Hugging Face's logo

amauriciogonzalez
/
dinov2-base-finetuned-har

Image Classification
Transformers
TensorBoard
Safetensors
dinov2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
amauriciogonzalez commited on
Commit
8454fbd
•
1 Parent(s): 768df8b

Model save

Browse files
Files changed (2) hide show
  1. README.md +62 -12
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  license: apache-2.0
3
  base_model: facebook/dinov2-base
4
  tags:
@@ -22,7 +23,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8634920634920635
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.4464
36
- - Accuracy: 0.8635
37
 
38
  ## Model description
39
 
@@ -53,26 +54,75 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
- - train_batch_size: 64
57
- - eval_batch_size: 64
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 256
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 1
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.8084 | 1.0 | 42 | 0.4464 | 0.8635 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71
 
72
 
73
  ### Framework versions
74
 
75
- - Transformers 4.44.0
76
- - Pytorch 2.4.0
77
  - Datasets 2.21.0
78
  - Tokenizers 0.19.1
 
1
  ---
2
+ library_name: transformers
3
  license: apache-2.0
4
  base_model: facebook/dinov2-base
5
  tags:
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.8957671957671958
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.4414
37
+ - Accuracy: 0.8958
38
 
39
  ## Model description
40
 
 
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 5e-05
57
+ - train_batch_size: 32
58
+ - eval_batch_size: 32
59
  - seed: 42
60
  - gradient_accumulation_steps: 4
61
+ - total_train_batch_size: 128
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 50
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
71
+ | 0.9155 | 0.9910 | 83 | 0.6204 | 0.8053 |
72
+ | 0.749 | 1.9940 | 167 | 0.4433 | 0.8667 |
73
+ | 0.8197 | 2.9970 | 251 | 0.4826 | 0.8571 |
74
+ | 0.6854 | 4.0 | 335 | 0.4243 | 0.8725 |
75
+ | 0.7058 | 4.9910 | 418 | 0.4349 | 0.8593 |
76
+ | 0.6717 | 5.9940 | 502 | 0.4984 | 0.8434 |
77
+ | 0.6544 | 6.9970 | 586 | 0.4730 | 0.8545 |
78
+ | 0.5846 | 8.0 | 670 | 0.4631 | 0.8630 |
79
+ | 0.5207 | 8.9910 | 753 | 0.4072 | 0.8751 |
80
+ | 0.4977 | 9.9940 | 837 | 0.4627 | 0.8608 |
81
+ | 0.4974 | 10.9970 | 921 | 0.4600 | 0.8661 |
82
+ | 0.4502 | 12.0 | 1005 | 0.4548 | 0.8725 |
83
+ | 0.4051 | 12.9910 | 1088 | 0.4404 | 0.8709 |
84
+ | 0.3862 | 13.9940 | 1172 | 0.4498 | 0.8772 |
85
+ | 0.351 | 14.9970 | 1256 | 0.4859 | 0.8677 |
86
+ | 0.3807 | 16.0 | 1340 | 0.5189 | 0.8556 |
87
+ | 0.3538 | 16.9910 | 1423 | 0.4959 | 0.8646 |
88
+ | 0.3181 | 17.9940 | 1507 | 0.4831 | 0.8698 |
89
+ | 0.3225 | 18.9970 | 1591 | 0.4890 | 0.8804 |
90
+ | 0.3257 | 20.0 | 1675 | 0.4817 | 0.8735 |
91
+ | 0.2667 | 20.9910 | 1758 | 0.5199 | 0.8683 |
92
+ | 0.2863 | 21.9940 | 1842 | 0.4835 | 0.8683 |
93
+ | 0.2527 | 22.9970 | 1926 | 0.4764 | 0.8772 |
94
+ | 0.2657 | 24.0 | 2010 | 0.4651 | 0.8767 |
95
+ | 0.1995 | 24.9910 | 2093 | 0.5079 | 0.8693 |
96
+ | 0.2481 | 25.9940 | 2177 | 0.5112 | 0.8698 |
97
+ | 0.2072 | 26.9970 | 2261 | 0.5082 | 0.8831 |
98
+ | 0.2164 | 28.0 | 2345 | 0.5002 | 0.8730 |
99
+ | 0.2198 | 28.9910 | 2428 | 0.4785 | 0.8778 |
100
+ | 0.2137 | 29.9940 | 2512 | 0.5012 | 0.8889 |
101
+ | 0.1936 | 30.9970 | 2596 | 0.4961 | 0.8757 |
102
+ | 0.2255 | 32.0 | 2680 | 0.4987 | 0.8788 |
103
+ | 0.1818 | 32.9910 | 2763 | 0.4840 | 0.8852 |
104
+ | 0.1644 | 33.9940 | 2847 | 0.4694 | 0.8862 |
105
+ | 0.1799 | 34.9970 | 2931 | 0.4599 | 0.8915 |
106
+ | 0.1624 | 36.0 | 3015 | 0.5122 | 0.8852 |
107
+ | 0.157 | 36.9910 | 3098 | 0.4546 | 0.8899 |
108
+ | 0.2165 | 37.9940 | 3182 | 0.5097 | 0.8836 |
109
+ | 0.1565 | 38.9970 | 3266 | 0.4566 | 0.8952 |
110
+ | 0.1476 | 40.0 | 3350 | 0.4579 | 0.8915 |
111
+ | 0.1296 | 40.9910 | 3433 | 0.4595 | 0.8931 |
112
+ | 0.1159 | 41.9940 | 3517 | 0.4841 | 0.8884 |
113
+ | 0.1071 | 42.9970 | 3601 | 0.4730 | 0.8820 |
114
+ | 0.1017 | 44.0 | 3685 | 0.4470 | 0.8931 |
115
+ | 0.11 | 44.9910 | 3768 | 0.4557 | 0.8910 |
116
+ | 0.126 | 45.9940 | 3852 | 0.4585 | 0.8926 |
117
+ | 0.1079 | 46.9970 | 3936 | 0.4551 | 0.8905 |
118
+ | 0.1194 | 48.0 | 4020 | 0.4401 | 0.8947 |
119
+ | 0.11 | 48.9910 | 4103 | 0.4424 | 0.8968 |
120
+ | 0.1104 | 49.5522 | 4150 | 0.4414 | 0.8958 |
121
 
122
 
123
  ### Framework versions
124
 
125
+ - Transformers 4.44.2
126
+ - Pytorch 2.4.1+cu121
127
  - Datasets 2.21.0
128
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:950cc3e5bdffeaeaacd5437a9e1b26a5e170cc30b7b864cadfa53b0da9dfda67
3
  size 346439852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530d851e2968f990ea02a06dbb354230d8c82f5dd9468efa14e22414d8d62907
3
  size 346439852