End of training
Browse files- README.md +114 -17
- model.safetensors +1 -1
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
license:
|
4 |
-
base_model:
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# my_awesome_food_model
|
18 |
|
19 |
-
This model is a fine-tuned version of [
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss:
|
22 |
-
- Accuracy: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -39,28 +39,125 @@ More information needed
|
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
- learning_rate: 5e-05
|
42 |
-
- train_batch_size:
|
43 |
-
- eval_batch_size:
|
44 |
- seed: 42
|
45 |
- gradient_accumulation_steps: 4
|
46 |
-
- total_train_batch_size:
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
- lr_scheduler_warmup_ratio: 0.1
|
50 |
-
- num_epochs:
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss | Epoch
|
55 |
-
|
56 |
-
|
|
57 |
-
|
|
58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
-
- Transformers 4.
|
64 |
-
- Pytorch 2.4.
|
65 |
- Datasets 3.0.1
|
66 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
license: other
|
4 |
+
base_model: apple/mobilevit-small
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
|
|
16 |
|
17 |
# my_awesome_food_model
|
18 |
|
19 |
+
This model is a fine-tuned version of [apple/mobilevit-small](https://huggingface.co/apple/mobilevit-small) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.4411
|
22 |
+
- Accuracy: 0.86
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
- learning_rate: 5e-05
|
42 |
+
- train_batch_size: 32
|
43 |
+
- eval_batch_size: 32
|
44 |
- seed: 42
|
45 |
- gradient_accumulation_steps: 4
|
46 |
+
- total_train_batch_size: 128
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: linear
|
49 |
- lr_scheduler_warmup_ratio: 0.1
|
50 |
+
- num_epochs: 100
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
55 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
56 |
+
| 4.2774 | 0.992 | 31 | 4.2776 | 0.563 |
|
57 |
+
| 4.2309 | 1.984 | 62 | 4.2272 | 0.616 |
|
58 |
+
| 4.1622 | 2.976 | 93 | 4.1229 | 0.646 |
|
59 |
+
| 4.045 | 4.0 | 125 | 3.9633 | 0.663 |
|
60 |
+
| 3.87 | 4.992 | 156 | 3.7407 | 0.68 |
|
61 |
+
| 3.6564 | 5.984 | 187 | 3.5054 | 0.694 |
|
62 |
+
| 3.4188 | 6.976 | 218 | 3.1871 | 0.681 |
|
63 |
+
| 3.0118 | 8.0 | 250 | 2.8682 | 0.682 |
|
64 |
+
| 2.6634 | 8.992 | 281 | 2.5058 | 0.668 |
|
65 |
+
| 2.3342 | 9.984 | 312 | 2.1583 | 0.687 |
|
66 |
+
| 2.0751 | 10.9760 | 343 | 1.8516 | 0.708 |
|
67 |
+
| 1.8887 | 12.0 | 375 | 1.6293 | 0.737 |
