Hugging Face's logo

turing552
/
siglipbase-wikiart-5ep

Zero-Shot Image Classification
Transformers
PyTorch
siglip
Generated from Trainer
Model card Files
xet
 Community
3
turing552 commited on
Commit
8161ff1
·
verified ·
1 Parent(s): 9f34972

Model save

Browse files
Files changed (2) hide show
  1. README.md +84 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google/siglip-base-patch16-224
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: siglipbase-wikiart-5ep
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # siglipbase-wikiart-5ep
16
+
17
+ This model is a fine-tuned version of [google/siglip-base-patch16-224](https://huggingface.co/google/siglip-base-patch16-224) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0301
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-06
39
+ - train_batch_size: 32
40
+ - eval_batch_size: 32
41
+ - seed: 42
42
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_ratio: 0.1
45
+ - num_epochs: 5
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:------:|:-----:|:---------------:|
51
+ | 0.035 | 0.1913 | 500 | 0.0324 |
52
+ | 0.029 | 0.3826 | 1000 | 0.0290 |
53
+ | 0.0291 | 0.5738 | 1500 | 0.0283 |
54
+ | 0.0239 | 0.7651 | 2000 | 0.0251 |
55
+ | 0.0232 | 0.9564 | 2500 | 0.0243 |
56
+ | 0.0175 | 1.1477 | 3000 | 0.0234 |
57
+ | 0.0163 | 1.3389 | 3500 | 0.0222 |
58
+ | 0.0164 | 1.5302 | 4000 | 0.0225 |
59
+ | 0.0168 | 1.7215 | 4500 | 0.0215 |
60
+ | 0.0155 | 1.9128 | 5000 | 0.0198 |
61
+ | 0.0094 | 2.1041 | 5500 | 0.0233 |
62
+ | 0.0087 | 2.2953 | 6000 | 0.0233 |
63
+ | 0.0093 | 2.4866 | 6500 | 0.0246 |
64
+ | 0.0093 | 2.6779 | 7000 | 0.0234 |
65
+ | 0.0087 | 2.8692 | 7500 | 0.0233 |
66
+ | 0.0058 | 3.0604 | 8000 | 0.0262 |
67
+ | 0.0063 | 3.2517 | 8500 | 0.0255 |
68
+ | 0.0059 | 3.4430 | 9000 | 0.0249 |
69
+ | 0.006 | 3.6343 | 9500 | 0.0254 |
70
+ | 0.0059 | 3.8256 | 10000 | 0.0262 |
71
+ | 0.0053 | 4.0168 | 10500 | 0.0283 |
72
+ | 0.0047 | 4.2081 | 11000 | 0.0290 |
73
+ | 0.0035 | 4.3994 | 11500 | 0.0286 |
74
+ | 0.0041 | 4.5907 | 12000 | 0.0305 |
75
+ | 0.0041 | 4.7819 | 12500 | 0.0302 |
76
+ | 0.0034 | 4.9732 | 13000 | 0.0301 |
77
+
78
+
79
+ ### Framework versions
80
+
81
+ - Transformers 4.57.1
82
+ - Pytorch 2.6.0+cu124
83
+ - Datasets 4.4.1
84
+ - Tokenizers 0.22.1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35d63b5b75f5822512b5ae9a9484fe975f8e452d5224c109d3e4fd0de5a72b2b
3
  size 812764266
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7314f28de3d1e8b3379d614042e19a7adae799313e11eb643b473f1586bba265
3
  size 812764266