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 +1,32 @@
+{
+  "_name_or_path": "studio-ousia/luke-japanese-base",
+  "architectures": [
+    "LukeForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bert_model_name": "models/luke-japanese/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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "luke",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "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:e067714dc43f11c0d14d84f760c16b87dbfd5225e463408c0baedec0c1aafd76
+size 22254903

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba55c638b669f59671357ab9f4f518782577cba22cdc1c07ee10491dc30c9795
+size 1116553555

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631fc76208ff7beae9e0c6d7a0c901c5bf1265378270f08ccb99d1d9a8f60099
+size 13547

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bea9f0a5c9cc0a035d104fe2ba262d564a3186335677a1cbeadb289186e6b11
+size 623

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 +1,79 @@
+{
+  "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>",
+  "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,
+  "name_or_path": "studio-ousia/luke-japanese-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "models/luke-japanese/hf_xlm_roberta/special_tokens_map.json",
+  "task": null,
+  "tokenizer_class": "MLukeTokenizer",
+  "tokenizer_file": "models/luke-japanese/hf_luke_japanese_epoch20/tokenizer.json",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.964221824686941,
+  "global_step": 5550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.5527728085867624e-05,
+      "loss": 0.9916,
+      "step": 500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.1055456171735245e-05,
+      "loss": 0.8946,
+      "step": 1000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 3.658318425760287e-05,
+      "loss": 0.6054,
+      "step": 1500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.211091234347048e-05,
+      "loss": 0.5278,
+      "step": 2000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 2.7638640429338103e-05,
+      "loss": 0.4049,
+      "step": 2500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 2.3166368515205725e-05,
+      "loss": 0.2935,
+      "step": 3000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 1.8694096601073346e-05,
+      "loss": 0.2635,
+      "step": 3500
+    },
+    {
+      "epoch": 3.58,
+      "learning_rate": 1.4221824686940966e-05,
+      "loss": 0.1482,
+      "step": 4000
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 9.749552772808588e-06,
+      "loss": 0.167,
+      "step": 4500
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 5.277280858676208e-06,
+      "loss": 0.0716,
+      "step": 5000
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 8.050089445438284e-07,
+      "loss": 0.0764,
+      "step": 5500
+    }
+  ],
+  "max_steps": 5590,
+  "num_train_epochs": 5,
+  "total_flos": 9126529033843200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aff66f79b89765ca236acfaf8db10372ef2fb19ba65943e5330bd6c2264fb26
+size 3439