|
68 |
+
| 1.7637 | 12.992 | 406 | 1.5026 | 0.733 |
|
69 |
+
| 1.6451 | 13.984 | 437 | 1.3837 | 0.745 |
|
70 |
+
| 1.4845 | 14.9760 | 468 | 1.2238 | 0.765 |
|
71 |
+
| 1.3586 | 16.0 | 500 | 1.1391 | 0.775 |
|
72 |
+
| 1.2649 | 16.992 | 531 | 0.9872 | 0.784 |
|
73 |
+
| 1.1469 | 17.984 | 562 | 0.9524 | 0.77 |
|
74 |
+
| 1.0319 | 18.976 | 593 | 0.8425 | 0.797 |
|
75 |
+
| 0.9926 | 20.0 | 625 | 0.8079 | 0.791 |
|
76 |
+
| 0.9592 | 20.992 | 656 | 0.7261 | 0.808 |
|
77 |
+
| 0.8481 | 21.984 | 687 | 0.7273 | 0.799 |
|
78 |
+
| 0.8027 | 22.976 | 718 | 0.6501 | 0.807 |
|
79 |
+
| 0.8258 | 24.0 | 750 | 0.6499 | 0.818 |
|
80 |
+
| 0.7785 | 24.992 | 781 | 0.6178 | 0.83 |
|
81 |
+
| 0.7881 | 25.984 | 812 | 0.6305 | 0.827 |
|
82 |
+
| 0.7034 | 26.976 | 843 | 0.6201 | 0.829 |
|
83 |
+
| 0.705 | 28.0 | 875 | 0.5611 | 0.842 |
|
84 |
+
| 0.6981 | 28.992 | 906 | 0.5357 | 0.846 |
|
85 |
+
| 0.675 | 29.984 | 937 | 0.5622 | 0.844 |
|
86 |
+
| 0.6339 | 30.976 | 968 | 0.5188 | 0.847 |
|
87 |
+
| 0.611 | 32.0 | 1000 | 0.4712 | 0.879 |
|
88 |
+
| 0.6036 | 32.992 | 1031 | 0.5218 | 0.847 |
|
89 |
+
| 0.5909 | 33.984 | 1062 | 0.5201 | 0.84 |
|
90 |
+
| 0.5695 | 34.976 | 1093 | 0.4935 | 0.854 |
|
91 |
+
| 0.5752 | 36.0 | 1125 | 0.4752 | 0.858 |
|
92 |
+
| 0.5487 | 36.992 | 1156 | 0.5121 | 0.837 |
|
93 |
+
| 0.5538 | 37.984 | 1187 | 0.5111 | 0.852 |
|
94 |
+
| 0.5267 | 38.976 | 1218 | 0.4884 | 0.853 |
|
95 |
+
| 0.4907 | 40.0 | 1250 | 0.4921 | 0.859 |
|
96 |
+
| 0.4901 | 40.992 | 1281 | 0.5001 | 0.849 |
|
97 |
+
| 0.5134 | 41.984 | 1312 | 0.4409 | 0.865 |
|
98 |
+
| 0.5019 | 42.976 | 1343 | 0.4730 | 0.863 |
|
99 |
+
| 0.4642 | 44.0 | 1375 | 0.4619 | 0.865 |
|
100 |
+
| 0.4778 | 44.992 | 1406 | 0.4911 | 0.861 |
|
101 |
+
| 0.4521 | 45.984 | 1437 | 0.4471 | 0.855 |
|
102 |
+
| 0.473 | 46.976 | 1468 | 0.4661 | 0.864 |
|
103 |
+
| 0.4752 | 48.0 | 1500 | 0.4917 | 0.848 |
|
104 |
+
| 0.4582 | 48.992 | 1531 | 0.4685 | 0.862 |
|
105 |
+
| 0.4282 | 49.984 | 1562 | 0.4314 | 0.875 |
|
106 |
+
| 0.4344 | 50.976 | 1593 | 0.4270 | 0.878 |
|
107 |
+
| 0.4212 | 52.0 | 1625 | 0.4657 | 0.861 |
|
108 |
+
| 0.4245 | 52.992 | 1656 | 0.4608 | 0.857 |
|
109 |
+
| 0.4055 | 53.984 | 1687 | 0.4717 | 0.856 |
|
110 |
+
| 0.3802 | 54.976 | 1718 | 0.4428 | 0.871 |
|
111 |
+
| 0.4221 | 56.0 | 1750 | 0.4088 | 0.88 |
|
112 |
+
| 0.4254 | 56.992 | 1781 | 0.4310 | 0.869 |
|
113 |
+
| 0.3963 | 57.984 | 1812 | 0.4320 | 0.864 |
|
114 |
+
| 0.4375 | 58.976 | 1843 | 0.4404 | 0.876 |
|
115 |
+
| 0.3685 | 60.0 | 1875 | 0.4369 | 0.866 |
