Hugging Face's logo

gagan3012
/
ViTGPT2_vizwiz

Image-to-Text
Transformers
PyTorch
vision-encoder-decoder
generated_from_trainer
Inference Endpoints
Model card Files Community
1
gagan3012 commited on
Commit
c4bfa83
•
1 Parent(s): 79301cf

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +99 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ model-index:
5
+ - name: ViTGPT2_vizwiz
6
+ results: []
7
+ ---
8
+
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ # ViTGPT2_vizwiz
13
+
14
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: 0.0719
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 2e-05
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - distributed_type: multi-GPU
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 3.0
43
+ - mixed_precision_training: Native AMP
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:-----:|:---------------:|
49
+ | 0.1207 | 0.07 | 1000 | 0.0906 |
50
+ | 0.0916 | 0.14 | 2000 | 0.0861 |
51
+ | 0.0879 | 0.2 | 3000 | 0.0840 |
52
+ | 0.0856 | 0.27 | 4000 | 0.0822 |
53
+ | 0.0834 | 0.34 | 5000 | 0.0806 |
54
+ | 0.0817 | 0.41 | 6000 | 0.0795 |
55
+ | 0.0812 | 0.48 | 7000 | 0.0785 |
56
+ | 0.0808 | 0.55 | 8000 | 0.0779 |
57
+ | 0.0796 | 0.61 | 9000 | 0.0771 |
58
+ | 0.0786 | 0.68 | 10000 | 0.0767 |
59
+ | 0.0774 | 0.75 | 11000 | 0.0762 |
60
+ | 0.0772 | 0.82 | 12000 | 0.0758 |
61
+ | 0.0756 | 0.89 | 13000 | 0.0754 |
62
+ | 0.0759 | 0.96 | 14000 | 0.0750 |
63
+ | 0.0756 | 1.02 | 15000 | 0.0748 |
64
+ | 0.0726 | 1.09 | 16000 | 0.0745 |
65
+ | 0.0727 | 1.16 | 17000 | 0.0745 |
66
+ | 0.0715 | 1.23 | 18000 | 0.0742 |
67
+ | 0.0726 | 1.3 | 19000 | 0.0741 |
68
+ | 0.072 | 1.37 | 20000 | 0.0738 |
69
+ | 0.0723 | 1.43 | 21000 | 0.0735 |
70
+ | 0.0715 | 1.5 | 22000 | 0.0734 |
71
+ | 0.0724 | 1.57 | 23000 | 0.0732 |
72
+ | 0.0723 | 1.64 | 24000 | 0.0730 |
73
+ | 0.0718 | 1.71 | 25000 | 0.0729 |
74
+ | 0.07 | 1.78 | 26000 | 0.0728 |
75
+ | 0.0702 | 1.84 | 27000 | 0.0726 |
76
+ | 0.0704 | 1.91 | 28000 | 0.0725 |
77
+ | 0.0703 | 1.98 | 29000 | 0.0725 |
78
+ | 0.0686 | 2.05 | 30000 | 0.0726 |
79
+ | 0.0687 | 2.12 | 31000 | 0.0726 |
80
+ | 0.0688 | 2.19 | 32000 | 0.0724 |
81
+ | 0.0677 | 2.25 | 33000 | 0.0724 |
82
+ | 0.0665 | 2.32 | 34000 | 0.0725 |
83
+ | 0.0684 | 2.39 | 35000 | 0.0723 |
84
+ | 0.0678 | 2.46 | 36000 | 0.0722 |
85
+ | 0.0686 | 2.53 | 37000 | 0.0722 |
86
+ | 0.067 | 2.59 | 38000 | 0.0721 |
87
+ | 0.0669 | 2.66 | 39000 | 0.0721 |
88
+ | 0.0673 | 2.73 | 40000 | 0.0721 |
89
+ | 0.0673 | 2.8 | 41000 | 0.0720 |
90
+ | 0.0662 | 2.87 | 42000 | 0.0720 |
91
+ | 0.0681 | 2.94 | 43000 | 0.0719 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.17.0.dev0
97
+ - Pytorch 1.10.2+cu102
98
+ - Datasets 1.18.2.dev0
99
+ - Tokenizers 0.11.0