Hugging Face's logo

drAbreu
/
soda-clip-finetuned

Feature Extraction
Transformers
Safetensors
vision-text-dual-encoder
Generated from Trainer
Inference Endpoints
Model card Files Community
drAbreu commited on
Commit
956bb81
•
1 Parent(s): 700fe49

Model save

Browse files
Files changed (2) hide show
  1. README.md +35 -35
  2. model.safetensors +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model was trained from scratch on the soda-clip-loader dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 4.8565
19
 
20
  ## Model description
21
 
@@ -34,7 +34,7 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 0.0001
38
  - train_batch_size: 128
39
  - eval_batch_size: 128
40
  - seed: 42
@@ -46,39 +46,39 @@ The following hyperparameters were used during training:
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 4.8557 | 0.15 | 100 | 4.8520 |
50
- | 4.852 | 0.29 | 200 | 4.8520 |
51
- | 4.8526 | 0.44 | 300 | 4.8522 |
52
- | 4.8521 | 0.59 | 400 | 4.8520 |
53
- | 4.852 | 0.74 | 500 | 4.8520 |
54
- | 4.852 | 0.88 | 600 | 4.8520 |
55
- | 4.852 | 1.03 | 700 | 4.8520 |
56
- | 4.8519 | 1.18 | 800 | 4.8542 |
57
- | 4.8522 | 1.33 | 900 | 4.8520 |
58
- | 4.852 | 1.47 | 1000 | 4.8520 |
59
- | 4.852 | 1.62 | 1100 | 4.8520 |
60
- | 4.852 | 1.77 | 1200 | 4.8520 |
61
- | 4.852 | 1.92 | 1300 | 4.8520 |
62
- | 4.852 | 2.06 | 1400 | 4.8520 |
63
- | 4.852 | 2.21 | 1500 | 4.8520 |
64
- | 4.852 | 2.36 | 1600 | 4.8520 |
65
- | 4.852 | 2.51 | 1700 | 4.8520 |
66
- | 4.852 | 2.65 | 1800 | 4.8520 |
67
- | 4.852 | 2.8 | 1900 | 4.8520 |
68
- | 4.852 | 2.95 | 2000 | 4.8522 |
69
- | 4.852 | 3.1 | 2100 | 4.8521 |
70
- | 4.852 | 3.24 | 2200 | 4.8521 |
71
- | 4.8519 | 3.39 | 2300 | 4.8523 |
72
- | 4.8521 | 3.54 | 2400 | 4.8521 |
73
- | 4.852 | 3.69 | 2500 | 4.8521 |
74
- | 4.8517 | 3.83 | 2600 | 4.8521 |
75
- | 4.852 | 3.98 | 2700 | 4.8520 |
76
- | 4.852 | 4.13 | 2800 | 4.8520 |
77
- | 4.852 | 4.28 | 2900 | 4.8520 |
78
- | 4.852 | 4.42 | 3000 | 4.8520 |
79
- | 4.8519 | 4.57 | 3100 | 4.8523 |
80
- | 4.8515 | 4.72 | 3200 | 4.8528 |
81
- | 4.851 | 4.87 | 3300 | 4.8565 |
82
 
83
 
84
  ### Framework versions
 
15
 
16
  This model was trained from scratch on the soda-clip-loader dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.9564
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
  - train_batch_size: 128
39
  - eval_batch_size: 128
40
  - seed: 42
 
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 4.6533 | 0.15 | 100 | 4.5663 |
50
+ | 4.5243 | 0.29 | 200 | 4.4131 |
51
+ | 4.2506 | 0.44 | 300 | 3.9908 |
52
+ | 3.9692 | 0.59 | 400 | 3.8105 |
53
+ | 3.7576 | 0.74 | 500 | 3.6515 |
54
+ | 3.5935 | 0.88 | 600 | 3.4758 |
55
+ | 3.3874 | 1.03 | 700 | 3.3259 |
56
+ | 3.1691 | 1.18 | 800 | 3.1645 |
57
+ | 3.021 | 1.33 | 900 | 3.0139 |
58
+ | 2.9045 | 1.47 | 1000 | 2.9027 |
59
+ | 2.8391 | 1.62 | 1100 | 2.8245 |
60
+ | 2.7293 | 1.77 | 1200 | 2.6703 |
61
+ | 2.6177 | 1.92 | 1300 | 2.5465 |
62
+ | 2.3473 | 2.06 | 1400 | 2.5076 |
63
+ | 2.1463 | 2.21 | 1500 | 2.4233 |
64
+ | 2.0842 | 2.36 | 1600 | 2.3488 |
65
+ | 2.0204 | 2.51 | 1700 | 2.2738 |
66
+ | 2.0013 | 2.65 | 1800 | 2.2473 |
67
+ | 1.9325 | 2.8 | 1900 | 2.2017 |
68
+ | 1.9072 | 2.95 | 2000 | 2.1397 |
69
+ | 1.5792 | 3.1 | 2100 | 2.1203 |
70
+ | 1.3949 | 3.24 | 2200 | 2.0973 |
71
+ | 1.3664 | 3.39 | 2300 | 2.0737 |
72
+ | 1.3545 | 3.54 | 2400 | 2.0320 |
73
+ | 1.3144 | 3.69 | 2500 | 2.0143 |
74
+ | 1.2897 | 3.83 | 2600 | 1.9552 |
75
+ | 1.2706 | 3.98 | 2700 | 1.9497 |
76
+ | 0.9014 | 4.13 | 2800 | 1.9983 |
77
+ | 0.8365 | 4.28 | 2900 | 1.9960 |
78
+ | 0.8187 | 4.42 | 3000 | 1.9886 |
79
+ | 0.8001 | 4.57 | 3100 | 1.9709 |
80
+ | 0.7979 | 4.72 | 3200 | 1.9513 |
81
+ | 0.7698 | 4.87 | 3300 | 1.9564 |
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13888d3c204db997a1c831666df91ef11194fc55686d12809d6de23f4b84734f
3
  size 851603588
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a675392d562938c7af775fe5faa1a6a23742bd5f0f155567e379d2b6353b005
3
  size 851603588