kanansharmaa
commited on
Commit
•
ce53cb1
1
Parent(s):
e79776b
End of training
Browse files- README.md +48 -0
- config.json +30 -0
- model.safetensors +3 -0
- preprocessor_config.json +25 -0
- runs/Feb22_11-51-22_innobit/events.out.tfevents.1708602685.innobit.821124.0 +3 -0
- runs/Feb22_11-51-22_innobit/events.out.tfevents.1708602838.innobit.821124.1 +3 -0
- runs/Feb22_11-51-22_innobit/events.out.tfevents.1708602858.innobit.821124.2 +3 -0
- runs/Feb22_11-54-39_innobit/events.out.tfevents.1708602879.innobit.821124.3 +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +79 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: impira/layoutlm-document-qa
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: layoutlm_document_qa
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# layoutlm_document_qa
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [impira/layoutlm-document-qa](https://huggingface.co/impira/layoutlm-document-qa) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 4
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 20
|
42 |
+
|
43 |
+
### Framework versions
|
44 |
+
|
45 |
+
- Transformers 4.39.0.dev0
|
46 |
+
- Pytorch 2.2.0+cu121
|
47 |
+
- Datasets 2.17.1.dev0
|
48 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "impira/layoutlm-document-qa",
|
3 |
+
"architectures": [
|
4 |
+
"LayoutLMForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_2d_position_embeddings": 1024,
|
18 |
+
"max_position_embeddings": 514,
|
19 |
+
"model_type": "layoutlm",
|
20 |
+
"num_attention_heads": 12,
|
21 |
+
"num_hidden_layers": 12,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "absolute",
|
24 |
+
"tokenizer_class": "RobertaTokenizer",
|
25 |
+
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.39.0.dev0",
|
27 |
+
"type_vocab_size": 1,
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 50265
|
30 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f44515b4be73106d9674068b0f1ac34b15c951e539c8be8c1c7fdcb8d1a86eec
|
3 |
+
size 511196416
|
preprocessor_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"apply_ocr",
|
8 |
+
"ocr_lang",
|
9 |
+
"tesseract_config",
|
10 |
+
"return_tensors",
|
11 |
+
"data_format",
|
12 |
+
"input_data_format"
|
13 |
+
],
|
14 |
+
"apply_ocr": true,
|
15 |
+
"do_resize": true,
|
16 |
+
"image_processor_type": "LayoutLMv2ImageProcessor",
|
17 |
+
"ocr_lang": null,
|
18 |
+
"processor_class": "LayoutLMv2Processor",
|
19 |
+
"resample": 2,
|
20 |
+
"size": {
|
21 |
+
"height": 224,
|
22 |
+
"width": 224
|
23 |
+
},
|
24 |
+
"tesseract_config": ""
|
25 |
+
}
|
runs/Feb22_11-51-22_innobit/events.out.tfevents.1708602685.innobit.821124.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e91fbdc1a2d9826e1f286444fe5b3f21186aa525d6693323ac05c097af16bebe
|
3 |
+
size 4747
|
runs/Feb22_11-51-22_innobit/events.out.tfevents.1708602838.innobit.821124.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64aa1c695944ea983036ae128794e9a08c200e418ea5a741c3c2f110777da394
|
3 |
+
size 4747
|
runs/Feb22_11-51-22_innobit/events.out.tfevents.1708602858.innobit.821124.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc076c1fcee28b62717b7b78eb26317634439f282c06282696d9f5d1d4e0ab2d
|
3 |
+
size 4747
|
runs/Feb22_11-54-39_innobit/events.out.tfevents.1708602879.innobit.821124.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f768ca4c999efd8388e9aba615d3dff48ab55a59e166279be3a2c0da81fdcc5
|
3 |
+
size 4747
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"cls_token_box": [
|
48 |
+
0,
|
49 |
+
0,
|
50 |
+
0,
|
51 |
+
0
|
52 |
+
],
|
53 |
+
"do_basic_tokenize": true,
|
54 |
+
"do_lower_case": true,
|
55 |
+
"mask_token": "[MASK]",
|
56 |
+
"model_max_length": 512,
|
57 |
+
"never_split": null,
|
58 |
+
"only_label_first_subword": true,
|
59 |
+
"pad_token": "[PAD]",
|
60 |
+
"pad_token_box": [
|
61 |
+
0,
|
62 |
+
0,
|
63 |
+
0,
|
64 |
+
0
|
65 |
+
],
|
66 |
+
"pad_token_label": -100,
|
67 |
+
"processor_class": "LayoutLMv2Processor",
|
68 |
+
"sep_token": "[SEP]",
|
69 |
+
"sep_token_box": [
|
70 |
+
1000,
|
71 |
+
1000,
|
72 |
+
1000,
|
73 |
+
1000
|
74 |
+
],
|
75 |
+
"strip_accents": null,
|
76 |
+
"tokenize_chinese_chars": true,
|
77 |
+
"tokenizer_class": "LayoutLMv2Tokenizer",
|
78 |
+
"unk_token": "[UNK]"
|
79 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4a20874c4c3d17dc0d1903a32114f50987d26c936c73c52ac6e30209c69f796
|
3 |
+
size 4920
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|