Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,114 @@
+{
+  "_name_or_path": "microsoft/layoutlmv3-base",
+  "architectures": [
+    "LayoutLMv3ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "coordinate_size": 128,
+  "eos_token_id": 2,
+  "has_relative_attention_bias": true,
+  "has_spatial_attention_bias": true,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "E-RECEIVERNAME",
+    "1": "E-RECEIVERADRESS",
+    "10": "B-RECEIVERADRESS",
+    "11": "B-EXPIRATIONDATE",
+    "12": "E-TOTALAMOUNT",
+    "13": "E-RECEIVERCITY",
+    "14": "E-SENDERADRESS",
+    "15": "E-VATAMOUNT",
+    "16": "I-RECEIVERNAME",
+    "17": "I-EXPIRATIONDATE",
+    "18": "E-RECEIVERZIPCODE",
+    "19": "I-SENDERADRESS",
+    "2": "I-SENDERNAME",
+    "20": "B-SENDERNAME",
+    "21": "I-INVOICEDATE",
+    "22": "B-TOTALAMOUNT",
+    "23": "E-EXPIRATIONDATE",
+    "24": "B-SENDERZIPCODE",
+    "25": "B-RECEIVERNAME",
+    "26": "E-SENDERNAME",
+    "27": "B-SENDERADRESS",
+    "28": "B-REFERENCE",
+    "29": "I-SENDERZIPCODE",
+    "3": "B-INVOICEDATE",
+    "30": "B-VATAMOUNT",
+    "31": "I-REFERENCE",
+    "32": "B-RECEIVERCITY",
+    "33": "B-RECEIVERZIPCODE",
+    "34": "I-SENDERCITY",
+    "4": "I-RECEIVERADRESS",
+    "5": "E-SENDERCITY",
+    "6": "E-INVOICEDATE",
+    "7": "E-SENDERZIPCODE",
+    "8": "B-SENDERCITY",
+    "9": "E-REFERENCE"
+  },
+  "initializer_range": 0.02,
+  "input_size": 224,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-EXPIRATIONDATE": 11,
+    "B-INVOICEDATE": 3,
+    "B-RECEIVERADRESS": 10,
+    "B-RECEIVERCITY": 32,
+    "B-RECEIVERNAME": 25,
+    "B-RECEIVERZIPCODE": 33,
+    "B-REFERENCE": 28,
+    "B-SENDERADRESS": 27,
+    "B-SENDERCITY": 8,
+    "B-SENDERNAME": 20,
+    "B-SENDERZIPCODE": 24,
+    "B-TOTALAMOUNT": 22,
+    "B-VATAMOUNT": 30,
+    "E-EXPIRATIONDATE": 23,
+    "E-INVOICEDATE": 6,
+    "E-RECEIVERADRESS": 1,
+    "E-RECEIVERCITY": 13,
+    "E-RECEIVERNAME": 0,
+    "E-RECEIVERZIPCODE": 18,
+    "E-REFERENCE": 9,
+    "E-SENDERADRESS": 14,
+    "E-SENDERCITY": 5,
+    "E-SENDERNAME": 26,
+    "E-SENDERZIPCODE": 7,
+    "E-TOTALAMOUNT": 12,
+    "E-VATAMOUNT": 15,
+    "I-EXPIRATIONDATE": 17,
+    "I-INVOICEDATE": 21,
+    "I-RECEIVERADRESS": 4,
+    "I-RECEIVERNAME": 16,
+    "I-REFERENCE": 31,
+    "I-SENDERADRESS": 19,
+    "I-SENDERCITY": 34,
+    "I-SENDERNAME": 2,
+    "I-SENDERZIPCODE": 29
+  },
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "max_rel_2d_pos": 256,
+  "max_rel_pos": 128,
+  "model_type": "layoutlmv3",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "patch_size": 16,
+  "rel_2d_pos_bins": 64,
+  "rel_pos_bins": 32,
+  "second_input_size": 112,
+  "shape_size": 128,
+  "text_embed": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0.dev0",
+  "type_vocab_size": 1,
+  "visual_embed": true,
+  "vocab_size": 50265
+}

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "apply_ocr": false,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "LayoutLMv3FeatureExtractor",
+  "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:f1401c50386727f3b1dfcf10395c23a444e02ee4afd201db36151bb39bd8870d
+size 503857143

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 +1,86 @@
+{
+  "add_prefix_space": true,
+  "apply_ocr": false,
+  "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:fbd59710f34851c9ddb077d5d665459ed8d239f122b6de53787302aa9ad9d33c
+size 3951