LiLT-RE-EN

.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:
+- funsd_re
+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 funsd_re dataset.
+It achieves the following results on the evaluation set:
+- Precision: 0.5
+- Recall: 0.0049
+- F1: 0.0098
+- Loss: 0.0786
+
+## 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 |
+|:-------------:|:------:|:-----:|:------:|:---------------:|:---------:|:------:|
+| 0.1604        | 26.32  | 500   | 0      | 0.1513          | 0         | 0      |
+| 0.1012        | 52.63  | 1000  | 0.0098 | 0.0786          | 0.5       | 0.0049 |
+| 0.0994        | 78.95  | 1500  | 0.3729 | 0.1901          | 0.2518    | 0.1847 |
+| 0.0694        | 105.26 | 2000  | 0.3667 | 0.3346          | 0.3499    | 0.1926 |
+| 0.0771        | 131.58 | 2500  | 0.3450 | 0.4370          | 0.3856    | 0.3295 |
+| 0.0565        | 157.89 | 3000  | 0.3293 | 0.4679          | 0.3865    | 0.4137 |
+| 0.0411        | 184.21 | 3500  | 0.3252 | 0.4593          | 0.3808    | 0.3624 |
+| 0.0463        | 210.53 | 4000  | 0.3221 | 0.4728          | 0.3832    | 0.5089 |
+| 0.0414        | 236.84 | 4500  | 0.3305 | 0.4790          | 0.3911    | 0.6137 |
+| 0.036         | 263.16 | 5000  | 0.3275 | 0.4852          | 0.3910    | 0.4428 |
+| 0.062         | 289.47 | 5500  | 0.3196 | 0.4802          | 0.3838    | 0.7425 |
+| 0.0208        | 315.79 | 6000  | 0.3252 | 0.4778          | 0.387     | 0.4978 |
+| 0.0245        | 342.11 | 6500  | 0.3229 | 0.4716          | 0.3833    | 0.7313 |
+| 0.0274        | 368.42 | 7000  | 0.3275 | 0.4815          | 0.3898    | 0.5429 |
+| 0.0232        | 394.74 | 7500  | 0.3262 | 0.4901          | 0.3917    | 0.4830 |
+| 0.0207        | 421.05 | 8000  | 0.3162 | 0.4790          | 0.3810    | 0.5178 |
+| 0.0346        | 447.37 | 8500  | 0.3274 | 0.4741          | 0.3873    | 0.4925 |
+| 0.0229        | 473.68 | 9000  | 0.3219 | 0.4654          | 0.3806    | 0.5514 |
+| 0.0253        | 500.0  | 9500  | 0.3261 | 0.4802          | 0.3884    | 0.5878 |
+| 0.0186        | 526.32 | 10000 | 0.3202 | 0.4728          | 0.3819    | 0.5508 |
+
+
+### 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 sha256:0604b82d33cc6a5bee474fcb3675fe69f3102cac5ef5700f6a9fa7e5dbd7be59
+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:ba7d488cdad0041bba4047214f0a19df317557d79caf1aacca1193412648e6eb
+size 4664