End of training
Browse files- README.md +106 -0
- config.json +294 -0
- logs/events.out.tfevents.1732922524.2cc3b3a5bf49.638.0 +3 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +26 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +80 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: cc-by-nc-sa-4.0
|
| 4 |
+
base_model: microsoft/layoutlmv3-base
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- layoutlmv3
|
| 9 |
+
metrics:
|
| 10 |
+
- precision
|
| 11 |
+
- recall
|
| 12 |
+
- f1
|
| 13 |
+
- accuracy
|
| 14 |
+
model-index:
|
| 15 |
+
- name: layoutlm-CC-7
|
| 16 |
+
results:
|
| 17 |
+
- task:
|
| 18 |
+
name: Token Classification
|
| 19 |
+
type: token-classification
|
| 20 |
+
dataset:
|
| 21 |
+
name: layoutlmv3
|
| 22 |
+
type: layoutlmv3
|
| 23 |
+
config: FormsDataset
|
| 24 |
+
split: test
|
| 25 |
+
args: FormsDataset
|
| 26 |
+
metrics:
|
| 27 |
+
- name: Precision
|
| 28 |
+
type: precision
|
| 29 |
+
value: 0.12529002320185614
|
| 30 |
+
- name: Recall
|
| 31 |
+
type: recall
|
| 32 |
+
value: 0.20224719101123595
|
| 33 |
+
- name: F1
|
| 34 |
+
type: f1
|
| 35 |
+
value: 0.15472779369627507
|
| 36 |
+
- name: Accuracy
|
| 37 |
+
type: accuracy
|
| 38 |
+
value: 0.19654427645788336
|
| 39 |
+
---
|
| 40 |
+
|
| 41 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 42 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 43 |
+
|
| 44 |
+
# layoutlm-CC-7
|
| 45 |
+
|
| 46 |
+
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the layoutlmv3 dataset.
|
| 47 |
+
It achieves the following results on the evaluation set:
|
| 48 |
+
- Loss: 4.1612
|
| 49 |
+
- Precision: 0.1253
|
| 50 |
+
- Recall: 0.2022
|
| 51 |
+
- F1: 0.1547
|
| 52 |
+
- Accuracy: 0.1965
|
| 53 |
+
|
| 54 |
+
## Model description
|
| 55 |
+
|
| 56 |
+
More information needed
|
| 57 |
+
|
| 58 |
+
## Intended uses & limitations
|
| 59 |
+
|
| 60 |
+
More information needed
|
| 61 |
+
|
| 62 |
+
## Training and evaluation data
|
| 63 |
+
|
| 64 |
+
More information needed
|
| 65 |
+
|
| 66 |
+
## Training procedure
|
| 67 |
+
|
| 68 |
+
### Training hyperparameters
|
| 69 |
+
|
| 70 |
+
The following hyperparameters were used during training:
|
| 71 |
+
- learning_rate: 3e-05
|
| 72 |
+
- train_batch_size: 16
|
| 73 |
