Training in progress, step 256

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+final/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,91 @@
----
-license: mit
----
+---
+license: mit
+base_model: klue/roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: ko-edu-classifier
+  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. -->
+
+It's a training checkpoint. I strongly recommend not to use this model 🤗
+
+# ko-edu-classifier
+
+This model is a fine-tuned version of [lemon-mint/LaBSE-EnKo-Nano-Preview-v0.3](https://huggingface.co/lemon-mint/LaBSE-EnKo-Nano-Preview-v0.3) on the None dataset.
+
+## 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: 0.0003
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
+| 8.2847        | 0.9922  | 128  | 5.7695          | 0.0554    | 0.1667 | 0.0832   | 0.3326   |
+| 2.9466        | 1.9845  | 256  | 2.4992          | 0.0297    | 0.1667 | 0.0504   | 0.1783   |
+| 2.2442        | 2.9767  | 384  | 2.2770          | 0.0972    | 0.1779 | 0.0789   | 0.1884   |
+| 2.11          | 3.9690  | 512  | 2.2539          | 0.1370    | 0.1917 | 0.1233   | 0.1966   |
+| 2.0444        | 4.9612  | 640  | 1.9768          | 0.2723    | 0.2069 | 0.1448   | 0.2171   |
+| 2.0458        | 5.9535  | 768  | 2.1823          | 0.1460    | 0.2022 | 0.1450   | 0.2021   |
+| 2.0249        | 6.9457  | 896  | 2.0237          | 0.2773    | 0.2019 | 0.1478   | 0.2062   |
+| 2.0141        | 7.9380  | 1024 | 2.0108          | 0.3220    | 0.2043 | 0.1498   | 0.2081   |
+| 2.0178        | 8.9302  | 1152 | 1.9606          | 0.2890    | 0.2066 | 0.1513   | 0.2127   |
+| 2.0145        | 9.9225  | 1280 | 2.0984          | 0.3189    | 0.2077 | 0.1561   | 0.2062   |
+| 2.0093        | 10.9147 | 1408 | 1.9506          | 0.2829    | 0.2089 | 0.1517   | 0.2157   |
+| 2.014         | 11.9070 | 1536 | 1.9494          | 0.3039    | 0.2086 | 0.1538   | 0.2152   |
+| 2.0137        | 12.8992 | 1664 | 1.9247          | 0.3109    | 0.2110 | 0.1548   | 0.2190   |
+| 2.0055        | 13.8915 | 1792 | 1.8977          | 0.3184    | 0.2121 | 0.1537   | 0.2223   |
+| 2.0058        | 14.8837 | 1920 | 1.9747          | 0.3245    | 0.2094 | 0.1539   | 0.2130   |
+| 1.9975        | 15.8760 | 2048 | 1.9288          | 0.3084    | 0.2109 | 0.1535   | 0.2187   |
+| 1.995         | 16.8682 | 2176 | 1.8964          | 0.3036    | 0.2142 | 0.1590   | 0.2247   |
+| 1.9959        | 17.8605 | 2304 | 1.9247          | 0.3164    | 0.2144 | 0.1605   | 0.2209   |
+| 2.003         | 18.8527 | 2432 | 1.9297          | 0.3152    | 0.2151 | 0.1595   | 0.2217   |
+| 1.9908        | 19.8450 | 2560 | 1.8936          | 0.3065    | 0.2144 | 0.1610   | 0.2256   |
+| 1.9843        | 20.8372 | 2688 | 1.9238          | 0.3201    | 0.2168 | 0.1613   | 0.2242   |
+| 2.0042        | 21.8295 | 2816 | 1.9712          | 0.3228    | 0.2095 | 0.1577   | 0.2119   |
+| 1.9913        | 22.8217 | 2944 | 1.9070          | 0.3134    | 0.2168 | 0.1612   | 0.2250   |
+| 1.9855        | 23.8140 | 3072 | 1.9155          | 0.3123    | 0.2166 | 0.1611   | 0.2242   |
+| 1.9892        | 24.8062 | 3200 | 1.9338          | 0.3213    | 0.2163 | 0.1619   | 0.2220   |
+| 1.9964        | 25.7984 | 3328 | 1.9309          | 0.3125    | 0.2167 | 0.1625   | 0.2226   |
+| 1.9704        | 26.7907 | 3456 | 1.9165          | 0.3101    | 0.2187 | 0.1648   | 0.2258   |
+| 1.9977        | 27.7829 | 3584 | 1.9165          | 0.3177    | 0.2193 | 0.1653   | 0.2264   |
+| 1.9976        | 28.7752 | 3712 | 1.9127          | 0.3099    | 0.2191 | 0.1643   | 0.2269   |
+| 1.9728        | 29.7674 | 3840 | 1.9129          | 0.3096    | 0.2186 | 0.1640   | 0.2264   |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.4.0+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "klue/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

final/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "intfloat/multilingual-e5-small",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": 0.3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

final/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2db5d380214c25f5d780371f1b916e6675ca8de761fa1d2a1132b1d0a88a6c
+size 472480332

final/sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

final/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

final/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd98e5698b201ba914efb8c18b6709fa8735ab71dcad8d2b431e52e8bf68d932
+size 17082800

final/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

final/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59a6f7928d1b4f27b7ed498b16c59aa39b052f2b2320a8d875ac0f82372de7e
+size 5176

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c165208e1f63b21cbda34ed523309daa6f071a7f136ebdae3815c98822ae6761
+size 442499668

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "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
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4c8cbad2af6c789147145d94979f35047578c60d85338a18f694243fc206a2e
+size 5176