LiLT-RE-JA

.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: nielsr/lilt-xlm-roberta-base
+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 [nielsr/lilt-xlm-roberta-base](https://huggingface.co/nielsr/lilt-xlm-roberta-base) on the xfun dataset.
+It achieves the following results on the evaluation set:
+- Precision: 0.4372
+- Recall: 0.6574
+- F1: 0.5252
+- Loss: 0.0001
+
+## 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 |
+|:-------------:|:-----:|:-----:|:------:|:---------------:|:---------:|:------:|
+| 0.1954        | 20.0  | 500   | 0      | 0.4094          | 0         | 0      |
+| 0.1588        | 40.0  | 1000  | 0.1420 | 0.3055          | 0.3587    | 0.0886 |
+| 0.1182        | 60.0  | 1500  | 0.4253 | 0.1384          | 0.3810    | 0.4812 |
+| 0.0477        | 80.0  | 2000  | 0.4764 | 0.0216          | 0.3949    | 0.6002 |
+| 0.069         | 100.0 | 2500  | 0.5198 | 0.0115          | 0.4564    | 0.6038 |
+| 0.0355        | 120.0 | 3000  | 0.5161 | 0.0018          | 0.4271    | 0.6521 |
+| 0.0268        | 140.0 | 3500  | 0.5254 | 0.0016          | 0.4395    | 0.6530 |
+| 0.0123        | 160.0 | 4000  | 0.5264 | 0.0015          | 0.4382    | 0.6592 |
+| 0.0039        | 180.0 | 4500  | 0.5353 | 0.0011          | 0.4510    | 0.6583 |
+| 0.0139        | 200.0 | 5000  | 0.5390 | 0.0011          | 0.4533    | 0.6646 |
+| 0.001         | 220.0 | 5500  | 0.5430 | 0.0042          | 0.4620    | 0.6583 |
+| 0.01          | 240.0 | 6000  | 0.5347 | 0.0013          | 0.4531    | 0.6521 |
+| 0.0065        | 260.0 | 6500  | 0.5404 | 0.0001          | 0.4540    | 0.6673 |
+| 0.0046        | 280.0 | 7000  | 0.5252 | 0.0001          | 0.4372    | 0.6574 |
+| 0.002         | 300.0 | 7500  | 0.5365 | 0.0007          | 0.4474    | 0.6699 |
+| 0.0002        | 320.0 | 8000  | 0.5393 | 0.0002          | 0.4546    | 0.6628 |
+| 0.0008        | 340.0 | 8500  | 0.5412 | 0.0002          | 0.4569    | 0.6637 |
+| 0.0024        | 360.0 | 9000  | 0.4677 | 0.6601          | 0.5475    | 0.0002 |
+| 0.0001        | 380.0 | 9500  | 0.4560 | 0.6673          | 0.5418    | 0.0002 |
+| 0.002         | 400.0 | 10000 | 0.4594 | 0.6628          | 0.5427    | 0.0003 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "nielsr/lilt-xlm-roberta-base",
+  "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": "4.35.2",
+  "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 sha256:786d2bab1e681707ef1cfd35c86396fe9647970b01d61dcd6adda31c56674f4e
+size 1147300280

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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:c01ed06c35797d3753fbcc1118ebbb539d38308f3d6ae3d1f58ed66e9ac32330
+size 4728