Hugging Face's logo

nemik
/
frost-vision-v2-google_vit-base-patch16-224-v2024-11-09

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Model card Files Metrics Community
nemik commited on
Commit
ad6b7b2
·
verified ·
1 Parent(s): 4a2af58

Model save

Browse files
Files changed (2) hide show
  1. README.md +30 -30
  2. model.safetensors +1 -1
README.md CHANGED
@@ -26,16 +26,16 @@ model-index:
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
- value: 0.9316901408450704
30
  - name: F1
31
  type: f1
32
- value: 0.8267857142857142
33
  - name: Precision
34
  type: precision
35
- value: 0.8312387791741472
36
  - name: Recall
37
  type: recall
38
- value: 0.822380106571936
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: 0.1769
49
- - Accuracy: 0.9317
50
- - F1: 0.8268
51
- - Precision: 0.8312
52
- - Recall: 0.8224
53
 
54
  ## Model description
55
 
@@ -82,27 +82,27 @@ The following hyperparameters were used during training:
82
 
83
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
84
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
85
- | 0.2067 | 1.4085 | 100 | 0.2229 | 0.9155 | 0.7736 | 0.8249 | 0.7282 |
86
- | 0.1989 | 2.8169 | 200 | 0.2252 | 0.9102 | 0.7650 | 0.7950 | 0.7371 |
87
- | 0.1364 | 4.2254 | 300 | 0.1834 | 0.9268 | 0.8163 | 0.8120 | 0.8206 |
88
- | 0.1368 | 5.6338 | 400 | 0.1874 | 0.9268 | 0.7981 | 0.8801 | 0.7300 |
89
- | 0.1197 | 7.0423 | 500 | 0.1769 | 0.9317 | 0.8268 | 0.8312 | 0.8224 |
90
- | 0.099 | 8.4507 | 600 | 0.1841 | 0.9313 | 0.8189 | 0.8580 | 0.7833 |
91
- | 0.0748 | 9.8592 | 700 | 0.1739 | 0.9359 | 0.8366 | 0.8457 | 0.8277 |
92
- | 0.0706 | 11.2676 | 800 | 0.1762 | 0.9373 | 0.8399 | 0.8506 | 0.8295 |
93
- | 0.0865 | 12.6761 | 900 | 0.1766 | 0.9408 | 0.8486 | 0.8611 | 0.8366 |
94
- | 0.061 | 14.0845 | 1000 | 0.1852 | 0.9380 | 0.8445 | 0.8401 | 0.8490 |
95
- | 0.0449 | 15.4930 | 1100 | 0.1795 | 0.9401 | 0.8482 | 0.8528 | 0.8437 |
96
- | 0.0488 | 16.9014 | 1200 | 0.2065 | 0.9310 | 0.8253 | 0.8283 | 0.8224 |
97
- | 0.0483 | 18.3099 | 1300 | 0.1977 | 0.9377 | 0.8427 | 0.8434 | 0.8419 |
98
- | 0.0317 | 19.7183 | 1400 | 0.2006 | 0.9370 | 0.8395 | 0.8478 | 0.8313 |
99
- | 0.0411 | 21.1268 | 1500 | 0.2068 | 0.9363 | 0.8368 | 0.8498 | 0.8242 |
100
- | 0.0512 | 22.5352 | 1600 | 0.2056 | 0.9391 | 0.8446 | 0.8545 | 0.8348 |
101
- | 0.0329 | 23.9437 | 1700 | 0.2127 | 0.9338 | 0.8294 | 0.8479 | 0.8117 |
102
- | 0.0197 | 25.3521 | 1800 | 0.2122 | 0.9335 | 0.8286 | 0.8463 | 0.8117 |
103
- | 0.0316 | 26.7606 | 1900 | 0.2050 | 0.9373 | 0.8399 | 0.8506 | 0.8295 |
104
- | 0.0133 | 28.1690 | 2000 | 0.2019 | 0.9408 | 0.8495 | 0.8571 | 0.8419 |
105
- | 0.0181 | 29.5775 | 2100 | 0.2031 | 0.9401 | 0.8474 | 0.8566 | 0.8384 |
106
 
