Hugging Face's logo

rogdevil
/
layoutlmv2-base-uncased_finetuned_docvqa

Document Question Answering
Transformers
TensorBoard
Safetensors
layoutlmv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
rogdevil commited on
Commit
ff7e498
·
verified ·
1 Parent(s): cbf6489

End of training

Browse files
Files changed (3) hide show
  1. README.md +146 -0
  2. model.safetensors +1 -1
  3. runs/Feb29_11-46-03_aryans-MacBook-Pro.local/events.out.tfevents.1709187760.aryans-MacBook-Pro.local.4915.0 +2 -2
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: 4.6788
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
+ | 5.3193 | 0.22 | 50 | 4.5453 |
50
+ | 4.5115 | 0.44 | 100 | 4.1632 |
51
+ | 4.1316 | 0.66 | 150 | 3.8496 |
52
+ | 3.7911 | 0.88 | 200 | 3.7418 |
53
+ | 3.5175 | 1.11 | 250 | 3.9454 |
54
+ | 3.2171 | 1.33 | 300 | 3.0430 |
55
+ | 3.0377 | 1.55 | 350 | 3.1317 |
56
+ | 3.1081 | 1.77 | 400 | 2.8709 |
57
+ | 2.6219 | 1.99 | 450 | 2.9745 |
58
+ | 2.2922 | 2.21 | 500 | 3.0184 |
59
+ | 2.2245 | 2.43 | 550 | 2.6649 |
60
+ | 2.0918 | 2.65 | 600 | 2.3156 |
61
+ | 2.0339 | 2.88 | 650 | 2.4970 |
62
+ | 1.7088 | 3.1 | 700 | 2.2817 |
63
+ | 1.4584 | 3.32 | 750 | 2.3237 |
64
+ | 1.4296 | 3.54 | 800 | 2.1868 |
65
+ | 1.4413 | 3.76 | 850 | 2.2775 |
66
+ | 1.4055 | 3.98 | 900 | 2.6660 |
67
+ | 1.0251 | 4.2 | 950 | 2.6155 |
68
+ | 1.1251 | 4.42 | 1000 | 2.9841 |
69
+ | 1.059 | 4.65 | 1050 | 2.7376 |
70
+ | 1.0179 | 4.87 | 1100 | 3.7345 |
71
+ | 1.1128 | 5.09 | 1150 | 2.6704 |
72
+ | 0.8461 | 5.31 | 1200 | 3.0422 |
73
+ | 0.86 | 5.53 | 1250 | 3.2093 |
74
+ | 0.9124 | 5.75 | 1300 | 3.2782 |
75
+ | 0.8687 | 5.97 | 1350 | 3.1477 |
76
+ | 0.7039 | 6.19 | 1400 | 2.6896 |
77
+ | 0.8908 | 6.42 | 1450 | 3.0843 |
78
+ | 0.7408 | 6.64 | 1500 | 2.9585 |
79
+ | 0.6026 | 6.86 | 1550 | 3.3629 |
80
+ | 0.4852 | 7.08 | 1600 | 3.1505 |
81
+ | 0.5496 | 7.3 | 1650 | 3.6285 |
82
+ | 0.5578 | 7.52 | 1700 | 3.3481 |
83
+ | 0.5897 | 7.74 | 1750 | 3.3201 |
84
+ | 0.4487 | 7.96 | 1800 | 3.1462 |
85
+ | 0.2182 | 8.19 | 1850 | 3.7251 |
86
+ | 0.3524 | 8.41 | 1900 | 3.5870 |
87
+ | 0.4516 | 8.63 | 1950 | 3.6300 |
88
+ | 0.5658 | 8.85 | 2000 | 3.1085 |
89
+ | 0.4877 | 9.07 | 2050 | 3.5353 |
90
+ | 0.2226 | 9.29 | 2100 | 3.6744 |
91
+ | 0.2544 | 9.51 | 2150 | 4.1244 |
92
+ | 0.6194 | 9.73 | 2200 | 3.4775 |
93
+ | 0.3759 | 9.96 | 2250 | 3.7031 |
94
+ | 0.2718 | 10.18 | 2300 | 3.6076 |
95
+ | 0.1322 | 10.4 | 2350 | 3.6885 |
96
+ | 0.2596 | 10.62 | 2400 | 3.9328 |
97
