End of training
Browse files- README.md +146 -0
- pytorch_model.bin +1 -1
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: 5.3353
|
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 |
+
| 0.153 | 0.22 | 50 | 5.3909 |
|
50 |
+
| 0.2793 | 0.44 | 100 | 5.0150 |
|
51 |
+
| 0.2634 | 0.66 | 150 | 4.6620 |
|
52 |
+
| 0.5192 | 0.88 | 200 | 4.7826 |
|
53 |
+
| 0.3096 | 1.11 | 250 | 4.9532 |
|
54 |
+
| 0.2638 | 1.33 | 300 | 5.2584 |
|
55 |
+
| 0.4727 | 1.55 | 350 | 4.0943 |
|
56 |
+
| 0.2763 | 1.77 | 400 | 4.8408 |
|
57 |
+
| 1.0425 | 1.99 | 450 | 5.0344 |
|
58 |
+
| 0.4477 | 2.21 | 500 | 4.9084 |
|
59 |
+
| 0.3266 | 2.43 | 550 | 5.0996 |
|
60 |
+
| 0.3085 | 2.65 | 600 | 4.4858 |
|
61 |
+
| 0.4648 | 2.88 | 650 | 4.0630 |
|
62 |
+
| 0.1845 | 3.1 | 700 | 5.3969 |
|
63 |
+
| 0.1616 | 3.32 | 750 | 4.8225 |
|
64 |
+
| 0.1752 | 3.54 | 800 | 5.2945 |
|
65 |
+
| 0.1877 | 3.76 | 850 | 5.2358 |
|
66 |
+
| 0.3172 | 3.98 | 900 | 5.2205 |
|
67 |
+
| 0.1627 | 4.2 | 950 | 4.9991 |
|
68 |
+
| 0.2548 | 4.42 | 1000 | 4.6917 |
|
69 |
+
| 0.1566 | 4.65 | 1050 | 5.1266 |
|
70 |
+
| 0.2616 | 4.87 | 1100 | 4.3241 |
|
71 |
+
| 0.1199 | 5.09 | 1150 | 4.9821 |
|
72 |
+
| 0.1372 | 5.31 | 1200 | 5.0838 |
|
73 |
+
| 0.1198 | 5.53 | 1250 | 5.0156 |
|
74 |
+
| 0.0558 | 5.75 | 1300 | 4.8638 |
|
75 |
+
| 0.1331 | 5.97 | 1350 | 4.9492 |
|
76 |
+
| 0.0689 | 6.19 | 1400 | 4.6926 |
|
77 |
+
| 0.0912 | 6.42 | 1450 | 4.5153 |
|
78 |
+
| 0.0495 | 6.64 | 1500 | 4.6969 |
|
79 |
+
| 0.0853 | 6.86 | 1550 | 4.7690 |
|
80 |
+
| 0.1072 | 7.08 | 1600 | 4.6783 |
|
81 |
+
| 0.034 | 7.3 | 1650 | 4.7351 |
|
82 |
+
| 0.2999 | 7.52 | 1700 | 4.5185 |
|
83 |
+
| 0.0763 | 7.74 | 1750 | 4.5825 |
|
84 |
+
| 0.0799 | 7.96 | 1800 | 4.7218 |
|
85 |
+
| 0.0343 | 8.19 | 1850 | 5.1508 |
|
86 |
+
| 0.0396 | 8.41 | 1900 | 5.4893 |
|
87 |
+
| 0.033 | 8.63 | 1950 | 5.5167 |
|
88 |
+
| 0.0295 | 8.85 | 2000 | 5.6252 |
|
89 |
+
| 0.2303 | 9.07 | 2050 | 4.7031 |
|
90 |
+
| 0.088 | 9.29 | 2100 | 4.7323 |
|
91 |
+
| 0.0666 | 9.51 | 2150 | 4.8688 |
|
92 |
+
| 0.0597 | 9.73 | 2200 | 5.6007 |
|
93 |
+
| 0.0615 | 9.96 | 2250 | 5.5403 |
|
94 |
+
| 0.1003 | 10.18 | 2300 | 5.3198 |
|
95 |
+
| 0.0457 | 10.4 | 2350 | 5.4828 |
|
96 |
+
| 0.0391 | 10.62 | 2400 | 5.5312 |
|
