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-IT
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: xfun
+      type: xfun
+      config: xfun.it
+      split: validation
+      args: xfun.it
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.726186733731531
+    - name: Recall
+      type: recall
+      value: 0.7927247769389156
+    - name: F1
+      type: f1
+      value: 0.7579983593109106
+    - name: Accuracy
+      type: accuracy
+      value: 0.768676917924818
+---
+
+<!-- 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-IT
+
+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: 2.5355
+- Precision: 0.7262
+- Recall: 0.7927
+- F1: 0.7580
+- Accuracy: 0.7687
+
+## 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 |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0696        | 7.46   | 500   | 1.0876          | 0.6322    | 0.6517 | 0.6418 | 0.7584   |
+| 0.0576        | 14.93  | 1000  | 1.3989          | 0.6712    | 0.7601 | 0.7129 | 0.7601   |
+| 0.0096        | 22.39  | 1500  | 1.8059          | 0.6774    | 0.7639 | 0.7181 | 0.7662   |
+| 0.0092        | 29.85  | 2000  | 2.0416          | 0.7266    | 0.7334 | 0.7300 | 0.7652   |
+| 0.0003        | 37.31  | 2500  | 2.0467          | 0.7166    | 0.7539 | 0.7348 | 0.7628   |
+| 0.0013        | 44.78  | 3000  | 2.0159          | 0.7027    | 0.7821 | 0.7403 | 0.7638   |
+| 0.0013        | 52.24  | 3500  | 2.2751          | 0.6961    | 0.7728 | 0.7325 | 0.7575   |
+| 0.0002        | 59.7   | 4000  | 2.2084          | 0.7236    | 0.7563 | 0.7396 | 0.7723   |
+| 0.0002        | 67.16  | 4500  | 2.1843          | 0.7048    | 0.7701 | 0.7360 | 0.7581   |
+| 0.0001        | 74.63  | 5000  | 2.2483          | 0.7366    | 0.7745 | 0.7551 | 0.7770   |
+| 0.0001        | 82.09  | 5500  | 2.2685          | 0.7171    | 0.7752 | 0.7451 | 0.7677   |
+| 0.0005        | 89.55  | 6000  | 2.2877          | 0.7180    | 0.7821 | 0.7487 | 0.7692   |
+| 0.0001        | 97.01  | 6500  | 2.2574          | 0.7308    | 0.7725 | 0.7511 | 0.7721   |
+| 0.0           | 104.48 | 7000  | 2.4696          | 0.7255    | 0.7862 | 0.7546 | 0.7660   |
+| 0.0           | 111.94 | 7500  | 2.3996          | 0.7140    | 0.7917 | 0.7509 | 0.7725   |
+| 0.0           | 119.4  | 8000  | 2.4592          | 0.7261    | 0.7852 | 0.7545 | 0.7665   |
+| 0.0           | 126.87 | 8500  | 2.4129          | 0.7336    | 0.7900 | 0.7607 | 0.7718   |
+| 0.0           | 134.33 | 9000  | 2.5367          | 0.7316    | 0.7896 | 0.7595 | 0.7666   |
+| 0.0           | 141.79 | 9500  | 2.5327          | 0.7278    | 0.7900 | 0.7576 | 0.7663   |
+| 0.0           | 149.25 | 10000 | 2.5355          | 0.7262    | 0.7927 | 0.7580 | 0.7687   |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- 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": "4.38.2",
+  "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 sha256:0dfffe604006b01517859cd4532faef21fbb1f445f080187437a5a3127b589b1
+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 sha256:02f145427418280474775071744bef2612f15a6a880862fb4b0e6f2c11fcbe38
+size 5048