seula09/kcbert-mbti-ie

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: beomi/kcbert-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: results_tf
+  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. -->
+
+# results_tf
+
+This model is a fine-tuned version of [beomi/kcbert-base](https://huggingface.co/beomi/kcbert-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0965
+- Accuracy: 0.9762
+- F1: 0.9761
+
+## 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: 16
+- eval_batch_size: 8
+- 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 48   | 0.0718          | 0.9881   | 0.9881 |
+| No log        | 2.0   | 96   | 0.0796          | 0.9881   | 0.9881 |
+| No log        | 3.0   | 144  | 0.0965          | 0.9762   | 0.9761 |
+
+
+### Framework versions
+
+- Transformers 4.57.3
+- Pytorch 2.9.0+cpu
+- Datasets 4.0.0
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "T",
+    "1": "F"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "F": 1,
+    "T": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 300,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ecaa97ad58f7f313faff4030f07027a715673ff08250d6dcec935bb3dfd4c4d
+size 435703792

runs/Jan06_07-56-02_6379d7b12f2d/events.out.tfevents.1767686166.6379d7b12f2d.451.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb918e32c383c481996b6a20506784beac8abd74f276bcb2d0be866fa31f314
+size 6759

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": 300,
+  "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 sha256:0e4bf3b186a37f7317696cfe95c0ab12176f0c34fd3634c519ef5b236898375b
+size 5841