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-JA
+tags:
+- generated_from_trainer
+datasets:
+- xfun
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: LiLT-SER-JA-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: 0.7378410438908659
+    - name: Recall
+      type: recall
+      value: 0.7660098522167488
+    - name: F1
+      type: f1
+      value: 0.7516616314199396
+    - name: Accuracy
+      type: accuracy
+      value: 0.8793659699817646
+---
+
+<!-- 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-JA-SIN
+
+This model is a fine-tuned version of [kavg/LiLT-SER-JA](https://huggingface.co/kavg/LiLT-SER-JA) on the xfun dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1113
+- Precision: 0.7378
+- Recall: 0.7660
+- F1: 0.7517
+- Accuracy: 0.8794
+
+## 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 |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0009        | 21.74  | 500   | 0.8785          | 0.6584    | 0.7217 | 0.6886 | 0.8505   |
+| 0.0031        | 43.48  | 1000  | 1.0637          | 0.7309    | 0.7291 | 0.7300 | 0.8533   |
+| 0.0046        | 65.22  | 1500  | 0.9166          | 0.7219    | 0.7512 | 0.7363 | 0.8729   |
+| 0.0002        | 86.96  | 2000  | 1.0366          | 0.7212    | 0.7389 | 0.7299 | 0.8721   |
+| 0.0           | 108.7  | 2500  | 1.0535          | 0.7191    | 0.7377 | 0.7283 | 0.8662   |
+| 0.0006        | 130.43 | 3000  | 1.1869          | 0.7409    | 0.7291 | 0.7349 | 0.8495   |
+| 0.005         | 152.17 | 3500  | 1.2062          | 0.7356    | 0.7401 | 0.7379 | 0.8627   |
+| 0.0002        | 173.91 | 4000  | 1.2067          | 0.7011    | 0.7192 | 0.7100 | 0.8451   |
+| 0.0002        | 195.65 | 4500  | 1.1819          | 0.7290    | 0.7389 | 0.7339 | 0.8578   |
+| 0.0           | 217.39 | 5000  | 1.1699          | 0.7463    | 0.75   | 0.7482 | 0.8632   |
+| 0.0           | 239.13 | 5500  | 1.1548          | 0.7267    | 0.7599 | 0.7429 | 0.8637   |
+| 0.0           | 260.87 | 6000  | 1.1867          | 0.7227    | 0.7574 | 0.7396 | 0.8651   |
+| 0.0           | 282.61 | 6500  | 1.1614          | 0.7222    | 0.7525 | 0.7370 | 0.8721   |
+| 0.0           | 304.35 | 7000  | 1.1884          | 0.7146    | 0.7648 | 0.7388 | 0.8681   |
+| 0.0           | 326.09 | 7500  | 1.2186          | 0.6975    | 0.7438 | 0.7199 | 0.8582   |
+| 0.0001        | 347.83 | 8000  | 1.0423          | 0.7313    | 0.7709 | 0.7506 | 0.8754   |
+| 0.0           | 369.57 | 8500  | 1.1254          | 0.7278    | 0.7574 | 0.7423 | 0.8705   |
+| 0.0           | 391.3  | 9000  | 1.1113          | 0.7378    | 0.7660 | 0.7517 | 0.8794   |
+| 0.0           | 413.04 | 9500  | 1.1517          | 0.7424    | 0.7562 | 0.7492 | 0.8732   |
+| 0.0           | 434.78 | 10000 | 1.1568          | 0.7413    | 0.7586 | 0.7498 | 0.8726   |
+
+
+### 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-JA",
+  "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:d7115123c68942a615b279a743789a8bb7fee1f73f881e2d2af804435f37c76d
+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:e72037e4b25dc4201b287bd0f0bc5a1662b73e1b45131838ec2599bbd44598e1
+size 5048