End of training

.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 +1,109 @@
+---
+license: mit
+base_model: nielsr/lilt-xlm-roberta-base
+tags:
+- generated_from_trainer
+datasets:
+- xfun
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: LiLT-SER-SIN
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: xfun
+      type: xfun
+      config: xfun.sin
+      split: validation
+      args: xfun.sin
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.7058139534883721
+    - name: Recall
+      type: recall
+      value: 0.7475369458128078
+    - name: F1
+      type: f1
+      value: 0.7260765550239234
+    - name: Accuracy
+      type: accuracy
+      value: 0.8621124982465984
+---
+
+<!-- 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. -->
+
+# LiLT-SER-SIN
+
+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:
+- Loss: 1.1967
+- Precision: 0.7058
+- Recall: 0.7475
+- F1: 0.7261
+- Accuracy: 0.8621
+
+## 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: 5e-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
+- training_steps: 10000
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Accuracy | F1     | Validation Loss | Precision | Recall |
+|:-------------:|:------:|:-----:|:--------:|:------:|:---------------:|:---------:|:------:|
+| 0.0739        | 21.74  | 500   | 0.8268   | 0.5620 | 0.7143          | 0.5       | 0.6416 |
+| 0.0509        | 43.48  | 1000  | 0.8324   | 0.5839 | 0.8499          | 0.5348    | 0.6429 |
+| 0.0004        | 65.22  | 1500  | 0.8398   | 0.6521 | 0.9889          | 0.6256    | 0.6810 |
+| 0.0004        | 86.96  | 2000  | 0.8461   | 0.6678 | 1.0577          | 0.6251    | 0.7167 |
+| 0.003         | 108.7  | 2500  | 0.8561   | 0.6929 | 1.0734          | 0.6532    | 0.7377 |
+| 0.0006        | 130.43 | 3000  | 0.8569   | 0.6924 | 1.1114          | 0.6686    | 0.7180 |
+| 0.0022        | 152.17 | 3500  | 0.8245   | 0.6749 | 1.4184          | 0.6774    | 0.6724 |
+| 0.0001        | 173.91 | 4000  | 0.8502   | 0.6937 | 1.0524          | 0.6546    | 0.7377 |
+| 0.001         | 195.65 | 4500  | 0.8493   | 0.6900 | 1.1949          | 0.6663    | 0.7155 |
+| 0.0001        | 217.39 | 5000  | 0.8460   | 0.6885 | 1.1462          | 0.6790    | 0.6983 |
+| 0.0001        | 239.13 | 5500  | 0.8641   | 0.6970 | 1.1296          | 0.6697    | 0.7266 |
+| 0.0           | 260.87 | 6000  | 0.8529   | 0.7046 | 1.2585          | 0.6929    | 0.7167 |
+| 0.0037        | 282.61 | 6500  | 0.8634   | 0.7139 | 1.2292          | 0.6917    | 0.7377 |
+| 0.0           | 304.35 | 7000  | 0.8621   | 0.7261 | 1.1967          | 0.7058    | 0.7475 |
+| 0.0           | 326.09 | 7500  | 0.8585   | 0.7230 | 1.2144          | 0.7089    | 0.7377 |
+| 0.0           | 347.83 | 8000  | 0.8609   | 0.7180 | 1.2117          | 0.6918    | 0.7463 |
+| 0.0           | 369.57 | 8500  | 0.8628   | 0.7135 | 1.1961          | 0.6755    | 0.7562 |
+| 0.0           | 391.3  | 9000  | 0.8624   | 0.7220 | 1.2292          | 0.7059    | 0.7389 |
+| 0.0           | 413.04 | 9500  | 0.8611   | 0.7262 | 1.2278          | 0.7071    | 0.7463 |
+| 0.0           | 434.78 | 10000 | 0.8609   | 0.7242 | 1.2317          | 0.7056    | 0.7438 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "nielsr/lilt-xlm-roberta-base",
+  "architectures": [
+    "LiltForTokenClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "O",
+    "1": "B-QUESTION",
+    "2": "B-ANSWER",
+    "3": "B-HEADER",
+    "4": "I-ANSWER",
+    "5": "I-QUESTION",
+    "6": "I-HEADER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANSWER": 2,
+    "B-HEADER": 3,
+    "B-QUESTION": 1,
+    "I-ANSWER": 4,
+    "I-HEADER": 6,
+    "I-QUESTION": 5,
+    "O": 0
+  },
+  "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:b542cc701d63d60aa65de3ab8124d594291c24d4d2b4dad5a4f29a5a32d12dda
+size 1134319924

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 +1,55 @@
+{
+  "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>",
+  "max_length": 512,
+  "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 sha256:809fd53948322d8bb580054409f558fd8aa637a40a0ca38e97e8dd268d48e6e5
+size 5048