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

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: studio-ousia/mluke-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- rouge
+model-index:
+- name: 08cac0e7fc2540de88af08514b4cd03e
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# 08cac0e7fc2540de88af08514b4cd03e
+
+This model is a fine-tuned version of [studio-ousia/mluke-base](https://huggingface.co/studio-ousia/mluke-base) on the fancyzhx/dbpedia_14 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0577
+- Data Size: 1.0
+- Epoch Runtime: 1586.1733
+- Accuracy: 0.9893
+- F1 Macro: 0.9893
+- Rouge1: 0.9893
+- Rouge2: 0.0
+- Rougel: 0.9893
+- Rougelsum: 0.9893
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- num_epochs: 50
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss | Data Size | Epoch Runtime | Accuracy | F1 Macro | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:------:|:---------------:|:---------:|:-------------:|:--------:|:--------:|:------:|:------:|:------:|:---------:|
+| No log        | 0     | 0      | 2.6273          | 0         | 54.8888       | 0.0830   | 0.0440   | 0.0831 | 0.0    | 0.0830 | 0.0831    |
+| 0.1405        | 1     | 17500  | 0.0760          | 0.0078    | 67.3486       | 0.9838   | 0.9839   | 0.9838 | 0.0    | 0.9838 | 0.9838    |
+| 0.0611        | 2     | 35000  | 0.0727          | 0.0156    | 79.5771       | 0.9857   | 0.9857   | 0.9857 | 0.0    | 0.9857 | 0.9857    |
+| 0.0641        | 3     | 52500  | 0.0825          | 0.0312    | 103.3333      | 0.9836   | 0.9835   | 0.9836 | 0.0    | 0.9836 | 0.9836    |
+| 0.0614        | 4     | 70000  | 0.0638          | 0.0625    | 150.7420      | 0.9867   | 0.9867   | 0.9867 | 0.0    | 0.9866 | 0.9867    |
+| 0.0472        | 5     | 87500  | 0.0638          | 0.125     | 244.0766      | 0.9871   | 0.9870   | 0.9871 | 0.0    | 0.9870 | 0.9871    |
+| 0.0591        | 6     | 105000 | 0.0506          | 0.25      | 430.5615      | 0.9887   | 0.9887   | 0.9887 | 0.0    | 0.9887 | 0.9887    |
+| 0.0004        | 7     | 122500 | 0.0464          | 0.5       | 817.6506      | 0.9897   | 0.9897   | 0.9898 | 0.0    | 0.9897 | 0.9897    |
+| 0.042         | 8.0   | 140000 | 0.0485          | 1.0       | 1586.6349     | 0.9906   | 0.9906   | 0.9907 | 0.0    | 0.9907 | 0.9906    |
+| 0.0325        | 9.0   | 157500 | 0.0513          | 1.0       | 1582.4599     | 0.9897   | 0.9897   | 0.9897 | 0.0    | 0.9897 | 0.9897    |
+| 0.0216        | 10.0  | 175000 | 0.0649          | 1.0       | 1581.0572     | 0.9890   | 0.9889   | 0.9890 | 0.0    | 0.9889 | 0.9890    |
+| 0.0431        | 11.0  | 192500 | 0.0577          | 1.0       | 1586.1733     | 0.9893   | 0.9893   | 0.9893 | 0.0    | 0.9893 | 0.9893    |
+
+
+### Framework versions
+
+- Transformers 4.57.0
+- Pytorch 2.8.0+cu128
+- Datasets 4.3.0
+- Tokenizers 0.22.1

added_tokens.json

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

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "LukeForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bert_model_name": "xlm-roberta-base",
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "cls_entity_prediction": false,
+  "deepspeed_transformer_layer_args": {},
+  "dtype": "float32",
+  "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,
+  "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",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "luke",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.57.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b19267cfe0ff489393908e547dccaeaaf355f8b9399bb85d214f6a065f0536
+size 2343423856

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "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

@@ -0,0 +1,103 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250002": {
+      "content": "<ent>",
+      "lstrip": 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": false,
+  "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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_entity_length": 32,
+  "max_mention_length": 30,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "task": null,
+  "tokenizer_class": "MLukeTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce534a5d87a2e745ced20326ca17b11c21ed224442e184e38a40baa08c964d7e
+size 5969