prashantloni
commited on
Commit
•
7dd51d3
1
Parent(s):
d9d923f
End of training
Browse files- README.md +54 -0
- added_tokens.json +25 -0
- generation_config.json +8 -0
- preprocessor_config.json +26 -0
- runs/Apr17_09-26-46_635c5d5ce1bb/events.out.tfevents.1681723818.635c5d5ce1bb.1639.0 +2 -2
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +39 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- imagefolder
|
7 |
+
model-index:
|
8 |
+
- name: aadhaar_front
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# aadhaar_front
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset.
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 2e-05
|
37 |
+
- train_batch_size: 2
|
38 |
+
- eval_batch_size: 8
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 30
|
43 |
+
- mixed_precision_training: Native AMP
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.28.1
|
52 |
+
- Pytorch 2.0.0+cu118
|
53 |
+
- Datasets 2.11.0
|
54 |
+
- Tokenizers 0.13.3
|
added_tokens.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s_aadhaar_number>": 57538,
|
3 |
+
"</s_address>": 57542,
|
4 |
+
"</s_address_2>": 57536,
|
5 |
+
"</s_dob>": 57540,
|
6 |
+
"</s_doy>": 57534,
|
7 |
+
"</s_father_mother>": 57532,
|
8 |
+
"</s_gender>": 57530,
|
9 |
+
"</s_mobile_no>": 57528,
|
10 |
+
"</s_mother_name>": 57544,
|
11 |
+
"</s_name>": 57526,
|
12 |
+
"<s_aadhaar_number>": 57537,
|
13 |
+
"<s_address>": 57541,
|
14 |
+
"<s_address_2>": 57535,
|
15 |
+
"<s_dob>": 57539,
|
16 |
+
"<s_doy>": 57533,
|
17 |
+
"<s_father_mother>": 57531,
|
18 |
+
"<s_gender>": 57529,
|
19 |
+
"<s_iitcdip>": 57523,
|
20 |
+
"<s_mobile_no>": 57527,
|
21 |
+
"<s_mother_name>": 57543,
|
22 |
+
"<s_name>": 57525,
|
23 |
+
"<s_synthdog>": 57524,
|
24 |
+
"<sep/>": 57522
|
25 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"forced_eos_token_id": 2,
|
6 |
+
"pad_token_id": 1,
|
7 |
+
"transformers_version": "4.28.1"
|
8 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_align_long_axis": false,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pad": true,
|
5 |
+
"do_rescale": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"do_thumbnail": true,
|
8 |
+
"image_mean": [
|
9 |
+
0.5,
|
10 |
+
0.5,
|
11 |
+
0.5
|
12 |
+
],
|
13 |
+
"image_processor_type": "DonutImageProcessor",
|
14 |
+
"image_std": [
|
15 |
+
0.5,
|
16 |
+
0.5,
|
17 |
+
0.5
|
18 |
+
],
|
19 |
+
"processor_class": "DonutProcessor",
|
20 |
+
"resample": 2,
|
21 |
+
"rescale_factor": 0.00392156862745098,
|
22 |
+
"size": [
|
23 |
+
720,
|
24 |
+
960
|
25 |
+
]
|
26 |
+
}
|
runs/Apr17_09-26-46_635c5d5ce1bb/events.out.tfevents.1681723818.635c5d5ce1bb.1639.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d39925d08860cb965c73cc3066aebf56684a8ac417a9568dd9a3af512bd6a013
|
3 |
+
size 9030
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
|
3 |
+
size 1296245
|
special_tokens_map.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s_name>",
|
4 |
+
"</s_name>",
|
5 |
+
"<s_mobile_no>",
|
6 |
+
"</s_mobile_no>",
|
7 |
+
"<s_gender>",
|
8 |
+
"</s_gender>",
|
9 |
+
"<s_father_mother>",
|
10 |
+
"</s_father_mother>",
|
11 |
+
"<s_doy>",
|
12 |
+
"</s_doy>",
|
13 |
+
"<s_address_2>",
|
14 |
+
"</s_address_2>",
|
15 |
+
"<s_aadhaar_number>",
|
16 |
+
"</s_aadhaar_number>",
|
17 |
+
"<s_dob>",
|
18 |
+
"</s_dob>",
|
19 |
+
"<s_address>",
|
20 |
+
"</s_address>",
|
21 |
+
"<s_mother_name>",
|
22 |
+
"</s_mother_name>",
|
23 |
+
"<s>",
|
24 |
+
"</s>"
|
25 |
+
],
|
26 |
+
"bos_token": "<s>",
|
27 |
+
"cls_token": "<s>",
|
28 |
+
"eos_token": "</s>",
|
29 |
+
"mask_token": {
|
30 |
+
"content": "<mask>",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"pad_token": "<pad>",
|
37 |
+
"sep_token": "</s>",
|
38 |
+
"unk_token": "<unk>"
|
39 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"mask_token": {
|
7 |
+
"__type": "AddedToken",
|
8 |
+
"content": "<mask>",
|
9 |
+
"lstrip": true,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"model_max_length": 1000000000000000019884624838656,
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"processor_class": "DonutProcessor",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"sp_model_kwargs": {},
|
19 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
20 |
+
"unk_token": "<unk>"
|
21 |
+
}
|