Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,71 @@
+{
+  "_name_or_path": "UBC-NLP/MARBERTv2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "RH:ISLAM",
+    "1": "RH:Judaism",
+    "2": "RH:Christianity",
+    "3": "UD_RH",
+    "4": "EH:ARAB",
+    "5": "EH:African",
+    "6": "UD_EH",
+    "7": "NH:Iranian",
+    "8": "NH:Israeli",
+    "9": "NH:Saudi",
+    "10": "NH:Turkish",
+    "11": "NH:Qatari",
+    "12": "NH:American",
+    "13": "UD_NH",
+    "14": "GH:Females",
+    "15": "GH:Males",
+    "16": "UD_GH"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "EH:ARAB": 4,
+    "EH:African": 5,
+    "GH:Females": 14,
+    "GH:Males": 15,
+    "NH:American": 12,
+    "NH:Iranian": 7,
+    "NH:Israeli": 8,
+    "NH:Qatari": 11,
+    "NH:Saudi": 9,
+    "NH:Turkish": 10,
+    "RH:Christianity": 2,
+    "RH:ISLAM": 0,
+    "RH:Judaism": 1,
+    "UD_EH": 6,
+    "UD_GH": 16,
+    "UD_NH": 13,
+    "UD_RH": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4f2a52d8bda59a5f68f6f01425d257db502083b8283ad1c209c84b72893396d
+size 651486065

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 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d66e9c99d82fea284c8a4f466c27883a6e2f1ae6bef30e424d1805e28c348080
+size 3963