update model card README.md
Browse files
README.md
CHANGED
@@ -3,7 +3,7 @@ license: cc-by-nc-sa-4.0
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
-
-
|
7 |
metrics:
|
8 |
- precision
|
9 |
- recall
|
@@ -16,24 +16,24 @@ model-index:
|
|
16 |
name: Token Classification
|
17 |
type: token-classification
|
18 |
dataset:
|
19 |
-
name:
|
20 |
-
type:
|
21 |
config: pasha
|
22 |
split: test
|
23 |
args: pasha
|
24 |
metrics:
|
25 |
- name: Precision
|
26 |
type: precision
|
27 |
-
value: 0.
|
28 |
- name: Recall
|
29 |
type: recall
|
30 |
-
value: 0.
|
31 |
- name: F1
|
32 |
type: f1
|
33 |
-
value: 0.
|
34 |
- name: Accuracy
|
35 |
type: accuracy
|
36 |
-
value: 0.
|
37 |
---
|
38 |
|
39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -41,13 +41,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
41 |
|
42 |
# pasha
|
43 |
|
44 |
-
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the
|
45 |
It achieves the following results on the evaluation set:
|
46 |
-
- Loss: 0.
|
47 |
-
- Precision: 0.
|
48 |
-
- Recall: 0.
|
49 |
- F1: 0.9869
|
50 |
-
- Accuracy: 0.
|
51 |
|
52 |
## Model description
|
53 |
|
@@ -78,16 +78,16 @@ The following hyperparameters were used during training:
|
|
78 |
|
79 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
80 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
81 |
-
| No log | 2.13 | 100 | 0.
|
82 |
-
| No log | 4.26 | 200 | 0.
|
83 |
-
| No log | 6.38 | 300 | 0.
|
84 |
-
| No log | 8.51 | 400 | 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
|
92 |
|
93 |
### Framework versions
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
+
- pasha
|
7 |
metrics:
|
8 |
- precision
|
9 |
- recall
|
|
|
16 |
name: Token Classification
|
17 |
type: token-classification
|
18 |
dataset:
|
19 |
+
name: pasha
|
20 |
+
type: pasha
|
21 |
config: pasha
|
22 |
split: test
|
23 |
args: pasha
|
24 |
metrics:
|
25 |
- name: Precision
|
26 |
type: precision
|
27 |
+
value: 0.984930032292788
|
28 |
- name: Recall
|
29 |
type: recall
|
30 |
+
value: 0.9888328530259366
|
31 |
- name: F1
|
32 |
type: f1
|
33 |
+
value: 0.9868775840373899
|
34 |
- name: Accuracy
|
35 |
type: accuracy
|
36 |
+
value: 0.990115718418515
|
37 |
---
|
38 |
|
39 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
41 |
|
42 |
# pasha
|
43 |
|
44 |
+
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the pasha dataset.
|
45 |
It achieves the following results on the evaluation set:
|
46 |
+
- Loss: 0.0571
|
47 |
+
- Precision: 0.9849
|
48 |
+
- Recall: 0.9888
|
49 |
- F1: 0.9869
|
50 |
+
- Accuracy: 0.9901
|
51 |
|
52 |
## Model description
|
53 |
|
|
|
78 |
|
79 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
80 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
81 |
+
| No log | 2.13 | 100 | 0.2664 | 0.9534 | 0.9438 | 0.9486 | 0.9571 |
|
82 |
+
| No log | 4.26 | 200 | 0.1044 | 0.9756 | 0.9802 | 0.9779 | 0.9838 |
|
83 |
+
| No log | 6.38 | 300 | 0.0672 | 0.9853 | 0.9899 | 0.9876 | 0.9904 |
|
84 |
+
| No log | 8.51 | 400 | 0.0634 | 0.9824 | 0.9860 | 0.9842 | 0.9884 |
|
85 |
+
| 0.2958 | 10.64 | 500 | 0.0585 | 0.9867 | 0.9892 | 0.9879 | 0.9906 |
|
86 |
+
| 0.2958 | 12.77 | 600 | 0.0511 | 0.9889 | 0.9928 | 0.9908 | 0.9928 |
|
87 |
+
| 0.2958 | 14.89 | 700 | 0.0503 | 0.9871 | 0.9921 | 0.9896 | 0.9925 |
|
88 |
+
| 0.2958 | 17.02 | 800 | 0.0529 | 0.9860 | 0.9903 | 0.9881 | 0.9913 |
|
89 |
+
| 0.2958 | 19.15 | 900 | 0.0581 | 0.9842 | 0.9892 | 0.9867 | 0.9904 |
|
90 |
+
| 0.0256 | 21.28 | 1000 | 0.0571 | 0.9849 | 0.9888 | 0.9869 | 0.9901 |
|
91 |
|
92 |
|
93 |
### Framework versions
|