davelotito
commited on
End of training
Browse files- README.md +32 -5
- generation_config.json +0 -1
- model.safetensors +1 -1
- preprocessor_config.json +4 -4
- special_tokens_map.json +10 -70
- tokenizer.json +0 -0
- tokenizer_config.json +7 -0
README.md
CHANGED
@@ -1,10 +1,13 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- imagefolder
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: donut-base-sroie-test
|
10 |
results: []
|
@@ -15,7 +18,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# donut-base-sroie-test
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -35,16 +48,30 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 2e-05
|
38 |
-
- train_batch_size:
|
39 |
-
- eval_batch_size:
|
40 |
- seed: 42
|
|
|
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
-
- num_epochs:
|
44 |
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
|
49 |
|
50 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: davelotito/donut-base-sroie-test
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- bleu
|
10 |
+
- wer
|
11 |
model-index:
|
12 |
- name: donut-base-sroie-test
|
13 |
results: []
|
|
|
18 |
|
19 |
# donut-base-sroie-test
|
20 |
|
21 |
+
This model is a fine-tuned version of [davelotito/donut-base-sroie-test](https://huggingface.co/davelotito/donut-base-sroie-test) on the imagefolder dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3913
|
24 |
+
- Bleu: 0.0706
|
25 |
+
- Precisions: [0.8125, 0.7440860215053764, 0.7064676616915423, 0.6637168141592921]
|
26 |
+
- Brevity Penalty: 0.0968
|
27 |
+
- Length Ratio: 0.2998
|
28 |
+
- Translation Length: 528
|
29 |
+
- Reference Length: 1761
|
30 |
+
- Cer: 0.7448
|
31 |
+
- Wer: 0.8259
|
32 |
|
33 |
## Model description
|
34 |
|
|
|
48 |
|
49 |
The following hyperparameters were used during training:
|
50 |
- learning_rate: 2e-05
|
51 |
+
- train_batch_size: 4
|
52 |
+
- eval_batch_size: 4
|
53 |
- seed: 42
|
54 |
+
- gradient_accumulation_steps: 2
|
55 |
+
- total_train_batch_size: 8
|
56 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
57 |
- lr_scheduler_type: linear
|
58 |
+
- num_epochs: 10
|
59 |
- mixed_precision_training: Native AMP
|
60 |
|
61 |
### Training results
|
62 |
|
63 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Cer | Wer |
|
64 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:------:|
|
65 |
+
| No log | 0.99 | 62 | 0.5515 | 0.0638 | [0.7647058823529411, 0.6831896551724138, 0.6309226932668329, 0.5857988165680473] | 0.0962 | 0.2993 | 527 | 1761 | 0.7627 | 0.8549 |
|
66 |
+
| 0.5624 | 2.0 | 125 | 0.4773 | 0.0665 | [0.7763157894736842, 0.6865671641791045, 0.6403940886699507, 0.5918367346938775] | 0.0992 | 0.3021 | 532 | 1761 | 0.7562 | 0.8390 |
|
67 |
+
| 0.5624 | 2.99 | 187 | 0.4273 | 0.0658 | [0.7840909090909091, 0.6903225806451613, 0.6517412935323383, 0.6047197640117994] | 0.0968 | 0.2998 | 528 | 1761 | 0.7513 | 0.8373 |
|
68 |
+
| 0.2964 | 4.0 | 250 | 0.4007 | 0.0679 | [0.800376647834275, 0.7072649572649573, 0.6592592592592592, 0.6023391812865497] | 0.0986 | 0.3015 | 531 | 1761 | 0.7478 | 0.8286 |
|
69 |
+
| 0.2238 | 4.99 | 312 | 0.3965 | 0.0710 | [0.8142589118198874, 0.7297872340425532, 0.683046683046683, 0.6308139534883721] | 0.0999 | 0.3027 | 533 | 1761 | 0.7427 | 0.8271 |
|
70 |
+
| 0.2238 | 6.0 | 375 | 0.3939 | 0.0719 | [0.8301886792452831, 0.7537473233404711, 0.7054455445544554, 0.656891495601173] | 0.0980 | 0.3010 | 530 | 1761 | 0.7414 | 0.8246 |
|
71 |
+
| 0.147 | 6.99 | 437 | 0.3853 | 0.0693 | [0.8159392789373814, 0.7370689655172413, 0.6932668329177057, 0.6449704142011834] | 0.0962 | 0.2993 | 527 | 1761 | 0.7437 | 0.8237 |
|
72 |
+
| 0.1316 | 8.0 | 500 | 0.3827 | 0.0698 | [0.8037735849056604, 0.7301927194860813, 0.6856435643564357, 0.6392961876832844] | 0.0980 | 0.3010 | 530 | 1761 | 0.7456 | 0.8296 |
|
73 |
+
| 0.1316 | 8.99 | 562 | 0.3895 | 0.0704 | [0.8174904942965779, 0.7516198704103672, 0.715, 0.6706231454005934] | 0.0956 | 0.2987 | 526 | 1761 | 0.7439 | 0.8259 |
|
74 |
+
