Upload fine-tuned AraBERT for Saudi EOU detection

README.md

@@ -0,0 +1,83 @@
+---
+library_name: peft
+base_model: aubmindlab/bert-base-arabertv02
+tags:
+- base_model:adapter:aubmindlab/bert-base-arabertv02
+- lora
+- transformers
+metrics:
+- accuracy
+model-index:
+- name: bert-eou-classifier_teacher
+  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. -->
+
+# bert-eou-classifier_teacher
+
+This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1555
+- Accuracy: 0.791
+- Auc: 0.865
+
+## 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: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Auc   |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:-----:|
+| 0.5875        | 1.0   | 622   | 0.4866          | 0.75     | 0.845 |
+| 0.4703        | 2.0   | 1244  | 0.5337          | 0.76     | 0.855 |
+| 0.4097        | 3.0   | 1866  | 0.5273          | 0.785    | 0.869 |
+| 0.3598        | 4.0   | 2488  | 0.5383          | 0.795    | 0.868 |
+| 0.3278        | 5.0   | 3110  | 0.6127          | 0.803    | 0.878 |
+| 0.3019        | 6.0   | 3732  | 0.6487          | 0.804    | 0.878 |
+| 0.2616        | 7.0   | 4354  | 0.7659          | 0.801    | 0.874 |
+| 0.2451        | 8.0   | 4976  | 0.8012          | 0.793    | 0.871 |
+| 0.2241        | 9.0   | 5598  | 0.8936          | 0.802    | 0.87  |
+| 0.2044        | 10.0  | 6220  | 0.9513          | 0.8      | 0.869 |
+| 0.2015        | 11.0  | 6842  | 0.9689          | 0.802    | 0.869 |
+| 0.1834        | 12.0  | 7464  | 0.9756          | 0.799    | 0.869 |
+| 0.1731        | 13.0  | 8086  | 0.9917          | 0.796    | 0.866 |
+| 0.1455        | 14.0  | 8708  | 1.0958          | 0.794    | 0.863 |
+| 0.1557        | 15.0  | 9330  | 1.0042          | 0.796    | 0.869 |
+| 0.1316        | 16.0  | 9952  | 1.0996          | 0.796    | 0.865 |
+| 0.1335        | 17.0  | 10574 | 1.2024          | 0.794    | 0.863 |
+| 0.1201        | 18.0  | 11196 | 1.1508          | 0.791    | 0.865 |
+| 0.1204        | 19.0  | 11818 | 1.1580          | 0.798    | 0.865 |
+| 0.1137        | 20.0  | 12440 | 1.1555          | 0.791    | 0.865 |
+
+
+### Framework versions
+
+- PEFT 0.18.0
+- Transformers 4.57.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.22.1

adapter_config.json

@@ -0,0 +1,45 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "aubmindlab/bert-base-arabertv02",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "key",
+    "value"
+  ],
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3884b3841e3a759768e3286cf5b3fff6bfb995975b83513629e77398065107
+size 1785816

runs/Dec09_04-32-29_ee40c7ab3786/events.out.tfevents.1765254750.ee40c7ab3786.3977.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf1bb7e90234eedf11d760fdd4f673a31bea7c95436794fda610242ea715792
+size 8013

runs/Dec09_04-45-55_ee40c7ab3786/events.out.tfevents.1765255558.ee40c7ab3786.3977.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f74d68e6ddf8a06db466ae8b571a41387562bf78302c7f4d5965609f4e083b8
+size 7432

runs/Dec09_05-01-35_ee40c7ab3786/events.out.tfevents.1765256497.ee40c7ab3786.3977.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4059d4c3955f6b8cbd79cc34a896acdb55e055aab9a5c31c9d330b18f8acc71
+size 9186

runs/Dec09_05-20-34_ee40c7ab3786/events.out.tfevents.1765257635.ee40c7ab3786.3977.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78eed4d3891fcef462d8b64b1658b3c1b2971c1715c8e7d3a873022b03ba76e7
+size 5171

runs/Dec09_05-21-46_ee40c7ab3786/events.out.tfevents.1765257707.ee40c7ab3786.3977.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb79d1054abb6f4fa38a9666d181982f9b70beeab3659c65980f5822156a217b
+size 5689

runs/Dec09_05-44-19_ee40c7ab3786/events.out.tfevents.1765259061.ee40c7ab3786.3977.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5997853492bb5e27d3dcfa3827566f27f01726f2dbc4b9bfd73a54ddef5414
+size 6851

runs/Dec09_06-13-21_ee40c7ab3786/events.out.tfevents.1765260803.ee40c7ab3786.3977.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae7a122af25d28e6a326e0b115e259bdeeb94f1d125b05695f2b7b645ff0537
+size 11272

runs/Dec09_06-19-52_ee40c7ab3786/events.out.tfevents.1765261193.ee40c7ab3786.3977.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3e85ebdd5505fa6891c5d2109ca2bb945e62d5009a1119c9720dbaee334c10
+size 6319

runs/Dec09_06-21-31_ee40c7ab3786/events.out.tfevents.1765261292.ee40c7ab3786.3977.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18c718a1787a62d78b2d08e559fa111cd4e74cb2886895d5cea1809b07f7365
+size 17082

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 +1,87 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "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
+    },
+    "5": {
+      "content": "[رابط]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "6": {
+      "content": "[بريد]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "7": {
+      "content": "[مستخدم]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "[بريد]",
+    "[مستخدم]",
+    "[رابط]"
+  ],
+  "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 sha256:502492914bf5c9271da60a8876cab0250843a3df2c2a9bec59cd72b91be169be
+size 5432