+
- eval_batch_size: 8
|
| 74 |
+
- seed: 42
|
| 75 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 76 |
+
- lr_scheduler_type: linear
|
| 77 |
+
- num_epochs: 15
|
| 78 |
+
- mixed_precision_training: Native AMP
|
| 79 |
+
|
| 80 |
+
### Training results
|
| 81 |
+
|
| 82 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 83 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 84 |
+
| 4.8141 | 1.0 | 1 | 4.7205 | 0.0921 | 0.1311 | 0.1082 | 0.0821 |
|
| 85 |
+
| 4.7028 | 2.0 | 2 | 4.6365 | 0.1414 | 0.2022 | 0.1664 | 0.1425 |
|
| 86 |
+
| 4.6011 | 3.0 | 3 | 4.5617 | 0.1230 | 0.2022 | 0.1530 | 0.1274 |
|
| 87 |
+
| 4.5126 | 4.0 | 4 | 4.4931 | 0.1174 | 0.2022 | 0.1486 | 0.1231 |
|
| 88 |
+
| 4.4376 | 5.0 | 5 | 4.4390 | 0.1166 | 0.2022 | 0.1479 | 0.1166 |
|
| 89 |
+
| 4.3778 | 6.0 | 6 | 4.3926 | 0.1166 | 0.2022 | 0.1479 | 0.1188 |
|
| 90 |
+
| 4.3224 | 7.0 | 7 | 4.3454 | 0.1166 | 0.2022 | 0.1479 | 0.1210 |
|
| 91 |
+
| 4.2658 | 8.0 | 8 | 4.3058 | 0.1166 | 0.2022 | 0.1479 | 0.1253 |
|
| 92 |
+
| 4.2182 | 9.0 | 9 | 4.2708 | 0.1179 | 0.2022 | 0.1490 | 0.1425 |
|
| 93 |
+
| 4.1796 | 10.0 | 10 | 4.2415 | 0.1208 | 0.2022 | 0.1513 | 0.1641 |
|
| 94 |
+
| 4.1423 | 11.0 | 11 | 4.2165 | 0.1222 | 0.2022 | 0.1523 | 0.1728 |
|
| 95 |
+
| 4.1197 | 12.0 | 12 | 4.1951 | 0.1230 | 0.2022 | 0.1530 | 0.1793 |
|
| 96 |
+
| 4.0976 | 13.0 | 13 | 4.1782 | 0.1241 | 0.2022 | 0.1538 | 0.1922 |
|
| 97 |
+
| 4.0801 | 14.0 | 14 | 4.1669 | 0.1253 | 0.2022 | 0.1547 | 0.1965 |
|
| 98 |
+
| 4.0627 | 15.0 | 15 | 4.1612 | 0.1253 | 0.2022 | 0.1547 | 0.1965 |
|
| 99 |
+
|
| 100 |
+
|
| 101 |
+
### Framework versions
|
| 102 |
+
|
| 103 |
+
- Transformers 4.47.0.dev0
|
| 104 |
+
- Pytorch 2.5.1+cu121
|
| 105 |
+
- Datasets 3.1.0
|
| 106 |
+
- Tokenizers 0.20.3
|
config.json
ADDED
|
@@ -0,0 +1,294 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/layoutlmv3-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LayoutLMv3ForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"coordinate_size": 128,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"has_relative_attention_bias": true,
|
| 12 |
+
"has_spatial_attention_bias": true,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.1,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "0",
