LiLT-RE-PT

.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: 0.2199
+- Recall: 0.5308
+- F1: 0.3109
+- Loss: 0.1355
+
+## 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  | Precision | Recall | F1     | Validation Loss |
+|:-------------:|:------:|:-----:|:---------:|:------:|:------:|:---------------:|
+| 0.1811        | 16.67  | 500   | 0         | 0      | 0      | 0.2498          |
+| 0.1861        | 33.33  | 1000  | 0.4207    | 0.0457 | 0.0825 | 0.2486          |
+| 0.0373        | 50.0   | 1500  | 0.4845    | 0.0517 | 0.0934 | 0.2116          |
+| 0.0856        | 66.67  | 2000  | 0.3184    | 0.1504 | 0.2043 | 0.1696          |
+| 0.0867        | 83.33  | 2500  | 0.2201    | 0.3472 | 0.2694 | 0.1691          |
+| 0.0832        | 100.0  | 3000  | 0.2369    | 0.3685 | 0.2884 | 0.1687          |
+| 0.0756        | 116.67 | 3500  | 0.2152    | 0.4301 | 0.2869 | 0.1561          |
+| 0.0454        | 133.33 | 4000  | 0.2075    | 0.4818 | 0.2900 | 0.1513          |
+| 0.0629        | 150.0  | 4500  | 0.2202    | 0.5282 | 0.3108 | 0.1748          |
+| 0.0503        | 166.67 | 5000  | 0.2058    | 0.5573 | 0.3006 | 0.1832          |
+| 0.05          | 183.33 | 5500  | 0.2263    | 0.5381 | 0.3186 | 0.1863          |
+| 0.0365        | 200.0  | 6000  | 0.2233    | 0.5712 | 0.3211 | 0.1524          |
+| 0.0366        | 216.67 | 6500  | 0.2219    | 0.5699 | 0.3195 | 0.1254          |
+| 0.0352        | 233.33 | 7000  | 0.2199    | 0.5308 | 0.3109 | 0.1355          |
+| 0.0524        | 250.0  | 7500  | 0.2184    | 0.5500 | 0.3126 | 0.1456          |
+| 0.0375        | 266.67 | 8000  | 0.2158    | 0.5401 | 0.3084 | 0.1549          |
+| 0.0324        | 283.33 | 8500  | 0.2068    | 0.5507 | 0.3007 | 0.1840          |
+| 0.0168        | 300.0  | 9000  | 0.2155    | 0.5520 | 0.3100 | 0.1686          |
+| 0.0306        | 316.67 | 9500  | 0.2160    | 0.5666 | 0.3128 | 0.1558          |
+| 0.0229        | 333.33 | 10000 | 0.2152    | 0.5712 | 0.3126 | 0.1633          |
+
+
+### 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": "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": "4.38.2",
+  "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 sha256:1d24c110a74cf0e063cdae347ac45597dafdd41c2ae907cdfa131c07628f2720
+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 sha256:94229c8cf8c133498149e4109dfecb9f1c5c79e52d203411ad2446cf894c8717
+size 5048