LiLT-RE-EN-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-EN
+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-EN](https://huggingface.co/kavg/LiLT-RE-EN) on the xfun dataset.
+It achieves the following results on the evaluation set:
+- Precision: 0.4702
+- Recall: 0.5581
+- F1: 0.5104
+- Loss: 0.5301
+
+## 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 |
+|:-------------:|:------:|:-----:|:------:|:---------------:|:---------:|:------:|
+| 0.0661        | 41.67  | 500   | 0.3769 | 0.2542          | 0.3360    | 0.4293 |
+| 0.0547        | 83.33  | 1000  | 0.4404 | 0.2624          | 0.3805    | 0.5227 |
+| 0.0671        | 125.0  | 1500  | 0.4580 | 0.2623          | 0.4031    | 0.5303 |
+| 0.0284        | 166.67 | 2000  | 0.4764 | 0.3800          | 0.4142    | 0.5606 |
+| 0.0177        | 208.33 | 2500  | 0.4883 | 0.3349          | 0.4371    | 0.5530 |
+| 0.0164        | 250.0  | 3000  | 0.4926 | 0.3123          | 0.4491    | 0.5455 |
+| 0.0081        | 291.67 | 3500  | 0.4966 | 0.3830          | 0.4458    | 0.5606 |
+| 0.0067        | 333.33 | 4000  | 0.4916 | 0.3459          | 0.4424    | 0.5530 |
+| 0.0048        | 375.0  | 4500  | 0.4989 | 0.4200          | 0.4527    | 0.5556 |
+| 0.0112        | 416.67 | 5000  | 0.5158 | 0.4377          | 0.4672    | 0.5758 |
+| 0.0052        | 458.33 | 5500  | 0.5085 | 0.4983          | 0.4619    | 0.5657 |
+| 0.0023        | 500.0  | 6000  | 0.5086 | 0.5621          | 0.4654    | 0.5606 |
+| 0.0022        | 541.67 | 6500  | 0.5074 | 0.5063          | 0.4635    | 0.5606 |
+| 0.0083        | 583.33 | 7000  | 0.5109 | 0.5471          | 0.4693    | 0.5606 |
+| 0.0023        | 625.0  | 7500  | 0.5028 | 0.5268          | 0.4559    | 0.5606 |
+| 0.0027        | 666.67 | 8000  | 0.5098 | 0.5385          | 0.4674    | 0.5606 |
+| 0.0078        | 708.33 | 8500  | 0.4581 | 0.5657          | 0.5062    | 0.5135 |
+| 0.0015        | 750.0  | 9000  | 0.4702 | 0.5581          | 0.5104    | 0.5301 |
+| 0.0043        | 791.67 | 9500  | 0.4595 | 0.5581          | 0.5040    | 0.5684 |
+| 0.0007        | 833.33 | 10000 | 0.4587 | 0.5606          | 0.5045    | 0.5711 |
+
+
+### 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-EN",
+  "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 sha256:12abac3002026083b5c19790ae807e88c4bc1e6dc899c9f73f1b7c930c0bc673
+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 sha256:438a175f538636e49706af744c54b69d08ee1ba570ce5c031b9a4aebf480b91f
+size 5048