|
| 18 |
+
"1": "B-AMOUNT_FINANCED",
|
| 19 |
+
"2": "B-AVERAGE_BANK_BALANCE",
|
| 20 |
+
"3": "B-COMPANY_ADDRESS",
|
| 21 |
+
"4": "B-COMPANY_CITY",
|
| 22 |
+
"5": "B-COMPANY_NAME",
|
| 23 |
+
"6": "B-COMPANY_PHONE",
|
| 24 |
+
"7": "B-COMPANY_STATE",
|
| 25 |
+
"8": "B-COMPANY_ZIP",
|
| 26 |
+
"9": "B-CONTACT_EMAIL",
|
| 27 |
+
"10": "B-CONTACT_NAME",
|
| 28 |
+
"11": "B-CONTACT_PHONE_NUM",
|
| 29 |
+
"12": "B-EQUIPMENT",
|
| 30 |
+
"13": "B-EQUIPMENT_ADDRESS",
|
| 31 |
+
"14": "B-EQUIPMENT_CITY",
|
| 32 |
+
"15": "B-EQUIPMENT_STATE",
|
| 33 |
+
"16": "B-EQUIPMENT_ZIP",
|
| 34 |
+
"17": "B-FEDERAL_TAX_ID",
|
| 35 |
+
"18": "B-Header",
|
| 36 |
+
"19": "B-NUMBER_EMPLOYEES",
|
| 37 |
+
"20": "B-NUM_YEARS_IN_BUSINESS",
|
| 38 |
+
"21": "B-PRINCIPAL_1_ADDRESS",
|
| 39 |
+
"22": "B-PRINCIPAL_1_CITY",
|
| 40 |
+
"23": "B-PRINCIPAL_1_EMAIL",
|
| 41 |
+
"24": "B-PRINCIPAL_1_NAME",
|
| 42 |
+
"25": "B-PRINCIPAL_1_OWNERSHIP",
|
| 43 |
+
"26": "B-PRINCIPAL_1_SSN",
|
| 44 |
+
"27": "B-PRINCIPAL_1_STATE",
|
| 45 |
+
"28": "B-PRINCIPAL_1_TITLE",
|
| 46 |
+
"29": "B-PRINCIPAL_1_ZIP",
|
| 47 |
+
"30": "B-PRINCIPAL_2_ADDRESS",
|
| 48 |
+
"31": "B-PRINCIPAL_2_CITY",
|
| 49 |
+
"32": "B-PRINCIPAL_2_EMAIL",
|
| 50 |
+
"33": "B-PRINCIPAL_2_NAME",
|
| 51 |
+
"34": "B-PRINCIPAL_2_OWNERSHIP",
|
| 52 |
+
"35": "B-PRINCIPAL_2_SSN",
|
| 53 |
+
"36": "B-PRINCIPAL_2_STATE",
|
| 54 |
+
"37": "B-PRINCIPAL_2_TITLE",
|
| 55 |
+
"38": "B-PRINCIPAL_2_ZIP",
|
| 56 |
+
"39": "B-QUESTION_AMOUNT_FINANCED",
|
| 57 |
+
"40": "B-QUESTION_AVERAGE_BANK_BALANCE",
|
| 58 |
+
"41": "B-QUESTION_COMPANY_ADDRESS",
|
| 59 |
+
"42": "B-QUESTION_COMPANY_CITY",
|
| 60 |
+
"43": "B-QUESTION_COMPANY_NAME",
|
| 61 |
+
"44": "B-QUESTION_COMPANY_PHONE",
|
| 62 |
+
"45": "B-QUESTION_COMPANY_STATE",
|
| 63 |
+
"46": "B-QUESTION_COMPANY_ZIP",
|
| 64 |
+
"47": "B-QUESTION_CONTACT_EMAIL",
|
| 65 |
+
"48": "B-QUESTION_CONTACT_NAME",
|
| 66 |
+
"49": "B-QUESTION_CONTACT_PHONE_NUM",
|
| 67 |
+
"50": "B-QUESTION_EQUIPMENT",
|
| 68 |
+
"51": "B-QUESTION_EQUIPMENT_ADDRESS",
|
| 69 |
+
"52": "B-QUESTION_EQUIPMENT_CITY",
|
| 70 |
+
"53": "B-QUESTION_EQUIPMENT_STATE",
|
| 71 |
+
"54": "B-QUESTION_EQUIPMENT_ZIP",
|
| 72 |
+
"55": "B-QUESTION_FEDERAL_TAX_ID",
|
| 73 |
+
