Commit
•
1a04c62
1
Parent(s):
9816768
update model card README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
-
value: 0.
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 0.
|
35 |
-
- Accuracy: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -57,65 +57,69 @@ The following hyperparameters were used during training:
|
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
-
- num_epochs:
|
61 |
- mixed_precision_training: Native AMP
|
62 |
|
63 |
### Training results
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
-
|
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
-
| 0.
|
98 |
-
| 0.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.
|
102 |
-
| 0.
|
103 |
-
| 0.
|
104 |
-
| 0.
|
105 |
-
| 0.
|
106 |
-
| 0.
|
107 |
-
| 0.
|
108 |
-
| 0.
|
109 |
-
| 0.
|
110 |
-
| 0.
|
111 |
-
| 0.
|
112 |
-
| 0.
|
113 |
-
| 0.
|
114 |
-
| 0.
|
115 |
-
| 0.
|
116 |
-
| 0.
|
117 |
-
| 0.
|
118 |
-
| 0.
|
|
|
|
|
|
|
|
|
119 |
|
120 |
|
121 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
+
value: 0.9429097605893186
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.2056
|
35 |
+
- Accuracy: 0.9429
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 14
|
61 |
- mixed_precision_training: Native AMP
|
62 |
|
63 |
### Training results
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| 0.4109 | 0.25 | 100 | 0.5246 | 0.8195 |
|
68 |
+
| 0.248 | 0.49 | 200 | 0.4594 | 0.8459 |
|
69 |
+
| 0.3389 | 0.74 | 300 | 0.4443 | 0.8551 |
|
70 |
+
| 0.4217 | 0.98 | 400 | 0.4500 | 0.8490 |
|
71 |
+
| 0.2815 | 1.23 | 500 | 0.3939 | 0.8588 |
|
72 |
+
| 0.3077 | 1.47 | 600 | 0.3813 | 0.8643 |
|
73 |
+
| 0.5098 | 1.72 | 700 | 0.4276 | 0.8576 |
|
74 |
+
| 0.3191 | 1.97 | 800 | 0.4218 | 0.8570 |
|
75 |
+
| 0.2761 | 2.21 | 900 | 0.3404 | 0.8883 |
|
76 |
+
| 0.2184 | 2.46 | 1000 | 0.3226 | 0.8889 |
|
77 |
+
| 0.3106 | 2.7 | 1100 | 0.3621 | 0.8729 |
|
78 |
+
| 0.3118 | 2.95 | 1200 | 0.3656 | 0.8797 |
|
79 |
+
| 0.2857 | 3.19 | 1300 | 0.3123 | 0.9012 |
|
80 |
+
| 0.2193 | 3.44 | 1400 | 0.2907 | 0.9048 |
|
81 |
+
| 0.2959 | 3.69 | 1500 | 0.3544 | 0.8840 |
|
82 |
+
| 0.3176 | 3.93 | 1600 | 0.3389 | 0.8877 |
|
83 |
+
| 0.2927 | 4.18 | 1700 | 0.3418 | 0.8864 |
|
84 |
+
| 0.2719 | 4.42 | 1800 | 0.3558 | 0.8821 |
|
85 |
+
| 0.2176 | 4.67 | 1900 | 0.3374 | 0.8981 |
|
86 |
+
| 0.1912 | 4.91 | 2000 | 0.3092 | 0.8999 |
|
87 |
+
| 0.2272 | 5.16 | 2100 | 0.2902 | 0.9128 |
|
88 |
+
| 0.175 | 5.41 | 2200 | 0.3002 | 0.9134 |
|
89 |
+
| 0.1513 | 5.65 | 2300 | 0.3356 | 0.8999 |
|
90 |
+
| 0.1439 | 5.9 | 2400 | 0.2954 | 0.9061 |
|
91 |
+
| 0.2341 | 6.14 | 2500 | 0.3343 | 0.8993 |
|
92 |
+
| 0.2178 | 6.39 | 2600 | 0.2891 | 0.9122 |
|
93 |
+
| 0.1731 | 6.63 | 2700 | 0.3235 | 0.9030 |
|
94 |
+
| 0.19 | 6.88 | 2800 | 0.2938 | 0.9042 |
|
95 |
+
| 0.1168 | 7.13 | 2900 | 0.2937 | 0.9110 |
|
96 |
+
| 0.1528 | 7.37 | 3000 | 0.2963 | 0.9104 |
|
97 |
+
| 0.1374 | 7.62 | 3100 | 0.2929 | 0.9085 |
|
98 |
+
| 0.2204 | 7.86 | 3200 | 0.3257 | 0.9048 |
|
99 |
+
| 0.1519 | 8.11 | 3300 | 0.2683 | 0.9171 |
|
100 |
+
| 0.0711 | 8.35 | 3400 | 0.2609 | 0.9251 |
|
101 |
+
| 0.1019 | 8.6 | 3500 | 0.2523 | 0.9251 |
|
102 |
+
| 0.1764 | 8.85 | 3600 | 0.2769 | 0.9202 |
|
103 |
+
| 0.0849 | 9.09 | 3700 | 0.2668 | 0.9214 |
|
104 |
+
| 0.2077 | 9.34 | 3800 | 0.2914 | 0.9165 |
|
105 |
+
| 0.2543 | 9.58 | 3900 | 0.2507 | 0.9251 |
|
106 |
+
| 0.0347 | 9.83 | 4000 | 0.2333 | 0.9269 |
|
107 |
+
| 0.0731 | 10.07 | 4100 | 0.2598 | 0.9269 |
|
108 |
+
| 0.238 | 10.32 | 4200 | 0.2675 | 0.9294 |
|
109 |
+
| 0.1114 | 10.57 | 4300 | 0.2317 | 0.9269 |
|
110 |
+
| 0.0836 | 10.81 | 4400 | 0.2344 | 0.9288 |
|
111 |
+
| 0.0598 | 11.06 | 4500 | 0.2499 | 0.9276 |
|
112 |
+
| 0.0488 | 11.3 | 4600 | 0.2361 | 0.9288 |
|
113 |
+
| 0.1437 | 11.55 | 4700 | 0.2551 | 0.9282 |
|
114 |
+
| 0.0773 | 11.79 | 4800 | 0.2276 | 0.9294 |
|
115 |
+
| 0.1013 | 12.04 | 4900 | 0.2537 | 0.9288 |
|
116 |
+
| 0.0943 | 12.29 | 5000 | 0.2368 | 0.9331 |
|
117 |
+
| 0.0538 | 12.53 | 5100 | 0.2157 | 0.9349 |
|
118 |
+
| 0.0425 | 12.78 | 5200 | 0.2330 | 0.9411 |
|
119 |
+
| 0.1301 | 13.02 | 5300 | 0.2564 | 0.9331 |
|
120 |
+
| 0.062 | 13.27 | 5400 | 0.2193 | 0.9417 |
|
121 |
+
| 0.1012 | 13.51 | 5500 | 0.1873 | 0.9466 |
|
122 |
+
| 0.1643 | 13.76 | 5600 | 0.2056 | 0.9429 |
|
123 |
|
124 |
|
125 |
### Framework versions
|