Commit
•
a593058
1
Parent(s):
c019f16
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/swin-tiny-patch4-window7-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: swin-tiny-patch4-window7-224-finetuned-fish
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
name: Image Classification
|
15 |
+
type: image-classification
|
16 |
+
dataset:
|
17 |
+
name: imagefolder
|
18 |
+
type: imagefolder
|
19 |
+
config: default
|
20 |
+
split: train
|
21 |
+
args: default
|
22 |
+
metrics:
|
23 |
+
- name: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.8823529411764706
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# swin-tiny-patch4-window7-224-finetuned-fish
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.1585
|
36 |
+
- Accuracy: 0.8824
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 32
|
57 |
+
- eval_batch_size: 32
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 128
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
64 |
+
- num_epochs: 75
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| No log | 0.8 | 1 | 1.8035 | 0.2941 |
|
71 |
+
| No log | 1.6 | 2 | 1.7861 | 0.2941 |
|
72 |
+
| No log | 2.4 | 3 | 1.7554 | 0.2941 |
|
73 |
+
| No log | 4.0 | 5 | 1.6954 | 0.3529 |
|
74 |
+
| No log | 4.8 | 6 | 1.6780 | 0.4118 |
|
75 |
+
| No log | 5.6 | 7 | 1.6536 | 0.4118 |
|
76 |
+
| No log | 6.4 | 8 | 1.6222 | 0.4118 |
|
77 |
+
| 1.6467 | 8.0 | 10 | 1.4682 | 0.5294 |
|
78 |
+
| 1.6467 | 8.8 | 11 | 1.3261 | 0.5294 |
|
79 |
+
| 1.6467 | 9.6 | 12 | 1.1888 | 0.5294 |
|
80 |
+
| 1.6467 | 10.4 | 13 | 1.0433 | 0.5294 |
|
81 |
+
| 1.6467 | 12.0 | 15 | 0.8212 | 0.5882 |
|
82 |
+
| 1.6467 | 12.8 | 16 | 0.7240 | 0.7059 |
|
83 |
+
| 1.6467 | 13.6 | 17 | 0.6390 | 0.8235 |
|
84 |
+
| 1.6467 | 14.4 | 18 | 0.5594 | 0.8824 |
|
85 |
+
| 0.782 | 16.0 | 20 | 0.4647 | 0.8235 |
|
86 |
+
| 0.782 | 16.8 | 21 | 0.4264 | 0.9412 |
|
87 |
+
| 0.782 | 17.6 | 22 | 0.3983 | 0.9412 |
|
88 |
+
| 0.782 | 18.4 | 23 | 0.3760 | 0.9412 |
|
89 |
+
| 0.782 | 20.0 | 25 | 0.3751 | 0.8824 |
|
90 |
+
| 0.782 | 20.8 | 26 | 0.3553 | 0.8824 |
|
91 |
+
| 0.782 | 21.6 | 27 | 0.3161 | 0.8824 |
|
92 |
+
| 0.782 | 22.4 | 28 | 0.2706 | 0.9412 |
|
93 |
+
| 0.3228 | 24.0 | 30 | 0.2100 | 0.9412 |
|
94 |
+
| 0.3228 | 24.8 | 31 | 0.1885 | 0.9412 |
|
95 |
+
| 0.3228 | 25.6 | 32 | 0.1727 | 0.9412 |
|
96 |
+
| 0.3228 | 26.4 | 33 | 0.1818 | 0.9412 |
|
97 |
+
| 0.3228 | 28.0 | 35 | 0.1959 | 0.8824 |
|
98 |
+
| 0.3228 | 28.8 | 36 | 0.1889 | 0.9412 |
|
99 |
+
| 0.3228 | 29.6 | 37 | 0.1995 | 0.8824 |
|
100 |
+
| 0.3228 | 30.4 | 38 | 0.2093 | 0.8824 |
|
101 |
+
| 0.2375 | 32.0 | 40 | 0.1869 | 0.9412 |
|
102 |
+
| 0.2375 | 32.8 | 41 | 0.1648 | 0.9412 |
|
103 |
+
| 0.2375 | 33.6 | 42 | 0.1576 | 0.9412 |
|
104 |
+
| 0.2375 | 34.4 | 43 | 0.1709 | 0.9412 |
|
105 |
+
| 0.2375 | 36.0 | 45 | 0.1717 | 0.9412 |
|
106 |
+
| 0.2375 | 36.8 | 46 | 0.1783 | 0.9412 |
|
107 |
+
| 0.2375 | 37.6 | 47 | 0.1993 | 0.8824 |
|
108 |
+
| 0.2375 | 38.4 | 48 | 0.2085 | 0.8824 |
|
109 |
+
| 0.1897 | 40.0 | 50 | 0.2028 | 0.8824 |
|
110 |
+
| 0.1897 | 40.8 | 51 | 0.1704 | 0.9412 |
|
111 |
+
| 0.1897 | 41.6 | 52 | 0.1520 | 0.9412 |
|
112 |
+
| 0.1897 | 42.4 | 53 | 0.1325 | 0.9412 |
|
113 |
+
| 0.1897 | 44.0 | 55 | 0.1451 | 0.9412 |
|
114 |
+
| 0.1897 | 44.8 | 56 | 0.1664 | 0.9412 |
|
115 |
+
| 0.1897 | 45.6 | 57 | 0.1927 | 0.8824 |
|
116 |
+
| 0.1897 | 46.4 | 58 | 0.2202 | 0.8824 |
|
117 |
+
| 0.1676 | 48.0 | 60 | 0.2569 | 0.8824 |
|
118 |
+
| 0.1676 | 48.8 | 61 | 0.2748 | 0.8824 |
|
119 |
+
| 0.1676 | 49.6 | 62 | 0.2612 | 0.8824 |
|
120 |
+
| 0.1676 | 50.4 | 63 | 0.2414 | 0.8824 |
|
121 |
+
| 0.1676 | 52.0 | 65 | 0.1842 | 0.8824 |
|
122 |
+
| 0.1676 | 52.8 | 66 | 0.1597 | 0.8824 |
|
123 |
+
| 0.1676 | 53.6 | 67 | 0.1447 | 0.8824 |
|
124 |
+
| 0.1676 | 54.4 | 68 | 0.1359 | 0.9412 |
|
125 |
+
| 0.1452 | 56.0 | 70 | 0.1367 | 0.9412 |
|
126 |
+
| 0.1452 | 56.8 | 71 | 0.1402 | 0.9412 |
|
127 |
+
| 0.1452 | 57.6 | 72 | 0.1462 | 0.8824 |
|
128 |
+
| 0.1452 | 58.4 | 73 | 0.1515 | 0.8824 |
|
129 |
+
| 0.1452 | 60.0 | 75 | 0.1585 | 0.8824 |
|
130 |
+
|
131 |
+
|
132 |
+
### Framework versions
|
133 |
+
|
134 |
+
- Transformers 4.40.0.dev0
|
135 |
+
- Pytorch 2.2.1+cu121
|
136 |
+
- Datasets 2.19.1
|
137 |
+
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 110358212
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:068ff123b7a2554bf2410a1cfc0ef6cb6e9c9c4cc8722e3a61f6b01445bdc76e
|
3 |
size 110358212
|
runs/May06_18-40-25_nandini-lokesh-reddy-mind/events.out.tfevents.1715035255.nandini-lokesh-reddy-mind.3082576.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05a4c5a896e671462bcdd1b111d5658a56c773c3335ec5994410c25ec5c2f4c3
|
3 |
+
size 26133
|