Upload 11 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* 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
+entity_vocab.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<ent2>": 32771,
+  "<ent>": 32770
+}

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "studio-ousia/luke-japanese-large",
+  "architectures": [
+    "LukeForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bert_model_name": "models/luke-japanese-large/hf_xlm_roberta",
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "cls_entity_prediction": false,
+  "entity_emb_size": 256,
+  "entity_vocab_size": 570505,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "luke",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "use_entity_aware_attention": true,
+  "vocab_size": 32772
+}

entity_vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b06f4585e52d018d7a4b19f1578313b5071c2bc049ee7085c59b668b27fab86
+size 21684396

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e6eb713c99abc9fc11fcd730b14e31295d780478a506a74cb67b4d5751b232
+size 2235493249

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b1f298375437845383fc52ca0e1806c97d89f6fc4b6fdf060d87a08bac6386
+size 14575

scheduler.pt

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

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b73a5e054936c920cf5b7d1ec21ce9c281977078269963beb821c6c86fbff7
+size 841889

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,78 @@
+{
+  "additional_special_tokens": [
+    {
+      "__type": "AddedToken",
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "__type": "AddedToken",
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "__type": "AddedToken",
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "__type": "AddedToken",
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "entity_mask2_token": "[MASK2]",
+  "entity_mask_token": "[MASK]",
+  "entity_pad_token": "[PAD]",
+  "entity_token_1": {
+    "__type": "AddedToken",
+    "content": "<ent>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "entity_token_2": {
+    "__type": "AddedToken",
+    "content": "<ent2>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "entity_unk_token": "[UNK]",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_entity_length": 32,
+  "max_mention_length": 30,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "task": null,
+  "tokenizer_class": "MLukeTokenizer",
+  "tokenizer_file": "models/luke-japanese-large/hf_luke_japanese_epoch20/tokenizer.json",
+  "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": 0.1267,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.079378068739771e-05,
+      "loss": 0.0395,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.567921440261866e-05,
+      "loss": 0.0312,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.05646481178396e-05,
+      "loss": 0.023,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.5450081833060556e-05,
+      "loss": 0.0228,
+      "step": 2500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 2.0335515548281506e-05,
+      "loss": 0.0144,
+      "step": 3000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.5220949263502457e-05,
+      "loss": 0.0126,
+      "step": 3500
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 1.0106382978723404e-05,
+      "loss": 0.0074,
+      "step": 4000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 4.991816693944354e-06,
+      "loss": 0.0076,
+      "step": 4500
+    }
+  ],
+  "max_steps": 4988,
+  "num_train_epochs": 4,
+  "total_flos": 8691993142769664.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7cf9aa8e159dbf907448265416ee1aed2ecba831f13be59bb81e95e5848dc2b
+size 3963