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-ZH
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: xfun
+      type: xfun
+      config: xfun.zh
+      split: validation
+      args: xfun.zh
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.8408488063660478
+    - name: Recall
+      type: recall
+      value: 0.9347968545216252
+    - name: F1
+      type: f1
+      value: 0.8853374709076804
+    - name: Accuracy
+      type: accuracy
+      value: 0.8116519985331867
+---
+
+<!-- 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-ZH
+
+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: 1.8792
+- Precision: 0.8408
+- Recall: 0.9348
+- F1: 0.8853
+- Accuracy: 0.8117
+
+## 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 |
+|:-------------:|:------:|:-----:|:--------:|:------:|:---------------:|:---------:|:------:|
+| 0.2166        | 10.64  | 500   | 0.7724   | 0.8544 | 1.1239          | 0.7932    | 0.9260 |
+| 0.0238        | 21.28  | 1000  | 0.8201   | 0.8624 | 1.0535          | 0.8572    | 0.8676 |
+| 0.0034        | 31.91  | 1500  | 0.8057   | 0.8599 | 1.4675          | 0.8088    | 0.9178 |
+| 0.0163        | 42.55  | 2000  | 0.8232   | 0.8729 | 1.2837          | 0.8572    | 0.8893 |
+| 0.0037        | 53.19  | 2500  | 0.8114   | 0.8627 | 1.5315          | 0.8142    | 0.9174 |
+| 0.0003        | 63.83  | 3000  | 0.8137   | 0.8652 | 1.4604          | 0.8471    | 0.8840 |
+| 0.0005        | 74.47  | 3500  | 0.8115   | 0.8767 | 1.5980          | 0.8409    | 0.9158 |
+| 0.0005        | 85.11  | 4000  | 0.8129   | 0.8634 | 1.5108          | 0.8261    | 0.9043 |
+| 0.0004        | 95.74  | 4500  | 0.8161   | 0.8817 | 1.7719          | 0.8397    | 0.9282 |
+| 0.0001        | 106.38 | 5000  | 0.8203   | 0.8813 | 1.4313          | 0.8600    | 0.9037 |
+| 0.0001        | 117.02 | 5500  | 0.8181   | 0.8832 | 1.5232          | 0.8509    | 0.9181 |
+| 0.0           | 127.66 | 6000  | 0.8069   | 0.8808 | 1.6845          | 0.8532    | 0.9102 |
+| 0.0179        | 138.3  | 6500  | 0.8192   | 0.8793 | 1.6293          | 0.8398    | 0.9227 |
+| 0.0           | 148.94 | 7000  | 0.8081   | 0.8815 | 1.8209          | 0.8381    | 0.9296 |
+| 0.0           | 159.57 | 7500  | 1.8224   | 0.8443 | 0.9184          | 0.8798    | 0.8070 |
+| 0.0           | 170.21 | 8000  | 1.7810   | 0.8450 | 0.9305          | 0.8857    | 0.8127 |
+| 0.0           | 180.85 | 8500  | 1.7531   | 0.8454 | 0.9230          | 0.8825    | 0.8088 |
+| 0.0           | 191.49 | 9000  | 1.8757   | 0.8394 | 0.9302          | 0.8825    | 0.8070 |
+| 0.0           | 202.13 | 9500  | 1.8757   | 0.8417 | 0.9338          | 0.8854    | 0.8123 |
+| 0.0           | 212.77 | 10000 | 1.8792   | 0.8408 | 0.9348          | 0.8853    | 0.8117 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.1

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": "4.35.2",
+  "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:ed2cc4c3389de7ee572fab53fa70e9a82df956536bc8d6a8d3d2ea0319a7635b
+size 1134319924

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 +1,55 @@
+{
+  "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:a279c6f7fdd6b60351e3a5cf0cfa5807a87e5442cda51b1ddb77aaa0822970ad
+size 4728