AraBert-finetuned-text-classification

README.md

@@ -0,0 +1,72 @@
+---
+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: 0.1192
+- Macro F1: 0.9610
+- Accuracy: 0.9612
+- Recall: 0.9612
+
+## 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        | 0.9912 | 56   | 0.9585   | 0.1400          | 0.9582   | 0.9585 |
+| No log        | 2.0    | 113  | 0.9601   | 0.1324          | 0.9600   | 0.9602 |
+| No log        | 2.9912 | 169  | 0.9612   | 0.1192          | 0.9610   | 0.9612 |
+| No log        | 4.0    | 226  | 0.9623   | 0.1393          | 0.9621   | 0.9623 |
+| No log        | 4.9912 | 282  | 0.9596   | 0.1366          | 0.9596   | 0.9595 |
+| No log        | 6.0    | 339  | 0.9607   | 0.1590          | 0.9606   | 0.9607 |
+| No log        | 6.9912 | 395  | 0.9601   | 0.1741          | 0.9600   | 0.9602 |
+| No log        | 8.0    | 452  | 0.9612   | 0.1824          | 0.9611   | 0.9612 |
+| 0.0099        | 8.9912 | 504  | 0.1775   | 0.9617          | 0.9618   | 0.9617 |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

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": "4.40.0",
+  "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:f886872bcce1cf6e4ea66f5cedee47a0635db2df34a98c38d542f7aaa6dd7dda
+size 540806148

runs/Apr22_15-24-51_b09ea90fa82a/events.out.tfevents.1713799498.b09ea90fa82a.1171.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596a23789553fc437d5c53f58954eac80487be799500c28b73fd1772b7be42ed
+size 8670

runs/Apr22_15-24-51_b09ea90fa82a/events.out.tfevents.1713802330.b09ea90fa82a.1171.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45bb793a4b43de928da39e2aa4e2564874ac0ecf70def955f51a6a09254c9acb
+size 6013

runs/Apr22_15-24-51_b09ea90fa82a/events.out.tfevents.1713802830.b09ea90fa82a.1171.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd08035a0b9af2fe7dfe6222e79aaf331a9e12a6782520d52e4c9d900e7d707
+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 sha256:951414973d567b7b6b3503e5027111fd9fd152f824a632e74ca259517ac3bdea
+size 5048