Hugging Face's logo

alexandroputra
/
medsiglip-448-ft-tb-screening

Zero-Shot Image Classification
Transformers
Safetensors
siglip
Generated from Trainer
Model card Files
xet
Community
alexandroputra commited on
Commit
7d4249a
·
verified ·
1 Parent(s): 28ac251

Model save

Browse files
Files changed (3) hide show
  1. README.md +50 -23
  2. epoch_metrics_log.csv +2 -0
  3. model.safetensors +1 -1
README.md CHANGED
@@ -1,5 +1,7 @@
1
  ---
2
  library_name: transformers
 
 
3
  tags:
4
  - generated_from_trainer
5
  model-index:
@@ -12,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # medsiglip-448-ft-tb-screening
14
 
15
- This model was trained from scratch on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 2.5291
18
 
19
  ## Model description
20
 
@@ -48,27 +50,52 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:------:|:----:|:---------------:|
51
- | 3.5828 | 0.4762 | 25 | 2.4233 |
52
- | 1.947 | 0.9524 | 50 | 2.6277 |
53
- | 1.9315 | 1.4190 | 75 | 2.4902 |
54
- | 1.9614 | 1.8952 | 100 | 2.5603 |
55
- | 1.9357 | 2.3619 | 125 | 2.5067 |
56
- | 1.9396 | 2.8381 | 150 | 2.6298 |
57
- | 1.9313 | 3.3048 | 175 | 2.5459 |
58
- | 1.8956 | 3.7810 | 200 | 2.5050 |
59
- | 1.9271 | 4.2476 | 225 | 2.5318 |
60
- | 1.9317 | 4.7238 | 250 | 2.5298 |
61
- | 1.9365 | 5.1905 | 275 | 2.5108 |
62
- | 1.9255 | 5.6667 | 300 | 2.5120 |
63
- | 1.9284 | 6.1333 | 325 | 2.5134 |
64
- | 1.907 | 6.6095 | 350 | 2.5199 |
65
- | 1.8996 | 7.0762 | 375 | 2.5279 |
66
- | 1.9321 | 7.5524 | 400 | 2.5274 |
67
- | 1.9101 | 8.0190 | 425 | 2.5273 |
68
- | 1.9131 | 8.4952 | 450 | 2.5293 |
69
- | 1.91 | 8.9714 | 475 | 2.5300 |
70
- | 1.919 | 9.4381 | 500 | 2.5290 |
71
- | 1.9189 | 9.9143 | 525 | 2.5291 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ license: other
4
+ base_model: google/medsiglip-448
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
14
 
15
  # medsiglip-448-ft-tb-screening
16
 
17
+ This model is a fine-tuned version of [google/medsiglip-448](https://huggingface.co/google/medsiglip-448) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 2.6822
20
 
