Training in progress epoch 0

README.md

@@ -0,0 +1,53 @@
+---
+base_model: aubmindlab/bert-base-arabertv02
+tags:
+- generated_from_keras_callback
+model-index:
+- name: chosenone80/arabert-ner-test-1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# chosenone80/arabert-ner-test-1
+
+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:
+- Train Loss: 0.1961
+- Validation Loss: 0.0515
+- Epoch: 0
+
+## 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:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1695, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 0.1961     | 0.0515          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- TensorFlow 2.15.0
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,110 @@
+{
+  "_name_or_path": "aubmindlab/bert-base-arabertv02",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-Allah",
+    "1": "I-Allah",
+    "2": "B-Book",
+    "3": "I-Book",
+    "4": "B-Clan",
+    "5": "I-Clan",
+    "6": "B-Crime",
+    "7": "I-Crime",
+    "8": "B-Date",
+    "9": "I-Date",
+    "10": "B-Day",
+    "11": "I-Day",
+    "12": "B-Hell",
+    "13": "I-Hell",
+    "14": "B-Loc",
+    "15": "I-Loc",
+    "16": "B-Meas",
+    "17": "I-Meas",
+    "18": "B-Mon",
+    "19": "I-Mon",
+    "20": "B-Month",
+    "21": "I-Month",
+    "22": "B-NatOb",
+    "23": "I-NatOb",
+    "24": "B-NUM",
+    "25": "I-NUM",
+    "26": "O",
+    "27": "B-Org",
+    "28": "I-Org",
+    "29": "B-Para",
+    "30": "I-Para",
+    "31": "B-Pers",
+    "32": "I-Pers",
+    "33": "B-Prophet",
+    "34": "I-Prophet",
+    "35": "B-Rlig",
+    "36": "I-Rlig",
+    "37": "B-Sect",
+    "38": "I-Sect",
+    "39": "B-Time",
+    "40": "I-Time"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Allah": 0,
+    "B-Book": 2,
+    "B-Clan": 4,
+    "B-Crime": 6,
+    "B-Date": 8,
+    "B-Day": 10,
+    "B-Hell": 12,
+    "B-Loc": 14,
+    "B-Meas": 16,
+    "B-Mon": 18,
+    "B-Month": 20,
+    "B-NUM": 24,
+    "B-NatOb": 22,
+    "B-Org": 27,
+    "B-Para": 29,
+    "B-Pers": 31,
+    "B-Prophet": 33,
+    "B-Rlig": 35,
+    "B-Sect": 37,
+    "B-Time": 39,
+    "I-Allah": 1,
+    "I-Book": 3,
+    "I-Clan": 5,
+    "I-Crime": 7,
+    "I-Date": 9,
+    "I-Day": 11,
+    "I-Hell": 13,
+    "I-Loc": 15,
+    "I-Meas": 17,
+    "I-Mon": 19,
+    "I-Month": 21,
+    "I-NUM": 25,
+    "I-NatOb": 23,
+    "I-Org": 28,
+    "I-Para": 30,
+    "I-Pers": 32,
+    "I-Prophet": 34,
+    "I-Rlig": 36,
+    "I-Sect": 38,
+    "I-Time": 40,
+    "O": 26
+  },
+  "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",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

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
+  }
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2801378ee744dd2ad0b6a31ed7de9375b96241ea331e2e2736f4aefe27e9c11
+size 538810476

tokenizer_config.json

@@ -0,0 +1,86 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "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]"
+}