Hugging Face's logo

rchan26
/
dit_base

Image Classification
Transformers
PyTorch
beit
Generated from Trainer
Inference Endpoints
Model card Files Community
2
rchan26 commited on
Commit
ac954ad
•
1 Parent(s): 0864dd5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +110 -0
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - accuracy
6
+ model-index:
7
+ - name: dit_base
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
+ # dit_base
15
+
16
+ This model is a fine-tuned version of [microsoft/dit-base](https://huggingface.co/microsoft/dit-base) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.4527
19
+ - Accuracy: 0.8190
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 16
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 64
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 50
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 0.89 | 6 | 1.7452 | 0.4095 |
54
+ | 1.8958 | 1.89 | 12 | 1.6185 | 0.4286 |
55
+ | 1.8958 | 2.89 | 18 | 1.4731 | 0.4857 |
56
+ | 1.8466 | 3.89 | 24 | 1.3459 | 0.5524 |
57
+ | 1.445 | 4.89 | 30 | 1.1766 | 0.5810 |
58
+ | 1.445 | 5.89 | 36 | 1.0902 | 0.6381 |
59
+ | 1.2077 | 6.89 | 42 | 0.9331 | 0.6762 |
60
+ | 1.2077 | 7.89 | 48 | 0.8431 | 0.6762 |
61
+ | 1.0254 | 8.89 | 54 | 0.8657 | 0.6857 |
62
+ | 0.8275 | 9.89 | 60 | 0.6801 | 0.7429 |
63
+ | 0.8275 | 10.89 | 66 | 0.6699 | 0.7810 |
64
+ | 0.8063 | 11.89 | 72 | 0.6296 | 0.7524 |
65
+ | 0.8063 | 12.89 | 78 | 0.5498 | 0.7905 |
66
+ | 0.7127 | 13.89 | 84 | 0.4974 | 0.8381 |
67
+ | 0.6356 | 14.89 | 90 | 0.6715 | 0.7619 |
68
+ | 0.6356 | 15.89 | 96 | 0.4602 | 0.8095 |
69
+ | 0.6438 | 16.89 | 102 | 0.4886 | 0.8095 |
70
+ | 0.6438 | 17.89 | 108 | 0.4332 | 0.8 |
71
+ | 0.5329 | 18.89 | 114 | 0.4197 | 0.8095 |
72
+ | 0.4932 | 19.89 | 120 | 0.4168 | 0.8190 |
73
+ | 0.4932 | 20.89 | 126 | 0.4691 | 0.8 |
74
+ | 0.4861 | 21.89 | 132 | 0.4263 | 0.8476 |
75
+ | 0.4861 | 22.89 | 138 | 0.4464 | 0.8190 |
76
+ | 0.4935 | 23.89 | 144 | 0.4857 | 0.7905 |
77
+ | 0.433 | 24.89 | 150 | 0.4873 | 0.7810 |
78
+ | 0.433 | 25.89 | 156 | 0.4641 | 0.8095 |
79
+ | 0.4289 | 26.89 | 162 | 0.5316 | 0.8 |
80
+ | 0.4289 | 27.89 | 168 | 0.3389 | 0.8571 |
81
+ | 0.4204 | 28.89 | 174 | 0.4272 | 0.8 |
82
+ | 0.3668 | 29.89 | 180 | 0.3493 | 0.8667 |
83
+ | 0.3668 | 30.89 | 186 | 0.3861 | 0.8571 |
84
+ | 0.4101 | 31.89 | 192 | 0.4216 | 0.8381 |
85
+ | 0.4101 | 32.89 | 198 | 0.4258 | 0.8190 |
86
+ | 0.3614 | 33.89 | 204 | 0.4409 | 0.8571 |
87
+ | 0.3267 | 34.89 | 210 | 0.4475 | 0.8190 |
88
+ | 0.3267 | 35.89 | 216 | 0.4316 | 0.8190 |
89
+ | 0.3423 | 36.89 | 222 | 0.4095 | 0.8381 |
90
+ | 0.3423 | 37.89 | 228 | 0.4671 | 0.8286 |
91
+ | 0.3325 | 38.89 | 234 | 0.3994 | 0.8286 |
92
+ | 0.3326 | 39.89 | 240 | 0.5004 | 0.8190 |
93
+ | 0.3326 | 40.89 | 246 | 0.4103 | 0.8381 |
94
+ | 0.2964 | 41.89 | 252 | 0.4469 | 0.8286 |
95
+ | 0.2964 | 42.89 | 258 | 0.4774 | 0.8286 |
96
+ | 0.3435 | 43.89 | 264 | 0.3843 | 0.8381 |
97
+ | 0.3146 | 44.89 | 270 | 0.3710 | 0.8667 |
98
+ | 0.3146 | 45.89 | 276 | 0.3392 | 0.8667 |
99
+ | 0.3168 | 46.89 | 282 | 0.3597 | 0.8667 |
100
+ | 0.3168 | 47.89 | 288 | 0.4143 | 0.8381 |
101
+ | 0.3081 | 48.89 | 294 | 0.3579 | 0.8571 |
102
+ | 0.3103 | 49.89 | 300 | 0.4527 | 0.8190 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - Transformers 4.25.1
108
+ - Pytorch 1.12.1
109
+ - Datasets 2.7.1
110
+ - Tokenizers 0.13.1