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 +1,85 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: studio-ousia/luke-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- rouge
+model-index:
+- name: 0f2142e9bd37e0ab1f2155dead0be1e5
+  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. -->
+
+# 0f2142e9bd37e0ab1f2155dead0be1e5
+
+This model is a fine-tuned version of [studio-ousia/luke-base](https://huggingface.co/studio-ousia/luke-base) on the nyu-mll/glue [cola] dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5325
+- Data Size: 1.0
+- Epoch Runtime: 25.4994
+- Accuracy: 0.8115
+- F1 Macro: 0.7662
+- Rouge1: 0.8115
+- Rouge2: 0.0
+- Rougel: 0.8115
+- Rougelsum: 0.8115
+
+## 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    | 0.6979          | 0         | 1.4878        | 0.3125   | 0.2391   | 0.3115 | 0.0    | 0.3115 | 0.3125    |
+| No log        | 1     | 267  | 0.6298          | 0.0078    | 2.3376        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
+| No log        | 2     | 534  | 0.6256          | 0.0156    | 2.1027        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
+| No log        | 3     | 801  | 0.6220          | 0.0312    | 2.7075        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
+| No log        | 4     | 1068 | 0.6202          | 0.0625    | 3.5640        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
+| 0.0369        | 5     | 1335 | 0.6259          | 0.125     | 5.1721        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
+| 0.6135        | 6     | 1602 | 0.6199          | 0.25      | 8.1249        | 0.6885   | 0.4078   | 0.6895 | 0.0    | 0.6885 | 0.6885    |
+| 0.5898        | 7     | 1869 | 0.5910          | 0.5       | 14.1801       | 0.7168   | 0.5070   | 0.7178 | 0.0    | 0.7168 | 0.7178    |
+| 0.4506        | 8.0   | 2136 | 0.4844          | 1.0       | 26.1606       | 0.7939   | 0.7166   | 0.7939 | 0.0    | 0.7939 | 0.7944    |
+| 0.3043        | 9.0   | 2403 | 0.5989          | 1.0       | 25.3615       | 0.7852   | 0.6916   | 0.7852 | 0.0    | 0.7861 | 0.7852    |
+| 0.2686        | 10.0  | 2670 | 0.6326          | 1.0       | 25.7104       | 0.8057   | 0.7419   | 0.8057 | 0.0    | 0.8057 | 0.8057    |
+| 0.1852        | 11.0  | 2937 | 0.7550          | 1.0       | 25.6559       | 0.7891   | 0.7035   | 0.7891 | 0.0    | 0.7900 | 0.7891    |
+| 0.2224        | 12.0  | 3204 | 0.5325          | 1.0       | 25.4994       | 0.8115   | 0.7662   | 0.8115 | 0.0    | 0.8115 | 0.8115    |
+
+
+### 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>": 50266,
+  "<ent>": 50265
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "LukeForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bert_model_name": "roberta-base",
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "entity_emb_size": 256,
+  "entity_vocab_size": 500000,
+  "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-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_entity_aware_attention": true,
+  "vocab_size": 50267
+}

entity_vocab.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72f741e7347ec41a9f27909eb042dbe0d830be3f9c8d201d46e790ceafc07e32
+size 16161138

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475c7b64f3483d733a7b08c2884cb110378496feb7c9acaad15827b5efc72118
+size 1098047840

special_tokens_map.json

@@ -0,0 +1,81 @@
+{
+  "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": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,88 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50265": {
+      "content": "<ent>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50266": {
+      "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": "<ent>",
+  "entity_token_2": "<ent2>",
+  "entity_unk_token": "[UNK]",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_entity_length": 32,
+  "max_mention_length": 30,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "task": null,
+  "tokenizer_class": "LukeTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e461532d6171ededd0f0a65a18ecac98ead39b67c499d694fe0ce53c9566e70
+size 5969