Training in progress, epoch 1

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+base_model: indobenchmark/indobert-base-p1
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: Zidan_model_output_v4
+  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. -->
+
+# Zidan_model_output_v4
+
+This model is a fine-tuned version of [indobenchmark/indobert-base-p1](https://huggingface.co/indobenchmark/indobert-base-p1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7156
+- Accuracy: 0.7078
+
+## 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: 1e-06
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 220  | 0.9842          | 0.5909   |
+| No log        | 2.0   | 440  | 0.8935          | 0.5714   |
+| 0.9631        | 3.0   | 660  | 0.8081          | 0.6169   |
+| 0.9631        | 4.0   | 880  | 0.7819          | 0.6299   |
+| 0.7467        | 5.0   | 1100 | 0.7760          | 0.6299   |
+| 0.7467        | 6.0   | 1320 | 0.7601          | 0.6558   |
+| 0.6817        | 7.0   | 1540 | 0.7578          | 0.6494   |
+| 0.6817        | 8.0   | 1760 | 0.7359          | 0.6753   |
+| 0.6817        | 9.0   | 1980 | 0.7643          | 0.6494   |
+| 0.621         | 10.0  | 2200 | 0.7156          | 0.7078   |
+| 0.621         | 11.0  | 2420 | 0.7310          | 0.6948   |
+| 0.576         | 12.0  | 2640 | 0.7199          | 0.7078   |
+| 0.576         | 13.0  | 2860 | 0.7199          | 0.7143   |
+| 0.5598        | 14.0  | 3080 | 0.7313          | 0.7013   |
+| 0.5598        | 15.0  | 3300 | 0.7253          | 0.7013   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "indobenchmark/indobert-base-p1",
+  "_num_labels": 5,
+  "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": "Manusia",
+    "1": "Kendaraan",
+    "2": "Lingkungan"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Kendaraan": 1,
+    "Lingkungan": 2,
+    "Manusia": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adc2e6514d7d7d851ffe9c54436ec36964418d8df8fcc7150a99e503b15686e6
+size 497798148

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": true,
+  "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:e25fe638a669b0cf31a81f0e44499392c90c73adce7190645bcee2963fa9f990
+size 5048