Hugging Face's logo

nemik
/
frost-vision-v2-google_vit-base-patch16-224-v2024-11-14

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
nemik commited on
Commit
ddb3152
·
verified ·
1 Parent(s): ed5f811

Model save

Browse files
Files changed (3) hide show
  1. README.md +34 -34
  2. model.safetensors +1 -1
  3. runs/Nov14_23-23-05_ba4b501b14a9/events.out.tfevents.1731626593.ba4b501b14a9.833.2 +2 -2
README.md CHANGED
@@ -26,16 +26,16 @@ model-index:
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
- value: 0.924074074074074
30
  - name: F1
31
  type: f1
32
- value: 0.8069073783359497
33
  - name: Precision
34
  type: precision
35
- value: 0.8524046434494196
36
  - name: Recall
37
  type: recall
38
- value: 0.7660208643815202
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
45
 
46
  This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the webdataset dataset.
47
  It achieves the following results on the evaluation set:
48
- - Loss: 0.1858
49
- - Accuracy: 0.9241
50
- - F1: 0.8069
51
- - Precision: 0.8524
52
- - Recall: 0.7660
53
 
54
  ## Model description
55
 
@@ -68,7 +68,7 @@ More information needed
68
  ### Training hyperparameters
69
 
70
  The following hyperparameters were used during training:
71
- - learning_rate: 0.0002
72
  - train_batch_size: 16
73
  - eval_batch_size: 8
74
  - seed: 42
@@ -82,30 +82,30 @@ The following hyperparameters were used during training:
82
 
83
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
84
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
85
- | 0.2436 | 1.2346 | 100 | 0.2455 | 0.9012 | 0.7444 | 0.8021 | 0.6945 |
86
- | 0.1639 | 2.4691 | 200 | 0.2007 | 0.9173 | 0.7982 | 0.8067 | 0.7899 |
87
- | 0.188 | 3.7037 | 300 | 0.1913 | 0.9219 | 0.8064 | 0.8286 | 0.7854 |
88
- | 0.1695 | 4.9383 | 400 | 0.1825 | 0.9244 | 0.8168 | 0.8198 | 0.8137 |
89
- | 0.1204 | 6.1728 | 500 | 0.1858 | 0.9241 | 0.8069 | 0.8524 | 0.7660 |
90
- | 0.1268 | 7.4074 | 600 | 0.1839 | 0.9222 | 0.8062 | 0.8331 | 0.7809 |
91
- | 0.1089 | 8.6420 | 700 | 0.1815 | 0.9272 | 0.8215 | 0.8341 | 0.8092 |
92
- | 0.0863 | 9.8765 | 800 | 0.2034 | 0.9241 | 0.8096 | 0.8422 | 0.7794 |
93
- | 0.0758 | 11.1111 | 900 | 0.1933 | 0.9293 | 0.8287 | 0.8318 | 0.8256 |
94
- | 0.0605 | 12.3457 | 1000 | 0.1942 | 0.9302 | 0.8293 | 0.8407 | 0.8182 |
95
- | 0.0726 | 13.5802 | 1100 | 0.1977 | 0.9272 | 0.8239 | 0.8251 | 0.8227 |
96
- | 0.0637 | 14.8148 | 1200 | 0.2040 | 0.9312 | 0.8325 | 0.8394 | 0.8256 |
97
- | 0.0549 | 16.0494 | 1300 | 0.2173 | 0.9309 | 0.8326 | 0.8351 | 0.8301 |
98
- | 0.0566 | 17.2840 | 1400 | 0.2072 | 0.9315 | 0.8353 | 0.8316 | 0.8390 |
99
- | 0.0491 | 18.5185 | 1500 | 0.2157 | 0.9284 | 0.8248 | 0.8361 | 0.8137 |
100
- | 0.0496 | 19.7531 | 1600 | 0.1968 | 0.9352 | 0.8438 | 0.8425 | 0.8450 |
101
- | 0.0317 | 20.9877 | 1700 | 0.2053 | 0.9361 | 0.8456 | 0.8463 | 0.8450 |
102
- | 0.0326 | 22.2222 | 1800 | 0.2132 | 0.9306 | 0.8289 | 0.8463 | 0.8122 |
103
- | 0.0307 | 23.4568 | 1900 | 0.2119 | 0.9309 | 0.8331 | 0.8331 | 0.8331 |
104
- | 0.0147 | 24.6914 | 2000 | 0.2153 | 0.9358 | 0.8448 | 0.8460 | 0.8435 |
105
- | 0.03 | 25.9259 | 2100 | 0.2148 | 0.9343 | 0.8421 | 0.8378 | 0.8465 |
106
- | 0.0228 | 27.1605 | 2200 | 0.2091 | 0.9386 | 0.8512 | 0.8544 | 0.8480 |
107
- | 0.0167 | 28.3951 | 2300 | 0.2104 | 0.9361 | 0.8447 | 0.8505 | 0.8390 |
108
- | 0.0273 | 29.6296 | 2400 | 0.2089 | 0.9364 | 0.8458 | 0.8496 | 0.8420 |
109
 
