | 0.1912          | 0.9305   | 0.8739   | 0.9278      | 0.9274    | 0.9305 |
+| 0.1402        | 0.0581 | 400  | 0.1224          | 0.9561   | 0.9181   | 0.9539      | 0.9557    | 0.9561 |
+| 0.1245        | 0.0871 | 600  | 0.1227          | 0.9582   | 0.9217   | 0.9561      | 0.9578    | 0.9582 |
+| 0.1091        | 0.1162 | 800  | 0.1066          | 0.9632   | 0.9364   | 0.9630      | 0.9629    | 0.9632 |
+| 0.1078        | 0.1452 | 1000 | 0.0957          | 0.9657   | 0.9398   | 0.9653      | 0.9651    | 0.9657 |
+
+
+### Framework versions
+
+- Transformers 4.48.0.dev0
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "dbmdz/bert-base-turkish-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.48.0.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:fa7d1d1839e52dac02a60f0f98cca24387c7ff819c8afdde121240579fc92608
+size 442502140

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:e4e51841518efb60a1f07899ff0d8588a95e3157f16f69252edf7960f8e9bd5a
+size 5432