CODA model upload

config.json

@@ -0,0 +1,197 @@
+{
+  "_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": "D*",
+    "1": "DK*",
+    "2": "D*KI_[\u0630\u0627]",
+    "3": "D*KI_[\u0646]K",
+    "4": "I_[ ]K*",
+    "5": "I_[ \u0627]K*",
+    "6": "I_[\u0627]K*",
+    "7": "I_[\u0627]KI_[\u0627]K*",
+    "8": "I_[\u0627]KI_[\u0644]K*",
+    "9": "I_[ \u0627\u0644]K*",
+    "10": "I_[\u0627\u0644]K*",
+    "11": "I_[ \u0644]K*",
+    "12": "I_[\u0647]K*",
+    "13": "I_[\u064a]K*",
+    "14": "K*",
+    "15": "K*D",
+    "16": "K*DK",
+    "17": "KDK*",
+    "18": "K*DKKK",
+    "19": "K*I_[ ]K",
+    "20": "KI_[ ]K*",
+    "21": "K*I_[\u0627]",
+    "22": "K*I_[\u0627]K",
+    "23": "KI_[\u0627 ]K*",
+    "24": "KI_[\u0627]K*",
+    "25": "K*I_[\u0627]KI_[\u0644]K",
+    "26": "KI_[\u0627\u0644]K*",
+    "27": "K*I_[\u0644]K",
+    "28": "KI_[\u0644]K*",
+    "29": "K*I_[\u0646]K",
+    "30": "KI_[\u0646]K*",
+    "31": "K*I_[\u0647]",
+    "32": "K*I_[\u0647]K",
+    "33": "K*I_[\u0648]K",
+    "34": "K*I_[\u064a]K",
+    "35": "KI_[\u064a]K*",
+    "36": "KKI_[ ]K*",
+    "37": "KKI_[ \u0627]K*",
+    "38": "KKI_[\u0627]K*",
+    "39": "KKKR_[\u0627]K*",
+    "40": "KKR_[\u0627]K*",
+    "41": "K*R_[ ]",
+    "42": "K*R_[\u0622]K",
+    "43": "K*R_[\u0627]",
+    "44": "KR_[\u0627]K*",
+    "45": "K*R_[\u0629]",
+    "46": "K*R_[\u062b]",
+    "47": "K*R_[\u062b]K",
+    "48": "K*R_[\u062b]KK",
+    "49": "K*R_[\u0630]",
+    "50": "K*R_[\u0638]",
+    "51": "K*R_[\u0639]",
+    "52": "K*R_[\u0642]",
+    "53": "K*R_[\u0642]K",
+    "54": "K*R_[\u0647]",
+    "55": "K*R_[\u0649]",
+    "56": "K*R_[\u064a]",
+    "57": "MI_[\u0627]K*",
+    "58": "MK*",
+    "59": "MK*R_[\u0629]",
+    "60": "MR_[\u0627]K*",
+    "61": "MR_[\u062b]K*",
+    "62": "R_[\u0622]K*",
+    "63": "R_[\u0627]",
+    "64": "R_[\u0627]K*",
+    "65": "R_[\u0627]K*I_[\u0644]K",
+    "66": "R_[\u0627]K*R_[\u062b]",
+    "67": "R_[\u0629]",
+    "68": "R_[\u062a]I_[\u0634]K*",
+    "69": "R_[\u062a]K*",
+    "70": "R_[\u062a]R_[\u0639]K*",
+    "71": "R_[\u062b]",
+    "72": "R_[\u062b]K*",
+    "73": "R_[\u062b]R_[\u0629]",
+    "74": "R_[\u0630]",
+    "75": "R_[\u0630]K*",
+    "76": "R_[\u0638]K*",
+    "77": "R_[\u063a]K*",
+    "78": "R_[\u0642]",
+    "79": "R_[\u0642]K*",
+    "80": "R_[\u0643]K*",
+    "81": "R_[\u0647]",
+    "82": "R_[\u0649]",
+    "83": "R_[\u064a]"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "D*": 0,
+    "D*KI_[\u0630\u0627]": 2,
+    "D*KI_[\u0646]K": 3,
+    "DK*": 1,
+    "I_[ ]K*": 4,
+    "I_[ \u0627]K*": 5,
+    "I_[ \u0627\u0644]K*": 9,
+    "I_[ \u0644]K*": 11,
+    "I_[\u0627]K*": 6,
+    "I_[\u0627]KI_[\u0627]K*": 7,
+    "I_[\u0627]KI_[\u0644]K*": 8,