"56": "B-QUESTION_NUMBER_EMPLOYEES",
|
| 74 |
+
"57": "B-QUESTION_NUM_YEARS_IN_BUSINESS",
|
| 75 |
+
"58": "B-QUESTION_PRINCIPAL_1_ADDRESS",
|
| 76 |
+
"59": "B-QUESTION_PRINCIPAL_1_CITY",
|
| 77 |
+
"60": "B-QUESTION_PRINCIPAL_1_EMAIL",
|
| 78 |
+
"61": "B-QUESTION_PRINCIPAL_1_NAME",
|
| 79 |
+
"62": "B-QUESTION_PRINCIPAL_1_OWNERSHIP",
|
| 80 |
+
"63": "B-QUESTION_PRINCIPAL_1_SSN",
|
| 81 |
+
"64": "B-QUESTION_PRINCIPAL_1_STATE",
|
| 82 |
+
"65": "B-QUESTION_PRINCIPAL_1_TITLE",
|
| 83 |
+
"66": "B-QUESTION_PRINCIPAL_1_ZIP",
|
| 84 |
+
"67": "B-QUESTION_PRINCIPAL_2_ADDRESS",
|
| 85 |
+
"68": "B-QUESTION_PRINCIPAL_2_CITY",
|
| 86 |
+
"69": "B-QUESTION_PRINCIPAL_2_EMAIL",
|
| 87 |
+
"70": "B-QUESTION_PRINCIPAL_2_NAME",
|
| 88 |
+
"71": "B-QUESTION_PRINCIPAL_2_OWNERSHIP",
|
| 89 |
+
"72": "B-QUESTION_PRINCIPAL_2_SSN",
|
| 90 |
+
"73": "B-QUESTION_PRINCIPAL_2_STATE",
|
| 91 |
+
"74": "B-QUESTION_PRINCIPAL_2_TITLE",
|
| 92 |
+
"75": "B-QUESTION_PRINCIPAL_2_ZIP",
|
| 93 |
+
"76": "B-QUESTION_SALES_REP_NAME",
|
| 94 |
+
"77": "B-QUESTION_YEARS_CUSTOMER",
|
| 95 |
+
"78": "B-SALES_REP_NAME",
|
| 96 |
+
"79": "B-YEARS_CUSTOMER",
|
| 97 |
+
"80": "I-AVERAGE_BANK_BALANCE",
|
| 98 |
+
"81": "I-COMPANY_ADDRESS",
|
| 99 |
+
"82": "I-COMPANY_NAME",
|
| 100 |
+
"83": "I-COMPANY_PHONE",
|
| 101 |
+
"84": "I-CONTACT_EMAIL",
|
| 102 |
+
"85": "I-CONTACT_NAME",
|
| 103 |
+
"86": "I-CONTACT_PHONE_NUM",
|
| 104 |
+
"87": "I-EQUIPMENT",
|
| 105 |
+
"88": "I-EQUIPMENT_ADDRESS",
|
| 106 |
+
"89": "I-FEDERAL_TAX_ID",
|
| 107 |
+
"90": "I-PRINCIPAL_1_ADDRESS",
|
| 108 |
+
"91": "I-PRINCIPAL_1_EMAIL",
|
| 109 |
+
"92": "I-PRINCIPAL_1_NAME",
|
| 110 |
+
"93": "I-PRINCIPAL_1_SSN",
|
| 111 |
+
"94": "I-PRINCIPAL_1_TITLE",
|
| 112 |
+
"95": "I-PRINCIPAL_2_ADDRESS",
|
| 113 |
+
"96": "I-PRINCIPAL_2_EMAIL",
|
| 114 |
+
"97": "I-PRINCIPAL_2_NAME",
|
| 115 |
+
"98": "I-PRINCIPAL_2_SSN",
|
| 116 |
+
"99": "I-PRINCIPAL_2_TITLE",
|
| 117 |
+
"100": "I-QUESTION_AMOUNT_FINANCED",
|
| 118 |
+
"101": "I-QUESTION_AVERAGE_BANK_BALANCE",
|
| 119 |
+
"102": "I-QUESTION_COMPANY_ADDRESS",
|
| 120 |
+
"103": "I-QUESTION_COMPANY_NAME",
|
| 121 |
+
"104": "I-QUESTION_COMPANY_PHONE",
|
| 122 |
+
"105": "I-QUESTION_CONTACT_EMAIL",
|
| 123 |
+
"106": "I-QUESTION_CONTACT_NAME",
|
| 124 |
