hyd1

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: beomi/kcbert-base
+tags:
+- hyundo
+- categorical
+- multi_laebl
+- 10_class
+- generated_from_trainer
+model-index:
+- name: model_output
+ 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. -->
+
+# model_output
+
+This model is a fine-tuned version of [beomi/kcbert-base](https://huggingface.co/beomi/kcbert-base) on the unsmile_data dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1311
+- Lrap: 0.8779
+
+## 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: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Lrap |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log | 1.0 | 235 | 0.1467 | 0.8596 |
+| No log | 2.0 | 470 | 0.1291 | 0.8725 |
+| 0.17 | 3.0 | 705 | 0.1251 | 0.8776 |
+| 0.17 | 4.0 | 940 | 0.1298 | 0.8794 |
+| 0.0776 | 5.0 | 1175 | 0.1311 | 0.8779 |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,56 @@
+{
+ "_name_or_path": "beomi/kcbert-base",
+ "architectures": [
+ "BertForSequenceClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "classifier_dropout": null,
+ "directionality": "bidi",
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1",
+ "2": "LABEL_2",
+ "3": "LABEL_3",
+ "4": "LABEL_4",
+ "5": "LABEL_5",
+ "6": "LABEL_6",
+ "7": "LABEL_7",
+ "8": "LABEL_8",
+ "9": "LABEL_9"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "LABEL_0": 0,
+ "LABEL_1": 1,
+ "LABEL_2": 2,
+ "LABEL_3": 3,
+ "LABEL_4": 4,
+ "LABEL_5": 5,
+ "LABEL_6": 6,
+ "LABEL_7": 7,
+ "LABEL_8": 8,
+ "LABEL_9": 9
+ },
+ "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": "multi_label_classification",
+ "torch_dtype": "float32",
+ "transformers_version": "4.44.2",
+ "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:feae42cb9dc33643148db921285c5795dd9c234ce7545610094e53cc8da02057
+size 435728400

runs/Oct10_00-21-06_041eec75f831/events.out.tfevents.1728520050.041eec75f831.220.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f463710f3e0cc2698cdeb75753281c2f1c82a896d167e37f9a07cfb7e326bc44
+size 10942

runs/Oct10_00-35-30_041eec75f831/events.out.tfevents.1728520535.041eec75f831.220.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4a55e473332feff8ce6eabde2fdd3b52772ef31b4fb82863db34cc89e8e06e
+size 5515

runs/Oct10_00-37-06_041eec75f831/events.out.tfevents.1728520638.041eec75f831.220.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c85e1a8ed33ed97b4d9e4ed54e167434c9f920ffa3a2b981e2ac7eae075e102
+size 7887

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 +1,57 @@
+{
+ "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,
+ "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:d1f99c7325f82a2ec3756d6eedb81febc072e5a0121985bdc6b8de42ae564240
+size 5176