Shwetang270899
commited on
Commit
•
afdec59
1
Parent(s):
2b7ff99
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,146 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
base_model: microsoft/layoutlmv2-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: layoutlmv2-base-uncased_finetuned_docvqa
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# layoutlmv2-base-uncased_finetuned_docvqa
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 4.5570
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 5e-05
|
38 |
+
- train_batch_size: 4
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 20
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 5.2892 | 0.22 | 50 | 4.6213 |
|
50 |
+
| 4.4958 | 0.44 | 100 | 4.1766 |
|
51 |
+
| 4.1602 | 0.66 | 150 | 3.8565 |
|
52 |
+
| 3.9538 | 0.88 | 200 | 3.5805 |
|
53 |
+
| 3.5903 | 1.11 | 250 | 3.4594 |
|
54 |
+
| 3.1555 | 1.33 | 300 | 3.1305 |
|
55 |
+
| 3.0041 | 1.55 | 350 | 2.9394 |
|
56 |
+
| 2.8133 | 1.77 | 400 | 2.7611 |
|
57 |
+
| 2.5517 | 1.99 | 450 | 2.6359 |
|
58 |
+
| 1.9883 | 2.21 | 500 | 2.6822 |
|
59 |
+
| 2.1057 | 2.43 | 550 | 2.4430 |
|
60 |
+
| 2.0872 | 2.65 | 600 | 2.4388 |
|
61 |
+
| 1.7591 | 2.88 | 650 | 2.3726 |
|
62 |
+
| 1.5244 | 3.1 | 700 | 2.3325 |
|
63 |
+
| 1.5257 | 3.32 | 750 | 2.7668 |
|
64 |
+
| 1.3295 | 3.54 | 800 | 2.2800 |
|
65 |
+
| 1.3167 | 3.76 | 850 | 2.3108 |
|
66 |
+
| 1.2051 | 3.98 | 900 | 2.6429 |
|
67 |
+
| 1.0532 | 4.2 | 950 | 3.1483 |
|
68 |
+
| 1.0167 | 4.42 | 1000 | 2.2237 |
|
69 |
+
| 1.1105 | 4.65 | 1050 | 2.3531 |
|
70 |
+
| 1.006 | 4.87 | 1100 | 2.8026 |
|
71 |
+
| 0.8193 | 5.09 | 1150 | 3.0897 |
|
72 |
+
| 0.7502 | 5.31 | 1200 | 3.5147 |
|
73 |
+
| 0.9308 | 5.53 | 1250 | 2.5877 |
|
74 |
+
| 0.6495 | 5.75 | 1300 | 2.8749 |
|
75 |
+
| 0.7933 | 5.97 | 1350 | 2.7216 |
|
76 |
+
| 0.7199 | 6.19 | 1400 | 3.1257 |
|
77 |
+
| 0.5458 | 6.42 | 1450 | 3.5710 |
|
78 |
+
| 0.7406 | 6.64 | 1500 | 2.5855 |
|
79 |
+
| 0.5537 | 6.86 | 1550 | 2.9661 |
|
80 |
+
| 0.493 | 7.08 | 1600 | 3.3691 |
|
81 |
+
| 0.4938 | 7.3 | 1650 | 3.1937 |
|
82 |
+
| 0.5407 | 7.52 | 1700 | 3.3585 |
|
83 |
+
| 0.5243 | 7.74 | 1750 | 2.7650 |
|
84 |
+
| 0.4177 | 7.96 | 1800 | 3.2618 |
|
85 |
+
| 0.4094 | 8.19 | 1850 | 3.2418 |
|
86 |
+
| 0.4061 | 8.41 | 1900 | 3.2710 |
|
87 |
+
| 0.3248 | 8.63 | 1950 | 3.3732 |
|
88 |
+
| 0.3787 | 8.85 | 2000 | 3.3467 |
|
89 |
+
| 0.2709 | 9.07 | 2050 | 3.1261 |
|
90 |
+
| 0.2655 | 9.29 | 2100 | 3.4552 |
|
91 |
+
| 0.2552 | 9.51 | 2150 | 3.4344 |
|
92 |
+
| 0.3321 | 9.73 | 2200 | 3.5558 |
|
93 |
+
| 0.4165 | 9.96 | 2250 | 3.0775 |
|
94 |
+