+
"107": "I-QUESTION_CONTACT_PHONE_NUM",
|
| 125 |
+
"108": "I-QUESTION_EQUIPMENT",
|
| 126 |
+
"109": "I-QUESTION_EQUIPMENT_ADDRESS",
|
| 127 |
+
"110": "I-QUESTION_FEDERAL_TAX_ID",
|
| 128 |
+
"111": "I-QUESTION_NUMBER_EMPLOYEES",
|
| 129 |
+
"112": "I-QUESTION_NUM_YEARS_IN_BUSINESS",
|
| 130 |
+
"113": "I-QUESTION_PRINCIPAL_1_ADDRESS",
|
| 131 |
+
"114": "I-QUESTION_PRINCIPAL_1_EMAIL",
|
| 132 |
+
"115": "I-QUESTION_PRINCIPAL_1_OWNERSHIP",
|
| 133 |
+
"116": "I-QUESTION_PRINCIPAL_1_SSN",
|
| 134 |
+
"117": "I-QUESTION_PRINCIPAL_2_ADDRESS",
|
| 135 |
+
"118": "I-QUESTION_PRINCIPAL_2_EMAIL",
|
| 136 |
+
"119": "I-QUESTION_PRINCIPAL_2_OWNERSHIP",
|
| 137 |
+
"120": "I-QUESTION_PRINCIPAL_2_SSN",
|
| 138 |
+
"121": "I-QUESTION_SALES_REP_NAME",
|
| 139 |
+
"122": "I-QUESTION_YEARS_CUSTOMER",
|
| 140 |
+
"123": "I-SALES_REP_NAME",
|
| 141 |
+
"124": "I-YEARS_CUSTOMER"
|
| 142 |
+
},
|
| 143 |
+
"initializer_range": 0.02,
|
| 144 |
+
"input_size": 224,
|
| 145 |
+
"intermediate_size": 3072,
|
| 146 |
+
"label2id": {
|
| 147 |
+
"0": 0,
|
| 148 |
+
"B-AMOUNT_FINANCED": 1,
|
| 149 |
+
"B-AVERAGE_BANK_BALANCE": 2,
|
| 150 |
+
"B-COMPANY_ADDRESS": 3,
|
| 151 |
+
"B-COMPANY_CITY": 4,
|
| 152 |
+
"B-COMPANY_NAME": 5,
|
| 153 |
+
"B-COMPANY_PHONE": 6,
|
| 154 |
+
"B-COMPANY_STATE": 7,
|
| 155 |
+
"B-COMPANY_ZIP": 8,
|
| 156 |
+
"B-CONTACT_EMAIL": 9,
|
| 157 |
+
"B-CONTACT_NAME": 10,
|
| 158 |
+
"B-CONTACT_PHONE_NUM": 11,
|
| 159 |
+
"B-EQUIPMENT": 12,
|
| 160 |
+
"B-EQUIPMENT_ADDRESS": 13,
|
| 161 |
+
"B-EQUIPMENT_CITY": 14,
|
| 162 |
+
"B-EQUIPMENT_STATE": 15,
|
| 163 |
+
"B-EQUIPMENT_ZIP": 16,
|
| 164 |
+
"B-FEDERAL_TAX_ID": 17,
|
| 165 |
+
"B-Header": 18,
|
| 166 |
+
"B-NUMBER_EMPLOYEES": 19,
|
| 167 |
+
"B-NUM_YEARS_IN_BUSINESS": 20,
|
| 168 |
+
"B-PRINCIPAL_1_ADDRESS": 21,
|
| 169 |
+
"B-PRINCIPAL_1_CITY": 22,
|
| 170 |
+
"B-PRINCIPAL_1_EMAIL": 23,
|
| 171 |
+
"B-PRINCIPAL_1_NAME": 24,
|
| 172 |
+
"B-PRINCIPAL_1_OWNERSHIP": 25,
|
| 173 |
+
"B-PRINCIPAL_1_SSN": 26,
|
| 174 |
+
"B-PRINCIPAL_1_STATE": 27,
|
| 175 |
+
"B-PRINCIPAL_1_TITLE": 28,
|
| 176 |
+
"B-PRINCIPAL_1_ZIP": 29,
|
| 177 |
+
"B-PRINCIPAL_2_ADDRESS": 30,
|
| 178 |
+
"B-PRINCIPAL_2_CITY": 31,
|
| 179 |
+
"B-PRINCIPAL_2_EMAIL": 32,
|
| 180 |
+
"B-PRINCIPAL_2_NAME": 33,
