Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "StivenLancheros/bert-base-arabert-BioNER-EN",
+  "_num_labels": 13,
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.5,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.5,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-Cell",
+    "1": "B-Chemical",
+    "2": "B-GENE",
+    "3": "B-Protein",
+    "4": "B-Sequence",
+    "5": "B-Taxon",
+    "6": "I-Cell",
+    "7": "I-Chemical",
+    "8": "I-GENE",
+    "9": "I-Protein",
+    "10": "I-Sequence",
+    "11": "I-Taxon",
+    "12": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c597446a52fc671885ffe175ea1aff30d1ce487a35bd5d7f87f0a25d6b3489
+size 538523117

runs/Apr24_07-15-14_37821872b012/1682320617.0931036/events.out.tfevents.1682320617.37821872b012.10746.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73f9ecd9bbb443838cf3adb69970f3d869e5d512c3979d8f4495d3b40a8835e
+size 5828

runs/Apr24_07-15-14_37821872b012/events.out.tfevents.1682320617.37821872b012.10746.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:724dfdebd7e21eef161223a04346958e0cf518e1d18bc5be23e15379f6651d7e
+size 5127

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": [
+    "+وا",
+    "س+",
+    "[مستخدم]",
+    "+ك",
+    "+هم",
+    "+ة",
+    "+ن",
+    "لل+",
+    "[بريد]",
+    "[رابط]",
+    "+ه",
+    "+كن",
+    "+ا",
+    "+ات",
+    "+ي",
+    "ب+",
+    "+نا",
+    "+هن",
+    "+كم",
+    "ك+",
+    "+ين",
+    "+هما",
+    "و+",
+    "+كما",
+    "+ان",
+    "+ت",
+    "+ون",
+    "ل+",
+    "+ها",
+    "ال+",
+    "ف+"
+  ],
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "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 sha256:4edabc213a5de64e9c3ae444a147dccba7aa54952f80f4405cc76c535474caea
+size 3643