AraBert-finetuned-text-classification

README.md

@@ -0,0 +1,73 @@
+---
+base_model: aubmindlab/bert-base-arabertv2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- recall
+model-index:
+- name: AraBert-finetuned-text-classification
+  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. -->
+
+# AraBert-finetuned-text-classification
+
+This model is a fine-tuned version of [aubmindlab/bert-base-arabertv2](https://huggingface.co/aubmindlab/bert-base-arabertv2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1147
+- Macro F1: 0.9623
+- Accuracy: 0.9623
+- Recall: 0.9622
+
+## 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: 4e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Accuracy | Validation Loss | Macro F1 | Recall |
+|:-------------:|:-----:|:----:|:--------:|:---------------:|:--------:|:------:|
+| No log        | 0.99  | 56   | 0.9430   | 0.1530          | 0.9427   | 0.9425 |
+| No log        | 1.99  | 112  | 0.9579   | 0.1230          | 0.9577   | 0.9577 |
+| No log        | 3.0   | 169  | 0.9607   | 0.1287          | 0.9605   | 0.9608 |
+| No log        | 3.99  | 225  | 0.9618   | 0.1296          | 0.9616   | 0.9618 |
+| No log        | 5.0   | 282  | 0.9623   | 0.1147          | 0.9623   | 0.9622 |
+| No log        | 5.99  | 338  | 0.9612   | 0.1500          | 0.9611   | 0.9612 |
+| No log        | 7.0   | 395  | 0.9601   | 0.1953          | 0.9599   | 0.9602 |
+| No log        | 7.99  | 451  | 0.9640   | 0.1713          | 0.9639   | 0.9640 |
+| 0.0526        | 9.0   | 508  | 0.9646   | 0.1748          | 0.9644   | 0.9645 |
+| 0.0526        | 9.92  | 560  | 0.9646   | 0.1768          | 0.9644   | 0.9645 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "aubmindlab/bert-base-arabertv2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "\u0633\u064a\u0627\u0633\u0629",
+    "1": "\u0627\u0642\u062a\u0635\u0627\u062f",
+    "2": "\u0635\u062d\u0629"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:456a160052cb408e7d5edf28653012868242b1e6f4b8389c64a49ab530229704
+size 540806148

runs/Mar12_12-21-20_b3d30659946c/events.out.tfevents.1710246089.b3d30659946c.660.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:279d761357c44d3b934adc521b311d868cd294c842f54dabc6e401755830c483
+size 4824

runs/Mar12_12-22-22_b3d30659946c/events.out.tfevents.1710246146.b3d30659946c.660.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c9f35bb4d302eda3fc77e0a1389634aebfef5fee64633ebf60cf174c8b2f4ab
+size 4873

runs/Mar12_12-22-53_b3d30659946c/events.out.tfevents.1710246176.b3d30659946c.660.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e07be193a65a71f1beb557899ebf73229fedfcb4f2c8a51acc33dfa07109c6
+size 4873

runs/Mar12_12-23-35_b3d30659946c/events.out.tfevents.1710246219.b3d30659946c.660.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4033839b8fd5223bc8211027b545ee0f8c222fdf86a3c5745ffaeffab329c075
+size 14499

runs/Mar12_12-23-35_b3d30659946c/events.out.tfevents.1710249676.b3d30659946c.660.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b061b5a815afd71bace6b681cbfeb65eb673e046d6e7970b773176d633693b
+size 5269

runs/Mar12_12-23-35_b3d30659946c/events.out.tfevents.1710249701.b3d30659946c.660.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d04383f1826ec7c6db81b19732bf035c0a62625aa43333266523ae547a0aaf
+size 5269

runs/Mar12_12-23-35_b3d30659946c/events.out.tfevents.1710249746.b3d30659946c.660.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc757da40429308a6b6c6dd020dd512b16a2fe81364c37f9dbd7177e768fcc4d
+size 513

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 +1,338 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "+ا",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "1": {
+      "content": "+ك",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "2": {
+      "content": "ب+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "3": {
+      "content": "+هم",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "4": {
+      "content": "+ات",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "5": {
+      "content": "+ي",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "6": {
+      "content": "ل+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "7": {
+      "content": "+هما",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "8": {
+      "content": "+نا",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "9": {
+      "content": "+ن",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "10": {
+      "content": "+ها",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "11": {
+      "content": "+كما",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "12": {
+      "content": "+ة",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "13": {
+      "content": "ف+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "14": {
+      "content": "+كم",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "15": {
+      "content": "+كن",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "16": {
+      "content": "+ت",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "17": {
+      "content": "[بريد]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "18": {
+      "content": "[مستخدم]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "19": {
+      "content": "لل+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "20": {
+      "content": "ال+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "21": {
+      "content": "[رابط]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "22": {
+      "content": "س+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "23": {
+      "content": "+ان",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "24": {
+      "content": "+وا",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "25": {
+      "content": "+ه",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "26": {
+      "content": "+ون",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "27": {
+      "content": "+هن",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "28": {
+      "content": "+ين",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "29": {
+      "content": "��+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "30": {
+      "content": "ك+",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "31": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "33": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "34": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "35": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "+ك",
+    "+كما",
+    "ك+",
+    "+وا",
+    "+ين",
+    "و+",
+    "+كن",
+    "+ان",
+    "+هم",
+    "+ة",
+    "[بريد]",
+    "لل+",
+    "+ي",
+    "+ت",
+    "+ن",
+    "س+",
+    "ل+",
+    "[مستخدم]",
+    "+كم",
+    "+ا",
+    "ب+",
+    "ف+",
+    "+نا",
+    "+ها",
+    "+ون",
+    "+هما",
+    "ال+",
+    "+ه",
+    "+هن",
+    "+ات",
+    "[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 sha256:17cfa63ecf7aad69aab67547831d779f753a4423421dc10bca5aa00af74b5b93
+size 4920