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: kavg/LiLT-SER-ZH
+tags:
+- generated_from_trainer
+datasets:
+- xfun
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: LiLT-SER-ZH-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: 0.7417061611374408
+    - name: Recall
+      type: recall
+      value: 0.770935960591133
+    - name: F1
+      type: f1
+      value: 0.7560386473429951
+    - name: Accuracy
+      type: accuracy
+      value: 0.8558002524898303
+---
+
+<!-- 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-SIN
+
+This model is a fine-tuned version of [kavg/LiLT-SER-ZH](https://huggingface.co/kavg/LiLT-SER-ZH) on the xfun dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2037
+- Precision: 0.7417
+- Recall: 0.7709
+- F1: 0.7560
+- Accuracy: 0.8558
+
+## 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  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0013        | 21.74  | 500   | 0.9018          | 0.6843    | 0.7475 | 0.7145 | 0.8599   |
+| 0.012         | 43.48  | 1000  | 1.0791          | 0.7115    | 0.7623 | 0.7360 | 0.8561   |
+| 0.0002        | 65.22  | 1500  | 1.0060          | 0.7360    | 0.7623 | 0.7489 | 0.8565   |
+| 0.03          | 86.96  | 2000  | 1.1521          | 0.7282    | 0.6700 | 0.6979 | 0.8313   |
+| 0.0013        | 108.7  | 2500  | 1.1517          | 0.7240    | 0.7463 | 0.7350 | 0.8579   |
+| 0.0016        | 130.43 | 3000  | 0.9393          | 0.7319    | 0.7697 | 0.7503 | 0.8732   |
+| 0.0021        | 152.17 | 3500  | 0.9972          | 0.7249    | 0.7562 | 0.7402 | 0.8635   |
+| 0.0001        | 173.91 | 4000  | 1.0485          | 0.7049    | 0.7796 | 0.7404 | 0.8583   |
+| 0.0002        | 195.65 | 4500  | 1.0827          | 0.7055    | 0.7315 | 0.7183 | 0.8433   |
+| 0.0           | 217.39 | 5000  | 1.0528          | 0.7354    | 0.7599 | 0.7474 | 0.8586   |
+| 0.0001        | 239.13 | 5500  | 1.1183          | 0.7001    | 0.7131 | 0.7065 | 0.8465   |
+| 0.0002        | 260.87 | 6000  | 1.1749          | 0.7231    | 0.7685 | 0.7451 | 0.8520   |
+| 0.0           | 282.61 | 6500  | 1.1206          | 0.7315    | 0.7685 | 0.7495 | 0.8611   |
+| 0.0           | 304.35 | 7000  | 1.2037          | 0.7417    | 0.7709 | 0.7560 | 0.8558   |
+| 0.0           | 326.09 | 7500  | 1.3737          | 0.7391    | 0.75   | 0.7445 | 0.8513   |
+| 0.0           | 347.83 | 8000  | 1.2926          | 0.7221    | 0.7648 | 0.7428 | 0.8475   |
+| 0.0           | 369.57 | 8500  | 1.4108          | 0.6966    | 0.7549 | 0.7246 | 0.8293   |
+| 0.0           | 391.3  | 9000  | 1.4346          | 0.7222    | 0.7586 | 0.7399 | 0.8303   |
+| 0.0           | 413.04 | 9500  | 1.4146          | 0.7225    | 0.7599 | 0.7407 | 0.8363   |
+| 0.0           | 434.78 | 10000 | 1.4097          | 0.7121    | 0.7586 | 0.7346 | 0.8346   |
+
+
+### Framework versions
+
+- Transformers 4.39.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "kavg/LiLT-SER-ZH",
+  "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": "4.39.1",
+  "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:f25721b816e06425c9d2163056eeedd9fd3131e08a9f9c7209ab03f1743c686c
+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:dcc13b66fbb9b0b162602229997ea27478112828615b195f1ca6fd1b26c5d847
+size 5048