qalb14 pnx pretrained model

config.json

@@ -0,0 +1,99 @@
+{
+  "_name_or_path": "/scratch/ba63/BERT_models/bert-base-arabertv02",
+  "architectures": [
+    "BertForTokenClassificationSingleLabel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "A_[\"]K*",
+    "1": "A_[-]K*",
+    "2": "I_[ . ]K*",
+    "3": "I_[ \u060c ]K*",
+    "4": "I_[ \u061f ]K*",
+    "5": "K*",
+    "6": "K*A_[!]",
+    "7": "K*A_[\" .]",
+    "8": "K*A_[\" \u060c]",
+    "9": "K*A_[\"]",
+    "10": "K*A_[(]",
+    "11": "K*A_[) .]",
+    "12": "K*A_[)]",
+    "13": "K*A_[-]",
+    "14": "K*A_[.]",
+    "15": "K*A_[: \"]",
+    "16": "K*A_[:]",
+    "17": "K*A_[\u060c]",
+    "18": "K*A_[\u061b]",
+    "19": "K*A_[\u061f]",
+    "20": "K*I_[ \u060c ]K",
+    "21": "R_[!]",
+    "22": "R_[\"]",
+    "23": "R_[(]",
+    "24": "R_[)]",
+    "25": "R_[,]",
+    "26": "R_[-]",
+    "27": "R_[.]",
+    "28": "R_[:]",
+    "29": "R_[\u060c]",
+    "30": "R_[\u061b]",
+    "31": "R_[\u061f]",
+    "32": "R_[\"]A_[.]",
+    "33": "R_[\"]A_[\u060c]",
+    "34": "R_[:]A_[\"]"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "A_[\"]K*": 0,
+    "A_[-]K*": 1,
+    "I_[ . ]K*": 2,
+    "I_[ \u060c ]K*": 3,
+    "I_[ \u061f ]K*": 4,
+    "K*": 5,
+    "K*A_[!]": 6,
+    "K*A_[\" .]": 7,
+    "K*A_[\" \u060c]": 8,
+    "K*A_[\"]": 9,
+    "K*A_[(]": 10,
+    "K*A_[) .]": 11,
+    "K*A_[)]": 12,
+    "K*A_[-]": 13,
+    "K*A_[.]": 14,
+    "K*A_[: \"]": 15,
+    "K*A_[:]": 16,
+    "K*A_[\u060c]": 17,
+    "K*A_[\u061b]": 18,
+    "K*A_[\u061f]": 19,
+    "K*I_[ \u060c ]K": 20,
+    "R_[!]": 21,
+    "R_[\"]": 22,
+    "R_[\"]A_[.]": 32,
+    "R_[\"]A_[\u060c]": 33,
+    "R_[(]": 23,
+    "R_[)]": 24,
+    "R_[,]": 25,
+    "R_[-]": 26,
+    "R_[.]": 27,
+    "R_[:]": 28,
+    "R_[:]A_[\"]": 34,
+    "R_[\u060c]": 29,
+    "R_[\u061b]": 30,
+    "R_[\u061f]": 31
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "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:d98d683f9ef1738c27f5031c99483d93e9f73c4116c158a97a678270c84fd262
+size 538589105

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 +1,20 @@
+{
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,22 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8237232289950577,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.5881383855024714e-05,
+      "loss": 0.1893,
+      "step": 500
+    }
+  ],
+  "max_steps": 6070,
+  "num_train_epochs": 10,
+  "total_flos": 725004451318080.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1b5d9df9dd904398d49aa31f53414ca0758a9b95775f15f7fb501e04192b5b9
+size 4079