djsull/sent_classification

README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+base_model: klue/roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: aha_sentence_classification
+  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. -->
+
+# aha_sentence_classification
+
+This model is a fine-tuned version of [klue/roberta-base](https://huggingface.co/klue/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7354
+- Accuracy: 0.7316
+- F1 Micro: 0.7316
+- F1 Macro: 0.4222
+- Precision Macro: 0.4524
+- Recall Macro: 0.4113
+
+## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 25
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | F1 Micro | F1 Macro | Precision Macro | Recall Macro |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|:--------:|:---------------:|:------------:|
+| 1.1113        | 0.5949 | 1000  | 0.9240          | 0.7121   | 0.7121   | 0.3417   | 0.3851          | 0.3598       |
+| 0.8622        | 1.1898 | 2000  | 0.8069          | 0.7146   | 0.7146   | 0.3950   | 0.4231          | 0.3979       |
+| 0.7967        | 1.7847 | 3000  | 0.7669          | 0.7212   | 0.7212   | 0.4115   | 0.4250          | 0.4221       |
+| 0.6931        | 2.3795 | 4000  | 0.7529          | 0.7219   | 0.7219   | 0.4319   | 0.4444          | 0.4246       |
+| 0.7087        | 2.9744 | 5000  | 0.7354          | 0.7316   | 0.7316   | 0.4222   | 0.4524          | 0.4113       |
+| 0.5718        | 3.5693 | 6000  | 0.7762          | 0.7184   | 0.7184   | 0.4239   | 0.4342          | 0.4215       |
+| 0.4475        | 4.1642 | 7000  | 0.8555          | 0.708    | 0.708    | 0.3976   | 0.4119          | 0.3899       |
+| 0.4542        | 4.7591 | 8000  | 0.8205          | 0.7224   | 0.7224   | 0.4015   | 0.4148          | 0.3925       |
+| 0.3716        | 5.3540 | 9000  | 0.9603          | 0.7039   | 0.7039   | 0.3931   | 0.4080          | 0.3939       |
+| 0.3644        | 5.9488 | 10000 | 0.9151          | 0.7099   | 0.7099   | 0.3965   | 0.4078          | 0.3922       |
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.7.0+cu126
+- Tokenizers 0.22.0

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\ud575\uc2ec\uc9c8\ubb38",
+    "1": "\uc11c\ube0c\uc9c8\ubb38",
+    "2": "\ubc30\uacbd/\uc0c1\ud669",
+    "3": "\uc2dc\ub3c4/\ud574\ubcf8\uac83",
+    "4": "\uc624\ub958/\uc99d\uc0c1",
+    "5": "\ud575\uc2ec\ub2f5\ubcc0/\uacb0\ub860",
+    "6": "\uc778\uc6a9/\ucc38\uc870",
+    "7": "\uadfc\uac70/\uc124\uba85",
+    "8": "\uc808\ucc28/\ubc29\ubc95",
+    "9": "\uc8fc\uc758/\ud55c\uacc4",
+    "10": "\ub300\uc548/\ube44\uad50",
+    "11": "\ucd94\uac00\uc815\ubcf4\uc694\uccad",
+    "12": "\uc778\uc0ac/\uac10\uc0ac/\uc751\uc6d0",
+    "13": "\ucd94\ucc9c/\ubcf4\uc0c1\uc720\ub3c4",
+    "14": "\uc608\uc2dc\ub370\uc774\ud130/\uc99d\ube59",
+    "15": "\uc758\ubbf8/\ud574\ub2f9\uc0ac\ud56d\uc5c6\uc74c"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "\uadfc\uac70/\uc124\uba85": 7,
+    "\ub300\uc548/\ube44\uad50": 10,
+    "\ubc30\uacbd/\uc0c1\ud669": 2,
+    "\uc11c\ube0c\uc9c8\ubb38": 1,
+    "\uc2dc\ub3c4/\ud574\ubcf8\uac83": 3,
+    "\uc608\uc2dc\ub370\uc774\ud130/\uc99d\ube59": 14,
+    "\uc624\ub958/\uc99d\uc0c1": 4,
+    "\uc758\ubbf8/\ud574\ub2f9\uc0ac\ud56d\uc5c6\uc74c": 15,
+    "\uc778\uc0ac/\uac10\uc0ac/\uc751\uc6d0": 12,
+    "\uc778\uc6a9/\ucc38\uc870": 6,
+    "\uc808\ucc28/\ubc29\ubc95": 8,
+    "\uc8fc\uc758/\ud55c\uacc4": 9,
+    "\ucd94\uac00\uc815\ubcf4\uc694\uccad": 11,
+    "\ucd94\ucc9c/\ubcf4\uc0c1\uc720\ub3c4": 13,
+    "\ud575\uc2ec\ub2f5\ubcc0/\uacb0\ub860": 5,
+    "\ud575\uc2ec\uc9c8\ubb38": 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": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a242d056612e4624f4de4d31513c4d0a8c4a879c3d73e0fb0dfa2e18b17db85c
+size 442545808

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 +1,60 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a1c4e17ad5d25dbf2f8b28524d6251bdac9277288d757f1766e38116fae9a5
+size 5905