aaa12963337
commited on
Commit
•
e8b5b67
1
Parent(s):
dd44977
End of training
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model: shi-labs/nat-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
@@ -22,7 +22,7 @@ model-index:
|
|
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 |
# msi
|
32 |
|
33 |
-
This model is a fine-tuned version of [shi-labs/nat-
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 1.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -52,7 +52,7 @@ More information needed
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
-
- learning_rate:
|
56 |
- train_batch_size: 16
|
57 |
- eval_batch_size: 16
|
58 |
- seed: 42
|
@@ -61,27 +61,20 @@ The following hyperparameters were used during training:
|
|
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
|
69 |
-
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.219 | 4.0 | 7434 | 1.3987 | 0.6419 |
|
74 |
-
| 0.1863 | 5.0 | 9292 | 1.5862 | 0.6248 |
|
75 |
-
| 0.1946 | 6.0 | 11151 | 1.4975 | 0.6848 |
|
76 |
-
| 0.1679 | 7.0 | 13009 | 1.6209 | 0.6518 |
|
77 |
-
| 0.1531 | 8.0 | 14868 | 1.6400 | 0.6599 |
|
78 |
-
| 0.15 | 9.0 | 16726 | 1.6733 | 0.6702 |
|
79 |
-
| 0.1377 | 10.0 | 18580 | 1.6797 | 0.6625 |
|
80 |
|
81 |
|
82 |
### Framework versions
|
83 |
|
84 |
-
- Transformers 4.
|
85 |
-
- Pytorch 2.0.1
|
86 |
- Datasets 2.15.0
|
87 |
- Tokenizers 0.15.0
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: shi-labs/nat-mini-in1k-224
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
+
value: 0.6347497903270898
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# msi
|
32 |
|
33 |
+
This model is a fine-tuned version of [shi-labs/nat-mini-in1k-224](https://huggingface.co/shi-labs/nat-mini-in1k-224) on the imagefolder dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.4313
|
36 |
+
- Accuracy: 0.6347
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
- train_batch_size: 16
|
57 |
- eval_batch_size: 16
|
58 |
- seed: 42
|
|
|
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 |
+
| 0.2585 | 1.0 | 2015 | 1.1175 | 0.6088 |
|
71 |
+
| 0.1938 | 2.0 | 4031 | 1.3762 | 0.6270 |
|
72 |
+
| 0.1452 | 3.0 | 6045 | 1.4313 | 0.6347 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
|
74 |
|
75 |
### Framework versions
|
76 |
|
77 |
+
- Transformers 4.36.0
|
78 |
+
- Pytorch 2.0.1
|
79 |
- Datasets 2.15.0
|
80 |
- Tokenizers 0.15.0
|