Upload folder using huggingface_hub

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: mit
+base_model: cahya/bert-base-indonesian-1.5G
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: bert-base-indonesian-1.5G-multilabel-indonesian-hate-speech-new
+  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. -->
+
+# bert-base-indonesian-1.5G-multilabel-indonesian-hate-speech-new
+
+This model is a fine-tuned version of [cahya/bert-base-indonesian-1.5G](https://huggingface.co/cahya/bert-base-indonesian-1.5G) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3641
+- F1: 0.7802
+- Roc Auc: 0.8639
+- Accuracy: 0.7156
+
+## 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: 8
+- eval_batch_size: 8
+- 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: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
+| 0.3106        | 1.0   | 659  | 0.2504          | 0.6779 | 0.7832  | 0.5978   |
+| 0.2235        | 2.0   | 1318 | 0.2113          | 0.7466 | 0.8392  | 0.6441   |
+| 0.1722        | 3.0   | 1977 | 0.2283          | 0.7511 | 0.8493  | 0.6581   |
+| 0.097         | 4.0   | 2636 | 0.2421          | 0.7626 | 0.8490  | 0.6874   |
+| 0.0643        | 5.0   | 3295 | 0.2727          | 0.7584 | 0.8417  | 0.6938   |
+| 0.0572        | 6.0   | 3954 | 0.2817          | 0.7662 | 0.8662  | 0.6737   |
+| 0.0304        | 7.0   | 4613 | 0.3075          | 0.7606 | 0.8475  | 0.6879   |
+| 0.021         | 8.0   | 5272 | 0.3195          | 0.7697 | 0.8626  | 0.6932   |
+| 0.0157        | 9.0   | 5931 | 0.3347          | 0.7663 | 0.8477  | 0.7052   |
+| 0.0095        | 10.0  | 6590 | 0.3353          | 0.7759 | 0.8598  | 0.7118   |
+| 0.0086        | 11.0  | 7249 | 0.3467          | 0.7768 | 0.8590  | 0.7136   |
+| 0.0063        | 12.0  | 7908 | 0.3503          | 0.7795 | 0.8644  | 0.7128   |
+| 0.0046        | 13.0  | 8567 | 0.3577          | 0.7797 | 0.8613  | 0.7153   |
+| 0.0037        | 14.0  | 9226 | 0.3622          | 0.7801 | 0.8674  | 0.7115   |
+| 0.0046        | 15.0  | 9885 | 0.3641          | 0.7802 | 0.8639  | 0.7156   |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.7.0+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "HS",
+    "1": "Abusive",
+    "2": "HS_Individual",
+    "3": "HS_Group",
+    "4": "HS_Religion",
+    "5": "HS_Race",
+    "6": "HS_Physical",
+    "7": "HS_Gender",
+    "8": "HS_Other",
+    "9": "HS_Weak",
+    "10": "HS_Moderate",
+    "11": "HS_Strong"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Abusive": 1,
+    "HS": 0,
+    "HS_Gender": 7,
+    "HS_Group": 3,
+    "HS_Individual": 2,
+    "HS_Moderate": 10,
+    "HS_Other": 8,
+    "HS_Physical": 6,
+    "HS_Race": 5,
+    "HS_Religion": 4,
+    "HS_Strong": 11,
+    "HS_Weak": 9
+  },
+  "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": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44dd13c351e7a830ade1768677de605ac74b272936dbb8defbbc6d05c250753
+size 442529824

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 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "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": true,
+  "extra_special_tokens": {},
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "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 sha256:3e53a5c664e8750d796839b8716817487b57d99eba5d850acd86370337413176
+size 5777