hugginglaoda commited on
Commit
5aa9a8a
1 Parent(s): 7238124

End of training

Browse files
README.md ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: layoutlmv2-base-uncased_finetuned_docvqa
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # layoutlmv2-base-uncased_finetuned_docvqa
14
+
15
+ This model is a fine-tuned version of [microsoft/layoutlmv2-base-uncased](https://huggingface.co/microsoft/layoutlmv2-base-uncased) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 4.8430
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 4
38
+ - eval_batch_size: 8
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 20
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | 5.3379 | 0.22 | 50 | 4.6257 |
49
+ | 4.4305 | 0.44 | 100 | 4.2230 |
50
+ | 4.0588 | 0.66 | 150 | 3.9539 |
51
+ | 3.7822 | 0.88 | 200 | 3.7040 |
52
+ | 3.4957 | 1.11 | 250 | 3.4754 |
53
+ | 3.2417 | 1.33 | 300 | 3.1954 |
54
+ | 2.8607 | 1.55 | 350 | 2.8809 |
55
+ | 2.6602 | 1.77 | 400 | 2.9741 |
56
+ | 2.621 | 1.99 | 450 | 2.8658 |
57
+ | 2.1733 | 2.21 | 500 | 2.7248 |
58
+ | 2.106 | 2.43 | 550 | 2.4072 |
59
+ | 1.8389 | 2.65 | 600 | 2.4147 |
60
+ | 1.7862 | 2.88 | 650 | 2.2116 |
61
+ | 1.4224 | 3.1 | 700 | 2.4379 |
62
+ | 1.4773 | 3.32 | 750 | 2.4346 |
63
+ | 1.2225 | 3.54 | 800 | 2.5779 |
64
+ | 1.5368 | 3.76 | 850 | 2.4343 |
65
+ | 1.479 | 3.98 | 900 | 2.1432 |
66
+ | 0.7982 | 4.2 | 950 | 2.5897 |
67
+ | 0.8336 | 4.42 | 1000 | 2.8477 |
68
+ | 1.0647 | 4.65 | 1050 | 2.7111 |
69
+ | 0.8795 | 4.87 | 1100 | 2.5601 |
70
+ | 0.9265 | 5.09 | 1150 | 2.9547 |
71
+ | 0.7111 | 5.31 | 1200 | 3.1621 |
72
+ | 0.7244 | 5.53 | 1250 | 2.7862 |
73
+ | 0.9501 | 5.75 | 1300 | 2.4007 |
74
+ | 0.7424 | 5.97 | 1350 | 2.9918 |
75
+ | 0.4422 | 6.19 | 1400 | 3.5247 |
76
+ | 0.5952 | 6.42 | 1450 | 2.8743 |
77
+ | 0.7173 | 6.64 | 1500 | 2.7440 |
78
+ | 0.6311 | 6.86 | 1550 | 2.9658 |
79
+ | 0.393 | 7.08 | 1600 | 3.0994 |
80
+ | 0.3655 | 7.3 | 1650 | 3.3074 |
81
+ | 0.3432 | 7.52 | 1700 | 3.1921 |
82
+ | 0.5986 | 7.74 | 1750 | 3.3517 |
83
+ | 0.5456 | 7.96 | 1800 | 3.1552 |
84
+ | 0.565 | 8.19 | 1850 | 2.9922 |
85
+ | 0.3902 | 8.41 | 1900 | 3.6814 |
86
+ | 0.3408 | 8.63 | 1950 | 3.2820 |
87
+ | 0.241 | 8.85 | 2000 | 3.5644 |
88
+ | 0.3172 | 9.07 | 2050 | 3.4752 |
89
+ | 0.294 | 9.29 | 2100 | 3.7023 |
90
+ | 0.2993 | 9.51 | 2150 | 3.5031 |
91
+ | 0.0928 | 9.73 | 2200 | 4.0305 |
92
+ | 0.4598 | 9.96 | 2250 | 3.4260 |
93
+ | 0.2795 | 10.18 | 2300 | 3.2730 |
94
+ | 0.0887 | 10.4 | 2350 | 3.7174 |
95
