Model save

README.md

@@ -0,0 +1,85 @@
+---
+license: mit
+base_model: indolem/indobert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: sentiment-seq_bn-rf64-4
+  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. -->
+
+# sentiment-seq_bn-rf64-4
+
+This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3252
+- Accuracy: 0.8496
+- Precision: 0.8202
+- Recall: 0.8136
+- F1: 0.8167
+
+## 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: 5e-05
+- train_batch_size: 30
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.5579        | 1.0   | 122  | 0.5390          | 0.7093   | 0.6626    | 0.6793 | 0.6678 |
+| 0.5043        | 2.0   | 244  | 0.4835          | 0.7644   | 0.7516    | 0.6308 | 0.6425 |
+| 0.4819        | 3.0   | 366  | 0.4585          | 0.7769   | 0.7322    | 0.7047 | 0.7150 |
+| 0.4474        | 4.0   | 488  | 0.4587          | 0.7820   | 0.7399    | 0.7582 | 0.7472 |
+| 0.4336        | 5.0   | 610  | 0.4243          | 0.8070   | 0.7756    | 0.7360 | 0.7504 |
+| 0.4036        | 6.0   | 732  | 0.3990          | 0.8221   | 0.7846    | 0.7941 | 0.7890 |
+| 0.3871        | 7.0   | 854  | 0.3843          | 0.8346   | 0.8074    | 0.7805 | 0.7917 |
+| 0.3704        | 8.0   | 976  | 0.3781          | 0.8371   | 0.8270    | 0.7622 | 0.7839 |
+| 0.3563        | 9.0   | 1098 | 0.3728          | 0.8446   | 0.8343    | 0.7751 | 0.7959 |
+| 0.34          | 10.0  | 1220 | 0.3545          | 0.8596   | 0.8360    | 0.8182 | 0.8262 |
+| 0.3394        | 11.0  | 1342 | 0.3446          | 0.8571   | 0.8310    | 0.8189 | 0.8245 |
+| 0.3182        | 12.0  | 1464 | 0.3411          | 0.8596   | 0.8389    | 0.8132 | 0.8243 |
+| 0.3226        | 13.0  | 1586 | 0.3353          | 0.8546   | 0.8254    | 0.8221 | 0.8238 |
+| 0.3181        | 14.0  | 1708 | 0.3369          | 0.8546   | 0.8228    | 0.8322 | 0.8272 |
+| 0.3044        | 15.0  | 1830 | 0.3312          | 0.8571   | 0.8289    | 0.8239 | 0.8264 |
+| 0.3038        | 16.0  | 1952 | 0.3287          | 0.8571   | 0.8273    | 0.8289 | 0.8281 |
+| 0.3033        | 17.0  | 2074 | 0.3268          | 0.8596   | 0.8293    | 0.8357 | 0.8324 |
+| 0.3018        | 18.0  | 2196 | 0.3251          | 0.8571   | 0.8266    | 0.8314 | 0.8289 |
+| 0.2955        | 19.0  | 2318 | 0.3253          | 0.8571   | 0.8273    | 0.8289 | 0.8281 |
+| 0.2999        | 20.0  | 2440 | 0.3252          | 0.8496   | 0.8202    | 0.8136 | 0.8167 |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter-sentiment/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "dropout": 0.0,
+    "factorized_phm_W": true,
+    "factorized_phm_rule": false,
+    "hypercomplex_nonlinearity": "glorot-uniform",
+    "init_weights": "bert",
+    "inv_adapter": null,
+    "inv_adapter_reduction_factor": null,
+    "is_parallel": false,
+    "learn_phm": true,
+    "leave_out": [],
+    "ln_after": false,
+    "ln_before": false,
+    "mh_adapter": false,
+    "non_linearity": "relu",
+    "original_ln_after": true,
+    "original_ln_before": true,
+    "output_adapter": true,
+    "phm_bias": true,
+    "phm_c_init": "normal",
+    "phm_dim": 4,
+    "phm_init_range": 0.0001,
+    "phm_layer": false,
+    "phm_rank": 1,
+    "reduction_factor": 64,
+    "residual_before_ln": true,
+    "scaling": 1.0,
+    "shared_W_phm": false,
+    "shared_phm_rule": true,
+    "use_gating": false
+  },
+  "config_id": "337ea3bbdc05e9b8",
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "indolem/indobert-base-uncased",
+  "model_type": "bert",
+  "name": "adapter-sentiment",
+  "version": "0.2.2"
+}

adapter-sentiment/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65d6eeb68fb549b81e97319b91cc332eb9f07f7d372c1276c8bcf98889ba8d2
+size 939494

default/head_config.json

@@ -0,0 +1,19 @@
+{
+  "config": {
+    "activation_function": "gelu",
+    "bias": true,
+    "embedding_size": 768,
+    "head_type": "masked_lm",
+    "label2id": null,
+    "layer_norm": true,
+    "layers": 2,
+    "shift_labels": false,
+    "vocab_size": 31923
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "indolem/indobert-base-uncased",
+  "model_type": "bert",
+  "name": "default",
+  "version": "0.2.2"
+}

default/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a181f0177f3154142b57d9cab72a7e6f72dea1fe172d1a480ff543e0c17b0f3f
+size 100566390

sentiment/head_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "dropout_prob": null,
+    "head_type": "classification",
+    "label2id": {
+      "0": 0,
+      "1": 1
+    },
+    "layers": 2,
+    "num_labels": 2,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "indolem/indobert-base-uncased",
+  "model_type": "bert",
+  "name": "sentiment",
+  "version": "0.2.2"
+}

sentiment/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9fa912aebe2cde97e333b0ee6bcbd8734ec148e3cf089df8dfc4acd27b7345
+size 2370664