110
 
111
  ### Framework versions
 
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
+ value: 0.9401234567901234
30
  - name: F1
31
  type: f1
32
+ value: 0.847723704866562
33
  - name: Precision
34
  type: precision
35
+ value: 0.864
36
  - name: Recall
37
  type: recall
38
+ value: 0.8320493066255779
39
  ---
40
 
41
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
45
 
46
  This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the webdataset dataset.
47
  It achieves the following results on the evaluation set:
48
+ - Loss: 0.1817
49
+ - Accuracy: 0.9401
50
+ - F1: 0.8477
51
+ - Precision: 0.864
52
+ - Recall: 0.8320
53
 
54
  ## Model description
55
 
 
68
  ### Training hyperparameters
69
 
70
  The following hyperparameters were used during training:
71
+ - learning_rate: 5e-05
72
  - train_batch_size: 16
73
  - eval_batch_size: 8
74
  - seed: 42
 
82
 
83
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
84
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
85
+ | 0.3381 | 1.2346 | 100 | 0.3271 | 0.8660 | 0.5669 | 0.8045 | 0.4376 |
86
+ | 0.2067 | 2.4691 | 200 | 0.2080 | 0.9194 | 0.7827 | 0.8514 | 0.7242 |
87
+ | 0.1745 | 3.7037 | 300 | 0.1864 | 0.9228 | 0.8003 | 0.8308 | 0.7720 |
88
+ | 0.1724 | 4.9383 | 400 | 0.1792 | 0.9299 | 0.8188 | 0.8493 | 0.7904 |
89
+ | 0.128 | 6.1728 | 500 | 0.1736 | 0.9327 | 0.8292 | 0.8437 | 0.8151 |
90
+ | 0.1034 | 7.4074 | 600 | 0.1672 | 0.9355 | 0.8348 | 0.8571 | 0.8136 |
91
+ | 0.0944 | 8.6420 | 700 | 0.1579 | 0.9392 | 0.8452 | 0.8622 | 0.8290 |
92
+ | 0.0919 | 9.8765 | 800 | 0.1631 | 0.9364 | 0.8347 | 0.8710 | 0.8012 |
93
+ | 0.0791 | 11.1111 | 900 | 0.1592 | 0.9380 | 0.8383 | 0.8771 | 0.8028 |
94
+ | 0.0684 | 12.3457 | 1000 | 0.1577 | 0.9389 | 0.8436 | 0.8655 | 0.8228 |
95
+ | 0.0737 | 13.5802 | 1100 | 0.1678 | 0.9380 | 0.8416 | 0.8613 | 0.8228 |
96
+ | 0.0625 | 14.8148 | 1200 | 0.1646 | 0.9426 | 0.8542 | 0.8692 | 0.8398 |
97
+ | 0.0591 | 16.0494 | 1300 | 0.1625 | 0.9432 | 0.8549 | 0.8756 | 0.8351 |
98
+ | 0.0464 | 17.2840 | 1400 | 0.1722 | 0.9386 | 0.8422 | 0.8676 | 0.8182 |
99
+ | 0.048 | 18.5185 | 1500 | 0.1694 | 0.9401 | 0.8472 | 0.8663 | 0.8290 |
100
+ | 0.0353 | 19.7531 | 1600 | 0.1715 | 0.9392 | 0.8462 | 0.8576 | 0.8351 |
101
+ | 0.0434 | 20.9877 | 1700 | 0.1817 | 0.9370 | 0.8386 | 0.8618 | 0.8166 |
102
+ | 0.0332 | 22.2222 | 1800 | 0.1797 | 0.9383 | 0.8423 | 0.8627 | 0.8228 |
103
+ | 0.0283 | 23.4568 | 1900 | 0.1810 | 0.9401 | 0.8482 | 0.8617 | 0.8351 |
104
+ | 0.0474 | 24.6914 | 2000 | 0.1765 | 0.9398 | 0.8454 | 0.8709 | 0.8213 |
105
+ | 0.0365 | 25.9259 | 2100 | 0.1835 | 0.9414 | 0.8516 | 0.8637 | 0.8398 |
106
+ | 0.0244 | 27.1605 | 2200 | 0.1822 | 0.9404 | 0.8479 | 0.8677 | 0.8290 |
107
+ | 0.0242 | 28.3951 | 2300 | 0.1808 | 0.9407 | 0.8483 | 0.8703 | 0.8274 |
108
+ | 0.0296 | 29.6296 | 2400 | 0.1817 | 0.9401 | 0.8477 | 0.864 | 0.8320 |
109
 
110
 
111
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c436f6f86794b49685ef25b7be43b700b676a77edf875bb928e0c96ea4ddc42
3
  size 343248584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3cf080cd5f5a587fa7aba51e6c1a12142700cb23936c4f30e96da42fc0c9d77
3
  size 343248584
runs/Nov14_23-23-05_ba4b501b14a9/events.out.tfevents.1731626593.ba4b501b14a9.833.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d3260da78a64b0c5e3baa98d61a0e273debb70ce58b045b55aaadfc125422c2
3
- size 57197
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50c1b1d2b40083564590021129df3755c26e6987145fe3e26a73d8c125e85547
3
+ size 68512