Takekazuchi
commited on
Commit
•
d904e61
1
Parent(s):
07de830
End of training
Browse files- README.md +80 -0
- all_results.json +12 -0
- config.json +0 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Jan09_14-08-48_RyRyWoods/events.out.tfevents.1704830953.RyRyWoods.13824.0 +3 -0
- runs/Jan10_12-27-45_RyRyWoods/events.out.tfevents.1704911272.RyRyWoods.18028.0 +3 -0
- runs/Jan10_14-27-46_RyRyWoods/events.out.tfevents.1704918473.RyRyWoods.18028.1 +3 -0
- runs/Jan10_14-27-46_RyRyWoods/events.out.tfevents.1705556351.RyRyWoods.18028.2 +3 -0
- train_results.json +7 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: vit-base-patch16-224-vit-base-patch16
|
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: 0.5851995594482614
|
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 |
+
# vit-base-patch16-224-vit-base-patch16
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.9156
|
36 |
+
- Accuracy: 0.5852
|
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: 3
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
70 |
+
| 4.0308 | 1.0 | 5362 | 3.6948 | 0.2491 |
|
71 |
+
| 2.694 | 2.0 | 10725 | 2.2586 | 0.5199 |
|
72 |
+
| 2.4475 | 3.0 | 16086 | 1.9156 | 0.5852 |
|
73 |
+
|
74 |
+
|
75 |
+
### Framework versions
|
76 |
+
|
77 |
+
- Transformers 4.36.2
|
78 |
+
- Pytorch 2.1.2+cpu
|
79 |
+
- Datasets 2.16.1
|
80 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.5851995594482614,
|
4 |
+
"eval_loss": 1.9156352281570435,
|
5 |
+
"eval_runtime": 8376.0076,
|
6 |
+
"eval_samples_per_second": 9.106,
|
7 |
+
"eval_steps_per_second": 0.285,
|
8 |
+
"train_loss": 3.7719367721047283,
|
9 |
+
"train_runtime": 628821.6026,
|
10 |
+
"train_samples_per_second": 3.275,
|
11 |
+
"train_steps_per_second": 0.026
|
12 |
+
}
|
config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.5851995594482614,
|
4 |
+
"eval_loss": 1.9156352281570435,
|
5 |
+
"eval_runtime": 8376.0076,
|
6 |
+
"eval_samples_per_second": 9.106,
|
7 |
+
"eval_steps_per_second": 0.285
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3aeda000e3aaf3505ff8317b2efabd5024303b1467719a6856de0288fcc892b7
|
3 |
+
size 351769152
|
preprocessor_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"do_rescale": true,
|
4 |
+
"do_resize": true,
|
5 |
+
"image_mean": [
|
6 |
+
0.5,
|
7 |
+
0.5,
|
8 |
+
0.5
|
9 |
+
],
|
10 |
+
"image_processor_type": "ViTImageProcessor",
|
11 |
+
"image_std": [
|
12 |
+
0.5,
|
13 |
+
0.5,
|
14 |
+
0.5
|
15 |
+
],
|
16 |
+
"resample": 2,
|
17 |
+
"rescale_factor": 0.00392156862745098,
|
18 |
+
"size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
}
|
22 |
+
}
|
runs/Jan09_14-08-48_RyRyWoods/events.out.tfevents.1704830953.RyRyWoods.13824.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ad368c2c862c2caf9aa9bb6bce0a823174f4dd51bef6ae3479dbe6d67164b49
|
3 |
+
size 221811
|
runs/Jan10_12-27-45_RyRyWoods/events.out.tfevents.1704911272.RyRyWoods.18028.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:664e8728dcf25c0c9a76f54dc48ea4909a5a504a1fef8bcd7a8cdbaaf0340a1d
|
3 |
+
size 192959
|
runs/Jan10_14-27-46_RyRyWoods/events.out.tfevents.1704918473.RyRyWoods.18028.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abfdc3ff4e1aeacdeb19b1163eb69559368bcd6085f52831ceb0cd6bba60e375
|
3 |
+
size 446702
|
runs/Jan10_14-27-46_RyRyWoods/events.out.tfevents.1705556351.RyRyWoods.18028.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d277ee1173017f72499efaf9f74afd26fe0c9240f5d89b974354eec48928620d
|
3 |
+
size 411
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 3.7719367721047283,
|
4 |
+
"train_runtime": 628821.6026,
|
5 |
+
"train_samples_per_second": 3.275,
|
6 |
+
"train_steps_per_second": 0.026
|
7 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee7977114db8be3828582646278441ec9a88ca62c739f36983752474d8325e50
|
3 |
+
size 4728
|