Model save
Browse files
README.md
CHANGED
@@ -1,9 +1,6 @@
|
|
1 |
---
|
2 |
base_model: d071696/vit-finetune-scrap
|
3 |
tags:
|
4 |
-
- image-classification
|
5 |
-
- image-feature-extraction
|
6 |
-
- image-to-text
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
- arrow
|
@@ -16,7 +13,7 @@ model-index:
|
|
16 |
name: Image Classification
|
17 |
type: image-classification
|
18 |
dataset:
|
19 |
-
name:
|
20 |
type: arrow
|
21 |
config: default
|
22 |
split: train
|
@@ -24,7 +21,7 @@ model-index:
|
|
24 |
metrics:
|
25 |
- name: Accuracy
|
26 |
type: accuracy
|
27 |
-
value: 0.
|
28 |
---
|
29 |
|
30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -32,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
32 |
|
33 |
# vit-finetune-scrap
|
34 |
|
35 |
-
This model is a fine-tuned version of [d071696/vit-finetune-scrap](https://huggingface.co/d071696/vit-finetune-scrap) on the
|
36 |
It achieves the following results on the evaluation set:
|
37 |
-
- Loss: 0.
|
38 |
-
- Accuracy: 0.
|
39 |
|
40 |
## Model description
|
41 |
|
@@ -55,7 +52,7 @@ More information needed
|
|
55 |
|
56 |
The following hyperparameters were used during training:
|
57 |
- learning_rate: 0.0002
|
58 |
-
- train_batch_size:
|
59 |
- eval_batch_size: 8
|
60 |
- seed: 42
|
61 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
@@ -66,12 +63,7 @@ The following hyperparameters were used during training:
|
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
68 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
69 |
-
| 0.
|
70 |
-
| 0.1277 | 1.28 | 200 | 0.2467 | 0.9373 |
|
71 |
-
| 0.0253 | 1.92 | 300 | 0.1588 | 0.9550 |
|
72 |
-
| 0.0224 | 2.56 | 400 | 0.1691 | 0.9534 |
|
73 |
-
| 0.0321 | 3.21 | 500 | 0.1751 | 0.9566 |
|
74 |
-
| 0.0112 | 3.85 | 600 | 0.1805 | 0.9550 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
1 |
---
|
2 |
base_model: d071696/vit-finetune-scrap
|
3 |
tags:
|
|
|
|
|
|
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
6 |
- arrow
|
|
|
13 |
name: Image Classification
|
14 |
type: image-classification
|
15 |
dataset:
|
16 |
+
name: arrow
|
17 |
type: arrow
|
18 |
config: default
|
19 |
split: train
|
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
+
value: 0.9260450160771704
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
29 |
|
30 |
# vit-finetune-scrap
|
31 |
|
32 |
+
This model is a fine-tuned version of [d071696/vit-finetune-scrap](https://huggingface.co/d071696/vit-finetune-scrap) on the arrow dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.3599
|
35 |
+
- Accuracy: 0.9260
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
- learning_rate: 0.0002
|
55 |
+
- train_batch_size: 8
|
56 |
- eval_batch_size: 8
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
+
| 0.0021 | 3.22 | 1000 | 0.3599 | 0.9260 |
|
|
|
|
|
|
|
|
|
|
|
67 |
|
68 |
|
69 |
### Framework versions
|
runs/Apr03_18-00-45_X5C922065N/events.out.tfevents.1712160051.X5C922065N.13113.1
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 sha256:63bb5b3ab0869fddcc180148e78da40b15a2a1c7eb4c2ca7220eece7967baf2d
|
3 |
+
size 31916
|