| 0.1153 | 9.92 | 620 | 0.3913 | 0.0706 | [0.8125, 0.7440860215053764, 0.7064676616915423, 0.6637168141592921] | 0.0968 | 0.2998 | 528 | 1761 | 0.7448 | 0.8259 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
generation_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 2,
|
5 |
"forced_eos_token_id": 2,
|
|
|
1 |
{
|
|
|
2 |
"bos_token_id": 0,
|
3 |
"eos_token_id": 2,
|
4 |
"forced_eos_token_id": 2,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 809103512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:048fac7623cc1510a16cd7a9ba640a2f288f8e8dd0084c2f4e9f058aa8eeabf7
|
3 |
size 809103512
|
preprocessor_config.json
CHANGED
@@ -37,8 +37,8 @@
|
|
37 |
"processor_class": "DonutProcessor",
|
38 |
"resample": 2,
|
39 |
"rescale_factor": 0.00392156862745098,
|
40 |
-
"size":
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
}
|
|
|
37 |
"processor_class": "DonutProcessor",
|
38 |
"resample": 2,
|
39 |
"rescale_factor": 0.00392156862745098,
|
40 |
+
"size": {
|
41 |
+
"height": 960,
|
42 |
+
"width": 720
|
43 |
+
}
|
44 |
}
|
special_tokens_map.json
CHANGED
@@ -1,75 +1,15 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
"normalized": false,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
},
|
17 |
-
{
|
18 |
-
"content": "<s_date>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
},
|
24 |
-
{
|
25 |
-
"content": "</s_date>",
|
26 |
-
"lstrip": false,
|
27 |
-
"normalized": false,
|
28 |
-
"rstrip": false,
|
29 |
-
"single_word": false
|
30 |
-
},
|
31 |
-
{
|
32 |
-
"content": "<s_company>",
|
33 |
-
"lstrip": false,
|
34 |
-
"normalized": false,
|
35 |
-
"rstrip": false,
|
36 |
-
"single_word": false
|
37 |
-
},
|
38 |
-
{
|
39 |
-
"content": "</s_company>",
|
40 |
-
"lstrip": false,
|
41 |
-
"normalized": false,
|
42 |
-
"rstrip": false,
|
43 |
-
"single_word": false
|
44 |
-
},
|
45 |
-
{
|
46 |
-
"content": "<s_address>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": false,
|
50 |
-
"single_word": false
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"content": "</s_address>",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false
|
58 |
-
},
|
59 |
-
{
|
60 |
-
"content": "<s>",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": false,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false
|
65 |
-
},
|
66 |
-
{
|
67 |
-
"content": "</s>",
|
68 |
-
"lstrip": false,
|
69 |
-
"normalized": false,
|
70 |
-
"rstrip": false,
|
71 |
-
"single_word": false
|
72 |
-
}
|
73 |
],
|
74 |
"bos_token": {
|
75 |
"content": "<s>",
|
|
|
1 |
{
|
2 |
"additional_special_tokens": [
|
3 |
+
"<s_total>",
|
4 |
+
"</s_total>",
|
5 |
+
"<s_date>",
|
6 |
+
"</s_date>",
|
7 |
+
"<s_company>",
|
8 |
+
"</s_company>",
|
9 |
+
"<s_address>",
|
10 |
+
"</s_address>",
|
11 |
+
"<s>",
|
12 |
+
"</s>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
],
|
14 |
"bos_token": {
|
15 |
"content": "<s>",
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -146,11 +146,18 @@
|
|
146 |
"cls_token": "<s>",
|
147 |
"eos_token": "</s>",
|
148 |
"mask_token": "<mask>",
|
|
|
149 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
150 |
"pad_token": "<pad>",
|
|
|
|
|
151 |
"processor_class": "DonutProcessor",
|
152 |
"sep_token": "</s>",
|
153 |
"sp_model_kwargs": {},
|
|
|
154 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
|
155 |
"unk_token": "<unk>"
|
156 |
}
|
|
|
146 |
"cls_token": "<s>",
|
147 |
"eos_token": "</s>",
|
148 |
"mask_token": "<mask>",
|
149 |
+
"max_length": 512,
|
150 |
"model_max_length": 1000000000000000019884624838656,
|
151 |
+
"pad_to_multiple_of": null,
|
152 |
"pad_token": "<pad>",
|
153 |
+
"pad_token_type_id": 0,
|
154 |
+
"padding_side": "right",
|
155 |
"processor_class": "DonutProcessor",
|
156 |
"sep_token": "</s>",
|
157 |
"sp_model_kwargs": {},
|
158 |
+
"stride": 0,
|
159 |
"tokenizer_class": "XLMRobertaTokenizer",
|
160 |
+
"truncation_side": "right",
|
161 |
+
"truncation_strategy": "longest_first",
|
162 |
"unk_token": "<unk>"
|
163 |
}
|