Model upload

config.json

@@ -0,0 +1,114 @@
+{
+  "_name_or_path": "/scratch/ba63/BERT_models/bert-base-arabic-camelbert-msa",
+  "architectures": [
+    "BertForTokenClassificationSingleLabel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "DELETE",
+    "1": "MERGE-B",
+    "2": "MERGE-I",
+    "3": "REPLACE_M",
+    "4": "REPLACE_MI",
+    "5": "REPLACE_MI+REPLACE_OH",
+    "6": "REPLACE_MT",
+    "7": "REPLACE_O",
+    "8": "REPLACE_OA",
+    "9": "REPLACE_OA+REPLACE_OH",
+    "10": "REPLACE_OA+REPLACE_OR",
+    "11": "REPLACE_OC",
+    "12": "REPLACE_OD",
+    "13": "REPLACE_OD+REPLACE_OG",
+    "14": "REPLACE_OD+REPLACE_OH",
+    "15": "REPLACE_OD+REPLACE_OM",
+    "16": "REPLACE_OD+REPLACE_OR",
+    "17": "REPLACE_OH",
+    "18": "REPLACE_OH+REPLACE_OM",
+    "19": "REPLACE_OH+REPLACE_OT",
+    "20": "REPLACE_OH+REPLACE_XC",
+    "21": "REPLACE_OM",
+    "22": "REPLACE_OM+REPLACE_OR",
+    "23": "REPLACE_OR",
+    "24": "REPLACE_OR+REPLACE_OT",
+    "25": "REPLACE_OT",
+    "26": "REPLACE_OW",
+    "27": "REPLACE_P",
+    "28": "REPLACE_S",
+    "29": "REPLACE_SF",
+    "30": "REPLACE_SW",
+    "31": "REPLACE_X",
+    "32": "REPLACE_XC",
+    "33": "REPLACE_XC+REPLACE_XG",
+    "34": "REPLACE_XC+REPLACE_XN",
+    "35": "REPLACE_XF",
+    "36": "REPLACE_XG",
+    "37": "REPLACE_XM",
+    "38": "REPLACE_XN",
+    "39": "REPLACE_XT",
+    "40": "SPLIT",
+    "41": "UC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "DELETE": 0,
+    "MERGE-B": 1,
+    "MERGE-I": 2,
+    "REPLACE_M": 3,
+    "REPLACE_MI": 4,
+    "REPLACE_MI+REPLACE_OH": 5,
+    "REPLACE_MT": 6,
+    "REPLACE_O": 7,
+    "REPLACE_OA": 8,
+    "REPLACE_OA+REPLACE_OH": 9,
+    "REPLACE_OA+REPLACE_OR": 10,
+    "REPLACE_OC": 11,
+    "REPLACE_OD": 12,
+    "REPLACE_OD+REPLACE_OG": 13,
+    "REPLACE_OD+REPLACE_OH": 14,
+    "REPLACE_OD+REPLACE_OM": 15,
+    "REPLACE_OD+REPLACE_OR": 16,
+    "REPLACE_OH": 17,
+    "REPLACE_OH+REPLACE_OM": 18,
+    "REPLACE_OH+REPLACE_OT": 19,
+    "REPLACE_OH+REPLACE_XC": 20,
+    "REPLACE_OM": 21,
+    "REPLACE_OM+REPLACE_OR": 22,
+    "REPLACE_OR": 23,
+    "REPLACE_OR+REPLACE_OT": 24,
+    "REPLACE_OT": 25,
+    "REPLACE_OW": 26,
+    "REPLACE_P": 27,
+    "REPLACE_S": 28,
+    "REPLACE_SF": 29,
+    "REPLACE_SW": 30,
+    "REPLACE_X": 31,
+    "REPLACE_XC": 32,
+    "REPLACE_XC+REPLACE_XG": 33,
+    "REPLACE_XC+REPLACE_XN": 34,
+    "REPLACE_XF": 35,
+    "REPLACE_XG": 36,
+    "REPLACE_XM": 37,
+    "REPLACE_XN": 38,
+    "REPLACE_XT": 39,
+    "SPLIT": 40,
+    "UC": 41
+  },
+  "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": "4.22.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63b7098db258825b72b92f1febaab113381b6fadeeb21386b52beaa2ef568eb
+size 434162609

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "/scratch/ba63/BERT_models/bert-base-arabic-camelbert-msa",
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.856682769726248,
+  "global_step": 5500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.597423510466989e-05,
+      "loss": 0.3372,
+      "step": 500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.194847020933977e-05,
+      "loss": 0.2233,
+      "step": 1000
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 3.7922705314009665e-05,
+      "loss": 0.1856,
+      "step": 1500
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 3.389694041867955e-05,
+      "loss": 0.1587,
+      "step": 2000
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 2.9871175523349438e-05,
+      "loss": 0.1332,
+      "step": 2500
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 2.5845410628019323e-05,
+      "loss": 0.1059,
+      "step": 3000
+    },
+    {
+      "epoch": 5.64,
+      "learning_rate": 2.1819645732689212e-05,
+      "loss": 0.0869,
+      "step": 3500
+    },
+    {
+      "epoch": 6.44,
+      "learning_rate": 1.77938808373591e-05,
+      "loss": 0.0743,
+      "step": 4000
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 1.3768115942028985e-05,
+      "loss": 0.0633,
+      "step": 4500
+    },
+    {
+      "epoch": 8.05,
+      "learning_rate": 9.742351046698874e-06,
+      "loss": 0.0537,
+      "step": 5000
+    },
+    {
+      "epoch": 8.86,
+      "learning_rate": 5.71658615136876e-06,
+      "loss": 0.0457,
+      "step": 5500
+    }
+  ],
+  "max_steps": 6210,
+  "num_train_epochs": 10,
+  "total_flos": 1.4222892248394192e+16,
+  "trial_name": null,
+  "trial_params": null
+}