+    "I_[\u0627\u0644]K*": 10,
+    "I_[\u0647]K*": 12,
+    "I_[\u064a]K*": 13,
+    "K*": 14,
+    "K*D": 15,
+    "K*DK": 16,
+    "K*DKKK": 18,
+    "K*I_[ ]K": 19,
+    "K*I_[\u0627]": 21,
+    "K*I_[\u0627]K": 22,
+    "K*I_[\u0627]KI_[\u0644]K": 25,
+    "K*I_[\u0644]K": 27,
+    "K*I_[\u0646]K": 29,
+    "K*I_[\u0647]": 31,
+    "K*I_[\u0647]K": 32,
+    "K*I_[\u0648]K": 33,
+    "K*I_[\u064a]K": 34,
+    "K*R_[ ]": 41,
+    "K*R_[\u0622]K": 42,
+    "K*R_[\u0627]": 43,
+    "K*R_[\u0629]": 45,
+    "K*R_[\u062b]": 46,
+    "K*R_[\u062b]K": 47,
+    "K*R_[\u062b]KK": 48,
+    "K*R_[\u0630]": 49,
+    "K*R_[\u0638]": 50,
+    "K*R_[\u0639]": 51,
+    "K*R_[\u0642]": 52,
+    "K*R_[\u0642]K": 53,
+    "K*R_[\u0647]": 54,
+    "K*R_[\u0649]": 55,
+    "K*R_[\u064a]": 56,
+    "KDK*": 17,
+    "KI_[ ]K*": 20,
+    "KI_[\u0627 ]K*": 23,
+    "KI_[\u0627]K*": 24,
+    "KI_[\u0627\u0644]K*": 26,
+    "KI_[\u0644]K*": 28,
+    "KI_[\u0646]K*": 30,
+    "KI_[\u064a]K*": 35,
+    "KKI_[ ]K*": 36,
+    "KKI_[ \u0627]K*": 37,
+    "KKI_[\u0627]K*": 38,
+    "KKKR_[\u0627]K*": 39,
+    "KKR_[\u0627]K*": 40,
+    "KR_[\u0627]K*": 44,
+    "MI_[\u0627]K*": 57,
+    "MK*": 58,
+    "MK*R_[\u0629]": 59,
+    "MR_[\u0627]K*": 60,
+    "MR_[\u062b]K*": 61,
+    "R_[\u0622]K*": 62,
+    "R_[\u0627]": 63,
+    "R_[\u0627]K*": 64,
+    "R_[\u0627]K*I_[\u0644]K": 65,
+    "R_[\u0627]K*R_[\u062b]": 66,
+    "R_[\u0629]": 67,
+    "R_[\u062a]I_[\u0634]K*": 68,
+    "R_[\u062a]K*": 69,
+    "R_[\u062a]R_[\u0639]K*": 70,
+    "R_[\u062b]": 71,
+    "R_[\u062b]K*": 72,
+    "R_[\u062b]R_[\u0629]": 73,
+    "R_[\u0630]": 74,
+    "R_[\u0630]K*": 75,
+    "R_[\u0638]K*": 76,
+    "R_[\u063a]K*": 77,
+    "R_[\u0642]": 78,
+    "R_[\u0642]K*": 79,
+    "R_[\u0643]K*": 80,
+    "R_[\u0647]": 81,
+    "R_[\u0649]": 82,
+    "R_[\u064a]": 83
+  },
+  "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:feec43453230e66980d940571d564d6689400d4eeded05468d5194a51e10bbdf
+size 538739825

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 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.8493150684931505,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.28,
+      "learning_rate": 3.8584474885844754e-05,
+      "loss": 0.3009,
+      "step": 500
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 2.71689497716895e-05,
+      "loss": 0.0796,
+      "step": 1000
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 1.5753424657534248e-05,
+      "loss": 0.0317,
+      "step": 1500
+    }
+  ],
+  "max_steps": 2190,
+  "num_train_epochs": 10,
+  "total_flos": 660892650498432.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c7c030beb1dfd05a088aa19f2c3f27f4b457f8f7979298c038a527af1e9753c
+size 4015