nifras365/ocr-scanner-v2

README.md

@@ -0,0 +1,89 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/layoutlm-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: layoutlm-receipts
+  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. -->
+
+# layoutlm-receipts
+
+This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0896
+- Precision: 0.75
+- Recall: 0.75
+- F1: 0.75
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 25
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
+| 0.1758        | 1.0   | 8    | 0.1713          | 0.3529    | 0.6    | 0.4444 |
+| 0.1438        | 2.0   | 16   | 0.2149          | 0.1111    | 0.15   | 0.1277 |
+| 0.0494        | 3.0   | 24   | 0.2381          | 0.36      | 0.45   | 0.4000 |
+| 0.042         | 4.0   | 32   | 0.1144          | 0.5455    | 0.6    | 0.5714 |
+| 0.0236        | 5.0   | 40   | 0.0788          | 0.7       | 0.7    | 0.7    |
+| 0.0111        | 6.0   | 48   | 0.0804          | 0.8333    | 0.75   | 0.7895 |
+| 0.0114        | 7.0   | 56   | 0.0964          | 0.6667    | 0.7    | 0.6829 |
+| 0.0031        | 8.0   | 64   | 0.0892          | 0.8333    | 0.75   | 0.7895 |
+| 0.0065        | 9.0   | 72   | 0.1038          | 0.75      | 0.75   | 0.75   |
+| 0.0014        | 10.0  | 80   | 0.1093          | 0.75      | 0.75   | 0.75   |
+| 0.0045        | 11.0  | 88   | 0.0998          | 0.75      | 0.75   | 0.75   |
+| 0.0027        | 12.0  | 96   | 0.0738          | 0.9444    | 0.85   | 0.8947 |
+| 0.0008        | 13.0  | 104  | 0.0745          | 0.9444    | 0.85   | 0.8947 |
+| 0.0029        | 14.0  | 112  | 0.1234          | 0.5833    | 0.7    | 0.6364 |
+| 0.004         | 15.0  | 120  | 0.0865          | 0.6364    | 0.7    | 0.6667 |
+| 0.0007        | 16.0  | 128  | 0.0888          | 0.8333    | 0.75   | 0.7895 |
+| 0.0055        | 17.0  | 136  | 0.0934          | 0.75      | 0.75   | 0.75   |
+| 0.0004        | 18.0  | 144  | 0.0854          | 0.8333    | 0.75   | 0.7895 |
+| 0.0004        | 19.0  | 152  | 0.0846          | 0.8333    | 0.75   | 0.7895 |
+| 0.0005        | 20.0  | 160  | 0.0843          | 0.8333    | 0.75   | 0.7895 |
+| 0.0005        | 21.0  | 168  | 0.0852          | 0.8333    | 0.75   | 0.7895 |
+| 0.0004        | 22.0  | 176  | 0.0862          | 0.8333    | 0.75   | 0.7895 |
+| 0.0005        | 23.0  | 184  | 0.0875          | 0.8333    | 0.75   | 0.7895 |
+| 0.0003        | 24.0  | 192  | 0.0892          | 0.75      | 0.75   | 0.75   |
+| 0.0005        | 25.0  | 200  | 0.0896          | 0.75      | 0.75   | 0.75   |
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.0

config.json

@@ -0,0 +1,37 @@
+{
+  "_position_embedding_type": "absolute",
+  "architectures": [
+    "LayoutLMForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "date_time",
+    "1": "item",
+    "2": "shop",
+    "3": "total"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "date_time": 0,
+    "item": 1,
+    "shop": 2,
+    "total": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 512,
+  "model_type": "layoutlm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.56.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5956e6863aa694e03137bee8630adf098414c6697f3c6795bee6160d461be90
+size 450548984

runs/Sep24_15-51-59_9f20a18de91f/events.out.tfevents.1758729130.9f20a18de91f.269.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:913fd9c2e43b1e2025ffe649cfc932344f2c6721f9999605647665819655444c
+size 11657

runs/Sep24_16-31-51_9f20a18de91f/events.out.tfevents.1758731515.9f20a18de91f.269.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9780bbf7f0a09d236fe79013e122cf16c2d3a24db161ea148a5382840fa580b
+size 21131

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "LayoutLMTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:130facdb7df9628bc38a7e698c62f68882feac17a51a3dea97abf1f1f43db9b2
+size 5777