Hugging Face's logo

p1atdev
/
siglip-tagger-test-3

Image Classification
Transformers
Safetensors
siglip_vision_model
Generated from Trainer
siglip
custom_code
Inference Endpoints
Model card Files Community
3
p1atdev commited on
Commit
bf982bf
•
1 Parent(s): 97ceaa0

Model save

Browse files
Files changed (2) hide show
  1. README.md +61 -31
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,26 +1,26 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/siglip-base-patch16-512
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
8
  - f1
9
  model-index:
10
- - name: siglip-tagger-test-2
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
- # siglip-tagger-test-2
18
 
19
- This model is a fine-tuned version of [google/siglip-base-patch16-512](https://huggingface.co/google/siglip-base-patch16-512) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 364.7850
22
- - Accuracy: 0.2539
23
- - F1: 0.9967
24
 
25
  ## Model description
26
 
@@ -40,38 +40,68 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 0.0001
43
- - train_batch_size: 32
44
- - eval_batch_size: 16
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: cosine
48
- - lr_scheduler_warmup_steps: 100
49
- - num_epochs: 20
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
- | 1496.9876 | 1.0 | 141 | 691.3267 | 0.1242 | 0.9957 |
56
- | 860.0218 | 2.0 | 282 | 433.5286 | 0.1626 | 0.9965 |
57
- | 775.4277 | 3.0 | 423 | 409.0374 | 0.1827 | 0.9966 |
58
- | 697.2465 | 4.0 | 564 | 396.5604 | 0.2025 | 0.9966 |
59
- | 582.6023 | 5.0 | 705 | 388.3294 | 0.2065 | 0.9966 |
60
- | 617.5087 | 6.0 | 846 | 382.2605 | 0.2213 | 0.9966 |
61
- | 627.533 | 7.0 | 987 | 377.6726 | 0.2269 | 0.9967 |
62
- | 595.4033 | 8.0 | 1128 | 374.3268 | 0.2327 | 0.9967 |
63
- | 593.3854 | 9.0 | 1269 | 371.4181 | 0.2409 | 0.9967 |
64
- | 537.9777 | 10.0 | 1410 | 369.5010 | 0.2421 | 0.9967 |
65
- | 552.3083 | 11.0 | 1551 | 368.0743 | 0.2468 | 0.9967 |
66
- | 570.5438 | 12.0 | 1692 | 366.8302 | 0.2498 | 0.9967 |
67
- | 507.5343 | 13.0 | 1833 | 366.1787 | 0.2499 | 0.9967 |
68
- | 515.5528 | 14.0 | 1974 | 365.5653 | 0.2525 | 0.9967 |
69
- | 458.5096 | 15.0 | 2115 | 365.1838 | 0.2528 | 0.9967 |
70
- | 515.6953 | 16.0 | 2256 | 364.9844 | 0.2535 | 0.9967 |
71
- | 533.7929 | 17.0 | 2397 | 364.8577 | 0.2538 | 0.9967 |
72
- | 520.3728 | 18.0 | 2538 | 364.8066 | 0.2537 | 0.9967 |
73
- | 525.1097 | 19.0 | 2679 | 364.7850 | 0.2539 | 0.9967 |
74
- | 482.0612 | 20.0 | 2820 | 364.7876 | 0.2539 | 0.9967 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: google/siglip-so400m-patch14-384
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
8
  - f1
9
  model-index:
10
+ - name: siglip-tagger-test-3
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ # siglip-tagger-test-3
18
 
