Manuappu5670 commited on
Commit
c7f663e
·
verified ·
1 Parent(s): 364494b

Model save

Browse files
Files changed (2) hide show
  1. README.md +108 -55
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [apple/mobilevit-xx-small](https://huggingface.co/apple/mobilevit-xx-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.0321
21
- - Accuracy: 0.66
22
 
23
  ## Model description
24
 
@@ -38,67 +38,120 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.003
41
- - train_batch_size: 32
42
- - eval_batch_size: 32
43
  - seed: 42
44
  - gradient_accumulation_steps: 4
45
- - total_train_batch_size: 128
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
- - num_epochs: 50
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
- |:-------------:|:-------:|:----:|:---------------:|:--------:|
55
- | No log | 0.9231 | 3 | 2.2814 | 0.11 |
56
- | No log | 1.8462 | 6 | 2.2279 | 0.26 |
57
- | No log | 2.7692 | 9 | 2.1060 | 0.29 |
58
- | 2.2256 | 4.0 | 13 | 1.8601 | 0.31 |
59
- | 2.2256 | 4.9231 | 16 | 1.8917 | 0.32 |
60
- | 2.2256 | 5.8462 | 19 | 1.7590 | 0.33 |
61
- | 1.8 | 6.7692 | 22 | 2.9505 | 0.21 |
62
- | 1.8 | 8.0 | 26 | 2.4407 | 0.19 |
63
- | 1.8 | 8.9231 | 29 | 2.6913 | 0.36 |
64
- | 1.6404 | 9.8462 | 32 | 1.4094 | 0.48 |
65
- | 1.6404 | 10.7692 | 35 | 1.4011 | 0.47 |
66
- | 1.6404 | 12.0 | 39 | 1.7594 | 0.45 |
67
- | 1.4817 | 12.9231 | 42 | 1.4313 | 0.46 |
68
- | 1.4817 | 13.8462 | 45 | 1.2744 | 0.49 |
69
- | 1.4817 | 14.7692 | 48 | 1.4527 | 0.46 |
70
- | 1.2872 | 16.0 | 52 | 1.5522 | 0.42 |
71
- | 1.2872 | 16.9231 | 55 | 1.7600 | 0.38 |
72
- | 1.2872 | 17.8462 | 58 | 1.3952 | 0.53 |
73
- | 1.2307 | 18.7692 | 61 | 1.5067 | 0.51 |
74
- | 1.2307 | 20.0 | 65 | 1.6311 | 0.51 |
75
- | 1.2307 | 20.9231 | 68 | 1.3987 | 0.58 |
76
- | 1.0604 | 21.8462 | 71 | 1.4128 | 0.54 |
77
- | 1.0604 | 22.7692 | 74 | 1.1939 | 0.56 |
78
- | 1.0604 | 24.0 | 78 | 1.4324 | 0.49 |
79
- | 1.0053 | 24.9231 | 81 | 1.3661 | 0.53 |
80
- | 1.0053 | 25.8462 | 84 | 1.2528 | 0.53 |
81
- | 1.0053 | 26.7692 | 87 | 1.2040 | 0.57 |
82
- | 0.8327 | 28.0 | 91 | 1.1886 | 0.61 |
83
- | 0.8327 | 28.9231 | 94 | 1.0321 | 0.66 |
84
- | 0.8327 | 29.8462 | 97 | 1.1496 | 0.61 |
85
- | 0.7456 | 30.7692 | 100 | 1.1801 | 0.61 |
86
- | 0.7456 | 32.0 | 104 | 1.2886 | 0.53 |
87
- | 0.7456 | 32.9231 | 107 | 1.2215 | 0.6 |
88
- | 0.7106 | 33.8462 | 110 | 1.2372 | 0.55 |
89
- | 0.7106 | 34.7692 | 113 | 1.1834 | 0.62 |
90
- | 0.7106 | 36.0 | 117 | 1.2001 | 0.64 |
91
- | 0.5914 | 36.9231 | 120 | 1.1182 | 0.63 |
92
- | 0.5914 | 37.8462 | 123 | 1.2223 | 0.62 |
93
- | 0.5914 | 38.7692 | 126 | 1.2443 | 0.59 |
94
- | 0.5601 | 40.0 | 130 | 1.2605 | 0.59 |
95
- | 0.5601 | 40.9231 | 133 | 1.2940 | 0.6 |
96
- | 0.5601 | 41.8462 | 136 | 1.2284 | 0.59 |
97
- | 0.5601 | 42.7692 | 139 | 1.1884 | 0.61 |
98
- | 0.5151 | 44.0 | 143 | 1.1789 | 0.63 |
99
- | 0.5151 | 44.9231 | 146 | 1.1297 | 0.62 |
100
- | 0.5151 | 45.8462 | 149 | 1.0879 | 0.63 |
101
- | 0.4531 | 46.1538 | 150 | 1.0688 | 0.64 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
102
 
