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-unipelt
+  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-unipelt
+
+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: 0.2811
+- Accuracy: 0.9023
+- Precision: 0.8773
+- Recall: 0.8933
+- F1: 0.8846
+
+## 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     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.5459        | 1.0   | 122  | 0.4639          | 0.7469   | 0.6922    | 0.6459 | 0.6573 |
+| 0.4335        | 2.0   | 244  | 0.4108          | 0.7845   | 0.7552    | 0.7975 | 0.7634 |
+| 0.3375        | 3.0   | 366  | 0.3283          | 0.8596   | 0.8347    | 0.8207 | 0.8272 |
+| 0.2801        | 4.0   | 488  | 0.3202          | 0.8596   | 0.8278    | 0.8432 | 0.8347 |
+| 0.2572        | 5.0   | 610  | 0.3109          | 0.8747   | 0.8438    | 0.8713 | 0.8550 |
+| 0.2339        | 6.0   | 732  | 0.3074          | 0.8672   | 0.8353    | 0.8660 | 0.8473 |
+| 0.2249        | 7.0   | 854  | 0.2915          | 0.8672   | 0.8353    | 0.8660 | 0.8473 |
+| 0.193         | 8.0   | 976  | 0.2540          | 0.8972   | 0.8781    | 0.8723 | 0.8751 |
+| 0.1899        | 9.0   | 1098 | 0.2636          | 0.8822   | 0.8526    | 0.8767 | 0.8628 |
+| 0.1801        | 10.0  | 1220 | 0.2371          | 0.9073   | 0.8840    | 0.8969 | 0.8900 |
+| 0.157         | 11.0  | 1342 | 0.2567          | 0.8997   | 0.8733    | 0.8941 | 0.8825 |
+| 0.1553        | 12.0  | 1464 | 0.2593          | 0.8972   | 0.8708    | 0.8898 | 0.8793 |
+| 0.1381        | 13.0  | 1586 | 0.2490          | 0.9173   | 0.9010    | 0.8990 | 0.9000 |
+| 0.1476        | 14.0  | 1708 | 0.2701          | 0.8997   | 0.8740    | 0.8916 | 0.8819 |
+| 0.1447        | 15.0  | 1830 | 0.2611          | 0.9123   | 0.8899    | 0.9029 | 0.8960 |
+| 0.1336        | 16.0  | 1952 | 0.3100          | 0.8997   | 0.8718    | 0.9016 | 0.8840 |
+| 0.1192        | 17.0  | 2074 | 0.2935          | 0.8972   | 0.8696    | 0.8948 | 0.8803 |
+| 0.1247        | 18.0  | 2196 | 0.2869          | 0.9023   | 0.8765    | 0.8958 | 0.8851 |
+| 0.117         | 19.0  | 2318 | 0.2761          | 0.9023   | 0.8773    | 0.8933 | 0.8846 |
+| 0.1092        | 20.0  | 2440 | 0.2811          | 0.9023   | 0.8773    | 0.8933 | 0.8846 |
+
+
+### 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/May18_09-02-32_indolem-petl-vm/events.out.tfevents.1716022960.indolem-petl-vm.1671931.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13584198b8bf28737a4da61bbd4a9049a8844eac7efef7c4cf16b7ff0ef3ea92
-size 18266
+oid sha256:d47a2dd0cc0078f3916f01f73b148b0a1f406022804f20bcda8a87084fceaec9
+size 19303

sentiment-unipelt/adapter_config.json

@@ -0,0 +1,77 @@
+{
+  "config": {
+    "architecture": "union",
+    "configs": [
+      {
+        "architecture": "prefix_tuning",
+        "bottleneck_size": 512,
+        "cross_prefix": true,
+        "dropout": 0.0,
+        "encoder_prefix": true,
+        "flat": false,
+        "leave_out": [],
+        "non_linearity": "tanh",
+        "prefix_length": 10,
+        "shared_gating": true,
+        "use_gating": true
+      },
+      {
+        "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": 16,
+        "residual_before_ln": true,
+        "scaling": 1.0,
+        "shared_W_phm": false,
+        "shared_phm_rule": true,
+        "use_gating": true
+      },
+      {
+        "alpha": 2,
+        "architecture": "lora",
+        "attn_matrices": [
+          "q",
+          "v"
+        ],
+        "composition_mode": "add",
+        "dropout": 0.0,
+        "init_weights": "lora",
+        "intermediate_lora": false,
+        "leave_out": [],
+        "output_lora": false,
+        "r": 8,
+        "selfattn_lora": true,
+        "use_gating": true
+      }
+    ]
+  },
+  "config_id": "67ac4937c601ad56",
+  "hidden_size": 768,
+  "model_class": "BertAdapterModel",
+  "model_name": "indolem/indobert-base-uncased",
+  "model_type": "bert",
+  "name": "sentiment-unipelt",
+  "version": "0.2.0"
+}

sentiment-unipelt/pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083316389a72483cf9e92a11d9171202c970659eabed7ab7c049064c41b33ec2
+size 44419376

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 sha256:0f480e37371b35ebfc39a2a264a5cf310250230b09eb3e58273b2da727b7d686
+size 2370664