107
 
108
  ### Framework versions
 
26
  metrics:
27
  - name: Accuracy
28
  type: accuracy
29
+ value: 0.9415492957746479
30
  - name: F1
31
  type: f1
32
+ value: 0.8501805054151624
33
  - name: Precision
34
  type: precision
35
+ value: 0.8517179023508138
36
  - name: Recall
37
  type: recall
38
+ value: 0.8486486486486486
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: 0.1914
49
+ - Accuracy: 0.9415
50
+ - F1: 0.8502
51
+ - Precision: 0.8517
52
+ - Recall: 0.8486
53
 
54
  ## Model description
55
 
 
82
 
83
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
84
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
85
+ | 0.2398 | 1.4085 | 100 | 0.2096 | 0.9215 | 0.7833 | 0.8502 | 0.7261 |
86
+ | 0.1746 | 2.8169 | 200 | 0.1676 | 0.9370 | 0.8362 | 0.8494 | 0.8234 |
87
+ | 0.1316 | 4.2254 | 300 | 0.1750 | 0.9282 | 0.8125 | 0.8293 | 0.7964 |
88
+ | 0.1305 | 5.6338 | 400 | 0.1671 | 0.9342 | 0.8270 | 0.8498 | 0.8054 |
89
+ | 0.1119 | 7.0423 | 500 | 0.1747 | 0.9317 | 0.8240 | 0.8300 | 0.8180 |
90
+ | 0.0913 | 8.4507 | 600 | 0.1515 | 0.9415 | 0.8505 | 0.8505 | 0.8505 |
91
+ | 0.0964 | 9.8592 | 700 | 0.1680 | 0.9377 | 0.8418 | 0.8351 | 0.8486 |
92
+ | 0.0659 | 11.2676 | 800 | 0.1891 | 0.9275 | 0.8144 | 0.8144 | 0.8144 |
93
+ | 0.0706 | 12.6761 | 900 | 0.1788 | 0.9320 | 0.8234 | 0.8364 | 0.8108 |
94
+ | 0.069 | 14.0845 | 1000 | 0.1716 | 0.9412 | 0.8486 | 0.8540 | 0.8432 |
95
+ | 0.0543 | 15.4930 | 1100 | 0.1847 | 0.9363 | 0.8341 | 0.8489 | 0.8198 |
96
+ | 0.0515 | 16.9014 | 1200 | 0.1741 | 0.9408 | 0.8470 | 0.8564 | 0.8378 |
97
+ | 0.0489 | 18.3099 | 1300 | 0.1793 | 0.9461 | 0.8620 | 0.8628 | 0.8613 |
98
+ | 0.0339 | 19.7183 | 1400 | 0.1806 | 0.9444 | 0.8569 | 0.8616 | 0.8523 |
99
+ | 0.0409 | 21.1268 | 1500 | 0.1784 | 0.9440 | 0.8569 | 0.8561 | 0.8577 |
100
+ | 0.0275 | 22.5352 | 1600 | 0.1839 | 0.9437 | 0.8548 | 0.8611 | 0.8486 |
101
+ | 0.0231 | 23.9437 | 1700 | 0.1865 | 0.9415 | 0.8480 | 0.8622 | 0.8342 |
102
+ | 0.0204 | 25.3521 | 1800 | 0.1884 | 0.9405 | 0.8482 | 0.8459 | 0.8505 |
103
+ | 0.0245 | 26.7606 | 1900 | 0.1935 | 0.9377 | 0.8410 | 0.8387 | 0.8432 |
104
+ | 0.0202 | 28.1690 | 2000 | 0.1888 | 0.9394 | 0.8456 | 0.8426 | 0.8486 |
105
+ | 0.0187 | 29.5775 | 2100 | 0.1914 | 0.9415 | 0.8502 | 0.8517 | 0.8486 |
106
 
107
 
108
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4989188594d66e59d0dcee4f866c95f598de87a31e181127958670277937829a
3
  size 343248584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5829499b00ca7322b48a4b43bd3e8d1eff088f53b33a811c343bc6951309fc45
3
  size 343248584