End of training
Browse files- README.md +24 -29
- pytorch_model.bin +1 -1
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
-
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
model-index:
|
@@ -14,15 +14,15 @@ model-index:
|
|
14 |
name: Image Classification
|
15 |
type: image-classification
|
16 |
dataset:
|
17 |
-
name:
|
18 |
-
type:
|
19 |
config: default
|
20 |
-
split: train
|
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
|
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
# image_classification
|
32 |
|
33 |
-
This model is a fine-tuned version of [
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -52,38 +52,33 @@ More information needed
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
-
- learning_rate:
|
56 |
-
- train_batch_size:
|
57 |
-
- eval_batch_size:
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
-
- num_epochs:
|
62 |
|
63 |
### Training results
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
-
| No log | 1.0 |
|
68 |
-
|
|
69 |
-
|
|
70 |
-
|
|
71 |
-
|
|
72 |
-
|
|
73 |
-
|
|
74 |
-
|
|
75 |
-
|
|
76 |
-
|
|
77 |
-
| No log | 11.0 | 473 | 1.5183 | 0.4375 |
|
78 |
-
| 1.6941 | 12.0 | 516 | 1.5211 | 0.4938 |
|
79 |
-
| 1.6941 | 13.0 | 559 | 1.4997 | 0.4562 |
|
80 |
-
| 1.6941 | 14.0 | 602 | 1.5191 | 0.4375 |
|
81 |
-
| 1.6941 | 15.0 | 645 | 1.4892 | 0.4875 |
|
82 |
|
83 |
|
84 |
### Framework versions
|
85 |
|
86 |
-
- Transformers 4.33.
|
87 |
- Pytorch 2.0.1+cu118
|
88 |
- Datasets 2.14.5
|
89 |
- Tokenizers 0.13.3
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: facebook/convnext-large-224-22k-1k
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
+
- imagenet_10
|
8 |
metrics:
|
9 |
- accuracy
|
10 |
model-index:
|
|
|
14 |
name: Image Classification
|
15 |
type: image-classification
|
16 |
dataset:
|
17 |
+
name: imagenet_10
|
18 |
+
type: imagenet_10
|
19 |
config: default
|
20 |
+
split: train[:7000]
|
21 |
args: default
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.9942857142857143
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# image_classification
|
32 |
|
33 |
+
This model is a fine-tuned version of [facebook/convnext-large-224-22k-1k](https://huggingface.co/facebook/convnext-large-224-22k-1k) on the imagenet_10 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.0357
|
36 |
+
- Accuracy: 0.9943
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 0.0001
|
56 |
+
- train_batch_size: 17
|
57 |
+
- eval_batch_size: 17
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 10
|
62 |
|
63 |
### Training results
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
67 |
+
| No log | 1.0 | 330 | 0.0637 | 0.9843 |
|
68 |
+
| 0.0602 | 2.0 | 660 | 0.0664 | 0.9821 |
|
69 |
+
| 0.0602 | 3.0 | 990 | 0.0843 | 0.9843 |
|
70 |
+
| 0.0468 | 4.0 | 1320 | 0.0452 | 0.9879 |
|
71 |
+
| 0.0313 | 5.0 | 1650 | 0.0347 | 0.9914 |
|
72 |
+
| 0.0313 | 6.0 | 1980 | 0.0432 | 0.9914 |
|
73 |
+
| 0.0232 | 7.0 | 2310 | 0.0314 | 0.99 |
|
74 |
+
| 0.0223 | 8.0 | 2640 | 0.0337 | 0.9921 |
|
75 |
+
| 0.0223 | 9.0 | 2970 | 0.0381 | 0.99 |
|
76 |
+
| 0.0177 | 10.0 | 3300 | 0.0321 | 0.9921 |
|
|
|
|
|
|
|
|
|
|
|
77 |
|
78 |
|
79 |
### Framework versions
|
80 |
|
81 |
+
- Transformers 4.33.3
|
82 |
- Pytorch 2.0.1+cu118
|
83 |
- Datasets 2.14.5
|
84 |
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 785101485
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b75edd40f7f11683848bf8633c211b986ff22540102c2efcdb94c97004b49b9d
|
3 |
size 785101485
|