zaebuc pnx pretrained model

config.json

@@ -0,0 +1,131 @@
+{
+  "_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_[ : ]K*",
+    "4": "I_[ \u060c ]K*",
+    "5": "I_[ \u061b ]K*",
+    "6": "I_[ \u061f ]K*",
+    "7": "I_[.]K*",
+    "8": "K*",
+    "9": "K*A_[!]",
+    "10": "K*A_[\" .]",
+    "11": "K*A_[\" \u060c]",
+    "12": "K*A_[\"]",
+    "13": "K*A_[(]",
+    "14": "K*A_[) .]",
+    "15": "K*A_[)]",
+    "16": "K*A_[,]",
+    "17": "K*A_[- .]",
+    "18": "K*A_[- : \"]",
+    "19": "K*A_[-]",
+    "20": "K*A_[. \"]",
+    "21": "K*A_[. -]",
+    "22": "K*A_[. . .]",
+    "23": "K*A_[.]",
+    "24": "K*A_[: \"]",
+    "25": "K*A_[:]",
+    "26": "K*A_[\u060c]",
+    "27": "K*A_[\u061b]",
+    "28": "K*A_[\u061f .]",
+    "29": "K*A_[\u061f]",
+    "30": "K*I_[ . ]K",
+    "31": "K*I_[ \u060c ]K",
+    "32": "R_[!]",
+    "33": "R_[\"]",
+    "34": "R_[(]",
+    "35": "R_[)]",
+    "36": "R_[,]",
+    "37": "R_[-]",
+    "38": "R_[.]",
+    "39": "R_[:]",
+    "40": "R_[?]",
+    "41": "R_[{]",
+    "42": "R_[}]",
+    "43": "R_[\u060c]",
+    "44": "R_[\u061b]",
+    "45": "R_[\u061f]",
+    "46": "R_[\"]A_[.]",
+    "47": "R_[\"]A_[\u060c]",
+    "48": "R_[.]A_[\"]",
+    "49": "R_[.]A_[.]",
+    "50": "R_[:]A_[\"]"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "A_[\"]K*": 0,
+    "A_[-]K*": 1,
+    "I_[ . ]K*": 2,
+    "I_[ : ]K*": 3,
+    "I_[ \u060c ]K*": 4,
+    "I_[ \u061b ]K*": 5,
+    "I_[ \u061f ]K*": 6,
+    "I_[.]K*": 7,
+    "K*": 8,
+    "K*A_[!]": 9,
+    "K*A_[\" .]": 10,
+    "K*A_[\" \u060c]": 11,
+    "K*A_[\"]": 12,
+    "K*A_[(]": 13,
+    "K*A_[) .]": 14,
+    "K*A_[)]": 15,
+    "K*A_[,]": 16,
+    "K*A_[- .]": 17,
+    "K*A_[- : \"]": 18,
+    "K*A_[-]": 19,
+    "K*A_[. \"]": 20,
+    "K*A_[. -]": 21,
+    "K*A_[. . .]": 22,
+    "K*A_[.]": 23,
+    "K*A_[: \"]": 24,
+    "K*A_[:]": 25,
+    "K*A_[\u060c]": 26,
+    "K*A_[\u061b]": 27,
+    "K*A_[\u061f .]": 28,
+    "K*A_[\u061f]": 29,
+    "K*I_[ . ]K": 30,
+    "K*I_[ \u060c ]K": 31,
+    "R_[!]": 32,
+    "R_[\"]": 33,
+    "R_[\"]A_[.]": 46,
+    "R_[\"]A_[\u060c]": 47,
+    "R_[(]": 34,
+    "R_[)]": 35,
+    "R_[,]": 36,
+    "R_[-]": 37,
+    "R_[.]": 38,
+    "R_[.]A_[\"]": 48,
+    "R_[.]A_[.]": 49,
+    "R_[:]": 39,
+    "R_[:]A_[\"]": 50,
+    "R_[?]": 40,
+    "R_[{]": 41,
+    "R_[}]": 42,
+    "R_[\u060c]": 43,
+    "R_[\u061b]": 44,
+    "R_[\u061f]": 45
+  },
+  "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 sha256:195696eaf09a5b92d8141f473e0e3a0d5a710649114b3180afb25cf76cdaa4f3
+size 538638321

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": 0.764525993883792,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.745158002038736e-05,
+      "loss": 0.1738,
+      "step": 500
+    }
+  ],
+  "max_steps": 9810,
+  "num_train_epochs": 15,
+  "total_flos": 1718607550347072.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a07b231dba304eb522c36ff96a50c5f3d416a69fdd5c4abe5edcba7dabe657b
+size 4143