|
| 181 |
+
"B-PRINCIPAL_2_OWNERSHIP": 34,
|
| 182 |
+
"B-PRINCIPAL_2_SSN": 35,
|
| 183 |
+
"B-PRINCIPAL_2_STATE": 36,
|
| 184 |
+
"B-PRINCIPAL_2_TITLE": 37,
|
| 185 |
+
"B-PRINCIPAL_2_ZIP": 38,
|
| 186 |
+
"B-QUESTION_AMOUNT_FINANCED": 39,
|
| 187 |
+
"B-QUESTION_AVERAGE_BANK_BALANCE": 40,
|
| 188 |
+
"B-QUESTION_COMPANY_ADDRESS": 41,
|
| 189 |
+
"B-QUESTION_COMPANY_CITY": 42,
|
| 190 |
+
"B-QUESTION_COMPANY_NAME": 43,
|
| 191 |
+
"B-QUESTION_COMPANY_PHONE": 44,
|
| 192 |
+
"B-QUESTION_COMPANY_STATE": 45,
|
| 193 |
+
"B-QUESTION_COMPANY_ZIP": 46,
|
| 194 |
+
"B-QUESTION_CONTACT_EMAIL": 47,
|
| 195 |
+
"B-QUESTION_CONTACT_NAME": 48,
|
| 196 |
+
"B-QUESTION_CONTACT_PHONE_NUM": 49,
|
| 197 |
+
"B-QUESTION_EQUIPMENT": 50,
|
| 198 |
+
"B-QUESTION_EQUIPMENT_ADDRESS": 51,
|
| 199 |
+
"B-QUESTION_EQUIPMENT_CITY": 52,
|
| 200 |
+
"B-QUESTION_EQUIPMENT_STATE": 53,
|
| 201 |
+
"B-QUESTION_EQUIPMENT_ZIP": 54,
|
| 202 |
+
"B-QUESTION_FEDERAL_TAX_ID": 55,
|
| 203 |
+
"B-QUESTION_NUMBER_EMPLOYEES": 56,
|
| 204 |
+
"B-QUESTION_NUM_YEARS_IN_BUSINESS": 57,
|
| 205 |
+
"B-QUESTION_PRINCIPAL_1_ADDRESS": 58,
|
| 206 |
+
"B-QUESTION_PRINCIPAL_1_CITY": 59,
|
| 207 |
+
"B-QUESTION_PRINCIPAL_1_EMAIL": 60,
|
| 208 |
+
"B-QUESTION_PRINCIPAL_1_NAME": 61,
|
| 209 |
+
"B-QUESTION_PRINCIPAL_1_OWNERSHIP": 62,
|
| 210 |
+
"B-QUESTION_PRINCIPAL_1_SSN": 63,
|
| 211 |
+
"B-QUESTION_PRINCIPAL_1_STATE": 64,
|
| 212 |
+
"B-QUESTION_PRINCIPAL_1_TITLE": 65,
|
| 213 |
+
"B-QUESTION_PRINCIPAL_1_ZIP": 66,
|
| 214 |
+
"B-QUESTION_PRINCIPAL_2_ADDRESS": 67,
|
| 215 |
+
"B-QUESTION_PRINCIPAL_2_CITY": 68,
|
| 216 |
+
"B-QUESTION_PRINCIPAL_2_EMAIL": 69,
|
| 217 |
+
"B-QUESTION_PRINCIPAL_2_NAME": 70,
|
| 218 |
+
"B-QUESTION_PRINCIPAL_2_OWNERSHIP": 71,
|
| 219 |
+
"B-QUESTION_PRINCIPAL_2_SSN": 72,
|
| 220 |
+
"B-QUESTION_PRINCIPAL_2_STATE": 73,
|
| 221 |
+
"B-QUESTION_PRINCIPAL_2_TITLE": 74,
|
| 222 |
+
"B-QUESTION_PRINCIPAL_2_ZIP": 75,
|
| 223 |
+
"B-QUESTION_SALES_REP_NAME": 76,
|
| 224 |
+
"B-QUESTION_YEARS_CUSTOMER": 77,
|
| 225 |
+
"B-SALES_REP_NAME": 78,
|
| 226 |
+
"B-YEARS_CUSTOMER": 79,
|
| 227 |
+
"I-AVERAGE_BANK_BALANCE": 80,
|
| 228 |
+
"I-COMPANY_ADDRESS": 81,
|
| 229 |
+
"I-COMPANY_NAME": 82,
|
| 230 |
+
"I-COMPANY_PHONE": 83,
|
| 231 |
+
