Hugging Face's logo

tangg555
/
clip-vit-large-patch14-finetuned-clip-vit-large-patch14-mnist_linear_probe

Image Classification
Transformers
Safetensors
clip
Generated from Trainer
Inference Endpoints
Model card Files Community
tangg555 commited on
Commit
45c75d4
•
1 Parent(s): a4592f3

Model save

Browse files
Files changed (2) hide show
  1. README.md +39 -12
  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 [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.1829
21
- - Accuracy: 0.2367
22
 
23
  ## Model description
24
 
@@ -38,23 +38,50 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
- - train_batch_size: 32
42
- - eval_batch_size: 32
43
  - seed: 42
44
- - gradient_accumulation_steps: 30
45
- - total_train_batch_size: 960
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: 3
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
- |:-------------:|:------:|:----:|:---------------:|:--------:|
55
- | 2.2886 | 0.9953 | 56 | 2.2661 | 0.157 |
56
- | 2.2153 | 1.9905 | 112 | 2.2004 | 0.1945 |
57
- | 2.1981 | 2.9858 | 168 | 2.1829 | 0.2367 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [openai/clip-vit-large-patch14](https://huggingface.co/openai/clip-vit-large-patch14) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.9687
21
+ - Accuracy: 0.9137
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 128
42
+ - eval_batch_size: 128
43
  - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 512
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: 30
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
55
+ | 2.4414 | 0.9953 | 105 | 2.3838 | 0.102 |
56
+ | 2.2431 | 2.0 | 211 | 2.2100 | 0.2698 |
57
+ | 2.1251 | 2.9953 | 316 | 2.0662 | 0.4987 |
58
+ | 2.0119 | 4.0 | 422 | 1.9232 | 0.6905 |
59
+ | 1.9134 | 4.9953 | 527 | 1.8080 | 0.7645 |
60
+ | 1.8314 | 6.0 | 633 | 1.7059 | 0.8053 |
61
+ | 1.7816 | 6.9953 | 738 | 1.6175 | 0.8215 |
62
+ | 1.7076 | 8.0 | 844 | 1.5373 | 0.845 |
63
+ | 1.6632 | 8.9953 | 949 | 1.4675 | 0.8592 |
64
+ | 1.6188 | 10.0 | 1055 | 1.4062 | 0.863 |
65
+ | 1.5606 | 10.9953 | 1160 | 1.3510 | 0.8718 |
66
+ | 1.5185 | 12.0 | 1266 | 1.3031 | 0.8718 |
67
+ | 1.5007 | 12.9953 | 1371 | 1.2591 | 0.881 |
68
+ | 1.4573 | 14.0 | 1477 | 1.2201 | 0.8833 |
69
+ | 1.4474 | 14.9953 | 1582 | 1.1841 | 0.8875 |
70
+ | 1.4308 | 16.0 | 1688 | 1.1524 | 0.8925 |
71
+ | 1.4091 | 16.9953 | 1793 | 1.1246 | 0.8943 |
72
+ | 1.3683 | 18.0 | 1899 | 1.0986 | 0.8985 |
73
+ | 1.365 | 18.9953 | 2004 | 1.0752 | 0.9042 |
74
+ | 1.3635 | 20.0 | 2110 | 1.0563 | 0.9033 |
75
+ | 1.3422 | 20.9953 | 2215 | 1.0389 | 0.9043 |
76
+ | 1.3248 | 22.0 | 2321 | 1.0231 | 0.9083 |
77
+ | 1.2961 | 22.9953 | 2426 | 1.0100 | 0.9093 |
78
+ | 1.3136 | 24.0 | 2532 | 0.9986 | 0.9107 |
79
+ | 1.3067 | 24.9953 | 2637 | 0.9897 | 0.911 |
80
+ | 1.2984 | 26.0 | 2743 | 0.9818 | 0.9115 |
81
+ | 1.3045 | 26.9953 | 2848 | 0.9759 | 0.9132 |
82
+ | 1.291 | 28.0 | 2954 | 0.9717 | 0.9132 |
83
+ | 1.2731 | 28.9953 | 3059 | 0.9692 | 0.9142 |
84
+ | 1.3034 | 29.8578 | 3150 | 0.9687 | 0.9137 |
85
 
86
 
87
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1df8da57145b75a6b643006fda4e56095bba4368e6d0ba808a7793dc4d244d6
3
  size 1212808056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e397e913af0c2b97cbcf999a154d351e9210bd05bc37a56a283843e8b6f57444
3
  size 1212808056