|
116 |
+
| 0.3911 | 60.992 | 1906 | 0.4491 | 0.861 |
|
117 |
+
| 0.3761 | 61.984 | 1937 | 0.4509 | 0.86 |
|
118 |
+
| 0.3703 | 62.976 | 1968 | 0.4468 | 0.861 |
|
119 |
+
| 0.3602 | 64.0 | 2000 | 0.4596 | 0.87 |
|
120 |
+
| 0.4034 | 64.992 | 2031 | 0.4232 | 0.86 |
|
121 |
+
| 0.3726 | 65.984 | 2062 | 0.4214 | 0.877 |
|
122 |
+
| 0.4187 | 66.976 | 2093 | 0.4509 | 0.868 |
|
123 |
+
| 0.3858 | 68.0 | 2125 | 0.4067 | 0.878 |
|
124 |
+
| 0.3933 | 68.992 | 2156 | 0.4295 | 0.879 |
|
125 |
+
| 0.3461 | 69.984 | 2187 | 0.4092 | 0.88 |
|
126 |
+
| 0.3909 | 70.976 | 2218 | 0.4518 | 0.862 |
|
127 |
+
| 0.3737 | 72.0 | 2250 | 0.4414 | 0.867 |
|
128 |
+
| 0.344 | 72.992 | 2281 | 0.4335 | 0.869 |
|
129 |
+
| 0.3403 | 73.984 | 2312 | 0.4470 | 0.863 |
|
130 |
+
| 0.3433 | 74.976 | 2343 | 0.4016 | 0.881 |
|
131 |
+
| 0.3292 | 76.0 | 2375 | 0.4565 | 0.861 |
|
132 |
+
| 0.3115 | 76.992 | 2406 | 0.4368 | 0.87 |
|
133 |
+
| 0.3498 | 77.984 | 2437 | 0.4516 | 0.862 |
|
134 |
+
| 0.3456 | 78.976 | 2468 | 0.3779 | 0.889 |
|
135 |
+
| 0.3284 | 80.0 | 2500 | 0.4441 | 0.865 |
|
136 |
+
| 0.3723 | 80.992 | 2531 | 0.4150 | 0.874 |
|
137 |
+
| 0.3269 | 81.984 | 2562 | 0.4491 | 0.864 |
|
138 |
+
| 0.3863 | 82.976 | 2593 | 0.4106 | 0.884 |
|
139 |
+
| 0.3376 | 84.0 | 2625 | 0.4367 | 0.87 |
|
140 |
+
| 0.3794 | 84.992 | 2656 | 0.4282 | 0.863 |
|
141 |
+
| 0.3498 | 85.984 | 2687 | 0.4185 | 0.877 |
|
142 |
+
| 0.293 | 86.976 | 2718 | 0.4207 | 0.87 |
|
143 |
+
| 0.3106 | 88.0 | 2750 | 0.4316 | 0.873 |
|
144 |
+
| 0.3061 | 88.992 | 2781 | 0.4254 | 0.874 |
|
145 |
+
| 0.3235 | 89.984 | 2812 | 0.4251 | 0.878 |
|
146 |
+
| 0.3182 | 90.976 | 2843 | 0.4247 | 0.873 |
|
147 |
+
| 0.3666 | 92.0 | 2875 | 0.4079 | 0.879 |
|
148 |
+
| 0.336 | 92.992 | 2906 | 0.4187 | 0.871 |
|
149 |
+
| 0.3262 | 93.984 | 2937 | 0.4461 | 0.868 |
|
150 |
+
| 0.3504 | 94.976 | 2968 | 0.4713 | 0.852 |
|
151 |
+
| 0.3106 | 96.0 | 3000 | 0.4610 | 0.863 |
|
152 |
+
| 0.2671 | 96.992 | 3031 | 0.4614 | 0.866 |
|
153 |
+
| 0.2929 | 97.984 | 3062 | 0.4278 | 0.872 |
|
154 |
+
| 0.353 | 98.976 | 3093 | 0.4134 | 0.872 |
|
155 |
+
| 0.3331 | 99.2 | 3100 | 0.4411 | 0.86 |
|
156 |
|
157 |
|
158 |
### Framework versions
|
159 |
|
160 |
+
- Transformers 4.45.1
|
161 |
+
- Pytorch 2.4.0
|
162 |
- Datasets 3.0.1
|
163 |
+
- Tokenizers 0.20.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20105428
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0750efcb2cf500af9ec824768b7206cb2d6d0f433f6d8fc392f71d28ea159710
|
3 |
size 20105428
|