update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,143 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- imagefolder
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: vit-base-beans-demo-v5
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Image Classification
|
14 |
+
type: image-classification
|
15 |
+
dataset:
|
16 |
+
name: imagefolder
|
17 |
+
type: imagefolder
|
18 |
+
config: default
|
19 |
+
split: validation
|
20 |
+
args: default
|
21 |
+
metrics:
|
22 |
+
- name: Accuracy
|
23 |
+
type: accuracy
|
24 |
+
value: 0.46791907514450864
|
25 |
+
---
|
26 |
+
|
27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
28 |
+
should probably proofread and complete it, then remove this comment. -->
|
29 |
+
|
30 |
+
# vit-base-beans-demo-v5
|
31 |
+
|
32 |
+
This model is a fine-tuned version of [google/vit-large-patch16-224-in21k](https://huggingface.co/google/vit-large-patch16-224-in21k) on the imagefolder dataset.
|
33 |
+
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 2.6708
|
35 |
+
- Accuracy: 0.4679
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 0.0002
|
55 |
+
- train_batch_size: 16
|
56 |
+
- eval_batch_size: 8
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 4
|
61 |
+
- mixed_precision_training: Native AMP
|
62 |
+
|
63 |
+
### Training results
|
64 |
+
|
65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| 5.9636 | 0.06 | 100 | 5.7983 | 0.1 |
|
68 |
+
| 5.8053 | 0.11 | 200 | 5.8683 | 0.1110 |
|
69 |
+
| 5.9476 | 0.17 | 300 | 5.9242 | 0.1006 |
|
70 |
+
| 5.6866 | 0.23 | 400 | 5.6640 | 0.1110 |
|
71 |
+
| 5.5886 | 0.29 | 500 | 5.6032 | 0.1153 |
|
72 |
+
| 5.4108 | 0.34 | 600 | 5.5314 | 0.1179 |
|
73 |
+
| 5.4427 | 0.4 | 700 | 5.4592 | 0.1188 |
|
74 |
+
| 5.1333 | 0.46 | 800 | 5.3569 | 0.1272 |
|
75 |
+
| 5.2427 | 0.52 | 900 | 5.2451 | 0.1318 |
|
76 |
+
| 5.2185 | 0.57 | 1000 | 5.1948 | 0.1355 |
|
77 |
+
| 4.777 | 0.63 | 1100 | 5.1379 | 0.1361 |
|
78 |
+
| 5.2378 | 0.69 | 1200 | 5.1043 | 0.1347 |
|
79 |
+
| 5.2246 | 0.74 | 1300 | 5.0783 | 0.1419 |
|
80 |
+
| 4.9846 | 0.8 | 1400 | 5.0425 | 0.1390 |
|
81 |
+
| 5.2708 | 0.86 | 1500 | 5.0202 | 0.1387 |
|
82 |
+
| 4.9169 | 0.92 | 1600 | 4.9382 | 0.1526 |
|
83 |
+
| 4.8091 | 0.97 | 1700 | 4.8691 | 0.1497 |
|
84 |
+
| 4.8795 | 1.03 | 1800 | 4.8124 | 0.1546 |
|
85 |
+
| 4.6634 | 1.09 | 1900 | 4.7816 | 0.1601 |
|
86 |
+
| 4.4967 | 1.15 | 2000 | 4.7105 | 0.1618 |
|
87 |
+
| 4.8389 | 1.2 | 2100 | 4.7104 | 0.1671 |
|
88 |
+
| 4.5872 | 1.26 | 2200 | 4.6636 | 0.1607 |
|
89 |
+
| 4.7063 | 1.32 | 2300 | 4.6506 | 0.1584 |
|
90 |
+