19
+ This model is a fine-tuned version of [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 692.4745
22
+ - Accuracy: 0.3465
23
+ - F1: 0.9969
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 0.0001
43
+ - train_batch_size: 64
44
+ - eval_batch_size: 32
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_steps: 10
49
+ - num_epochs: 50
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
55
+ | 1066.981 | 1.0 | 71 | 1873.5417 | 0.1412 | 0.9939 |
56
+ | 547.3158 | 2.0 | 142 | 934.3269 | 0.1904 | 0.9964 |
57
+ | 534.6942 | 3.0 | 213 | 814.0771 | 0.2170 | 0.9966 |
58
+ | 414.1278 | 4.0 | 284 | 774.0230 | 0.2398 | 0.9967 |
59
+ | 365.4994 | 5.0 | 355 | 751.2046 | 0.2459 | 0.9967 |
60
+ | 352.3663 | 6.0 | 426 | 735.6580 | 0.2610 | 0.9967 |
61
+ | 414.3976 | 7.0 | 497 | 723.2065 | 0.2684 | 0.9968 |
62
+ | 350.8201 | 8.0 | 568 | 714.0453 | 0.2788 | 0.9968 |
63
+ | 364.5016 | 9.0 | 639 | 706.5261 | 0.2890 | 0.9968 |
64
+ | 309.1184 | 10.0 | 710 | 700.7808 | 0.2933 | 0.9968 |
65
+ | 288.5186 | 11.0 | 781 | 695.7027 | 0.3008 | 0.9968 |
66
+ | 287.4452 | 12.0 | 852 | 691.5306 | 0.3037 | 0.9968 |
67
+ | 280.9088 | 13.0 | 923 | 688.8063 | 0.3084 | 0.9969 |
68
+ | 296.8389 | 14.0 | 994 | 686.1077 | 0.3132 | 0.9968 |
69
+ | 265.1467 | 15.0 | 1065 | 683.7382 | 0.3167 | 0.9969 |
70
+ | 268.5263 | 16.0 | 1136 | 682.1683 | 0.3206 | 0.9969 |
71
+ | 309.7871 | 17.0 | 1207 | 681.1995 | 0.3199 | 0.9969 |
72
+ | 307.6475 | 18.0 | 1278 | 680.1700 | 0.3230 | 0.9969 |
73
+ | 262.0677 | 19.0 | 1349 | 679.2177 | 0.3270 | 0.9969 |
74
+ | 275.3823 | 20.0 | 1420 | 678.9730 | 0.3294 | 0.9969 |
75
+ | 273.984 | 21.0 | 1491 | 678.6031 | 0.3318 | 0.9969 |
76
+ | 273.5361 | 22.0 | 1562 | 678.1285 | 0.3332 | 0.9969 |
77
+ | 279.6474 | 23.0 | 1633 | 678.4264 | 0.3348 | 0.9969 |
78
+ | 232.5045 | 24.0 | 1704 | 678.3773 | 0.3357 | 0.9969 |
79
+ | 269.621 | 25.0 | 1775 | 678.4922 | 0.3372 | 0.9969 |
80
+ | 289.8389 | 26.0 | 1846 | 679.0094 | 0.3397 | 0.9969 |
81
+ | 256.7373 | 27.0 | 1917 | 679.5618 | 0.3407 | 0.9969 |
82
+ | 262.3969 | 28.0 | 1988 | 680.1168 | 0.3414 | 0.9969 |
83
+ | 266.2439 | 29.0 | 2059 | 681.0101 | 0.3421 | 0.9969 |
84
+ | 247.7932 | 30.0 | 2130 | 681.9800 | 0.3422 | 0.9969 |
85
+ | 246.8083 | 31.0 | 2201 | 682.8550 | 0.3416 | 0.9969 |
86
+ | 270.827 | 32.0 | 2272 | 683.9250 | 0.3434 | 0.9969 |
87
+ | 256.4384 | 33.0 | 2343 | 685.0451 | 0.3448 | 0.9969 |
88
+ | 270.461 | 34.0 | 2414 | 686.2427 | 0.3439 | 0.9969 |
89
+ | 253.8104 | 35.0 | 2485 | 687.4274 | 0.3441 | 0.9969 |
90
+ | 265.532 | 36.0 | 2556 | 688.4856 | 0.3451 | 0.9969 |
91
+ | 249.1426 | 37.0 | 2627 | 689.5027 | 0.3457 | 0.9969 |
92
+ | 229.5651 | 38.0 | 2698 | 690.4455 | 0.3455 | 0.9969 |
93
+ | 251.9008 | 39.0 | 2769 | 691.2324 | 0.3463 | 0.9969 |
94
+ | 281.8228 | 40.0 | 2840 | 691.7993 | 0.3464 | 0.9969 |
95
+ | 242.5272 | 41.0 | 2911 | 692.1788 | 0.3465 | 0.9969 |
96
+ | 229.5605 | 42.0 | 2982 | 692.3799 | 0.3465 | 0.9969 |
97
+ | 245.0876 | 43.0 | 3053 | 692.4745 | 0.3465 | 0.9969 |
98
+ | 271.22 | 44.0 | 3124 | 692.5084 | 0.3465 | 0.9969 |
99
+ | 244.3045 | 45.0 | 3195 | 692.5108 | 0.3465 | 0.9969 |
100
+ | 243.9542 | 46.0 | 3266 | 692.5128 | 0.3465 | 0.9969 |
101
+ | 274.6664 | 47.0 | 3337 | 692.5095 | 0.3465 | 0.9969 |
102
+ | 231.1361 | 48.0 | 3408 | 692.5107 | 0.3465 | 0.9969 |
103
+ | 274.5513 | 49.0 | 3479 | 692.5108 | 0.3465 | 0.9969 |
104
+ | 316.0833 | 50.0 | 3550 | 692.5107 | 0.3465 | 0.9969 |
105
 
106
 
107
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be643eb7ab1f807afd63f0222b463eea5d0733a602ed4deb28bc92833d3647c5
3
  size 878455682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce46ef29aec79fcf0fbe8280521acb10381ef5000706af5f870c08af781fb3eb
3
  size 878455682