Hugging Face's logo

Fireworks12
/
git-base-pokemon

Image-to-Text
Transformers
PyTorch
TensorBoard
git
image-text-to-text
Generated from Trainer
vision
image-captioning
Inference Endpoints
Model card Files Metrics Community
2
Fireworks12 commited on
Commit
aa277b6
·
1 Parent(s): dd18d3c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +131 -0
README.md ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ model-index:
8
+ - name: git-base-pokemon
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # git-base-pokemon
16
+
17
+ This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the imagefolder dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1817
20
+ - Wer Score: 9.0938
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 1
41
+ - eval_batch_size: 1
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 2
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 50
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer Score |
52
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|
53
+ | 7.3974 | 0.7 | 50 | 4.5248 | 4.5234 |
54
+ | 2.2794 | 1.4 | 100 | 0.4021 | 5.1680 |
55
+ | 0.1697 | 2.1 | 150 | 0.1398 | 1.5039 |
56
+ | 0.0816 | 2.8 | 200 | 0.1458 | 9.9570 |
57
+ | 0.0556 | 3.5 | 250 | 0.1417 | 2.5234 |
58
+ | 0.043 | 4.2 | 300 | 0.1448 | 12.8086 |
59
+ | 0.0285 | 4.9 | 350 | 0.1469 | 7.3867 |
60
+ | 0.021 | 5.59 | 400 | 0.1505 | 13.0312 |
61
+ | 0.0205 | 6.29 | 450 | 0.1499 | 6.3281 |
62
+ | 0.0179 | 6.99 | 500 | 0.1527 | 13.0234 |
63
+ | 0.0157 | 7.69 | 550 | 0.1552 | 6.3047 |
64
+ | 0.015 | 8.39 | 600 | 0.1571 | 6.7656 |
65
+ | 0.015 | 9.09 | 650 | 0.1579 | 10.2305 |
66
+ | 0.0137 | 9.79 | 700 | 0.1585 | 11.4219 |
67
+ | 0.0132 | 10.49 | 750 | 0.1598 | 5.8320 |
68
+ | 0.0132 | 11.19 | 800 | 0.1591 | 12.0508 |
69
+ | 0.013 | 11.89 | 850 | 0.1612 | 7.9492 |
70
+ | 0.0117 | 12.59 | 900 | 0.1621 | 8.1758 |
71
+ | 0.0123 | 13.29 | 950 | 0.1632 | 12.9961 |
72
+ | 0.0125 | 13.99 | 1000 | 0.1613 | 10.2031 |
73
+ | 0.0116 | 14.69 | 1050 | 0.1642 | 5.7930 |
74
+ | 0.0112 | 15.38 | 1100 | 0.1636 | 6.1719 |
75
+ | 0.0112 | 16.08 | 1150 | 0.1652 | 7.2422 |
76
+ | 0.0107 | 16.78 | 1200 | 0.1644 | 12.9961 |
77
+ | 0.0108 | 17.48 | 1250 | 0.1661 | 5.0117 |
78
+ | 0.0109 | 18.18 | 1300 | 0.1658 | 7.3242 |
79
+ | 0.0108 | 18.88 | 1350 | 0.1691 | 6.0547 |
80
+ | 0.0101 | 19.58 | 1400 | 0.1690 | 6.9141 |
81
+ | 0.0103 | 20.28 | 1450 | 0.1692 | 7.1680 |
82
+ | 0.0107 | 20.98 | 1500 | 0.1702 | 12.3281 |
83
+ | 0.0099 | 21.68 | 1550 | 0.1708 | 10.75 |
84
+ | 0.0103 | 22.38 | 1600 | 0.1714 | 9.5586 |
85
+ | 0.0101 | 23.08 | 1650 | 0.1713 | 12.9805 |
86
+ | 0.0098 | 23.78 | 1700 | 0.1712 | 11.4883 |
87
+ | 0.0095 | 24.48 | 1750 | 0.1711 | 9.3320 |
88
+ | 0.0096 | 25.17 | 1800 | 0.1738 | 8.6523 |
89
+ | 0.0097 | 25.87 | 1850 | 0.1717 | 11.5078 |
90
+ | 0.0091 | 26.57 | 1900 | 0.1735 | 7.9570 |
91
+ | 0.0092 | 27.27 | 1950 | 0.1729 | 9.8242 |
92
+ | 0.0093 | 27.97 | 2000 | 0.1721 | 10.5078 |
93
+ | 0.0087 | 28.67 | 2050 | 0.1732 | 9.3906 |
94
+ | 0.009 | 29.37 | 2100 | 0.1760 | 8.0664 |
95
+ | 0.009 | 30.07 | 2150 | 0.1769 | 10.5312 |
96
+ | 0.0086 | 30.77 | 2200 | 0.1743 | 10.8555 |
97
+ | 0.0087 | 31.47 | 2250 | 0.1772 | 10.2188 |
98
+ | 0.0089 | 32.17 | 2300 | 0.1757 | 11.6016 |
99
+ | 0.0088 | 32.87 | 2350 | 0.1765 | 8.9297 |
100
+ | 0.0082 | 33.57 | 2400 | 0.1754 | 9.6484 |
101
+ | 0.0082 | 34.27 | 2450 | 0.1770 | 12.3711 |
102
+ | 0.0084 | 34.97 | 2500 | 0.1761 | 10.1523 |
103
+ | 0.0076 | 35.66 | 2550 | 0.1774 | 9.1055 |
104
+ | 0.0077 | 36.36 | 2600 | 0.1788 | 8.7852 |
105
+ | 0.0079 | 37.06 | 2650 | 0.1782 | 11.8086 |
106
+ | 0.0071 | 37.76 | 2700 | 0.1784 | 10.5234 |
107
+ | 0.0075 | 38.46 | 2750 | 0.1789 | 8.8828 |
108
+ | 0.0072 | 39.16 | 2800 | 0.1796 | 8.5664 |
109
+ | 0.0071 | 39.86 | 2850 | 0.1804 | 9.5391 |
110
+ | 0.0069 | 40.56 | 2900 | 0.1796 | 9.4062 |
111
+ | 0.0068 | 41.26 | 2950 | 0.1797 | 8.9883 |
112
+ | 0.0067 | 41.96 | 3000 | 0.1809 | 10.5273 |
113
+ | 0.0062 | 42.66 | 3050 | 0.1801 | 10.4531 |
114
+ | 0.0062 | 43.36 | 3100 | 0.1803 | 7.2188 |
115
+ | 0.0063 | 44.06 | 3150 | 0.1808 | 8.7930 |
116
+ | 0.0058 | 44.76 | 3200 | 0.1804 | 10.5156 |
117
+ | 0.0057 | 45.45 | 3250 | 0.1807 | 11.1328 |
118
+ | 0.0059 | 46.15 | 3300 | 0.1812 | 8.6875 |
119
+ | 0.0055 | 46.85 | 3350 | 0.1811 | 10.2773 |
120
+ | 0.0053 | 47.55 | 3400 | 0.1814 | 10.0391 |
121
+ | 0.0054 | 48.25 | 3450 | 0.1817 | 8.5391 |
122
+ | 0.0053 | 48.95 | 3500 | 0.1818 | 8.9688 |
123
+ | 0.005 | 49.65 | 3550 | 0.1817 | 9.0938 |
124
+
125
+
126
+ ### Framework versions
127
+
128
+ - Transformers 4.30.2
129
+ - Pytorch 2.0.1+cu118
130
+ - Datasets 2.13.1
131
+ - Tokenizers 0.13.3