End of training

README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+base_model: studio-ousia/luke-large-lite
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- rouge
+model-index:
+- name: cb3b44cc8e60bf559eae3299ff06fbab
+  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. -->
+
+# cb3b44cc8e60bf559eae3299ff06fbab
+
+This model is a fine-tuned version of [studio-ousia/luke-large-lite](https://huggingface.co/studio-ousia/luke-large-lite) on the google/boolq dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6717
+- Data Size: 0.25
+- Epoch Runtime: 20.3356
+- Accuracy: 0.6213
+- F1 Macro: 0.3832
+- Rouge1: 0.6213
+- Rouge2: 0.0
+- Rougel: 0.6207
+- Rougelsum: 0.6210
+
+## 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    | 0.6734          | 0         | 5.7268        | 0.6213   | 0.3832   | 0.6213 | 0.0    | 0.6207 | 0.6210    |
+| No log        | 1     | 294  | 0.7040          | 0.0078    | 6.4820        | 0.3934   | 0.3378   | 0.3931 | 0.0    | 0.3937 | 0.3931    |
+| No log        | 2     | 588  | 0.6640          | 0.0156    | 6.9528        | 0.6213   | 0.3832   | 0.6213 | 0.0    | 0.6207 | 0.6210    |
+| No log        | 3     | 882  | 0.6654          | 0.0312    | 8.5753        | 0.6213   | 0.3832   | 0.6213 | 0.0    | 0.6207 | 0.6210    |
+| 0.0277        | 4     | 1176 | 0.6708          | 0.0625    | 10.9820       | 0.6213   | 0.3832   | 0.6213 | 0.0    | 0.6207 | 0.6210    |
+| 0.0575        | 5     | 1470 | 0.6649          | 0.125     | 14.1243       | 0.6213   | 0.3832   | 0.6213 | 0.0    | 0.6207 | 0.6210    |
+| 0.0989        | 6     | 1764 | 0.6717          | 0.25      | 20.3356       | 0.6213   | 0.3832   | 0.6213 | 0.0    | 0.6207 | 0.6210    |
+
+
+### 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-large",
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "entity_emb_size": 256,
+  "entity_vocab_size": 4,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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,
+  "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 +1,6 @@
+{
+  "[MASK2]": 3,
+  "[MASK]": 0,
+  "[PAD]": 2,
+  "[UNK]": 1
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d91b54ba3280c27e3d889969607b8654f76ec428b82d9dff09fca7d2dbdfdb03
+size 1726976480

special_tokens_map.json

@@ -0,0 +1,95 @@
+{
+  "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
+    },
+    {
+      "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 +1,90 @@
+{
+  "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>",
+    "<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:be1d42f854ef6e557aafd8100fc5ae8e85587d73b449a4435b9a5a7d782ed1bc
+size 5969