Hugging Face's logo

drAbreu
/
soda-clip

Feature Extraction
Transformers
Safetensors
vision-text-dual-encoder
Generated from Trainer
Inference Endpoints
Model card Files Community
drAbreu commited on
Commit
a9a06b9
·
verified ·
1 Parent(s): 6ad3c42

Model save

Browse files
Files changed (2) hide show
  1. README.md +94 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - soda-panelized-clip-loader
6
+ model-index:
7
+ - name: soda-clip
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # soda-clip
15
+
16
+ This model was trained from scratch on the soda-panelized-clip-loader dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.9732
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 64
39
+ - eval_batch_size: 64
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 5.0
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 4.0258 | 0.13 | 100 | 3.7622 |
50
+ | 3.556 | 0.26 | 200 | 3.4317 |
51
+ | 3.3307 | 0.39 | 300 | 3.2219 |
52
+ | 3.2305 | 0.51 | 400 | 3.1044 |
53
+ | 3.1104 | 0.64 | 500 | 2.9733 |
54
+ | 2.9966 | 0.77 | 600 | 2.8562 |
55
+ | 2.8576 | 0.9 | 700 | 2.8080 |
56
+ | 2.7558 | 1.03 | 800 | 2.6612 |
57
+ | 2.5565 | 1.16 | 900 | 2.6441 |
58
+ | 2.4791 | 1.28 | 1000 | 2.5369 |
59
+ | 2.4483 | 1.41 | 1100 | 2.4951 |
60
+ | 2.3751 | 1.54 | 1200 | 2.3893 |
61
+ | 2.3408 | 1.67 | 1300 | 2.3960 |
62
+ | 2.2761 | 1.8 | 1400 | 2.2943 |
63
+ | 2.2426 | 1.93 | 1500 | 2.2422 |
64
+ | 2.0389 | 2.05 | 1600 | 2.2475 |
65
+ | 1.8415 | 2.18 | 1700 | 2.1555 |
66
+ | 1.8286 | 2.31 | 1800 | 2.1755 |
67
+ | 1.7927 | 2.44 | 1900 | 2.1267 |
68
+ | 1.7693 | 2.57 | 2000 | 2.0621 |
69
+ | 1.7448 | 2.7 | 2100 | 2.0653 |
70
+ | 1.7027 | 2.82 | 2200 | 2.0110 |
71
+ | 1.7184 | 2.95 | 2300 | 1.9699 |
72
+ | 1.4059 | 3.08 | 2400 | 1.9781 |
73
+ | 1.2499 | 3.21 | 2500 | 1.9837 |
74
+ | 1.2478 | 3.34 | 2600 | 1.9859 |
75
+ | 1.1903 | 3.47 | 2700 | 1.9470 |
76
+ | 1.1989 | 3.59 | 2800 | 1.9819 |
77
+ | 1.169 | 3.72 | 2900 | 1.9825 |
78
+ | 1.1538 | 3.85 | 3000 | 1.9429 |
79
+ | 1.1178 | 3.98 | 3100 | 1.9387 |
80
+ | 0.8271 | 4.11 | 3200 | 1.9931 |
81
+ | 0.748 | 4.24 | 3300 | 1.9974 |
82
+ | 0.7123 | 4.36 | 3400 | 1.9994 |
83
+ | 0.7012 | 4.49 | 3500 | 1.9967 |
84
+ | 0.7163 | 4.62 | 3600 | 1.9914 |
85
+ | 0.6899 | 4.75 | 3700 | 1.9836 |
86
+ | 0.6608 | 4.88 | 3800 | 1.9732 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.37.2
92
+ - Pytorch 2.2.0+cu121
93
+ - Datasets 2.17.0
94
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:685ef4001ec76e64daaa4b584fe8d9458f6a03e83677f233f1c98942dbc0d8e8
3
  size 851603588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc111f0fcc251a29a7479e2c181b6f3c323014cb1dbe8bf7816b6405ff384281
3
  size 851603588