End of training

README.md

@@ -0,0 +1,74 @@
+---
+license: mit
+base_model: SCUT-DLVCLab/lilt-roberta-en-base
+tags:
+- generated_from_trainer
+model-index:
+- name: Data_extraction
+  results: []
+---
+
+<!-- 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. -->
+
+# Data_extraction
+
+This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+- Ign: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933}
+- Overall Precision: 1.0
+- Overall Recall: 1.0
+- Overall F1: 1.0
+- Overall Accuracy: 1.0
+
+## 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: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 2500
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch    | Step | Validation Loss | Ign                                                          | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:--------:|:----:|:---------------:|:------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.032         | 18.1818  | 200  | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 36.3636  | 400  | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 54.5455  | 600  | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 72.7273  | 800  | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 90.9091  | 1000 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 109.0909 | 1200 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 127.2727 | 1400 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 145.4545 | 1600 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 163.6364 | 1800 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 181.8182 | 2000 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 200.0    | 2200 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+| 0.0           | 218.1818 | 2400 | 0.0000          | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 6933} | 1.0               | 1.0            | 1.0        | 1.0              |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

logs/events.out.tfevents.1718693421.0d694fabe53e.5012.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9db4435c8408fc5a4298d9dde26d210d63d99ae220e07156ba16d90070a168ad
-size 13748
+oid sha256:d9166f422438521c47c28a4571988ec59e476327c7f39487f08ed3fd432f0243
+size 14102

logs/events.out.tfevents.1718694853.0d694fabe53e.5012.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a65219e981ca11e44566f4eec9c4d068afd3754a606872217c0c10379ae854e
+size 592

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d788ecbae4fef1edb0cb93d4ab3d1ab339df2c80f3c4c8cd2a2b6c5c5585c87c
+oid sha256:4f2b23e6b0bf05602b59e24a2812067462d9302c32d3e8dd4f76d70f36299854
 size 520721412

preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "_valid_processor_keys": [
+    "images",
+    "do_resize",
+    "size",
+    "resample",
+    "do_rescale",
+    "rescale_factor",
+    "do_normalize",
+    "image_mean",
+    "image_std",
+    "apply_ocr",
+    "ocr_lang",
+    "tesseract_config",
+    "return_tensors",
+    "data_format",
+    "input_data_format"
+  ],
+  "apply_ocr": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "LayoutLMv3FeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "ocr_lang": null,
+  "processor_class": "LayoutLMv3Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  },
+  "tesseract_config": ""
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,78 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "only_label_first_subword": true,
+  "pad_token": "<pad>",
+  "pad_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "pad_token_label": -100,
+  "processor_class": "LayoutLMv3Processor",
+  "sep_token": "</s>",
+  "sep_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}