LiLT-RE-JA-SIN

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,86 @@
+---
+license: mit
+base_model: kavg/LiLT-RE-JA
+tags:
+- generated_from_trainer
+datasets:
+- xfun
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: checkpoints
+  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. -->
+
+# checkpoints
+
+This model is a fine-tuned version of [kavg/LiLT-RE-JA](https://huggingface.co/kavg/LiLT-RE-JA) on the xfun dataset.
+It achieves the following results on the evaluation set:
+- Precision: 0.4744
+- Recall: 0.6540
+- F1: 0.5499
+- Loss: 0.5293
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 10000
+
+### Training results
+
+| Training Loss | Epoch  | Step  | F1     | Validation Loss | Precision | Recall |
+|:-------------:|:------:|:-----:|:------:|:---------------:|:---------:|:------:|
+| 0.0815        | 41.67  | 500   | 0.4149 | 0.1502          | 0.3521    | 0.5051 |
+| 0.0408        | 83.33  | 1000  | 0.4931 | 0.1593          | 0.4244    | 0.5884 |
+| 0.0435        | 125.0  | 1500  | 0.5041 | 0.2311          | 0.4218    | 0.6263 |
+| 0.0168        | 166.67 | 2000  | 0.5097 | 0.3195          | 0.4286    | 0.6288 |
+| 0.0073        | 208.33 | 2500  | 0.5088 | 0.3313          | 0.4308    | 0.6212 |
+| 0.0051        | 250.0  | 3000  | 0.5264 | 0.3939          | 0.4349    | 0.6667 |
+| 0.0038        | 291.67 | 3500  | 0.5252 | 0.3958          | 0.4435    | 0.6439 |
+| 0.0016        | 333.33 | 4000  | 0.5335 | 0.4708          | 0.4606    | 0.6338 |
+| 0.0082        | 375.0  | 4500  | 0.5340 | 0.4429          | 0.4562    | 0.6439 |
+| 0.0079        | 416.67 | 5000  | 0.5305 | 0.4498          | 0.4601    | 0.6263 |
+| 0.0028        | 458.33 | 5500  | 0.5352 | 0.4993          | 0.4578    | 0.6439 |
+| 0.0003        | 500.0  | 6000  | 0.5422 | 0.5253          | 0.4695    | 0.6414 |
+| 0.0014        | 541.67 | 6500  | 0.5437 | 0.5134          | 0.4705    | 0.6439 |
+| 0.0043        | 583.33 | 7000  | 0.5393 | 0.5308          | 0.4652    | 0.6414 |
+| 0.0002        | 625.0  | 7500  | 0.5378 | 0.5572          | 0.4604    | 0.6465 |
+| 0.0014        | 666.67 | 8000  | 0.5386 | 0.5451          | 0.4591    | 0.6515 |
+| 0.0027        | 708.33 | 8500  | 0.4629 | 0.6465          | 0.5395    | 0.5747 |
+| 0.0036        | 750.0  | 9000  | 0.4744 | 0.6540          | 0.5499    | 0.5293 |
+| 0.0021        | 791.67 | 9500  | 0.4610 | 0.6566          | 0.5417    | 0.5391 |
+| 0.0002        | 833.33 | 10000 | 0.4625 | 0.6540          | 0.5418    | 0.5359 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "kavg/LiLT-RE-JA",
+  "architectures": [
+    "LiLTRobertaLikeForRelationExtraction"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "channel_shrink_ratio": 4,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "model_type": "lilt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46307fd8862f490421399e3c26bb1d03bd4d2a1cf77287cab5a94e49d3efab47
+size 1147300280

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
+size 17082756

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:253a689029d2b7f0f4c94c313d9a46cf1abc77e72a082c2d31630b6124acd42a
+size 5048