Training in progress, epoch 1

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "bongsoo/mdistilbertV3.1",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-movie",
+    "2": "I-movie",
+    "3": "B-genre",
+    "4": "I-genre",
+    "5": "B-contry",
+    "6": "I-contry",
+    "7": "B-person",
+    "8": "I-person",
+    "9": "B-date",
+    "10": "I-date",
+    "11": "B-ott",
+    "12": "I-ott",
+    "13": "B-state",
+    "14": "I-state",
+    "15": "B-tag",
+    "16": "I-tag"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-contry": 5,
+    "B-date": 9,
+    "B-genre": 3,
+    "B-movie": 1,
+    "B-ott": 11,
+    "B-person": 7,
+    "B-state": 13,
+    "B-tag": 15,
+    "I-contry": 6,
+    "I-date": 10,
+    "I-genre": 4,
+    "I-movie": 2,
+    "I-ott": 12,
+    "I-person": 8,
+    "I-state": 14,
+    "I-tag": 16,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 159552
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b48438dac3dac3bb9db98375d917d075309ed85d55774fccc8589b9e9a4013
+size 661896324

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 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_len": 128,
+  "max_length": 128,
+  "model_max_length": 128,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": false,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d73e71d60b6f0fc3767c7b87ed2a84f920f25e6eee80f0c0291fb95a70554345
+size 4536