candylion

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: beomi/kcbert-base
+tags:
+- HHD
+- 10_class
+- multi_labels
+- 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: 0.1386
+- Lrap: 0.8792
+
+## 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: 32
+- eval_batch_size: 32
+- 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   | 469  | 0.1345          | 0.8668 |
+| 0.1901        | 2.0   | 938  | 0.1251          | 0.8719 |
+| 0.1054        | 3.0   | 1407 | 0.1232          | 0.8814 |
+| 0.0719        | 4.0   | 1876 | 0.1347          | 0.8812 |
+| 0.0487        | 5.0   | 2345 | 0.1386          | 0.8792 |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- 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 sha256:9dc2e7ff79426a7a3531d2363b24aad182db28252ce0904c7b16d8d3d8e3e5b9
+size 435728400

runs/Sep02_00-42-36_9320396363cd/events.out.tfevents.1725238220.9320396363cd.184.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410d92a28f4c65daa4a00e70237764ae6b83c01439824465f9e1056c6345f2d6
+size 10804

runs/Sep02_00-42-36_9320396363cd/events.out.tfevents.1725238847.9320396363cd.184.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281121189f1a59d2f18e142185a76c4baf01f60fbe69cdf53fc99bd667fbeba6
+size 5446

runs/Sep02_01-02-13_9320396363cd/events.out.tfevents.1725238936.9320396363cd.184.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10161544208357d17efb769546755ef8d8b96477989dc6f151b09cce54b32936
+size 6506

runs/Sep02_10-24-37_484d9a7d95aa/events.out.tfevents.1725272679.484d9a7d95aa.994.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e30fc9436307738b1e8e7fe6027754e6fedc5fee8d6f743527f86a91c0c5d0c
+size 5446

runs/Sep02_11-15-22_484d9a7d95aa/events.out.tfevents.1725275726.484d9a7d95aa.13864.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06d4a2bc724f37ca178661d0d1423f2594e8edc0494551dd816cc93b69b281d
+size 6506

runs/Sep03_00-05-08_01405061d7d6/events.out.tfevents.1725321912.01405061d7d6.169.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1384d8afd71a016fff71e2db3dd2295152483e07402fc698cd1e28cb48db1a9c
+size 5446

runs/Sep05_00-57-53_f25899d9857a/events.out.tfevents.1725497875.f25899d9857a.1052.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed9caa76db223cf98af67ba0ae63774c8283dfb04026b2bc49b101bf1d5990e
+size 8309

runs/Sep05_05-06-07_d38a9c012584/events.out.tfevents.1725512770.d38a9c012584.508.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a0a5a20f795fe068237348fdc94671bc3b791d0d08cc47adf1283b3cc519874
+size 8309

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 sha256:245ae9b733f30233af87e774bd324faf21c1d787a2876a1ab49a7f5192a7b044
+size 5176