Upload 11 files

added_tokens.json

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

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "studio-ousia/luke-japanese-large-lite",
+  "architectures": [
+    "LukeForSequenceClassification"
+  ],
+  "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": 4,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7
+  },
+  "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",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "use_entity_aware_attention": true,
+  "vocab_size": 32772
+}

entity_vocab.json

@@ -0,0 +1,6 @@
+{
+  "[MASK2]": 3,
+  "[MASK]": 0,
+  "[PAD]": 2,
+  "[UNK]": 1
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbb5124461d44a1bbfffa868cb498fb77daee7011262657d1d921c00750d82d
+size 1655458499

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f34f56ba239ada44c80231ab5bf95ed34710adb531fd1cc7f0b377e4d2ce7c4a
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4cedc8a71c35f12124c99e1f7741fff4ad7d9474abced2c058bba036dce148
+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-large-lite",
+  "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_large_lite_epoch20/tokenizer.json",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.2806,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.2282,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9e-06,
+      "loss": 0.2146,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.2067,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.2059,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.2037,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.666666666666667e-06,
+      "loss": 0.1921,
+      "step": 3500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.1955,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7e-06,
+      "loss": 0.1917,
+      "step": 4500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.191,
+      "step": 5000
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.1565,
+      "step": 5500
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6e-06,
+      "loss": 0.1535,
+      "step": 6000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 5.666666666666667e-06,
+      "loss": 0.1555,
+      "step": 6500
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.1503,
+      "step": 7000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 5e-06,
+      "loss": 0.1541,
+      "step": 7500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.1545,
+      "step": 8000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 4.333333333333334e-06,
+      "loss": 0.1524,
+      "step": 8500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1456,
+      "step": 9000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.6666666666666666e-06,
+      "loss": 0.1544,
+      "step": 9500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.1518,
+      "step": 10000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 3e-06,
+      "loss": 0.1049,
+      "step": 10500
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.1133,
+      "step": 11000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 0.1072,
+      "step": 11500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1141,
+      "step": 12000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.1126,
+      "step": 12500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.1164,
+      "step": 13000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.1145,
+      "step": 13500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 0.1132,
+      "step": 14000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 3.3333333333333335e-07,
+      "loss": 0.112,
+      "step": 14500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.1113,
+      "step": 15000
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 3,
+  "total_flos": 3.494749741056e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f13921ee7a89de1f23965c17a045a5485ededc7e8e23c32a468b30a357ca30
+size 3503