103
 
104
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [apple/mobilevit-xx-small](https://huggingface.co/apple/mobilevit-xx-small) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 7.3961
21
+ - Accuracy: 0.09
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 0.003
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 1
43
  - seed: 42
44
  - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 4
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 100
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
55
+ | 2.2991 | 1.0 | 100 | 2.2896 | 0.16 |
56
+ | 2.3041 | 2.0 | 200 | 2.4578 | 0.12 |
57
+ | 2.2833 | 3.0 | 300 | 2.3022 | 0.12 |
58
+ | 2.2755 | 4.0 | 400 | 2.4039 | 0.17 |
59
+ | 2.3063 | 5.0 | 500 | 2.5689 | 0.1 |
60
+ | 2.3247 | 6.0 | 600 | 2.5307 | 0.05 |
61
+ | 2.2867 | 7.0 | 700 | 4.1296 | 0.08 |
62
+ | 2.2696 | 8.0 | 800 | 3.0869 | 0.07 |
63
+ | 2.2688 | 9.0 | 900 | 3.6086 | 0.08 |
64
+ | 2.2616 | 10.0 | 1000 | 6.5422 | 0.13 |
65
+ | 2.3896 | 11.0 | 1100 | 3.2715 | 0.11 |
66
+ | 2.3264 | 12.0 | 1200 | 2.6975 | 0.08 |
67
+ | 2.2603 | 13.0 | 1300 | 2.4012 | 0.17 |
68
+ | 2.2845 | 14.0 | 1400 | 3.0856 | 0.19 |
69
+ | 2.2813 | 15.0 | 1500 | 3.2556 | 0.17 |
70
+ | 2.2232 | 16.0 | 1600 | 3.5357 | 0.18 |
71
+ | 2.2332 | 17.0 | 1700 | 3.8758 | 0.11 |
72
+ | 2.3568 | 18.0 | 1800 | 3.0675 | 0.13 |
73
+ | 2.2627 | 19.0 | 1900 | 3.1308 | 0.16 |
74
+ | 2.2528 | 20.0 | 2000 | 2.7741 | 0.1 |
75
+ | 2.2039 | 21.0 | 2100 | 2.7257 | 0.14 |
76
+ | 2.389 | 22.0 | 2200 | 2.6245 | 0.08 |
77
+ | 2.31 | 23.0 | 2300 | 3.1870 | 0.1 |
78
+ | 2.1471 | 24.0 | 2400 | 2.8313 | 0.02 |
79
+ | 2.1658 | 25.0 | 2500 | 2.9323 | 0.11 |
80
+ | 2.0946 | 26.0 | 2600 | 2.8372 | 0.14 |
81
+ | 2.0924 | 27.0 | 2700 | 2.7403 | 0.16 |
82
+ | 2.2634 | 28.0 | 2800 | 2.8991 | 0.14 |
83
+ | 2.1897 | 29.0 | 2900 | 2.8778 | 0.13 |
84
+ | 2.144 | 30.0 | 3000 | 2.6043 | 0.15 |
85
+ | 2.108 | 31.0 | 3100 | 2.9231 | 0.1 |
86
+ | 2.0792 | 32.0 | 3200 | 2.8421 | 0.12 |
87
+ | 2.1552 | 33.0 | 3300 | 2.8106 | 0.12 |
88
+ | 1.9701 | 34.0 | 3400 | 2.8279 | 0.11 |
89
+ | 1.9291 | 35.0 | 3500 | 3.0954 | 0.2 |
90
+ | 2.0341 | 36.0 | 3600 | 3.8294 | 0.14 |
91
+ | 1.9165 | 37.0 | 3700 | 4.5289 | 0.11 |
92
+ | 1.9736 | 38.0 | 3800 | 3.0090 | 0.14 |
93
+ | 1.9811 | 39.0 | 3900 | 5.3900 | 0.14 |
94
+ | 1.9522 | 40.0 | 4000 | 3.5710 | 0.08 |
95
+ | 2.047 | 41.0 | 4100 | 3.4724 | 0.13 |
96
+ | 1.9999 | 42.0 | 4200 | 7.2604 | 0.11 |
97
+ | 1.9869 | 43.0 | 4300 | 7.9946 | 0.06 |
98
+ | 1.9428 | 44.0 | 4400 | 6.1566 | 0.08 |
99
+ | 1.7922 | 45.0 | 4500 | 4.9919 | 0.03 |
100
+ | 1.9047 | 46.0 | 4600 | 7.1934 | 0.13 |
101
+ | 1.9419 | 47.0 | 4700 | 4.3265 | 0.08 |
102
+ | 1.7765 | 48.0 | 4800 | 4.6136 | 0.12 |
103
