Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<pad>": 0,
+  "<unk>": 1,
+  "[CLS]": 2,
+  "[MASK]": 4,
+  "[SEP]": 3
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "line-corporation/line-distilbert-base-japanese",
+  "activation": "gelu",
+  "architectures": [
+    "ConsistentSentenceClassifier"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_hidden_states": true,
+  "pad_token_id": 0,
+  "problem_type": "multi_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": true,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0",
+  "vocab_size": 32768
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb5042faed7e8ecb5fe8c631145f59fc59af57cf9cb4c2c593b859a57c04663
+size 274755245

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfafc8c0662d9c8f39621a64c74260f2ad120310c8dd24886de2dddaf599b4e
+size 439391

tokenizer_config.json

@@ -0,0 +1,76 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "auto_map": {
+    "AutoTokenizer": [
+      "line-corporation/line-distilbert-base-japanese--distilbert_japanese_tokenizer.DistilBertJapaneseTokenizer",
+      null
+    ]
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "do_subword_tokenize": true,
+  "do_word_tokenize": true,
+  "eos_token": "[SEP]",
+  "jumanpp_kwargs": null,
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "mecab_kwargs": {
+    "mecab_dic": "unidic_lite"
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "subword_tokenizer_type": "sentencepiece",
+  "sudachi_kwargs": null,
+  "tokenize_chinese_chars": false,
+  "tokenizer_class": "BertJapaneseTokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>",
+  "word_tokenizer_type": "mecab"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ddcc7d5119c6fd91ecb61efc17a9a5ba7c88bdd9b98a9ec768ce1b6bb179bd2
+size 4155