+ | 0.1675 | 10.84 | 2450 | 4.1439 |
98
+ | 0.158 | 11.06 | 2500 | 4.4306 |
99
+ | 0.1462 | 11.28 | 2550 | 4.3744 |
100
+ | 0.2187 | 11.5 | 2600 | 4.4111 |
101
+ | 0.264 | 11.73 | 2650 | 3.9780 |
102
+ | 0.1997 | 11.95 | 2700 | 4.2383 |
103
+ | 0.1369 | 12.17 | 2750 | 4.1329 |
104
+ | 0.1204 | 12.39 | 2800 | 4.2738 |
105
+ | 0.2001 | 12.61 | 2850 | 4.0106 |
106
+ | 0.2132 | 12.83 | 2900 | 4.1816 |
107
+ | 0.1472 | 13.05 | 2950 | 4.4600 |
108
+ | 0.0603 | 13.27 | 3000 | 4.0050 |
109
+ | 0.0911 | 13.5 | 3050 | 4.1838 |
110
+ | 0.1016 | 13.72 | 3100 | 4.4429 |
111
+ | 0.0887 | 13.94 | 3150 | 4.1510 |
112
+ | 0.0495 | 14.16 | 3200 | 4.2938 |
113
+ | 0.0677 | 14.38 | 3250 | 4.6133 |
114
+ | 0.1263 | 14.6 | 3300 | 4.4634 |
115
+ | 0.1953 | 14.82 | 3350 | 3.9348 |
116
+ | 0.0212 | 15.04 | 3400 | 4.1726 |
117
+ | 0.0082 | 15.27 | 3450 | 4.3512 |
118
+ | 0.0432 | 15.49 | 3500 | 4.2992 |
119
+ | 0.0975 | 15.71 | 3550 | 4.2274 |
120
+ | 0.0933 | 15.93 | 3600 | 4.4028 |
121
+ | 0.024 | 16.15 | 3650 | 4.4662 |
122
+ | 0.0964 | 16.37 | 3700 | 4.3964 |
123
+ | 0.0487 | 16.59 | 3750 | 4.4827 |
124
+ | 0.0147 | 16.81 | 3800 | 4.5577 |
125
+ | 0.0951 | 17.04 | 3850 | 4.5640 |
126
+ | 0.0508 | 17.26 | 3900 | 4.4473 |
127
+ | 0.1163 | 17.48 | 3950 | 4.4565 |
128
+ | 0.0151 | 17.7 | 4000 | 4.5511 |
129
+ | 0.0569 | 17.92 | 4050 | 4.5298 |
130
+ | 0.0639 | 18.14 | 4100 | 4.5417 |
131
+ | 0.0155 | 18.36 | 4150 | 4.6398 |
132
+ | 0.0107 | 18.58 | 4200 | 4.7664 |
133
+ | 0.0044 | 18.81 | 4250 | 4.8119 |
134
+ | 0.0906 | 19.03 | 4300 | 4.7168 |
135
+ | 0.0533 | 19.25 | 4350 | 4.7032 |
136
+ | 0.0496 | 19.47 | 4400 | 4.6918 |
137
+ | 0.0938 | 19.69 | 4450 | 4.6824 |
138
+ | 0.0483 | 19.91 | 4500 | 4.6788 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - Transformers 4.38.1
144
+ - Pytorch 2.2.1
145
+ - Datasets 2.17.1
146
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c0e2f456bcf8eb0b29037125704bbf182088c10f1a47ee3be24a78eaecf3f27
3
  size 802053752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6ab5918f02b4bd109dfe678b1385e7ca3af8b7642b73425388f8d3212ab8a6
3
  size 802053752
runs/Feb29_11-46-03_aryans-MacBook-Pro.local/events.out.tfevents.1709187760.aryans-MacBook-Pro.local.4915.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd981139d0a4486e5945187427ac42ae37552aae47188bf290d0f1403a36a520
3
- size 49080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:756c4457049e7676ed74bfef07d4032f0cde7c1154c39a2c66eb02950d80485e
3
+ size 50398