update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
model-index:
|
8 |
+
- name: exper6_mesum5
|
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 |
+
# exper6_mesum5
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.8805
|
20 |
+
- Accuracy: 0.8243
|
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: 0.0002
|
40 |
+
- train_batch_size: 16
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
+
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 16
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| 3.9276 | 0.23 | 100 | 3.8550 | 0.2089 |
|
53 |
+
| 3.0853 | 0.47 | 200 | 3.1106 | 0.3414 |
|
54 |
+
| 2.604 | 0.7 | 300 | 2.5732 | 0.4379 |
|
55 |
+
| 2.3183 | 0.93 | 400 | 2.2308 | 0.4882 |
|
56 |
+
| 1.5326 | 1.16 | 500 | 1.7903 | 0.5828 |
|
57 |
+
| 1.3367 | 1.4 | 600 | 1.5524 | 0.6349 |
|
58 |
+
| 1.1544 | 1.63 | 700 | 1.3167 | 0.6645 |
|
59 |
+
| 1.0788 | 1.86 | 800 | 1.3423 | 0.6385 |
|
60 |
+
| 0.6762 | 2.09 | 900 | 1.0780 | 0.7124 |
|
61 |
+
| 0.6483 | 2.33 | 1000 | 1.0090 | 0.7284 |
|
62 |
+
| 0.6321 | 2.56 | 1100 | 1.0861 | 0.7024 |
|
63 |
+
| 0.5558 | 2.79 | 1200 | 0.9933 | 0.7183 |
|
64 |
+
| 0.342 | 3.02 | 1300 | 0.8871 | 0.7462 |
|
65 |
+
| 0.2964 | 3.26 | 1400 | 0.9330 | 0.7408 |
|
66 |
+
| 0.1959 | 3.49 | 1500 | 0.9367 | 0.7343 |
|
67 |
+
| 0.368 | 3.72 | 1600 | 0.8472 | 0.7550 |
|
68 |
+
| 0.1821 | 3.95 | 1700 | 0.8937 | 0.7568 |
|
69 |
+
| 0.1851 | 4.19 | 1800 | 0.9546 | 0.7485 |
|
70 |
+
| 0.1648 | 4.42 | 1900 | 0.9790 | 0.7355 |
|
71 |
+
| 0.172 | 4.65 | 2000 | 0.8947 | 0.7627 |
|
72 |
+
| 0.0928 | 4.88 | 2100 | 1.0093 | 0.7462 |
|
73 |
+
| 0.0699 | 5.12 | 2200 | 0.8374 | 0.7639 |
|
74 |
+
| 0.0988 | 5.35 | 2300 | 0.9189 | 0.7645 |
|
75 |
+
| 0.0822 | 5.58 | 2400 | 0.9512 | 0.7580 |
|
76 |
+
| 0.1223 | 5.81 | 2500 | 1.0809 | 0.7349 |
|
77 |
+
| 0.0509 | 6.05 | 2600 | 0.9297 | 0.7769 |
|
78 |
+
| 0.0511 | 6.28 | 2700 | 0.8981 | 0.7822 |
|
79 |
+
| 0.0596 | 6.51 | 2800 | 0.9468 | 0.7704 |
|
80 |
+
| 0.0494 | 6.74 | 2900 | 0.9045 | 0.7870 |
|
81 |
+
| 0.0643 | 6.98 | 3000 | 1.1559 | 0.7391 |
|
82 |
+
| 0.0158 | 7.21 | 3100 | 0.8450 | 0.7899 |
|
83 |
+
| 0.0129 | 7.44 | 3200 | 0.8241 | 0.8036 |
|
84 |
+
| 0.0441 | 7.67 | 3300 | 0.9679 | 0.7751 |
|
85 |
+
| 0.0697 | 7.91 | 3400 | 1.0387 | 0.7751 |
|
86 |
+
| 0.0084 | 8.14 | 3500 | 0.9441 | 0.7947 |
|
87 |
+
| 0.0182 | 8.37 | 3600 | 0.8967 | 0.7994 |
|
88 |
+
| 0.0042 | 8.6 | 3700 | 0.8750 | 0.8041 |
|
89 |
+
| 0.0028 | 8.84 | 3800 | 0.9349 | 0.8041 |
|
90 |
+
| 0.0053 | 9.07 | 3900 | 0.9403 | 0.7982 |
|
91 |
+
| 0.0266 | 9.3 | 4000 | 0.9966 | 0.7959 |
|
92 |
+
| 0.0022 | 9.53 | 4100 | 0.9472 | 0.8018 |
|
93 |
+
| 0.0018 | 9.77 | 4200 | 0.8717 | 0.8136 |
|
94 |
+
| 0.0018 | 10.0 | 4300 | 0.8964 | 0.8083 |
|
95 |
+
| 0.0046 | 10.23 | 4400 | 0.8623 | 0.8160 |
|
96 |
+
| 0.0037 | 10.47 | 4500 | 0.8762 | 0.8172 |
|
97 |
+
| 0.0013 | 10.7 | 4600 | 0.9028 | 0.8142 |
|
98 |
+
| 0.0013 | 10.93 | 4700 | 0.9084 | 0.8178 |
|
99 |
+
| 0.0013 | 11.16 | 4800 | 0.8733 | 0.8213 |
|
100 |
+
| 0.001 | 11.4 | 4900 | 0.8823 | 0.8207 |
|
101 |
+
| 0.0009 | 11.63 | 5000 | 0.8769 | 0.8213 |
|
102 |
+
| 0.0282 | 11.86 | 5100 | 0.8791 | 0.8219 |
|
103 |
+
| 0.001 | 12.09 | 5200 | 0.8673 | 0.8249 |
|
104 |
+
| 0.0016 | 12.33 | 5300 | 0.8633 | 0.8225 |
|
105 |
+
| 0.0008 | 12.56 | 5400 | 0.8766 | 0.8195 |
|
106 |
+
| 0.0008 | 12.79 | 5500 | 0.8743 | 0.8225 |
|
107 |
+
| 0.0008 | 13.02 | 5600 | 0.8752 | 0.8231 |
|
108 |
+
| 0.0008 | 13.26 | 5700 | 0.8676 | 0.8237 |
|
109 |
+
| 0.0007 | 13.49 | 5800 | 0.8677 | 0.8237 |
|
110 |
+
| 0.0008 | 13.72 | 5900 | 0.8703 | 0.8237 |
|
111 |
+
| 0.0007 | 13.95 | 6000 | 0.8725 | 0.8237 |
|
112 |
+
| 0.0006 | 14.19 | 6100 | 0.8741 | 0.8231 |
|
113 |
+
| 0.0006 | 14.42 | 6200 | 0.8758 | 0.8237 |
|
114 |
+
| 0.0008 | 14.65 | 6300 | 0.8746 | 0.8243 |
|
115 |
+
| 0.0007 | 14.88 | 6400 | 0.8759 | 0.8243 |
|
116 |
+
| 0.0007 | 15.12 | 6500 | 0.8803 | 0.8231 |
|
117 |
+
| 0.0007 | 15.35 | 6600 | 0.8808 | 0.8237 |
|
118 |
+
| 0.0007 | 15.58 | 6700 | 0.8798 | 0.8243 |
|
119 |
+
| 0.0007 | 15.81 | 6800 | 0.8805 | 0.8243 |
|
120 |
+
|
121 |
+
|
122 |
+
### Framework versions
|
123 |
+
|
124 |
+
- Transformers 4.20.1
|
125 |
+
- Pytorch 1.12.0+cu113
|
126 |
+
- Datasets 2.3.2
|
127 |
+
- Tokenizers 0.12.1
|