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-lora-r16
+  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-lora-r16
+
+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: 0.3032
+- Accuracy: 0.8647
+- Precision: 0.8359
+- Recall: 0.8392
+- F1: 0.8376
+
+## 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     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.56          | 1.0   | 122  | 0.4986          | 0.7243   | 0.6584    | 0.6324 | 0.6401 |
+| 0.4895        | 2.0   | 244  | 0.4648          | 0.7519   | 0.7208    | 0.7570 | 0.7272 |
+| 0.407         | 3.0   | 366  | 0.3817          | 0.8346   | 0.8       | 0.8030 | 0.8015 |
+| 0.347         | 4.0   | 488  | 0.3600          | 0.8521   | 0.8271    | 0.8079 | 0.8164 |
+| 0.3094        | 5.0   | 610  | 0.3662          | 0.8296   | 0.7932    | 0.8144 | 0.8020 |
+| 0.2924        | 6.0   | 732  | 0.3677          | 0.8421   | 0.8074    | 0.8333 | 0.8177 |
+| 0.2723        | 7.0   | 854  | 0.3360          | 0.8546   | 0.8228    | 0.8322 | 0.8272 |
+| 0.2611        | 8.0   | 976  | 0.3210          | 0.8546   | 0.8273    | 0.8171 | 0.8219 |
+| 0.2584        | 9.0   | 1098 | 0.3484          | 0.8521   | 0.8188    | 0.8379 | 0.8270 |
+| 0.2432        | 10.0  | 1220 | 0.3248          | 0.8596   | 0.8325    | 0.8257 | 0.8290 |
+| 0.2387        | 11.0  | 1342 | 0.3166          | 0.8596   | 0.8307    | 0.8307 | 0.8307 |
+| 0.2273        | 12.0  | 1464 | 0.3224          | 0.8546   | 0.8239    | 0.8272 | 0.8255 |
+| 0.2259        | 13.0  | 1586 | 0.3088          | 0.8647   | 0.8398    | 0.8292 | 0.8342 |
+| 0.2268        | 14.0  | 1708 | 0.3109          | 0.8647   | 0.8359    | 0.8392 | 0.8376 |
+| 0.2226        | 15.0  | 1830 | 0.3157          | 0.8722   | 0.8431    | 0.8546 | 0.8484 |
+| 0.2214        | 16.0  | 1952 | 0.3112          | 0.8647   | 0.8346    | 0.8442 | 0.8391 |
+| 0.2148        | 17.0  | 2074 | 0.3018          | 0.8647   | 0.8367    | 0.8367 | 0.8367 |
+| 0.2088        | 18.0  | 2196 | 0.3112          | 0.8622   | 0.8309    | 0.8450 | 0.8373 |
+| 0.2116        | 19.0  | 2318 | 0.3025          | 0.8596   | 0.8299    | 0.8332 | 0.8315 |
+| 0.2099        | 20.0  | 2440 | 0.3032          | 0.8647   | 0.8359    | 0.8392 | 0.8376 |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.15.2

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": "0.2.0"
+}

default/pytorch_model_head.bin

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

runs/May26_20-19-30_indolem-petl-vm/events.out.tfevents.1716754776.indolem-petl-vm.3085243.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdfaba97226da8763909d0c3009cf1d89cad004ca5b83e51b2ab4fc563a2b936
-size 18318
+oid sha256:983a58ed2f2c1eb2d90ef156171cd6dfe9b4f3ee20ed29b3dee38d3b433cc7c0
+size 19355

sentiment-lora/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "config": {
+    "alpha": 8,
+    "architecture": "lora",
+    "attn_matrices": [
+      "q",
+      "v"
+    ],
+    "composition_mode": "add",
+    "dropout": 0.0,
+    "init_weights": "lora",
+    "intermediate_lora": false,
+    "leave_out": [],
+    "output_lora": false,
+    "r": 16,
+    "selfattn_lora": true,
+    "use_gating": false
+  },
+  "config_id": "141b248112091265",
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "indolem/indobert-base-uncased",
+  "model_type": "bert",
+  "name": "sentiment-lora",
+  "version": "0.2.0"
+}

sentiment-lora/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c7b2139902053959d9c0627f8005d887e96af11060b3680b37e2de808f84e40
+size 2377126

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": "0.2.0"
+}

sentiment/pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55de4f1569407e59cb33acb0857e773a1901508537dba55dcbd714c75f950dd6
+size 2370664