ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa-tuning

README.md

@@ -0,0 +1,66 @@
+---
+license: mit
+base_model: ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model is a fine-tuned version of [ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa](https://huggingface.co/ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7283
+- Accuracy: 0.6978
+- F1 Score: 0.6979
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1 Score |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|
+| 0.4822        | 1.0   | 1952  | 0.7514          | 0.6989   | 0.7001   |
+| 0.6036        | 2.0   | 3904  | 0.7232          | 0.7020   | 0.7030   |
+| 0.6004        | 3.0   | 5856  | 0.7226          | 0.7020   | 0.7027   |
+| 0.5904        | 4.0   | 7808  | 0.7260          | 0.7037   | 0.7046   |
+| 0.5919        | 5.0   | 9760  | 0.7250          | 0.7039   | 0.7048   |
+| 0.5939        | 6.0   | 11712 | 0.7260          | 0.7053   | 0.7060   |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa",
+  "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": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "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:a8cf34b3137a8d667c61a023062d18fac7d3f8d1a57f749176c022f0d1d91008
+size 442502140

runs/May16_17-32-22_3ec345c9650e/events.out.tfevents.1715880742.3ec345c9650e.286.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9129049817f16331b1747c4f9295a5d621f14f59f02b61a4f3b35056dbc3773d
+size 4928

runs/May16_17-32-35_3ec345c9650e/events.out.tfevents.1715880756.3ec345c9650e.286.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe85c79d1c990d8eede891e39abe1d774c3f2f781ffa15419f7e0fbddb39c814
+size 4928

runs/May16_17-35-07_3ec345c9650e/events.out.tfevents.1715880910.3ec345c9650e.286.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8c76832ef4e7add344118c9981b03847346783c4394c661919344ab27e364d
+size 4928

runs/May16_17-37-07_3ec345c9650e/events.out.tfevents.1715881027.3ec345c9650e.2022.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00b1797f4fa8c5c7c33bbe64aa2cd1fe5a3fdf400c6fc2dcee2cd8567bfad7d
+size 6686

runs/May16_17-41-33_3ec345c9650e/events.out.tfevents.1715881296.3ec345c9650e.2022.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eade70b749c4d303c1bc078ef245b70bd3351503e29ca7c382e2cba69d1fd982
+size 12382

runs/May16_17-41-33_3ec345c9650e/events.out.tfevents.1715882641.3ec345c9650e.2022.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba23ffb2953bfcec0309880e00eb31707129dc39286624e4a59475cb2c9cb405
+size 838

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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": "[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,
+  "num_classes": 3,
+  "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 sha256:7d258494cda47bcde5dd8d82f63d7928b1f98b7c289d5e92e9b74d3cf2f0420e
+size 4984