Training in progress, epoch 1

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "SI2M-Lab/DarijaBERT-arabizi",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-PER",
+    "2": "I-ORG",
+    "3": "I-MISC",
+    "4": "I-LOC",
+    "5": "B-PER",
+    "6": "B-ORG",
+    "7": "B-MISC",
+    "8": "B-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-LOC": 8,
+    "B-MISC": 7,
+    "B-ORG": 6,
+    "B-PER": 5,
+    "I-LOC": 4,
+    "I-MISC": 3,
+    "I-ORG": 2,
+    "I-PER": 1,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "mask_token": "[MASK]",
+  "max_len": 128,
+  "max_position_embeddings": 512,
+  "model_max_length": 128,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token": "[PAD]",
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sep_token": "[SEP]",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "unk_token": "[UNK]",
+  "use_cache": true,
+  "vocab_size": 110000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5304d3ef971b7eeb5b0790d3875ff3842ec8fe31c70fa56a19d883a49e3cd1db
+size 679774052

runs/Jan13_21-01-38_instance-4/events.out.tfevents.1705179701.instance-4.689517.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c09c087f65b5563a3e5eee83446519f1640bb96ba287e1d3ef4a78d36f74d24
+size 5363

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 +1,57 @@
+{
+  "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,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "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 sha256:0e1b2e9a27bc30a7969a03b014045db8e9e514dcc3f3dfd5386a49a6a1bcc5ac
+size 4728