"I-CONTACT_EMAIL": 84,
|
| 232 |
+
"I-CONTACT_NAME": 85,
|
| 233 |
+
"I-CONTACT_PHONE_NUM": 86,
|
| 234 |
+
"I-EQUIPMENT": 87,
|
| 235 |
+
"I-EQUIPMENT_ADDRESS": 88,
|
| 236 |
+
"I-FEDERAL_TAX_ID": 89,
|
| 237 |
+
"I-PRINCIPAL_1_ADDRESS": 90,
|
| 238 |
+
"I-PRINCIPAL_1_EMAIL": 91,
|
| 239 |
+
"I-PRINCIPAL_1_NAME": 92,
|
| 240 |
+
"I-PRINCIPAL_1_SSN": 93,
|
| 241 |
+
"I-PRINCIPAL_1_TITLE": 94,
|
| 242 |
+
"I-PRINCIPAL_2_ADDRESS": 95,
|
| 243 |
+
"I-PRINCIPAL_2_EMAIL": 96,
|
| 244 |
+
"I-PRINCIPAL_2_NAME": 97,
|
| 245 |
+
"I-PRINCIPAL_2_SSN": 98,
|
| 246 |
+
"I-PRINCIPAL_2_TITLE": 99,
|
| 247 |
+
"I-QUESTION_AMOUNT_FINANCED": 100,
|
| 248 |
+
"I-QUESTION_AVERAGE_BANK_BALANCE": 101,
|
| 249 |
+
"I-QUESTION_COMPANY_ADDRESS": 102,
|
| 250 |
+
"I-QUESTION_COMPANY_NAME": 103,
|
| 251 |
+
"I-QUESTION_COMPANY_PHONE": 104,
|
| 252 |
+
"I-QUESTION_CONTACT_EMAIL": 105,
|
| 253 |
+
"I-QUESTION_CONTACT_NAME": 106,
|
| 254 |
+
"I-QUESTION_CONTACT_PHONE_NUM": 107,
|
| 255 |
+
"I-QUESTION_EQUIPMENT": 108,
|
| 256 |
+
"I-QUESTION_EQUIPMENT_ADDRESS": 109,
|
| 257 |
+
"I-QUESTION_FEDERAL_TAX_ID": 110,
|
| 258 |
+
"I-QUESTION_NUMBER_EMPLOYEES": 111,
|
| 259 |
+
"I-QUESTION_NUM_YEARS_IN_BUSINESS": 112,
|
| 260 |
+
"I-QUESTION_PRINCIPAL_1_ADDRESS": 113,
|
| 261 |
+
"I-QUESTION_PRINCIPAL_1_EMAIL": 114,
|
| 262 |
+
"I-QUESTION_PRINCIPAL_1_OWNERSHIP": 115,
|
| 263 |
+
"I-QUESTION_PRINCIPAL_1_SSN": 116,
|
| 264 |
+
"I-QUESTION_PRINCIPAL_2_ADDRESS": 117,
|
| 265 |
+
"I-QUESTION_PRINCIPAL_2_EMAIL": 118,
|
| 266 |
+
"I-QUESTION_PRINCIPAL_2_OWNERSHIP": 119,
|
| 267 |
+
"I-QUESTION_PRINCIPAL_2_SSN": 120,
|
| 268 |
+
"I-QUESTION_SALES_REP_NAME": 121,
|
| 269 |
+
"I-QUESTION_YEARS_CUSTOMER": 122,
|
| 270 |
+
"I-SALES_REP_NAME": 123,
|
| 271 |
+
"I-YEARS_CUSTOMER": 124
|
| 272 |
+
},
|
| 273 |
+
"layer_norm_eps": 1e-05,
|
| 274 |
+
"max_2d_position_embeddings": 1024,
|
| 275 |
+
"max_position_embeddings": 514,
|
| 276 |
+
"max_rel_2d_pos": 256,
|
| 277 |
+
"max_rel_pos": 128,
|
| 278 |
+
"model_type": "layoutlmv3",
|
| 279 |
+
"num_attention_heads": 12,
|
| 280 |
+
"num_channels": 3,
|
| 281 |
+
"num_hidden_layers": 12,
|
| 282 |
+
"pad_token_id": 1,
|
| 283 |
+
"patch_size": 16,
|
| 284 |
+
"rel_2d_pos_bins": 64,
|
| 285 |
+
"rel_pos_bins": 32,
|
| 286 |
