Uploading model

config.json

@@ -0,0 +1,54 @@
+{
+  "_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_M+REPLACE_O",
+    "5": "REPLACE_O",
+    "6": "REPLACE_O+REPLACE_X",
+    "7": "REPLACE_P",
+    "8": "REPLACE_S",
+    "9": "REPLACE_X",
+    "10": "SPLIT",
+    "11": "UC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "DELETE": 0,
+    "MERGE-B": 1,
+    "MERGE-I": 2,
+    "REPLACE_M": 3,
+    "REPLACE_M+REPLACE_O": 4,
+    "REPLACE_O": 5,
+    "REPLACE_O+REPLACE_X": 6,
+    "REPLACE_P": 7,
+    "REPLACE_S": 8,
+    "REPLACE_X": 9,
+    "SPLIT": 10,
+    "UC": 11
+  },
+  "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 sha256:23385ffe560860a8f5e9e46e05b66a31c33a4b0bd58e9a718933fdab8161f50f
+size 434070321

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 +1,17 @@
+{
+  "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 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.471169686985173,
+  "global_step": 1500,
+  "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": 0.2327,
+      "step": 500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.1762767710049426e-05,
+      "loss": 0.1542,
+      "step": 1000
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 3.764415156507414e-05,
+      "loss": 0.129,
+      "step": 1500
+    }
+  ],
+  "max_steps": 6070,
+  "num_train_epochs": 10,
+  "total_flos": 2461668607000800.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eff349da6fdc072af07b2f875d41bd8d85b1fcf203f4935e6e833c1531fd24a
+size 3439