Upload model

README.md

@@ -1,84 +1,44 @@
 ---
-license: apache-2.0
 tags:
-- generated_from_trainer
-metrics:
-- accuracy
-- f1
-- precision
-- recall
-model-index:
-- name: ABSA-SentencePair-domainAdapt-SemEval-Adapter-pfeiffer_madx-run2
-  results: []
+- bert
+- adapterhub:Arabic ABSA/SemEvalHotelReview
+- adapter-transformers
+datasets:
+- Hotel
 ---
 
-<!-- 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. -->
+# Adapter `salohnana2018/ABSA-SentencePair-domainAdapt-SemEval-Adapter-pfeiffer_madx-run2` for CAMeL-Lab/bert-base-arabic-camelbert-msa
 
-# ABSA-SentencePair-domainAdapt-SemEval-Adapter-pfeiffer_madx-run2
+An [adapter](https://adapterhub.ml) for the `CAMeL-Lab/bert-base-arabic-camelbert-msa` model that was trained on the [Arabic ABSA/SemEvalHotelReview](https://adapterhub.ml/explore/Arabic ABSA/SemEvalHotelReview/) dataset and includes a prediction head for classification.
 
-This model is a fine-tuned version of [CAMeL-Lab/bert-base-arabic-camelbert-msa](https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-msa) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3666
-- Accuracy: 0.8603
-- F1: 0.8603
-- Precision: 0.8603
-- Recall: 0.8603
+This adapter was created for usage with the **[adapter-transformers](https://github.com/Adapter-Hub/adapter-transformers)** library.
 
-## Model description
+## Usage
 
-More information needed
+First, install `adapter-transformers`:
 
-## Intended uses & limitations
+```
+pip install -U adapter-transformers
+```
+_Note: adapter-transformers is a fork of transformers that acts as a drop-in replacement with adapter support. [More](https://docs.adapterhub.ml/installation.html)_
 
-More information needed
+Now, the adapter can be loaded and activated like this:
 
-## Training and evaluation data
+```python
+from transformers import AutoAdapterModel
 
-More information needed
+model = AutoAdapterModel.from_pretrained("CAMeL-Lab/bert-base-arabic-camelbert-msa")
+adapter_name = model.load_adapter("salohnana2018/ABSA-SentencePair-domainAdapt-SemEval-Adapter-pfeiffer_madx-run2", source="hf", set_active=True)
+```
 
-## Training procedure
+## Architecture & Training
 
-### Training hyperparameters
+<!-- Add some description here -->
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 32
-- eval_batch_size: 32
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 20
+## Evaluation results
 
-### Training results
+<!-- Add some description here -->
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.5161        | 1.0   | 206  | 0.3972          | 0.8633   | 0.8633 | 0.8633    | 0.8633 |
-| 0.3989        | 2.0   | 412  | 0.3739          | 0.8670   | 0.8670 | 0.8670    | 0.8670 |
-| 0.3725        | 3.0   | 618  | 0.3870          | 0.8615   | 0.8615 | 0.8615    | 0.8615 |
-| 0.3503        | 4.0   | 824  | 0.3892          | 0.8609   | 0.8609 | 0.8609    | 0.8609 |
-| 0.3313        | 5.0   | 1030 | 0.3743          | 0.8682   | 0.8682 | 0.8682    | 0.8682 |
-| 0.3118        | 6.0   | 1236 | 0.3666          | 0.8603   | 0.8603 | 0.8603    | 0.8603 |
-| 0.2982        | 7.0   | 1442 | 0.3972          | 0.8621   | 0.8621 | 0.8621    | 0.8621 |
-| 0.2854        | 8.0   | 1648 | 0.4064          | 0.8335   | 0.8335 | 0.8335    | 0.8335 |
-| 0.2723        | 9.0   | 1854 | 0.3981          | 0.8505   | 0.8505 | 0.8505    | 0.8505 |
-| 0.2641        | 10.0  | 2060 | 0.4067          | 0.8481   | 0.8481 | 0.8481    | 0.8481 |
-| 0.2507        | 11.0  | 2266 | 0.4130          | 0.8439   | 0.8439 | 0.8439    | 0.8439 |
-| 0.2518        | 12.0  | 2472 | 0.4023          | 0.8499   | 0.8499 | 0.8499    | 0.8499 |
-| 0.2387        | 13.0  | 2678 | 0.4123          | 0.8451   | 0.8451 | 0.8451    | 0.8451 |
-| 0.2304        | 14.0  | 2884 | 0.4369          | 0.8560   | 0.8560 | 0.8560    | 0.8560 |
-| 0.2258        | 15.0  | 3090 | 0.4453          | 0.8384   | 0.8384 | 0.8384    | 0.8384 |
-| 0.2258        | 16.0  | 3296 | 0.4272          | 0.8433   | 0.8433 | 0.8433    | 0.8433 |
-| 0.2185        | 17.0  | 3502 | 0.4482          | 0.8420   | 0.8420 | 0.8420    | 0.8420 |
-| 0.2097        | 18.0  | 3708 | 0.4532          | 0.8414   | 0.8414 | 0.8414    | 0.8414 |
-| 0.2069        | 19.0  | 3914 | 0.4580          | 0.8439   | 0.8439 | 0.8439    | 0.8439 |
-| 0.2072        | 20.0  | 4120 | 0.4556          | 0.8433   | 0.8433 | 0.8433    | 0.8433 |
+## Citation
 
-
-### Framework versions
-
-- Transformers 4.26.1
-- Pytorch 2.0.1+cu118
-- Datasets 2.13.1
-- Tokenizers 0.13.3
+<!-- Add some description here -->

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "config": {
+    "adapter_residual_before_ln": false,
+    "cross_adapter": false,
+    "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": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertModelWithHeads",
+  "model_name": "CAMeL-Lab/bert-base-arabic-camelbert-msa",
+  "model_type": "bert",
+  "name": "ABSA_Sentiment_classification_pfeiffer",
+  "version": "3.2.1"
+}

head_config.json

@@ -0,0 +1,21 @@
+{
+  "config": {
+    "activation_function": "tanh",
+    "bias": true,
+    "head_type": "classification",
+    "label2id": {
+      "negative": 0,
+      "neutral": 2,
+      "positive": 1
+    },
+    "layers": 2,
+    "num_labels": 3,
+    "use_pooler": false
+  },
+  "hidden_size": 768,
+  "model_class": "BertModelWithHeads",
+  "model_name": "CAMeL-Lab/bert-base-arabic-camelbert-msa",
+  "model_type": "bert",
+  "name": "ABSA_Sentiment_classification_pfeiffer",
+  "version": "3.2.1"
+}

pytorch_adapter.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e48536ebbac71b93040f49ab238974788b0fb9cd89d74d91e933dc04a0fef6c
+size 3596581

pytorch_model_head.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa195e5ed6c591bf43cc5ff3d601fff605b03d316fde9e10dcff78a63a9096eb
+size 2373409