+
"second_input_size": 112,
|
| 287 |
+
"shape_size": 128,
|
| 288 |
+
"text_embed": true,
|
| 289 |
+
"torch_dtype": "float32",
|
| 290 |
+
"transformers_version": "4.47.0.dev0",
|
| 291 |
+
"type_vocab_size": 1,
|
| 292 |
+
"visual_embed": true,
|
| 293 |
+
"vocab_size": 50265
|
| 294 |
+
}
|
logs/events.out.tfevents.1732922524.2cc3b3a5bf49.638.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a780e7b37892df0eb0d64f2ebf4d20bbe0407059afccddf3331238806035d185
|
| 3 |
+
size 24516
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e62c0be87bfc2984c28d1513a632e294c6bda464c91c129ecfa464105166024c
|
| 3 |
+
size 504081100
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"apply_ocr": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "LayoutLMv3ImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"ocr_lang": null,
|
| 18 |
+
"processor_class": "LayoutLMv3Processor",
|
| 19 |
+
"resample": 2,
|
| 20 |
+
"rescale_factor": 0.00392156862745098,
|
| 21 |
+
"size": {
|
| 22 |
+
"height": 224,
|
| 23 |
+
"width": 224
|
| 24 |
+
},
|
| 25 |
+
"tesseract_config": ""
|
| 26 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"apply_ocr": false,
|
| 46 |
+
"bos_token": "<s>",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"cls_token": "<s>",
|
| 49 |
+
"cls_token_box": [
|
| 50 |
+
0,
|
| 51 |
+
0,
|
| 52 |
+
0,
|
| 53 |
+
0
|
| 54 |
+
],
|
| 55 |
+
"eos_token": "</s>",
|
| 56 |
+
"errors": "replace",
|
| 57 |
+
"extra_special_tokens": {},
|
| 58 |
+
"mask_token": "<mask>",
|
| 59 |
+
"model_max_length": 512,
|
| 60 |
+
"only_label_first_subword": true,
|
| 61 |
+
"pad_token": "<pad>",
|
| 62 |
+
"pad_token_box": [
|
| 63 |
+
0,
|
| 64 |
+
0,
|
| 65 |
+
0,
|
| 66 |
+
0
|
| 67 |
+
],
|
| 68 |
+
"pad_token_label": -100,
|
| 69 |
+
"processor_class": "LayoutLMv3Processor",
|
| 70 |
+
"sep_token": "</s>",
|
| 71 |
+
"sep_token_box": [
|
| 72 |
+
0,
|
| 73 |
+
0,
|
| 74 |
+
0,
|
| 75 |
+
0
|
| 76 |
+
],
|
| 77 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
| 78 |
+
"trim_offsets": true,
|
| 79 |
+
"unk_token": "<unk>"
|
| 80 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a08f24aad176d47d80fa10a485df4a8a14a4d1c2216f9a6c0e12cf54660df59
|
| 3 |
+
size 5304
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|