21
  ## Model description
22
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:------:|:----:|:---------------:|
53
+ | 3.5064 | 0.2140 | 25 | 2.4667 |
54
+ | 1.9406 | 0.4280 | 50 | 2.5449 |
55
+ | 1.9175 | 0.6421 | 75 | 2.5669 |
56
+ | 1.8659 | 0.8561 | 100 | 2.7958 |
57
+ | 1.9603 | 1.0685 | 125 | 2.6281 |
58
+ | 1.8811 | 1.2825 | 150 | 2.5601 |
59
+ | 1.8955 | 1.4965 | 175 | 2.5833 |
60
+ | 1.8982 | 1.7105 | 200 | 2.6373 |
61
+ | 1.825 | 1.9246 | 225 | 2.6426 |
62
+ | 1.88 | 2.1370 | 250 | 2.8641 |
63
+ | 1.851 | 2.3510 | 275 | 2.6415 |
64
+ | 1.8619 | 2.5650 | 300 | 2.5749 |
65
+ | 1.8365 | 2.7790 | 325 | 2.6245 |
66
+ | 1.8783 | 2.9930 | 350 | 2.5929 |
67
+ | 1.8693 | 3.2055 | 375 | 2.5986 |
68
+ | 1.8605 | 3.4195 | 400 | 2.6601 |
69
+ | 1.8759 | 3.6335 | 425 | 2.5904 |
70
+ | 1.8731 | 3.8475 | 450 | 2.6054 |
71
+ | 1.8536 | 4.0599 | 475 | 2.6441 |
72
+ | 1.8509 | 4.2739 | 500 | 2.6678 |
73
+ | 1.8609 | 4.4880 | 525 | 2.6946 |
74
+ | 1.8478 | 4.7020 | 550 | 2.6386 |
75
+ | 1.8492 | 4.9160 | 575 | 2.6799 |
76
+ | 1.8549 | 5.1284 | 600 | 2.6355 |
77
+ | 1.88 | 5.3424 | 625 | 2.7021 |
78
+ | 1.8569 | 5.5564 | 650 | 2.6380 |
79
+ | 1.862 | 5.7705 | 675 | 2.6349 |
80
+ | 1.8486 | 5.9845 | 700 | 2.6843 |
81
+ | 1.8503 | 6.1969 | 725 | 2.6926 |
82
+ | 1.8503 | 6.4109 | 750 | 2.6962 |
83
+ | 1.84 | 6.6249 | 775 | 2.6286 |
84
+ | 1.8466 | 6.8390 | 800 | 2.6278 |
85
+ | 1.8584 | 7.0514 | 825 | 2.6274 |
86
+ | 1.8633 | 7.2654 | 850 | 2.6308 |
87
+ | 1.8744 | 7.4794 | 875 | 2.6365 |
88
+ | 1.8522 | 7.6934 | 900 | 2.6514 |
89
+ | 1.8578 | 7.9074 | 925 | 2.6701 |
90
+ | 1.8661 | 8.1199 | 950 | 2.6817 |
91
+ | 1.8301 | 8.3339 | 975 | 2.6813 |
92
+ | 1.8499 | 8.5479 | 1000 | 2.6841 |
93
+ | 1.8484 | 8.7619 | 1025 | 2.6832 |
94
+ | 1.8815 | 8.9759 | 1050 | 2.6814 |
95
+ | 1.8082 | 9.1883 | 1075 | 2.6836 |
96
+ | 1.8302 | 9.4024 | 1100 | 2.6839 |
97
+ | 1.8822 | 9.6164 | 1125 | 2.6824 |
98
+ | 1.8648 | 9.8304 | 1150 | 2.6822 |
99
 
100
 
101
  ### Framework versions
epoch_metrics_log.csv CHANGED
@@ -17,3 +17,5 @@ timestamp,epoch,split,samples,accuracy,sensitivity,specificity,tp,tn,fp,fn
17
  2025-09-04T22:57:56.099301,8,eval,440,0.981818,0.963636,1.000000,212,220,0,8
18
  2025-09-05T03:13:22.648636,9,train,7476,1.000000,1.000000,1.000000,1560,5916,0,0
19
  2025-09-05T03:13:22.648636,9,eval,440,0.981818,0.963636,1.000000,212,220,0,8
 
 
 
17
  2025-09-04T22:57:56.099301,8,eval,440,0.981818,0.963636,1.000000,212,220,0,8
18
  2025-09-05T03:13:22.648636,9,train,7476,1.000000,1.000000,1.000000,1560,5916,0,0
19
  2025-09-05T03:13:22.648636,9,eval,440,0.981818,0.963636,1.000000,212,220,0,8
20
+ 2025-09-05T07:26:19.264439,10,train,7476,1.000000,1.000000,1.000000,1560,5916,0,0
21
+ 2025-09-05T07:26:19.264439,10,eval,440,0.981818,0.963636,1.000000,212,220,0,8
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44bc3254b87075404a808e63c3e14e127399112ee0e01bcc6fce02c8d4bbbe30
3
  size 3513309984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd54f6365d24bb810ef86ade781a13406c141549c01b467d4a4aabcf06cd1f3
3
  size 3513309984