97 |
+
| 0.0325 | 10.84 | 2450 | 5.7410 |
|
98 |
+
| 0.0147 | 11.06 | 2500 | 5.8749 |
|
99 |
+
| 0.1013 | 11.28 | 2550 | 5.6522 |
|
100 |
+
| 0.001 | 11.5 | 2600 | 5.7776 |
|
101 |
+
| 0.0002 | 11.73 | 2650 | 5.8431 |
|
102 |
+
| 0.03 | 11.95 | 2700 | 5.9751 |
|
103 |
+
| 0.0452 | 12.17 | 2750 | 5.6928 |
|
104 |
+
| 0.0002 | 12.39 | 2800 | 5.6264 |
|
105 |
+
| 0.0109 | 12.61 | 2850 | 5.2688 |
|
106 |
+
| 0.0801 | 12.83 | 2900 | 5.2780 |
|
107 |
+
| 0.0216 | 13.05 | 2950 | 5.3691 |
|
108 |
+
| 0.0002 | 13.27 | 3000 | 5.5237 |
|
109 |
+
| 0.0092 | 13.5 | 3050 | 5.3662 |
|
110 |
+
| 0.0124 | 13.72 | 3100 | 5.4474 |
|
111 |
+
| 0.0515 | 13.94 | 3150 | 5.3623 |
|
112 |
+
| 0.0032 | 14.16 | 3200 | 5.4168 |
|
113 |
+
| 0.0051 | 14.38 | 3250 | 5.2897 |
|
114 |
+
| 0.0002 | 14.6 | 3300 | 5.3205 |
|
115 |
+
| 0.014 | 14.82 | 3350 | 5.2114 |
|
116 |
+
| 0.0004 | 15.04 | 3400 | 5.2342 |
|
117 |
+
| 0.0104 | 15.27 | 3450 | 5.2562 |
|
118 |
+
| 0.0107 | 15.49 | 3500 | 5.1112 |
|
119 |
+
| 0.0002 | 15.71 | 3550 | 5.1515 |
|
120 |
+
| 0.0002 | 15.93 | 3600 | 5.2054 |
|
121 |
+
| 0.0002 | 16.15 | 3650 | 5.1968 |
|
122 |
+
| 0.0003 | 16.37 | 3700 | 5.3196 |
|
123 |
+
| 0.0246 | 16.59 | 3750 | 5.3111 |
|
124 |
+
| 0.0054 | 16.81 | 3800 | 5.3335 |
|
125 |
+
| 0.0001 | 17.04 | 3850 | 5.3488 |
|
126 |
+
| 0.0243 | 17.26 | 3900 | 5.2597 |
|
127 |
+
| 0.0217 | 17.48 | 3950 | 5.2834 |
|
128 |
+
| 0.0002 | 17.7 | 4000 | 5.2947 |
|
129 |
+
| 0.0002 | 17.92 | 4050 | 5.3131 |
|
130 |
+
| 0.0001 | 18.14 | 4100 | 5.3240 |
|
131 |
+
| 0.0016 | 18.36 | 4150 | 5.3129 |
|
132 |
+
| 0.0133 | 18.58 | 4200 | 5.3241 |
|
133 |
+
| 0.0002 | 18.81 | 4250 | 5.3382 |
|
134 |
+
| 0.0159 | 19.03 | 4300 | 5.3764 |
|
135 |
+
| 0.003 | 19.25 | 4350 | 5.3776 |
|
136 |
+
| 0.0516 | 19.47 | 4400 | 5.3389 |
|
137 |
+
| 0.016 | 19.69 | 4450 | 5.3275 |
|
138 |
+
| 0.0105 | 19.91 | 4500 | 5.3353 |
|
139 |
+
|
140 |
+
|
141 |
+
### Framework versions
|
142 |
+
|
143 |
+
- Transformers 4.33.2
|
144 |
+
- Pytorch 2.0.1+cpu
|
145 |
+
- Datasets 2.14.5
|
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 802204017
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf3be09d14a74ae6e90688e642d861dc03136620588de4e0a99f9678c35c507e
|
3 |
size 802204017
|