Upload 9 files

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "ku-nlp/deberta-v2-large-japanese",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d",
+    "2": "I-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d",
+    "3": "B-\u6cd5\u4eba\u540d",
+    "4": "I-\u6cd5\u4eba\u540d",
+    "5": "B-\u5730\u540d",
+    "6": "I-\u5730\u540d",
+    "7": "B-\u4eba\u540d",
+    "8": "I-\u4eba\u540d",
+    "9": "B-\u65bd\u8a2d\u540d",
+    "10": "I-\u65bd\u8a2d\u540d",
+    "11": "B-\u30a4\u30d9\u30f3\u30c8\u540d",
+    "12": "I-\u30a4\u30d9\u30f3\u30c8\u540d",
+    "13": "B-\u653f\u6cbb\u7684\u7d44\u7e54\u540d",
+    "14": "I-\u653f\u6cbb\u7684\u7d44\u7e54\u540d",
+    "15": "B-\u88fd\u54c1\u540d",
+    "16": "I-\u88fd\u54c1\u540d"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d": 1,
+    "B-\u30a4\u30d9\u30f3\u30c8\u540d": 11,
+    "B-\u4eba\u540d": 7,
+    "B-\u5730\u540d": 5,
+    "B-\u653f\u6cbb\u7684\u7d44\u7e54\u540d": 13,
+    "B-\u65bd\u8a2d\u540d": 9,
+    "B-\u6cd5\u4eba\u540d": 3,
+    "B-\u88fd\u54c1\u540d": 15,
+    "I-\u305d\u306e\u4ed6\u306e\u7d44\u7e54\u540d": 2,
+    "I-\u30a4\u30d9\u30f3\u30c8\u540d": 12,
+    "I-\u4eba\u540d": 8,
+    "I-\u5730\u540d": 6,
+    "I-\u653f\u6cbb\u7684\u7d44\u7e54\u540d": 14,
+    "I-\u65bd\u8a2d\u540d": 10,
+    "I-\u6cd5\u4eba\u540d": 4,
+    "I-\u88fd\u54c1\u540d": 16,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 0,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b06006e5c980570a52f722fb574f23d4c05ee41e4e118e1c646c64725b2916f1
+size 1355229697

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07df9c38027080a29bdfdc466ec78d1b6500129b38ffad3b262619c6b854a9ca
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4db5523c7c7e23368b5f50223787d2962cc7f9cf051bdb8078f4ccc89dd732
+size 627

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]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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]"
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 4988,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.590834697217676e-05,
+      "loss": 0.1357,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.079378068739771e-05,
+      "loss": 0.049,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.567921440261866e-05,
+      "loss": 0.035,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.05646481178396e-05,
+      "loss": 0.0247,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.5450081833060556e-05,
+      "loss": 0.0269,
+      "step": 2500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.0335515548281506e-05,
+      "loss": 0.0128,
+      "step": 3000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.5220949263502457e-05,
+      "loss": 0.0125,
+      "step": 3500
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 1.0106382978723404e-05,
+      "loss": 0.0064,
+      "step": 4000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 4.991816693944354e-06,
+      "loss": 0.0054,
+      "step": 4500
+    }
+  ],
+  "max_steps": 4988,
+  "num_train_epochs": 4,
+  "total_flos": 7021360413554688.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:848e345325b92eaa6b2476e2e68814bbae0572e6baa6119c6ee7f8070af9f003
+size 3643