+ | 0.3682 | 10.62 | 2400 | 3.4060 |
96
+ | 0.1924 | 10.84 | 2450 | 4.1368 |
97
+ | 0.1825 | 11.06 | 2500 | 4.1640 |
98
+ | 0.1987 | 11.28 | 2550 | 3.9908 |
99
+ | 0.0875 | 11.5 | 2600 | 4.1872 |
100
+ | 0.1719 | 11.73 | 2650 | 3.9948 |
101
+ | 0.2844 | 11.95 | 2700 | 4.1731 |
102
+ | 0.1085 | 12.17 | 2750 | 3.9568 |
103
+ | 0.1496 | 12.39 | 2800 | 3.9272 |
104
+ | 0.0701 | 12.61 | 2850 | 4.2957 |
105
+ | 0.1617 | 12.83 | 2900 | 4.2806 |
106
+ | 0.0934 | 13.05 | 2950 | 4.3200 |
107
+ | 0.0405 | 13.27 | 3000 | 4.1869 |
108
+ | 0.0898 | 13.5 | 3050 | 4.1207 |
109
+ | 0.189 | 13.72 | 3100 | 4.4437 |
110
+ | 0.0798 | 13.94 | 3150 | 4.6480 |
111
+ | 0.1199 | 14.16 | 3200 | 4.4105 |
112
+ | 0.0922 | 14.38 | 3250 | 4.4321 |
113
+ | 0.1556 | 14.6 | 3300 | 4.3353 |
114
+ | 0.1933 | 14.82 | 3350 | 4.0635 |
115
+ | 0.0164 | 15.04 | 3400 | 4.1792 |
116
+ | 0.064 | 15.27 | 3450 | 4.2202 |
117
+ | 0.0914 | 15.49 | 3500 | 4.2382 |
118
+ | 0.0287 | 15.71 | 3550 | 4.4255 |
119
+ | 0.1054 | 15.93 | 3600 | 4.5788 |
120
+ | 0.0306 | 16.15 | 3650 | 4.7566 |
121
+ | 0.0297 | 16.37 | 3700 | 4.6610 |
122
+ | 0.0529 | 16.59 | 3750 | 4.6494 |
123
+ | 0.0729 | 16.81 | 3800 | 4.6314 |
124
+ | 0.0388 | 17.04 | 3850 | 4.6675 |
125
+ | 0.0207 | 17.26 | 3900 | 4.7816 |
126
+ | 0.0889 | 17.48 | 3950 | 4.6941 |
127
+ | 0.0058 | 17.7 | 4000 | 4.6818 |
128
+ | 0.0068 | 17.92 | 4050 | 4.7755 |
129
+ | 0.0222 | 18.14 | 4100 | 4.7658 |
130
+ | 0.1152 | 18.36 | 4150 | 4.8247 |
131
+ | 0.0181 | 18.58 | 4200 | 4.8290 |
132
+ | 0.0349 | 18.81 | 4250 | 4.7989 |
133
+ | 0.0165 | 19.03 | 4300 | 4.8208 |
134
+ | 0.029 | 19.25 | 4350 | 4.8401 |
135
+ | 0.0073 | 19.47 | 4400 | 4.8544 |
136
+ | 0.0277 | 19.69 | 4450 | 4.8356 |
137
+ | 0.0164 | 19.91 | 4500 | 4.8430 |
138
+
139
+
140
+ ### Framework versions
141
+
142
+ - Transformers 4.27.4
143
+ - Pytorch 2.0.0+cu117
144
+ - Datasets 2.11.0
145
+ - Tokenizers 0.13.2
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5028e34264ff08981680d20f2934a6fb2d3dc106846f2c7fad59e619dcfe323
3
  size 802219069
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f20202b0040091ff42ed41f3269223f0660b6e4d6140473ae3b66accc735638
3
  size 802219069
runs/Apr02_10-52-51_4439cc648e9b/events.out.tfevents.1680432786.4439cc648e9b.92.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9721d71cf3c0d46c4e56724e505d275b46d275cc075e493017ea0a1b12e27c7
3
- size 43669
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcb59c95cc545d951b38b697c24bbcb20773d04787ea03fba85e60d5d235158b
3
+ size 44879