End of training
Browse files
README.md
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: google/vit-base-patch16-224-in21k
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- imagefolder
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: image_classification
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Image Classification
|
16 |
+
type: image-classification
|
17 |
+
dataset:
|
18 |
+
name: imagefolder
|
19 |
+
type: imagefolder
|
20 |
+
config: default
|
21 |
+
split: train
|
22 |
+
args: default
|
23 |
+
metrics:
|
24 |
+
- name: Accuracy
|
25 |
+
type: accuracy
|
26 |
+
value: 0.5625
|
27 |
+
---
|
28 |
+
|
29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
30 |
+
should probably proofread and complete it, then remove this comment. -->
|
31 |
+
|
32 |
+
# image_classification
|
33 |
+
|
34 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
35 |
+
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 1.2386
|
37 |
+
- Accuracy: 0.5625
|
38 |
+
|
39 |
+
## Model description
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Intended uses & limitations
|
44 |
+
|
45 |
+
More information needed
|
46 |
+
|
47 |
+
## Training and evaluation data
|
48 |
+
|
49 |
+
More information needed
|
50 |
+
|
51 |
+
## Training procedure
|
52 |
+
|
53 |
+
### Training hyperparameters
|
54 |
+
|
55 |
+
The following hyperparameters were used during training:
|
56 |
+
- learning_rate: 5e-05
|
57 |
+
- train_batch_size: 16
|
58 |
+
- eval_batch_size: 16
|
59 |
+
- seed: 42
|
60 |
+
- gradient_accumulation_steps: 4
|
61 |
+
- total_train_batch_size: 64
|
62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
63 |
+
- lr_scheduler_type: linear
|
64 |
+
- lr_scheduler_warmup_ratio: 0.1
|
65 |
+
- num_epochs: 30
|
66 |
+
|
67 |
+
### Training results
|
68 |
+
|
69 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
70 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
71 |
+
| 2.0874 | 1.0 | 10 | 2.0621 | 0.2313 |
|
72 |
+
| 2.036 | 2.0 | 20 | 2.0392 | 0.2375 |
|
73 |
+
| 1.9297 | 3.0 | 30 | 1.9592 | 0.3 |
|
74 |
+
| 1.7723 | 4.0 | 40 | 1.7877 | 0.3937 |
|
75 |
+
| 1.6184 | 5.0 | 50 | 1.6475 | 0.45 |
|
76 |
+
| 1.5407 | 6.0 | 60 | 1.5514 | 0.4875 |
|
77 |
+
| 1.4197 | 7.0 | 70 | 1.4967 | 0.4938 |
|
78 |
+
| 1.3092 | 8.0 | 80 | 1.4332 | 0.4813 |
|
79 |
+
| 1.1251 | 9.0 | 90 | 1.4457 | 0.4688 |
|
80 |
+
| 1.2081 | 10.0 | 100 | 1.3603 | 0.4938 |
|
81 |
+
| 0.9803 | 11.0 | 110 | 1.3501 | 0.5188 |
|
82 |
+
| 1.0105 | 12.0 | 120 | 1.3212 | 0.55 |
|
83 |
+
| 0.9264 | 13.0 | 130 | 1.2895 | 0.575 |
|
84 |
+
| 0.9229 | 14.0 | 140 | 1.2882 | 0.5188 |
|
85 |
+
| 0.9397 | 15.0 | 150 | 1.4027 | 0.475 |
|
86 |
+
| 0.8322 | 16.0 | 160 | 1.2824 | 0.5312 |
|
87 |
+
| 0.8185 | 17.0 | 170 | 1.3025 | 0.5 |
|
88 |
+
| 0.7592 | 18.0 | 180 | 1.3629 | 0.475 |
|
89 |
+
| 0.7416 | 19.0 | 190 | 1.3221 | 0.5437 |
|
90 |
+
| 0.6323 | 20.0 | 200 | 1.2714 | 0.5563 |
|
91 |
+
| 0.6453 | 21.0 | 210 | 1.3015 | 0.4938 |
|
92 |
+
| 0.6049 | 22.0 | 220 | 1.3065 | 0.5375 |
|
93 |
+
| 0.5919 | 23.0 | 230 | 1.2579 | 0.5375 |
|
94 |
+
| 0.5354 | 24.0 | 240 | 1.2428 | 0.55 |
|
95 |
+
| 0.6379 | 25.0 | 250 | 1.2884 | 0.5375 |
|
96 |
+
| 0.5681 | 26.0 | 260 | 1.2201 | 0.5938 |
|
97 |
+
| 0.4275 | 27.0 | 270 | 1.3199 | 0.4875 |
|
98 |
+
| 0.4791 | 28.0 | 280 | 1.3027 | 0.5312 |
|
99 |
+
| 0.4693 | 29.0 | 290 | 1.3737 | 0.4813 |
|
100 |
+
| 0.5528 | 30.0 | 300 | 1.3342 | 0.4688 |
|
101 |
+
|
102 |
+
|
103 |
+
### Framework versions
|
104 |
+
|
105 |
+
- Transformers 4.44.2
|
106 |
+
- Pytorch 2.4.0+cu121
|
107 |
+
- Datasets 2.21.0
|
108 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343242432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c292d028197ddd067870ce0067d2ffb44a6d416020d09ac2d05a3001449745e2
|
3 |
size 343242432
|
runs/Sep06_00-21-52_d902e596bcd6/events.out.tfevents.1725582137.d902e596bcd6.3651.0
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 sha256:12e4a033631f063d794e0c331d0d0b9dec0431902f35f411c28292a1ae5d3a85
|
3 |
+
size 77922
|
runs/Sep06_00-21-52_d902e596bcd6/events.out.tfevents.1725583312.d902e596bcd6.3651.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf22c4be24f5b50bdd8b35fc6e5e9530c39d1d962acad1ff4295bd2f679c3d6e
|
3 |
+
size 411
|