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-large",
+  "architectures": [
+    "LukeForMultipleChoice"
+  ],
+  "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,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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": "4.26.0",
+  "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 sha256:7b06f4585e52d018d7a4b19f1578313b5071c2bc049ee7085c59b668b27fab86
+size 21684396

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a0fc26f89bfebea68cabc67ddd3390fa87df549fe71313e450258add67eccce
+size 2239626697

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97465ee8dcb4826c490fecf47b269bb78fb99fb72384db27a6dd705906ff3f7
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:747e4fc5ed3de820f508567a3a688b540a2037e3f88f829ff473064a927a575c
+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-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "models/luke-japanese-large/hf_xlm_roberta/special_tokens_map.json",
+  "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 +1,78 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6442953020134228,
+  "global_step": 4900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9328859060402687e-05,
+      "loss": 1.0712,
+      "step": 500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.865771812080537e-05,
+      "loss": 0.7775,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.7986577181208054e-05,
+      "loss": 0.7932,
+      "step": 1500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.731543624161074e-05,
+      "loss": 0.8078,
+      "step": 2000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6644295302013425e-05,
+      "loss": 0.7557,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.4945272207260132,
+      "eval_runtime": 65.3538,
+      "eval_samples_per_second": 17.122,
+      "eval_steps_per_second": 5.707,
+      "step": 2980
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5973154362416107e-05,
+      "loss": 0.7255,
+      "step": 3000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.5302013422818792e-05,
+      "loss": 0.4163,
+      "step": 3500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.4630872483221479e-05,
+      "loss": 0.5084,
+      "step": 4000
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.3959731543624163e-05,
+      "loss": 0.4503,
+      "step": 4500
+    }
+  ],
+  "max_steps": 14900,
+  "num_train_epochs": 5,
+  "total_flos": 1.070174051569728e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596b7906b70f2a9daa106ac93f82ca17cc618dda2889c1a92ab22c55ac4bba88
+size 3515