LiLT-RE-PT-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-PT
+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-PT](https://huggingface.co/kavg/LiLT-RE-PT) on the xfun dataset.
+It achieves the following results on the evaluation set:
+- Precision: 0.3631
+- Recall: 0.4823
+- F1: 0.4143
+- Loss: 0.1671
+
+## 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 |
+|:-------------:|:------:|:-----:|:---------:|:------:|:------:|:---------------:|
+| 0.0907        | 41.67  | 500   | 0.3315    | 0.3106 | 0.3207 | 0.2039          |
+| 0.0766        | 83.33  | 1000  | 0.3631    | 0.4823 | 0.4143 | 0.1671          |
+| 0.0639        | 125.0  | 1500  | 0.3640    | 0.6086 | 0.4556 | 0.2525          |
+| 0.0309        | 166.67 | 2000  | 0.3973    | 0.6010 | 0.4784 | 0.2339          |
+| 0.0318        | 208.33 | 2500  | 0.4045    | 0.6414 | 0.4961 | 0.3325          |
+| 0.0144        | 250.0  | 3000  | 0.4268    | 0.6187 | 0.5052 | 0.3513          |
+| 0.0163        | 291.67 | 3500  | 0.4273    | 0.6086 | 0.5021 | 0.2880          |
+| 0.0062        | 333.33 | 4000  | 0.4368    | 0.6288 | 0.5155 | 0.3064          |
+| 0.0115        | 375.0  | 4500  | 0.4386    | 0.6313 | 0.5176 | 0.3283          |
+| 0.0168        | 416.67 | 5000  | 0.4373    | 0.6162 | 0.5115 | 0.3258          |
+| 0.0062        | 458.33 | 5500  | 0.4530    | 0.6086 | 0.5194 | 0.3467          |
+| 0.0074        | 500.0  | 6000  | 0.4569    | 0.6162 | 0.5247 | 0.3401          |
+| 0.0037        | 541.67 | 6500  | 0.4559    | 0.6136 | 0.5231 | 0.3526          |
+| 0.008         | 583.33 | 7000  | 0.4650    | 0.6035 | 0.5253 | 0.3076          |
+| 0.0045        | 625.0  | 7500  | 0.4610    | 0.6111 | 0.5255 | 0.3799          |
+| 0.0045        | 666.67 | 8000  | 0.4551    | 0.6136 | 0.5226 | 0.3692          |
+| 0.0052        | 708.33 | 8500  | 0.4535    | 0.6162 | 0.5225 | 0.3492          |
+| 0.0002        | 750.0  | 9000  | 0.4537    | 0.6061 | 0.5189 | 0.4075          |
+| 0.0027        | 791.67 | 9500  | 0.4581    | 0.6212 | 0.5273 | 0.3816          |
+| 0.0009        | 833.33 | 10000 | 0.4569    | 0.6162 | 0.5247 | 0.3834          |
+
+
+### 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-PT",
+  "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 sha256:42ea5c9f4d20eb639313019ff66842c714d9b6523b776a5c30837fb5f7d76166
+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:cefea6284d8fd126731da6372c68392d0a31ffe1db15409e37e4862b500f3dde
+size 5048