End of training
Browse files- README.md +53 -3
- logs/events.out.tfevents.1748886368.phi-ThinkPad-T490 +1 -1
- preprocessor_config.json +13 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +81 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,53 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
base_model: microsoft/layoutlm-large-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: Layoutlmlargetest
|
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 |
+
# Layoutlmlargetest
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [microsoft/layoutlm-large-uncased](https://huggingface.co/microsoft/layoutlm-large-uncased) on the None 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: 3e-05
|
36 |
+
- train_batch_size: 16
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 5
|
42 |
+
- mixed_precision_training: Native AMP
|
43 |
+
|
44 |
+
### Training results
|
45 |
+
|
46 |
+
|
47 |
+
|
48 |
+
### Framework versions
|
49 |
+
|
50 |
+
- Transformers 4.53.0.dev0
|
51 |
+
- Pytorch 2.7.0+cu126
|
52 |
+
- Datasets 3.6.0
|
53 |
+
- Tokenizers 0.21.1
|
logs/events.out.tfevents.1748886368.phi-ThinkPad-T490
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
oid sha256:7bfce0bfd3f83d3c2cdb83f5ed9ea8b8b7a34b97ef6ca4a152ad0c0b1e7561cd
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
oid sha256:7bfce0bfd3f83d3c2cdb83f5ed9ea8b8b7a34b97ef6ca4a152ad0c0b1e7561cd
|
3 |
+
size 9032
|
preprocessor_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"apply_ocr": true,
|
3 |
+
"do_resize": true,
|
4 |
+
"image_processor_type": "LayoutLMv2ImageProcessor",
|
5 |
+
"ocr_lang": null,
|
6 |
+
"processor_class": "LayoutLMv2Processor",
|
7 |
+
"resample": 2,
|
8 |
+
"size": {
|
9 |
+
"height": 224,
|
10 |
+
"width": 224
|
11 |
+
},
|
12 |
+
"tesseract_config": ""
|
13 |
+
}
|
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 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"apply_ocr": false,
|
46 |
+
"clean_up_tokenization_spaces": false,
|
47 |
+
"cls_token": "[CLS]",
|
48 |
+
"cls_token_box": [
|
49 |
+
0,
|
50 |
+
0,
|
51 |
+
0,
|
52 |
+
0
|
53 |
+
],
|
54 |
+
"do_basic_tokenize": true,
|
55 |
+
"do_lower_case": true,
|
56 |
+
"extra_special_tokens": {},
|
57 |
+
"mask_token": "[MASK]",
|
58 |
+
"model_max_length": 512,
|
59 |
+
"never_split": null,
|
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": "LayoutLMv2Processor",
|
70 |
+
"sep_token": "[SEP]",
|
71 |
+
"sep_token_box": [
|
72 |
+
1000,
|
73 |
+
1000,
|
74 |
+
1000,
|
75 |
+
1000
|
76 |
+
],
|
77 |
+
"strip_accents": null,
|
78 |
+
"tokenize_chinese_chars": true,
|
79 |
+
"tokenizer_class": "LayoutLMv2Tokenizer",
|
80 |
+
"unk_token": "[UNK]"
|
81 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|