End of training

.gitattributes

@@ -33,3 +33,4 @@ 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

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google-bert/bert-base-multilingual-cased
+base_model: studio-ousia/mluke-base
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # exp_number1
 
-This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on the None dataset.
+This model is a fine-tuned version of [studio-ousia/mluke-base](https://huggingface.co/studio-ousia/mluke-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2623
+- Loss: 0.2131
 
 ## Model description
 
@@ -34,28 +34,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 8
+- learning_rate: 5e-05
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3388        | 1.0   | 443  | 0.4651          |
-| 0.3435        | 2.0   | 886  | 0.3720          |
-| 0.2449        | 3.0   | 1329 | 0.3122          |
-| 0.1175        | 4.0   | 1772 | 0.3218          |
-| 0.1389        | 5.0   | 2215 | 0.3442          |
-| 0.149         | 6.0   | 2658 | 0.2398          |
-| 0.1102        | 7.0   | 3101 | 0.2547          |
-| 0.0479        | 8.0   | 3544 | 0.2352          |
-| 0.0651        | 9.0   | 3987 | 0.2485          |
-| 0.0806        | 10.0  | 4430 | 0.2623          |
+| 0.4351        | 1.0   | 221  | 0.5519          |
+| 0.3954        | 2.0   | 443  | 0.3151          |
+| 0.2607        | 3.0   | 664  | 0.3064          |
+| 0.222         | 4.0   | 886  | 0.2342          |
+| 0.1296        | 4.99  | 1105 | 0.2131          |
 
 
 ### Framework versions

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<ent2>": 250003,
+  "<ent>": 250002
+}

config.json

@@ -1,32 +1,37 @@
 {
-  "_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "_name_or_path": "studio-ousia/mluke-base",
   "architectures": [
-    "BertForSequenceClassification"
+    "LukeForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bert_model_name": "xlm-roberta-base",
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "directionality": "bidi",
+  "cls_entity_prediction": false,
+  "deepspeed_transformer_layer_args": {},
+  "entity_emb_size": 256,
+  "entity_vocab_size": 1200001,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "luke",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 119547
+  "use_deepspeed_transformer_layer": false,
+  "use_entity_aware_attention": false,
+  "vocab_size": 250004
 }

entity_vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebeabade0acbb5f6fb6562490c081441746f7bf9bd06a3fa8d86b0bce7461c8d
+size 336948106

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb5534fe2da667670d4573836309d688d6c60ac1cfe278ad584d439866e4efc5
-size 711443456
+oid sha256:a8eb5efbee3c159e9bfe0f109f5bf50badf6de76910b6f5f20adc7abd2f7c600
+size 2343386936

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -1,7 +1,45 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "additional_special_tokens": [
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
+      "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

@@ -1,55 +1,102 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250002": {
+      "content": "<ent>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250003": {
+      "content": "<ent2>",
+      "lstrip": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<ent>",
+    "<ent2>",
+    "<ent>",
+    "<ent2>"
+  ],
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
+  "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,
+    "special": false
+  },
+  "entity_token_2": {
+    "__type": "AddedToken",
+    "content": "<ent2>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false,
+    "special": false
+  },
+  "entity_unk_token": "[UNK]",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_entity_length": 32,
+  "max_mention_length": 30,
   "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "task": null,
+  "tokenizer_class": "MLukeTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b22469dc7aac031b98bea37e4cfb674f9e1c73c99bd20848e6075e1a8d536f5
-size 4856
+oid sha256:5e6e2251e262f9cd187f4ffee4f240581585b807a7b2e3491f7a8b515338a391
+size 4920