Upload folder using huggingface_hub

base_model/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

base_model/config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 96871,
+  "dtype": "float32",
+  "eos_token_id": 96868,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 96869,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "transformers_version": "4.57.3",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 96900
+}

base_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7405eb902f13104f959d441ab69dfdef44dd761cb7afa7e1f68c33cfeebdeca3
+size 642260656

base_model/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

base_model/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "96867": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96868": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96869": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96870": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "96871": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]"
+}

base_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f62848675760897c3d02bd6e8686ab5e4e122e4fa061eeaf3cc74f603b3ef0
+size 5905

best_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:513c713b88290668d27bed3f705e1b95f9c26c0446a81dd3acb53ef47b38a779
+size 639695148

config.json

@@ -0,0 +1,31 @@
+{
+  "model_dir": "models/deberta_v3_mlm",
+  "task1_csv": "Data_for_deberta/processed/task1_ready/train.csv",
+  "task2_csv": "Data_for_deberta/processed/task2_ready/train.csv",
+  "output_dir": "outputs/train_runs",
+  "max_length": 384,
+  "val_ratio": 0.1,
+  "seed": 42,
+  "batch_size": 16,
+  "max_epochs": 10,
+  "min_epochs": 3,
+  "early_stop_patience": 2,
+  "learning_rate": 1.5e-05,
+  "weight_decay": 0.01,
+  "warmup_ratio": 0.06,
+  "boost_mult": 1.0,
+  "focal_gamma_task1": 0.0,
+  "rdrop_alpha_task2": 0.7,
+  "lambda_task1": 1.0,
+  "lambda_task2": 1.0,
+  "label_smoothing_task1": 0.02,
+  "label_smoothing_task2": 0.05,
+  "task2_balance_power": 0.5,
+  "task2_balance_min": 0.2,
+  "task2_balance_max": 5.0,
+  "title_empty_token": "[TITLE_EMPTY]",
+  "use_amp": true,
+  "cartography": true,
+  "cartography_lowmean_q": 0.005,
+  "cartography_task2_per_category_cap": 30
+}

label_map.json

@@ -0,0 +1,89 @@
+{
+  "CSR活動": 0,
+  "DX": 1,
+  "M&A": 2,
+  "イベント": 3,
+  "サイバー攻撃": 4,
+  "システム障害": 5,
+  "ダイバーシティ": 6,
+  "ハラスメント問題": 7,
+  "リニューアルオープン": 8,
+  "不法就労": 9,
+  "不適切広告": 10,
+  "不適切発言": 11,
+  "事故": 12,
+  "事業効率化": 13,
+  "事業縮小": 14,
+  "人事異動": 15,
+  "人材育成": 16,
+  "代表者死亡": 17,
+  "企業間トラブル": 18,
+  "企業間取引解消": 19,
+  "価格変更": 20,
+  "債務超過": 21,
+  "債権回収不能": 22,
+  "債権譲渡": 23,
+  "公害": 24,
+  "再建型倒産": 25,
+  "労働争議": 26,
+  "労働災害": 27,
+  "労働者の自殺・失踪": 28,
+  "反社会的勢力関与": 29,
+  "受賞": 30,
+  "品質管理不正": 31,
+  "商品表示の不備": 32,
+  "広報活動": 33,
+  "役員変更": 34,
+  "従業員の不祥事": 35,
+  "従業員数減少": 36,
+  "情報漏洩": 37,
+  "批判的投稿": 38,
+  "提携": 39,
+  "新商品の展開": 40,
+  "新工場竣工": 41,
+  "新店舗開店": 42,
+  "新施設開設": 43,
+  "新規事業参入": 44,
+  "新規採用": 45,
+  "新設備導入": 46,
+  "本社住所移転": 47,
+  "株主変更": 48,
+  "株主総会開催": 49,
+  "株式保有率変更": 50,
+  "株式公開": 51,
+  "業績悪化": 52,
+  "業績改善": 53,
+  "横領": 54,
+  "海外進出": 55,
+  "清算型倒産": 56,
+  "特許取得": 57,
+  "生産停止": 58,
+  "生産再開": 59,
+  "生産拡大": 60,
+  "異物混入": 61,
+  "知的財産権の侵害": 62,
+  "研究開発": 63,
+  "社名変更": 64,
+  "税務違反": 65,
+  "粉飾決算": 66,
+  "組織体制変更": 67,
+  "経営計画": 68,
+  "職場環境改善": 69,
+  "行政処分": 70,
+  "補助金獲得": 71,
+  "設備投資": 72,
+  "訴訟": 73,
+  "詐欺": 74,
+  "認定取得": 75,
+  "談合": 76,
+  "販路拡大": 77,
+  "賃上げ": 78,
+  "賃金未払い": 79,
+  "資本金の変更": 80,
+  "資金調達": 81,
+  "贈収賄": 82,
+  "通信障害": 83,
+  "逮捕": 84,
+  "違法残業": 85,
+  "顧客トラブル": 86
+}

selected_b_trial.json

@@ -0,0 +1,23 @@
+{
+  "sweep_dir": "outputs/train_runs/sweep_20260207_073651",
+  "best_trial_dir": "outputs/train_runs/sweep_20260207_073651/trial_02_B_gamma0.0_rdrop0.7",
+  "model_path": "outputs/train_runs/sweep_20260207_073651/best_model.pt",
+  "config_path": "outputs/train_runs/sweep_20260207_073651/best_config.json",
+  "label_map_path": "outputs/train_runs/sweep_20260207_073651/trial_02_B_gamma0.0_rdrop0.7/label_map.json",
+  "selected": {
+    "source": "summary.csv",
+    "row": {
+      "stage": "B",
+      "trial": "2",
+      "learning_rate": "1.5e-05",
+      "boost_mult": "1.0",
+      "focal_gamma_task1": "0.0",
+      "rdrop_alpha_task2": "0.7",
+      "task1_acc_task1only": "0.8830057070386811",
+      "task1_acc": "0.8830057070386811",
+      "task2_acc": "0.865073787772312",
+      "score": "1.7480794948109932",
+      "epoch": "4"
+    }
+  }
+}

summary.csv

@@ -0,0 +1,7 @@
+stage,trial,learning_rate,boost_mult,focal_gamma_task1,rdrop_alpha_task2,task1_acc_task1only,task1_acc,task2_acc,score,epoch
+B,1,1.5e-05,1.0,0.0,0.3,0.8880786303107165,0.8880786303107165,0.8531271960646521,1.7412058263753687,2
+B,2,1.5e-05,1.0,0.0,0.7,0.8830057070386811,0.8830057070386811,0.865073787772312,1.7480794948109932,4
+B,3,1.5e-05,1.0,1.0,0.3,0.8822130627774255,0.8822130627774255,0.8657765284609978,1.7479895912384233,2
+B,4,1.5e-05,1.0,1.0,0.7,0.8836398224476855,0.8836398224476855,0.8636683063949403,1.7473081288426258,2
+B,5,1.5e-05,1.0,2.0,0.3,0.8731769181991123,0.8731769181991123,0.8699929725931131,1.7431698907922253,4
+B,6,1.5e-05,1.0,2.0,0.7,0.8746036778693722,0.8746036778693722,0.8552354181307098,1.729839096000082,2