Tatiana239
commited on
Commit
•
b262b52
1
Parent(s):
c6adc94
End of training
Browse files- README.md +77 -0
- logs/events.out.tfevents.1674192485.pc092u.2751622.0 +2 -2
- logs/events.out.tfevents.1674192502.pc092u.2751622.2 +3 -0
- merges.txt +0 -0
- preprocessor_config.json +26 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +86 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: lilt-ruroberta
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# lilt-ruroberta
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.7493
|
18 |
+
- Comment: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8}
|
19 |
+
- Date: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 23}
|
20 |
+
- Labname: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 18}
|
21 |
+
- Laboratory: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1}
|
22 |
+
- Measure: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5}
|
23 |
+
- Ref Value: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10}
|
24 |
+
- Result: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3}
|
25 |
+
- Overall Precision: 0.0
|
26 |
+
- Overall Recall: 0.0
|
27 |
+
- Overall F1: 0.0
|
28 |
+
- Overall Accuracy: 0.375
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 5e-05
|
48 |
+
- train_batch_size: 1
|
49 |
+
- eval_batch_size: 1
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- training_steps: 10
|
54 |
+
- mixed_precision_training: Native AMP
|
55 |
+
|
56 |
+
### Training results
|
57 |
+
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss | Comment | Date | Labname | Laboratory | Measure | Ref Value | Result | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|
59 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------:|:---------------------------------------------------------:|:----------------------------------------------------------:|:---------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
|
60 |
+
| 2.6158 | 0.5 | 1 | 2.6467 | {'precision': 0.06666666666666667, 'recall': 0.375, 'f1': 0.11320754716981134, 'number': 8} | {'precision': 0.13333333333333333, 'recall': 0.17391304347826086, 'f1': 0.15094339622641512, 'number': 23} | {'precision': 0.16666666666666666, 'recall': 0.1111111111111111, 'f1': 0.13333333333333333, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.0657 | 0.1324 | 0.0878 | 0.0375 |
|
61 |
+
| 2.6704 | 1.0 | 2 | 2.6467 | {'precision': 0.06666666666666667, 'recall': 0.375, 'f1': 0.11320754716981134, 'number': 8} | {'precision': 0.13333333333333333, 'recall': 0.17391304347826086, 'f1': 0.15094339622641512, 'number': 23} | {'precision': 0.16666666666666666, 'recall': 0.1111111111111111, 'f1': 0.13333333333333333, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.0657 | 0.1324 | 0.0878 | 0.0375 |
|
62 |
+
| 2.6164 | 1.5 | 3 | 2.6467 | {'precision': 0.06666666666666667, 'recall': 0.375, 'f1': 0.11320754716981134, 'number': 8} | {'precision': 0.13333333333333333, 'recall': 0.17391304347826086, 'f1': 0.15094339622641512, 'number': 23} | {'precision': 0.16666666666666666, 'recall': 0.1111111111111111, 'f1': 0.13333333333333333, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.0657 | 0.1324 | 0.0878 | 0.0375 |
|
63 |
+
| 2.6707 | 2.0 | 4 | 2.2168 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 23} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.0 | 0.0 | 0.0 | 0.375 |
|
64 |
+
| 1.8689 | 2.5 | 5 | 2.1469 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 23} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.0 | 0.0 | 0.0 | 0.375 |
|
65 |
+
| 2.1588 | 3.0 | 6 | 1.9684 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 23} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.0 | 0.0 | 0.0 | 0.375 |
|
66 |
+
| 1.0594 | 3.5 | 7 | 2.0123 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 23} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.0 | 0.0 | 0.0 | 0.375 |
|
67 |
+
| 2.0705 | 4.0 | 8 | 1.8896 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 23} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.0 | 0.0 | 0.0 | 0.375 |
|
68 |
+
| 1.9698 | 4.5 | 9 | 1.7493 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 23} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.0 | 0.0 | 0.0 | 0.375 |
|
69 |
+
| 0.8502 | 5.0 | 10 | 1.6972 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 8} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 23} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 18} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 1} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 5} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 10} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 3} | 0.0 | 0.0 | 0.0 | 0.375 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.25.1
|
75 |
+
- Pytorch 1.12.1
|
76 |
+
- Datasets 2.8.0
|
77 |
+
- Tokenizers 0.13.2
|
logs/events.out.tfevents.1674192485.pc092u.2751622.0
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 sha256:72d81ab550b41dd954a392633d7bc61595eb6c7f28134bbded76d026f2968a02
|
3 |
+
size 11258
|
logs/events.out.tfevents.1674192502.pc092u.2751622.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64dc8c4fcef726b4903eac288131c21cb8f2a9dc3d6811b01b2d2c81ce1fe028
|
3 |
+
size 535
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": true,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"cls_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"cls_token_box": [
|
20 |
+
0,
|
21 |
+
0,
|
22 |
+
0,
|
23 |
+
0
|
24 |
+
],
|
25 |
+
"eos_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "</s>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
},
|
33 |
+
"errors": "replace",
|
34 |
+
"mask_token": {
|
35 |
+
"__type": "AddedToken",
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false
|
41 |
+
},
|
42 |
+
"model_max_length": 512,
|
43 |
+
"name_or_path": "SCUT-DLVCLab/lilt-roberta-en-base",
|
44 |
+
"only_label_first_subword": true,
|
45 |
+
"pad_token": {
|
46 |
+
"__type": "AddedToken",
|
47 |
+
"content": "<pad>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false
|
52 |
+
},
|
53 |
+
"pad_token_box": [
|
54 |
+
0,
|
55 |
+
0,
|
56 |
+
0,
|
57 |
+
0
|
58 |
+
],
|
59 |
+
"pad_token_label": -100,
|
60 |
+
"processor_class": "LayoutLMv3Processor",
|
61 |
+
"sep_token": {
|
62 |
+
"__type": "AddedToken",
|
63 |
+
"content": "</s>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false
|
68 |
+
},
|
69 |
+
"sep_token_box": [
|
70 |
+
0,
|
71 |
+
0,
|
72 |
+
0,
|
73 |
+
0
|
74 |
+
],
|
75 |
+
"special_tokens_map_file": null,
|
76 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
77 |
+
"trim_offsets": true,
|
78 |
+
"unk_token": {
|
79 |
+
"__type": "AddedToken",
|
80 |
+
"content": "<unk>",
|
81 |
+
"lstrip": false,
|
82 |
+
"normalized": true,
|
83 |
+
"rstrip": false,
|
84 |
+
"single_word": false
|
85 |
+
}
|
86 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|