End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,68 @@
+---
+license: mit
+base_model: SCUT-DLVCLab/lilt-roberta-en-base
+tags:
+- generated_from_trainer
+model-index:
+- name: lilt-invoices
+  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. -->
+
+# lilt-invoices
+
+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: 0.1475
+- Endorname: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1}
+- Escription: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1}
+- Illingaddress: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1}
+- Mount: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1}
+- Nitprice: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 2}
+- Nvoicedate: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1}
+- Nvoicetotal: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1}
+- Otaltax: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1}
+- Uantity: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1}
+- Ubtotal: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 1}
+- 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: 20
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "SCUT-DLVCLab/lilt-roberta-en-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": "TotalTax",
+    "1": "Amount",
+    "2": "SubTotal",
+    "3": "Quantity",
+    "4": "Description",
+    "5": "UnitPrice",
+    "6": "InvoiceDate",
+    "7": "BillingAddress",
+    "8": "VendorName",
+    "9": "InvoiceTotal"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Amount": 1,
+    "BillingAddress": 7,
+    "Description": 4,
+    "InvoiceDate": 6,
+    "InvoiceTotal": 9,
+    "Quantity": 3,
+    "SubTotal": 2,
+    "TotalTax": 0,
+    "UnitPrice": 5,
+    "VendorName": 8
+  },
+  "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,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

logs/events.out.tfevents.1692627705.063f00bfc104.540.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dec4c9f77d94675406407a401c531f3cca3cad41b48d10523c91971c37c3caf
+size 4948

logs/events.out.tfevents.1692627824.063f00bfc104.540.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37841095eeccff030bf21e80d3218e7d4f50f3ecbce218a77a409291a0175c4a
+size 4948

logs/events.out.tfevents.1692627829.063f00bfc104.540.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d19a77cd96208a074cbbaad5baed43b443c8446690c64fd1e14bf05e064914
+size 583

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "apply_ocr": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "LayoutLMv3ImageProcessor",
+  "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": ""
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:035866f664a2e44dd093a50100e5e72f5905042a9fd64473b90a31b281f25f99
+size 520825933

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 +1,85 @@
+{
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "only_label_first_subword": true,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "pad_token_label": -100,
+  "processor_class": "LayoutLMv3Processor",
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token_box": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "tokenizer_class": "LayoutLMv3Tokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb05715bb76354e8b164b4f65f8f7182e0a993f33d816d744f55afd242c31e7
+size 3963