End of training

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: mit
+base_model: artiwise-ai/modernbert-base-tr-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: turkish-sentiment2
+  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-sentiment2
+
+This model is a fine-tuned version of [artiwise-ai/modernbert-base-tr-uncased](https://huggingface.co/artiwise-ai/modernbert-base-tr-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1083
+- Accuracy: 0.9615
+- F1 Macro: 0.9351
+- F1 Weighted: 0.9612
+- Precision Macro: 0.9415
+- Recall Macro: 0.9291
+
+## 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: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use OptimizerNames.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: 400
+- training_steps: 2000
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1 Macro | F1 Weighted | Precision Macro | Recall Macro |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------------:|:------------:|
+| 0.1987        | 0.0073 | 200  | 0.1654          | 0.9400   | 0.9074   | 0.9413      | 0.8944          | 0.9236       |
+| 0.1978        | 0.0145 | 400  | 0.1653          | 0.9407   | 0.9092   | 0.9427      | 0.8938          | 0.9303       |
+| 0.1444        | 0.0218 | 600  | 0.1572          | 0.9520   | 0.9157   | 0.9502      | 0.9425          | 0.8957       |
+| 0.1446        | 0.0290 | 800  | 0.1252          | 0.9560   | 0.9239   | 0.9549      | 0.9407          | 0.9101       |
+| 0.1067        | 0.0363 | 1000 | 0.1389          | 0.9574   | 0.9294   | 0.9574      | 0.9313          | 0.9275       |
+| 0.1333        | 0.0436 | 1200 | 0.1244          | 0.9587   | 0.9279   | 0.9576      | 0.9464          | 0.9128       |
+| 0.0935        | 0.0508 | 1400 | 0.1297          | 0.9596   | 0.9336   | 0.9598      | 0.9309          | 0.9365       |
+| 0.1072        | 0.0581 | 1600 | 0.1196          | 0.9604   | 0.9309   | 0.9593      | 0.9497          | 0.9156       |
+| 0.1235        | 0.0654 | 1800 | 0.1121          | 0.9614   | 0.9339   | 0.9607      | 0.9450          | 0.9242       |
+| 0.1097        | 0.0726 | 2000 | 0.1083          | 0.9615   | 0.9351   | 0.9612      | 0.9415          | 0.9291       |
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.2

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "ModernBertForSequenceClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 2,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Positive",
+    "1": "Neutral",
+    "2": "Negative"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "Negative": 2,
+    "Neutral": 1,
+    "Positive": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "mask_token_id": 4,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 3,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "unk_token_id": 1,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0e15ff28b277a268a97fa5d4ff161456cccababfd511471fa2c9f10063c2f03
+size 542016364

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_len": 8192,
+  "max_length": 8192,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0361fee2a7f5dd6a80bf3cb763d21b3fb23bc94c93b87f080758faf6ff41052b
+size 5240