Model save
Browse files
README.md
CHANGED
@@ -17,12 +17,12 @@ model-index:
|
|
17 |
name: imagefolder
|
18 |
type: imagefolder
|
19 |
config: default
|
20 |
-
split:
|
21 |
args: default
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
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: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -53,23 +53,30 @@ More information needed
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 5e-05
|
56 |
-
- train_batch_size:
|
57 |
-
- eval_batch_size:
|
58 |
- seed: 42
|
59 |
- gradient_accumulation_steps: 4
|
60 |
-
- total_train_batch_size:
|
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:
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
|
74 |
|
75 |
### Framework versions
|
|
|
17 |
name: imagefolder
|
18 |
type: imagefolder
|
19 |
config: default
|
20 |
+
split: test
|
21 |
args: default
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.8446601941747572
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
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: 0.3894
|
36 |
+
- Accuracy: 0.8447
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 128
|
57 |
+
- eval_batch_size: 128
|
58 |
- seed: 42
|
59 |
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 512
|
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: 10
|
65 |
|
66 |
### Training results
|
67 |
|
68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| No log | 1.0 | 5 | 1.0761 | 0.5469 |
|
71 |
+
| 1.1435 | 2.0 | 10 | 0.6466 | 0.7735 |
|
72 |
+
| 1.1435 | 3.0 | 15 | 0.4962 | 0.8123 |
|
73 |
+
| 0.5372 | 4.0 | 20 | 0.4365 | 0.8252 |
|
74 |
+
| 0.5372 | 5.0 | 25 | 0.4118 | 0.8382 |
|
75 |
+
| 0.362 | 6.0 | 30 | 0.4031 | 0.8414 |
|
76 |
+
| 0.362 | 7.0 | 35 | 0.3944 | 0.8511 |
|
77 |
+
| 0.3028 | 8.0 | 40 | 0.3930 | 0.8414 |
|
78 |
+
| 0.3028 | 9.0 | 45 | 0.3928 | 0.8479 |
|
79 |
+
| 0.2708 | 10.0 | 50 | 0.3894 | 0.8447 |
|
80 |
|
81 |
|
82 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343230128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:abe12790a2a3a3c6f3d1102566dfbf9a1bdf70611dc5cc0ad741df1d461a1ece
|
3 |
size 343230128
|
runs/Jun18_21-55-04_DangPC/events.out.tfevents.1718722504.DangPC.22553.0
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 sha256:9f146dca2db80b0aafc951ef429b9dcad843090f6687e12bee4429c8c8ad6b8a
|
3 |
+
size 8679
|