Upload 11 files

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-lite",
+  "architectures": [
+    "LukeForQuestionAnswering"
+  ],
+  "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,
+  "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": "4.24.0",
+  "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 sha256:3982374bd24a09aa3deacca98d4d543c615139ae54536574d9969387924eebc5
+size 1651227335

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca45aad89a153fb09a178bb6f6f6316b454073026de5baeba27638efe01caee
+size 13547

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27617c79b467bcfab635b9ce51cc47f24cc2d3ebeb0772c41bb63e5892c6103d
+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 +1,124 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.984126984126984,
+  "global_step": 9400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 5e-05,
+      "loss": 2.1043,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.7206703910614525e-05,
+      "loss": 1.4607,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.4413407821229054e-05,
+      "loss": 1.331,
+      "step": 1500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.1620111731843576e-05,
+      "loss": 1.2417,
+      "step": 2000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.8826815642458106e-05,
+      "loss": 1.1599,
+      "step": 2500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.603351955307263e-05,
+      "loss": 1.1286,
+      "step": 3000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 3.324022346368715e-05,
+      "loss": 0.978,
+      "step": 3500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 3.0446927374301676e-05,
+      "loss": 0.9336,
+      "step": 4000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.7653631284916205e-05,
+      "loss": 0.9469,
+      "step": 4500
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.4860335195530728e-05,
+      "loss": 0.9089,
+      "step": 5000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.206703910614525e-05,
+      "loss": 0.8395,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.9273743016759776e-05,
+      "loss": 0.8046,
+      "step": 6000
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.64804469273743e-05,
+      "loss": 0.7157,
+      "step": 6500
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.3687150837988827e-05,
+      "loss": 0.6048,
+      "step": 7000
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.0893854748603351e-05,
+      "loss": 0.618,
+      "step": 7500
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 8.100558659217877e-06,
+      "loss": 0.6173,
+      "step": 8000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.307262569832402e-06,
+      "loss": 0.6185,
+      "step": 8500
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 2.5139664804469276e-06,
+      "loss": 0.5967,
+      "step": 9000
+    }
+  ],
+  "max_steps": 9450,
+  "num_train_epochs": 3,
+  "total_flos": 2.1134250039809664e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8042f97bb6147b1177e70c65953cfeac7128458c8968176ae8dc8de07b489da2
+size 3439