Pushing the best model checkpoint

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+license: mit
+base_model: dbmdz/bert-base-turkish-cased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: turkish-zeroshot
+  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-zeroshot
+
+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: 0.6236
+- Accuracy: 0.7438
+- F1: 0.7437
+- Precision: 0.7550
+- Recall: 0.7438
+
+## 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: 64
+- eval_batch_size: 32
+- 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_steps: 500
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 1.0967        | 0.0326 | 200  | 1.0926          | 0.3655   | 0.3273 | 0.3712    | 0.3655 |
+| 1.0547        | 0.0652 | 400  | 1.0466          | 0.4317   | 0.4121 | 0.4572    | 0.4317 |
+| 0.9249        | 0.0978 | 600  | 0.8336          | 0.6285   | 0.6293 | 0.6351    | 0.6285 |
+| 0.829         | 0.1304 | 800  | 0.7639          | 0.6627   | 0.6634 | 0.6743    | 0.6627 |
+| 0.8159        | 0.1630 | 1000 | 0.7307          | 0.6908   | 0.6925 | 0.7025    | 0.6908 |
+| 0.7782        | 0.1956 | 1200 | 0.7309          | 0.6839   | 0.6852 | 0.7157    | 0.6839 |
+| 0.7736        | 0.2282 | 1400 | 0.7196          | 0.6888   | 0.6895 | 0.7202    | 0.6888 |
+| 0.7566        | 0.2608 | 1600 | 0.6871          | 0.7185   | 0.7186 | 0.7301    | 0.7185 |
+| 0.7259        | 0.2934 | 1800 | 0.6727          | 0.7165   | 0.7181 | 0.7330    | 0.7165 |
+| 0.7084        | 0.3259 | 2000 | 0.6540          | 0.7277   | 0.7274 | 0.7319    | 0.7277 |
+| 0.7404        | 0.3585 | 2200 | 0.7097          | 0.7153   | 0.7131 | 0.7346    | 0.7153 |
+| 0.7223        | 0.3911 | 2400 | 0.7047          | 0.7129   | 0.7136 | 0.7443    | 0.7129 |
+| 0.7022        | 0.4237 | 2600 | 0.6454          | 0.7301   | 0.7318 | 0.7457    | 0.7301 |
+| 0.712         | 0.4563 | 2800 | 0.6243          | 0.7426   | 0.7437 | 0.7497    | 0.7426 |
+| 0.7055        | 0.4889 | 3000 | 0.6151          | 0.7534   | 0.7539 | 0.7565    | 0.7534 |
+| 0.7031        | 0.5215 | 3200 | 0.6365          | 0.7406   | 0.7416 | 0.7584    | 0.7406 |
+| 0.6922        | 0.5541 | 3400 | 0.6103          | 0.7498   | 0.7497 | 0.7549    | 0.7498 |
+| 0.6677        | 0.5867 | 3600 | 0.6236          | 0.7438   | 0.7437 | 0.7550    | 0.7438 |
+
+
+### 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": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "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:c55898f13e54e7db8a1af0732c992342ab9744c408bd20bede81bbc2ffedbc62
+size 442502140

runs/Jan08_19-54-01_ip-10-10-25-149.eu-central-1.compute.internal/events.out.tfevents.1736366041.ip-10-10-25-149.eu-central-1.compute.internal.4661.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93056517b8101609be6de89bc90aab34c37a0e68156e0eafe3dec5e3cc7440a7
+size 29227

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": 128,
+  "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:f5f243560127a7e609a13d788f44da35761926626dbf6215cd9e4fa36cbdad84
+size 5432