Ubin2/language_inteligence_4th

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+language:
+- ko
+base_model: lang-brain-4
+tags:
+- ynat-classification
+- korean_NLP
+- koELECTRA
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: ynat_model
+  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. -->
+
+# ynat_model
+
+This model is a fine-tuned version of [lang-brain-4](https://huggingface.co/lang-brain-4) on the klue-ynat dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5163
+- Accuracy: 0.8589
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.3899        | 1.0   | 714  | 0.4416          | 0.8499   |
+| 0.3074        | 2.0   | 1428 | 0.4062          | 0.8553   |
+| 0.2401        | 3.0   | 2142 | 0.4479          | 0.8547   |
+| 0.1839        | 4.0   | 2856 | 0.4771          | 0.8591   |
+| 0.1231        | 5.0   | 3570 | 0.5163          | 0.8589   |
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.0

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "IT/\uacfc\ud559",
+    "1": "\uacbd\uc81c",
+    "2": "\uc0ac\ud68c",
+    "3": "\uc0dd\ud65c\ubb38\ud654",
+    "4": "\uc138\uacc4",
+    "5": "\uc2a4\ud3ec\uce20",
+    "6": "\uc815\uce58"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "IT/\uacfc\ud559": 0,
+    "\uacbd\uc81c": 1,
+    "\uc0ac\ud68c": 2,
+    "\uc0dd\ud65c\ubb38\ud654": 3,
+    "\uc138\uacc4": 4,
+    "\uc2a4\ud3ec\uce20": 5,
+    "\uc815\uce58": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 35000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a6cb57aa27fe2ba265dfbf3132b8295b0c82df53026cd1c5b2ee14a0c87a69
+size 451731052

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 +1,58 @@
+{
+  "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]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42fe14c82c61bf9529e1232de1d9112b5f2ad2855fa480cacbd502f6e1e8171
+size 5777