LiLT-RE-DE

.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: 0.3054
+- Recall: 0.6032
+- F1: 0.4055
+- Loss: 0.2164
+
+## 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 |
+|:-------------:|:------:|:-----:|:---------:|:------:|:------:|:---------------:|
+| 0.1914        | 20.83  | 500   | 0         | 0      | 0      | 0.2039          |
+| 0.1638        | 41.67  | 1000  | 0.4688    | 0.0252 | 0.0478 | 0.2196          |
+| 0.0928        | 62.5   | 1500  | 0.3790    | 0.1669 | 0.2318 | 0.2127          |
+| 0.0948        | 83.33  | 2000  | 0.3125    | 0.4245 | 0.3600 | 0.2987          |
+| 0.0796        | 104.17 | 2500  | 0.3102    | 0.5587 | 0.3989 | 0.3636          |
+| 0.0469        | 125.0  | 3000  | 0.3204    | 0.5134 | 0.3946 | 0.3587          |
+| 0.0471        | 145.83 | 3500  | 0.3303    | 0.5243 | 0.4053 | 0.2792          |
+| 0.0486        | 166.67 | 4000  | 0.2967    | 0.5973 | 0.3964 | 0.2973          |
+| 0.0381        | 187.5  | 4500  | 0.3066    | 0.6007 | 0.4060 | 0.3003          |
+| 0.0392        | 208.33 | 5000  | 0.3054    | 0.6032 | 0.4055 | 0.2164          |
+| 0.0268        | 229.17 | 5500  | 0.3052    | 0.6158 | 0.4081 | 0.3159          |
+| 0.029         | 250.0  | 6000  | 0.2850    | 0.6292 | 0.3923 | 0.3108          |
+| 0.0217        | 270.83 | 6500  | 0.2964    | 0.6141 | 0.3998 | 0.3130          |
+| 0.0241        | 291.67 | 7000  | 0.3012    | 0.6216 | 0.4058 | 0.3197          |
+| 0.038         | 312.5  | 7500  | 0.3051    | 0.6216 | 0.4093 | 0.2627          |
+| 0.0374        | 333.33 | 8000  | 0.2914    | 0.6359 | 0.3997 | 0.3388          |
+| 0.0194        | 354.17 | 8500  | 0.2975    | 0.6275 | 0.4037 | 0.3155          |
+| 0.0189        | 375.0  | 9000  | 0.3037    | 0.625  | 0.4088 | 0.2911          |
+| 0.0147        | 395.83 | 9500  | 0.2993    | 0.6242 | 0.4046 | 0.3417          |
+| 0.0328        | 416.67 | 10000 | 0.3012    | 0.6242 | 0.4063 | 0.3210          |
+
+
+### 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:b25c24d00ea00b5252c85f1e364df97dde7573680a094bc9f50f5926cfd10a92
+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 sha256:3de23360592c1650d81e26cda6fad83c21a18be9e167f2134e4fe723d75a8205
+size 5048