| 0.2052 | 10.18 | 2300 | 3.4985 |
|
95 |
+
| 0.2642 | 10.4 | 2350 | 3.8930 |
|
96 |
+
| 0.2461 | 10.62 | 2400 | 3.7029 |
|
97 |
+
| 0.2895 | 10.84 | 2450 | 3.4143 |
|
98 |
+
| 0.1041 | 11.06 | 2500 | 3.6652 |
|
99 |
+
| 0.1316 | 11.28 | 2550 | 3.8867 |
|
100 |
+
| 0.1165 | 11.5 | 2600 | 4.1669 |
|
101 |
+
| 0.1925 | 11.73 | 2650 | 4.3376 |
|
102 |
+
| 0.371 | 11.95 | 2700 | 3.9125 |
|
103 |
+
| 0.1793 | 12.17 | 2750 | 4.0051 |
|
104 |
+
| 0.1771 | 12.39 | 2800 | 3.8161 |
|
105 |
+
| 0.2158 | 12.61 | 2850 | 3.8786 |
|
106 |
+
| 0.1838 | 12.83 | 2900 | 3.7687 |
|
107 |
+
| 0.1364 | 13.05 | 2950 | 4.1103 |
|
108 |
+
| 0.0364 | 13.27 | 3000 | 4.1468 |
|
109 |
+
| 0.2488 | 13.5 | 3050 | 4.1149 |
|
110 |
+
| 0.1046 | 13.72 | 3100 | 4.1887 |
|
111 |
+
| 0.1254 | 13.94 | 3150 | 4.0097 |
|
112 |
+
| 0.033 | 14.16 | 3200 | 4.3023 |
|
113 |
+
| 0.0373 | 14.38 | 3250 | 4.3530 |
|
114 |
+
| 0.0911 | 14.6 | 3300 | 4.2621 |
|
115 |
+
| 0.1014 | 14.82 | 3350 | 3.8815 |
|
116 |
+
| 0.0238 | 15.04 | 3400 | 4.4097 |
|
117 |
+
| 0.1141 | 15.27 | 3450 | 4.4720 |
|
118 |
+
| 0.0278 | 15.49 | 3500 | 4.4407 |
|
119 |
+
| 0.0673 | 15.71 | 3550 | 4.4176 |
|
120 |
+
| 0.0691 | 15.93 | 3600 | 4.4863 |
|
121 |
+
| 0.0379 | 16.15 | 3650 | 4.6924 |
|
122 |
+
| 0.057 | 16.37 | 3700 | 4.5305 |
|
123 |
+
| 0.1087 | 16.59 | 3750 | 4.5050 |
|
124 |
+
| 0.0047 | 16.81 | 3800 | 4.5652 |
|
125 |
+
| 0.051 | 17.04 | 3850 | 4.5482 |
|
126 |
+
| 0.0054 | 17.26 | 3900 | 4.5337 |
|
127 |
+
| 0.0542 | 17.48 | 3950 | 4.5370 |
|
128 |
+
| 0.0132 | 17.7 | 4000 | 4.4744 |
|
129 |
+
| 0.0698 | 17.92 | 4050 | 4.4535 |
|
130 |
+
| 0.0214 | 18.14 | 4100 | 4.4660 |
|
131 |
+
| 0.033 | 18.36 | 4150 | 4.4818 |
|
132 |
+
| 0.029 | 18.58 | 4200 | 4.5033 |
|
133 |
+
| 0.0283 | 18.81 | 4250 | 4.4825 |
|
134 |
+
| 0.013 | 19.03 | 4300 | 4.4794 |
|
135 |
+
| 0.0538 | 19.25 | 4350 | 4.5183 |
|
136 |
+
| 0.0171 | 19.47 | 4400 | 4.5373 |
|
137 |
+
| 0.0122 | 19.69 | 4450 | 4.5501 |
|
138 |
+
| 0.0222 | 19.91 | 4500 | 4.5570 |
|
139 |
+
|
140 |
+
|
141 |
+
### Framework versions
|
142 |
+
|
143 |
+
- Transformers 4.31.0
|
144 |
+
- Pytorch 2.0.1+cu118
|
145 |
+
- Datasets 2.14.4
|
146 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 802214001
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da9f5712da617a09848f88a4ffc35694ff48d52359d0439187202ba29dadc20f
|
3 |
size 802214001
|
runs/Aug14_19-19-30_c7eddaa25bde/events.out.tfevents.1692041074.c7eddaa25bde.44492.0
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 sha256:2d857b0fe3dba5ad6901d8bd1bf3df442ba8442c88c077ed5a6f20c3b5e5b703
|
3 |
+
size 45011
|