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 +1,43 @@
+{
+  "_name_or_path": "studio-ousia/luke-japanese-base",
+  "architectures": [
+    "LukeForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "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:a6619af51c9c03a94887d5a17273a299852c7620b2c541d6bf360f7b9ba09567
+size 1116561961

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc4b1664b32d6a2c89a7ffbcbef4540607493c7e5cc1c6c4fffafbce0a735bc2
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350993ba93565f86b9cbab9f456499a8d43a72dc299df1de11f87676dfdd2b40
+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 +1,79 @@
+{
+  "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 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 395,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8114215283483976,
+      "eval_f1": 0.818616230475624,
+      "eval_loss": 0.4595734179019928,
+      "eval_precision": 0.8389816919950399,
+      "eval_recall": 0.8114215283483976,
+      "eval_runtime": 305.353,
+      "eval_samples_per_second": 7.971,
+      "eval_steps_per_second": 0.033,
+      "step": 79
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8952341824157765,
+      "eval_f1": 0.8954913458940253,
+      "eval_loss": 0.28638511896133423,
+      "eval_precision": 0.8961827409877436,
+      "eval_recall": 0.8952341824157765,
+      "eval_runtime": 306.1964,
+      "eval_samples_per_second": 7.949,
+      "eval_steps_per_second": 0.033,
+      "step": 158
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8878389482333607,
+      "eval_f1": 0.8917239250068452,
+      "eval_loss": 0.2966187298297882,
+      "eval_precision": 0.8994920866634257,
+      "eval_recall": 0.8878389482333607,
+      "eval_runtime": 309.8999,
+      "eval_samples_per_second": 7.854,
+      "eval_steps_per_second": 0.032,
+      "step": 237
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8964667214461791,
+      "eval_f1": 0.8983882066368747,
+      "eval_loss": 0.2941748797893524,
+      "eval_precision": 0.9015125324656873,
+      "eval_recall": 0.8964667214461791,
+      "eval_runtime": 308.8193,
+      "eval_samples_per_second": 7.882,
+      "eval_steps_per_second": 0.032,
+      "step": 316
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8976992604765818,
+      "eval_f1": 0.8991780621741491,
+      "eval_loss": 0.3037779927253723,
+      "eval_precision": 0.9013216300304917,
+      "eval_recall": 0.8976992604765818,
+      "eval_runtime": 306.6866,
+      "eval_samples_per_second": 7.936,
+      "eval_steps_per_second": 0.033,
+      "step": 395
+    }
+  ],
+  "max_steps": 395,
+  "num_train_epochs": 5,
+  "total_flos": 8255946278073600.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec995683874c1b40d267b2c8d07633352c6f18789b65f422488271b94db557fe
+size 3515