Upload 10 files

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "ku-nlp/deberta-v2-base-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": 768,
+  "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": 3072,
+  "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": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "type_vocab_size": 0,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7099c9850ba05d6c88973b2771eb3aada343c19b8cf55e5b32a16e72d322de81
+size 447316455

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9d528f7c4cc80cd6b5c854a264a152146fc50cddcbf10034cea36c6e0b5747
+size 13547

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76822ed9ed440beeb88bd2798c1b73ec24e9423717a4060252143f17ebf1c14b
+size 623

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]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c111c16e2e52366dcac46b886e40650bb843fe2938a65f5970271fc5697a127
+size 805061

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": true,
+  "mask_token": "[MASK]",
+  "name_or_path": "ku-nlp/deberta-v2-base-japanese",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.880341880341881,
+  "global_step": 3220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.9289772727272735e-05,
+      "loss": 0.2614,
+      "step": 500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 4.041193181818182e-05,
+      "loss": 0.039,
+      "step": 1000
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 3.153409090909091e-05,
+      "loss": 0.0193,
+      "step": 1500
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 2.2656250000000002e-05,
+      "loss": 0.0112,
+      "step": 2000
+    },
+    {
+      "epoch": 5.34,
+      "learning_rate": 1.3778409090909091e-05,
+      "loss": 0.0071,
+      "step": 2500
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 4.900568181818182e-06,
+      "loss": 0.0048,
+      "step": 3000
+    }
+  ],
+  "max_steps": 3276,
+  "num_train_epochs": 7,
+  "total_flos": 3433722892293120.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29d38418f87ce57471282aa5f86d629e47bbba7f1b710e2cfe7896957557d8ae
+size 3375