End of training

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+base_model: Omartificial-Intelligence-Space/SA-BERT-V1
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: Mohammed_Saudi_Classifier_SABERT
+  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. -->
+
+# Mohammed_Saudi_Classifier_SABERT
+
+This model is a fine-tuned version of [Omartificial-Intelligence-Space/SA-BERT-V1](https://huggingface.co/Omartificial-Intelligence-Space/SA-BERT-V1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0890
+- Accuracy: 0.6355
+- F1: 0.6159
+
+## 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: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.0   | 60   | 3.7608          | 0.0093   | 0.0002 |
+| No log        | 2.0   | 120  | 3.6178          | 0.2243   | 0.2016 |
+| No log        | 3.0   | 180  | 3.1702          | 0.4486   | 0.3837 |
+| No log        | 4.0   | 240  | 2.8401          | 0.4860   | 0.4399 |
+| No log        | 5.0   | 300  | 2.5739          | 0.5514   | 0.5257 |
+| No log        | 6.0   | 360  | 2.4024          | 0.5981   | 0.5784 |
+| No log        | 7.0   | 420  | 2.2519          | 0.5794   | 0.5480 |
+| No log        | 8.0   | 480  | 2.1640          | 0.5981   | 0.5746 |
+| 2.693         | 9.0   | 540  | 2.1130          | 0.6075   | 0.5796 |
+| 2.693         | 10.0  | 600  | 2.0890          | 0.6355   | 0.6159 |
+
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.7.1+cu126
+- Datasets 3.6.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,123 @@
+{
+  "_name_or_path": "Omartificial-Intelligence-Space/SA-BERT-V1",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Arts and Media",
+    "1": "Business and Money",
+    "2": "Cars and Driving",
+    "3": "Culture and Traditions",
+    "4": "Daily Life",
+    "5": "Days and Dates",
+    "6": "Descriptions",
+    "7": "Directions",
+    "8": "Economy and Finance",
+    "9": "Education and Training",
+    "10": "Emotions",
+    "11": "Entertainment",
+    "12": "Environment and Nature",
+    "13": "Events and Celebrations",
+    "14": "Family and Relationships",
+    "15": "Fitness and Exercise",
+    "16": "Food and Dining",
+    "17": "Greetings",
+    "18": "Health",
+    "19": "Hobbies and Interests",
+    "20": "Home and Living",
+    "21": "Instructions and Guidelines",
+    "22": "Law and Justice",
+    "23": "Mental Health",
+    "24": "Opinions",
+    "25": "Planning and Decisions",
+    "26": "Questions",
+    "27": "Real Estate and Housing",
+    "28": "Religion and Spirituality",
+    "29": "Responses",
+    "30": "Saudi Cities and Regions",
+    "31": "Shopping",
+    "32": "Social Media",
+    "33": "Sports",
+    "34": "Study and Education",
+    "35": "Technology",
+    "36": "Time",
+    "37": "Tourism",
+    "38": "Transport",
+    "39": "Travel",
+    "40": "Weather",
+    "41": "Wishes and Dreams",
+    "42": "Work"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Arts and Media": 0,
+    "Business and Money": 1,
+    "Cars and Driving": 2,
+    "Culture and Traditions": 3,
+    "Daily Life": 4,
+    "Days and Dates": 5,
+    "Descriptions": 6,
+    "Directions": 7,
+    "Economy and Finance": 8,
+    "Education and Training": 9,
+    "Emotions": 10,
+    "Entertainment": 11,
+    "Environment and Nature": 12,
+    "Events and Celebrations": 13,
+    "Family and Relationships": 14,
+    "Fitness and Exercise": 15,
+    "Food and Dining": 16,
+    "Greetings": 17,
+    "Health": 18,
+    "Hobbies and Interests": 19,
+    "Home and Living": 20,
+    "Instructions and Guidelines": 21,
+    "Law and Justice": 22,
+    "Mental Health": 23,
+    "Opinions": 24,
+    "Planning and Decisions": 25,
+    "Questions": 26,
+    "Real Estate and Housing": 27,
+    "Religion and Spirituality": 28,
+    "Responses": 29,
+    "Saudi Cities and Regions": 30,
+    "Shopping": 31,
+    "Social Media": 32,
+    "Sports": 33,
+    "Study and Education": 34,
+    "Technology": 35,
+    "Time": 36,
+    "Tourism": 37,
+    "Transport": 38,
+    "Travel": 39,
+    "Weather": 40,
+    "Wishes and Dreams": 41,
+    "Work": 42
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0091947d2bfb86bb15f4058e034effe26537cc77d5c09d018cc057bbb90e95e
+size 651521196

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 +1,65 @@
+{
+  "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
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aae2f4dd42b9e52cc3adaae6f09df8274e98ca8570b6fb19679c4491e8efc37
+size 5585