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-JA
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: xfun
+      type: xfun
+      config: xfun.ja
+      split: validation
+      args: xfun.ja
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.7244408945686901
+    - name: Recall
+      type: recall
+      value: 0.8754826254826255
+    - name: F1
+      type: f1
+      value: 0.7928321678321678
+    - name: Accuracy
+      type: accuracy
+      value: 0.7835245046923879
+---
+
+<!-- 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
+
+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: 2.3482
+- Precision: 0.7244
+- Recall: 0.8755
+- F1: 0.7928
+- Accuracy: 0.7835
+
+## 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 |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0726        | 10.2   | 500   | 1.0347          | 0.6824    | 0.8359 | 0.7514 | 0.7829   |
+| 0.0015        | 20.41  | 1000  | 1.6415          | 0.6828    | 0.8808 | 0.7692 | 0.7700   |
+| 0.0062        | 30.61  | 1500  | 1.7000          | 0.7063    | 0.8427 | 0.7685 | 0.7828   |
+| 0.0145        | 40.82  | 2000  | 1.9098          | 0.6979    | 0.8885 | 0.7817 | 0.7729   |
+| 0.0014        | 51.02  | 2500  | 1.6868          | 0.7117    | 0.8509 | 0.7751 | 0.7859   |
+| 0.0009        | 61.22  | 3000  | 1.8930          | 0.7087    | 0.8441 | 0.7705 | 0.7782   |
+| 0.0001        | 71.43  | 3500  | 2.0325          | 0.7217    | 0.8736 | 0.7904 | 0.7845   |
+| 0.0006        | 81.63  | 4000  | 1.8854          | 0.7032    | 0.8769 | 0.7805 | 0.7904   |
+| 0.0001        | 91.84  | 4500  | 2.2205          | 0.6977    | 0.8721 | 0.7752 | 0.7577   |
+| 0.0002        | 102.04 | 5000  | 2.1731          | 0.7090    | 0.8702 | 0.7814 | 0.7786   |
+| 0.0           | 112.24 | 5500  | 2.3198          | 0.7150    | 0.8707 | 0.7852 | 0.7681   |
+| 0.0003        | 122.45 | 6000  | 1.9680          | 0.7188    | 0.8649 | 0.7851 | 0.7896   |
+| 0.0           | 132.65 | 6500  | 2.2202          | 0.7316    | 0.8523 | 0.7873 | 0.7815   |
+| 0.0           | 142.86 | 7000  | 2.2800          | 0.7013    | 0.8818 | 0.7813 | 0.7727   |
+| 0.0           | 153.06 | 7500  | 2.2149          | 0.7202    | 0.8784 | 0.7915 | 0.7790   |
+| 0.0           | 163.27 | 8000  | 2.2384          | 0.7264    | 0.8663 | 0.7902 | 0.7834   |
+| 0.0001        | 173.47 | 8500  | 2.2177          | 0.7269    | 0.8682 | 0.7913 | 0.7842   |
+| 0.0           | 183.67 | 9000  | 2.2768          | 0.7333    | 0.8731 | 0.7971 | 0.7872   |
+| 0.0           | 193.88 | 9500  | 2.2996          | 0.7344    | 0.8716 | 0.7972 | 0.7878   |
+| 0.0           | 204.08 | 10000 | 2.3482          | 0.7244    | 0.8755 | 0.7928 | 0.7835   |
+
+
+### 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": "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": "4.39.1",
+  "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 sha256:167c4f641d1651cdb5ac66b9bb75e59dc031d3519a79dd0006166ae50f2755a0
+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 sha256:258c4cda89f1ddb3dc555276f91b07faa33a97d2ecafa41cbea6f6f39cab2876
+size 5048