| 4.5526 | 1.38 | 2400 | 4.5932 | 0.1743 |
|
91 |
+
| 4.4984 | 1.43 | 2500 | 4.5266 | 0.1792 |
|
92 |
+
| 4.2266 | 1.49 | 2600 | 4.4860 | 0.1850 |
|
93 |
+
| 4.5827 | 1.55 | 2700 | 4.4237 | 0.1844 |
|
94 |
+
| 3.9383 | 1.6 | 2800 | 4.3919 | 0.1887 |
|
95 |
+
| 4.5361 | 1.66 | 2900 | 4.3408 | 0.1971 |
|
96 |
+
| 4.5067 | 1.72 | 3000 | 4.2708 | 0.1965 |
|
97 |
+
| 4.3133 | 1.78 | 3100 | 4.2283 | 0.1997 |
|
98 |
+
| 4.4104 | 1.83 | 3200 | 4.1830 | 0.2061 |
|
99 |
+
| 3.965 | 1.89 | 3300 | 4.1360 | 0.2133 |
|
100 |
+
| 4.3425 | 1.95 | 3400 | 4.0754 | 0.2237 |
|
101 |
+
| 3.9526 | 2.01 | 3500 | 4.0885 | 0.2188 |
|
102 |
+
| 3.9037 | 2.06 | 3600 | 3.9629 | 0.2396 |
|
103 |
+
| 3.6883 | 2.12 | 3700 | 4.0130 | 0.2289 |
|
104 |
+
| 3.8445 | 2.18 | 3800 | 3.9220 | 0.2540 |
|
105 |
+
| 3.6093 | 2.23 | 3900 | 3.9453 | 0.2353 |
|
106 |
+
| 3.7109 | 2.29 | 4000 | 3.8822 | 0.2402 |
|
107 |
+
| 3.588 | 2.35 | 4100 | 3.7765 | 0.2679 |
|
108 |
+
| 3.4878 | 2.41 | 4200 | 3.7138 | 0.2821 |
|
109 |
+
| 3.8276 | 2.46 | 4300 | 3.7137 | 0.2694 |
|
110 |
+
| 3.7288 | 2.52 | 4400 | 3.6505 | 0.2821 |
|
111 |
+
| 3.4948 | 2.58 | 4500 | 3.6280 | 0.2835 |
|
112 |
+
| 3.3436 | 2.64 | 4600 | 3.5212 | 0.3145 |
|
113 |
+
| 3.3389 | 2.69 | 4700 | 3.5006 | 0.3208 |
|
114 |
+
| 3.4803 | 2.75 | 4800 | 3.4130 | 0.3361 |
|
115 |
+
| 3.3953 | 2.81 | 4900 | 3.3506 | 0.3370 |
|
116 |
+
| 3.3648 | 2.87 | 5000 | 3.3132 | 0.3462 |
|
117 |
+
| 3.1838 | 2.92 | 5100 | 3.2632 | 0.3543 |
|
118 |
+
| 3.1927 | 2.98 | 5200 | 3.2335 | 0.3613 |
|
119 |
+
| 2.8337 | 3.04 | 5300 | 3.1633 | 0.3760 |
|
120 |
+
| 2.6126 | 3.09 | 5400 | 3.1287 | 0.3803 |
|
121 |
+
| 2.7718 | 3.15 | 5500 | 3.0715 | 0.3876 |
|
122 |
+
| 2.7694 | 3.21 | 5600 | 3.0283 | 0.4040 |
|
123 |
+
| 2.7131 | 3.27 | 5700 | 2.9859 | 0.4040 |
|
124 |
+
| 2.6204 | 3.32 | 5800 | 2.9461 | 0.4078 |
|
125 |
+
| 2.4889 | 3.38 | 5900 | 2.9413 | 0.4081 |
|
126 |
+
| 2.5283 | 3.44 | 6000 | 2.9001 | 0.4147 |
|
127 |
+
| 2.6986 | 3.5 | 6100 | 2.8428 | 0.4335 |
|
128 |
+
| 2.8514 | 3.55 | 6200 | 2.8352 | 0.4399 |
|
129 |
+
| 2.2355 | 3.61 | 6300 | 2.7825 | 0.4462 |
|
130 |
+
| 2.4485 | 3.67 | 6400 | 2.7580 | 0.4535 |
|
131 |
+
| 2.3359 | 3.72 | 6500 | 2.7330 | 0.4549 |
|
132 |
+
| 2.5904 | 3.78 | 6600 | 2.7096 | 0.4613 |
|
133 |
+
| 2.5366 | 3.84 | 6700 | 2.6906 | 0.4642 |
|
134 |
+
| 2.3954 | 3.9 | 6800 | 2.6797 | 0.4691 |
|
135 |
+
| 2.3722 | 3.95 | 6900 | 2.6708 | 0.4679 |
|
136 |
+
|
137 |
+
|
138 |
+
### Framework versions
|
139 |
+
|
140 |
+
- Transformers 4.28.0
|
141 |
+
- Pytorch 2.2.1+cu121
|
142 |
+
- Datasets 2.19.1
|
143 |
+
- Tokenizers 0.13.3
|