End of training
Browse files- README.md +42 -11
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -5,9 +5,36 @@ tags:
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- generated
|
|
|
|
|
|
|
|
|
|
|
8 |
model-index:
|
9 |
- name: layoutlmv3-finetuned-invoice
|
10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -17,15 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the generated dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
-
|
21 |
-
-
|
22 |
-
-
|
23 |
-
-
|
24 |
-
-
|
25 |
-
- eval_runtime: 31.3704
|
26 |
-
- eval_samples_per_second: 1.594
|
27 |
-
- eval_steps_per_second: 1.594
|
28 |
-
- step: 0
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -50,7 +73,15 @@ The following hyperparameters were used during training:
|
|
50 |
- seed: 42
|
51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
- lr_scheduler_type: linear
|
53 |
-
- training_steps:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
### Framework versions
|
56 |
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- generated
|
8 |
+
metrics:
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
- f1
|
12 |
+
- accuracy
|
13 |
model-index:
|
14 |
- name: layoutlmv3-finetuned-invoice
|
15 |
+
results:
|
16 |
+
- task:
|
17 |
+
name: Token Classification
|
18 |
+
type: token-classification
|
19 |
+
dataset:
|
20 |
+
name: generated
|
21 |
+
type: generated
|
22 |
+
config: sroie
|
23 |
+
split: test
|
24 |
+
args: sroie
|
25 |
+
metrics:
|
26 |
+
- name: Precision
|
27 |
+
type: precision
|
28 |
+
value: 0.9698795180722891
|
29 |
+
- name: Recall
|
30 |
+
type: recall
|
31 |
+
value: 0.9797160243407708
|
32 |
+
- name: F1
|
33 |
+
type: f1
|
34 |
+
value: 0.9747729566094854
|
35 |
+
- name: Accuracy
|
36 |
+
type: accuracy
|
37 |
+
value: 0.9964187908152518
|
38 |
---
|
39 |
|
40 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
44 |
|
45 |
This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the generated dataset.
|
46 |
It achieves the following results on the evaluation set:
|
47 |
+
- Loss: 0.0826
|
48 |
+
- Precision: 0.9699
|
49 |
+
- Recall: 0.9797
|
50 |
+
- F1: 0.9748
|
51 |
+
- Accuracy: 0.9964
|
|
|
|
|
|
|
|
|
52 |
|
53 |
## Model description
|
54 |
|
|
|
73 |
- seed: 42
|
74 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
75 |
- lr_scheduler_type: linear
|
76 |
+
- training_steps: 200
|
77 |
+
|
78 |
+
### Training results
|
79 |
+
|
80 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
81 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
82 |
+
| No log | 1.0 | 100 | 0.1528 | 0.9478 | 0.9574 | 0.9526 | 0.9941 |
|
83 |
+
| No log | 2.0 | 200 | 0.0826 | 0.9699 | 0.9797 | 0.9748 | 0.9964 |
|
84 |
+
|
85 |
|
86 |
### Framework versions
|
87 |
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 503782186
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be3573a959b855b775c189d50991f7f19aa44d442cffa7a9f1476abae6aeff72
|
3 |
size 503782186
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48d2a3c3bfa588ae4642f096b664ec593035d119fcfad09527800082be604abb
|
3 |
size 4536
|