Training complete

README.md

@@ -0,0 +1,59 @@
+---
+license: mit
+base_model: cahya/distilbert-base-indonesian
+tags:
+- generated_from_trainer
+model-index:
+- name: distilbert-base-indonesian-fire-classification-silvanus
+  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. -->
+
+# distilbert-base-indonesian-fire-classification-silvanus
+
+This model is a fine-tuned version of [cahya/distilbert-base-indonesian](https://huggingface.co/cahya/distilbert-base-indonesian) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1890
+
+## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 49   | 0.1673          |
+| No log        | 2.0   | 98   | 0.1883          |
+| No log        | 3.0   | 147  | 0.1890          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "cahya/distilbert-base-indonesian",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "Not Fire",
+    "1": "Fire"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "Fire": 1,
+    "Not Fire": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_hidden_states": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee744c83efe5f64064b5eb6a6fd93250987776c45959629f649863dc9c9f50d2
+size 272372984

runs/Jun28_11-12-52_server-cvis/events.out.tfevents.1719547994.server-cvis.3090328.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9cd061e7a9d86b09dc2f844448d9e01f280df5ad2c83bea738d586528e3ec1c
+size 4312

runs/Jun28_11-12-52_server-cvis/events.out.tfevents.1719548048.server-cvis.3090328.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9011614528436e413c636d0f78c010ad3a50e1173621b006d285ed04075c56d8
+size 4136

runs/Jun28_11-12-52_server-cvis/events.out.tfevents.1719548080.server-cvis.3090328.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed88e254a2ae5be5c38ab7c5ef0935039abf837fe1533a14410f015987e06ff
+size 4136

runs/Jun28_11-12-52_server-cvis/events.out.tfevents.1719548111.server-cvis.3090328.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb0d6030d99ff697f931578074909b6759c23250ebe9f808b12adf0f6c91109
+size 5518

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 +1,58 @@
+{
+  "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,
+  "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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d1cc9a3239c52edd7331ac4d1e83e59d14257894973865dcc34786b41967f2
+size 4664