+ | 1.7962 | 49.0 | 4900 | 13.4765 | 0.14 |
104
+ | 2.0226 | 50.0 | 5000 | 8.1225 | 0.08 |
105
+ | 2.1393 | 51.0 | 5100 | 7.7941 | 0.17 |
106
+ | 1.8256 | 52.0 | 5200 | 5.4134 | 0.12 |
107
+ | 1.9116 | 53.0 | 5300 | 6.1129 | 0.08 |
108
+ | 2.1156 | 54.0 | 5400 | 4.1454 | 0.14 |
109
+ | 1.7501 | 55.0 | 5500 | 6.2134 | 0.09 |
110
+ | 1.8722 | 56.0 | 5600 | 6.4985 | 0.12 |
111
+ | 1.9432 | 57.0 | 5700 | 5.2718 | 0.12 |
112
+ | 1.7713 | 58.0 | 5800 | 12.3311 | 0.08 |
113
+ | 1.6786 | 59.0 | 5900 | 7.1599 | 0.07 |
114
+ | 1.5969 | 60.0 | 6000 | 6.0869 | 0.08 |
115
+ | 1.8203 | 61.0 | 6100 | 8.8250 | 0.14 |
116
+ | 1.7148 | 62.0 | 6200 | 19.0942 | 0.11 |
117
+ | 1.6627 | 63.0 | 6300 | 12.4329 | 0.16 |
118
+ | 1.7134 | 64.0 | 6400 | 5.5367 | 0.11 |
119
+ | 1.8841 | 65.0 | 6500 | 9.1239 | 0.11 |
120
+ | 1.6822 | 66.0 | 6600 | 9.4719 | 0.11 |
121
+ | 1.8892 | 67.0 | 6700 | 5.6084 | 0.09 |
122
+ | 1.72 | 68.0 | 6800 | 8.7854 | 0.12 |
123
+ | 1.8751 | 69.0 | 6900 | 7.5571 | 0.11 |
124
+ | 1.3783 | 70.0 | 7000 | 11.6321 | 0.12 |
125
+ | 1.6403 | 71.0 | 7100 | 7.5354 | 0.15 |
126
+ | 2.087 | 72.0 | 7200 | 13.7248 | 0.11 |
127
+ | 1.6402 | 73.0 | 7300 | 5.4883 | 0.12 |
128
+ | 1.8016 | 74.0 | 7400 | 7.8351 | 0.13 |
129
+ | 1.4308 | 75.0 | 7500 | 4.6966 | 0.13 |
130
+ | 1.6833 | 76.0 | 7600 | 5.9138 | 0.12 |
131
+ | 1.5684 | 77.0 | 7700 | 11.9864 | 0.15 |
132
+ | 1.6765 | 78.0 | 7800 | 12.2146 | 0.1 |
133
+ | 1.7482 | 79.0 | 7900 | 4.6041 | 0.12 |
134
+ | 1.7836 | 80.0 | 8000 | 9.7217 | 0.13 |
135
+ | 1.5195 | 81.0 | 8100 | 7.5132 | 0.12 |
136
+ | 1.4384 | 82.0 | 8200 | 6.6091 | 0.13 |
137
+ | 1.5538 | 83.0 | 8300 | 7.0786 | 0.13 |
138
+ | 1.5705 | 84.0 | 8400 | 12.5851 | 0.14 |
139
+ | 1.7255 | 85.0 | 8500 | 9.9331 | 0.11 |
140
+ | 1.6063 | 86.0 | 8600 | 11.3630 | 0.14 |
141
+ | 1.5201 | 87.0 | 8700 | 20.8011 | 0.08 |
142
+ | 1.3734 | 88.0 | 8800 | 5.2354 | 0.09 |
143
+ | 1.5931 | 89.0 | 8900 | 6.5090 | 0.1 |
144
+ | 1.5562 | 90.0 | 9000 | 11.8341 | 0.1 |
145
+ | 1.576 | 91.0 | 9100 | 6.9521 | 0.11 |
146
+ | 1.542 | 92.0 | 9200 | 5.4470 | 0.11 |
147
+ | 1.4968 | 93.0 | 9300 | 11.3896 | 0.08 |
148
+ | 1.5031 | 94.0 | 9400 | 11.9717 | 0.09 |
149
+ | 1.797 | 95.0 | 9500 | 5.6596 | 0.15 |
150
+ | 1.5389 | 96.0 | 9600 | 5.3947 | 0.15 |
151
+ | 1.6494 | 97.0 | 9700 | 12.2707 | 0.09 |
152
+ | 1.73 | 98.0 | 9800 | 7.7482 | 0.09 |
153
+ | 1.6781 | 99.0 | 9900 | 8.2178 | 0.09 |
154
+ | 1.6353 | 100.0 | 10000 | 7.3961 | 0.09 |
155
 
156
 
157
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7d93b79e0fec12edbdf75f79754983cfbeef00f17d7a1a8164716d7d6664cd5
3
  size 3879632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdbb9d2206b12a5828dcfd0821048d87244c17dac1fffe9112c5b1bc34b48b53
3
  size 3879632