Hugging Face's logo

MaxP
/
vit-base-riego

Image Classification
Transformers
PyTorch
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
1
MaxP commited on
Commit
a9cc5a3
·
1 Parent(s): 858059e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -13
README.md CHANGED
@@ -16,12 +16,12 @@ model-index:
16
  name: imagefolder
17
  type: imagefolder
18
  config: MaxP--agro_riego
19
- split: train
20
  args: MaxP--agro_riego
21
  metrics:
22
  - name: F1
23
  type: f1
24
- value: 0.9853801169590642
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.0544
35
- - F1: 0.9854
36
 
37
  ## Model description
38
 
@@ -64,17 +64,19 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | F1 |
66
  |:-------------:|:-----:|:----:|:---------------:|:------:|
67
- | 0.0443 | 0.48 | 100 | 0.4737 | 0.8742 |
68
- | 0.0349 | 0.95 | 200 | 0.0774 | 0.9733 |
69
- | 0.003 | 1.43 | 300 | 0.0675 | 0.9794 |
70
- | 0.002 | 1.9 | 400 | 0.0674 | 0.9810 |
71
- | 0.0014 | 2.38 | 500 | 0.0431 | 0.9871 |
72
- | 0.0011 | 2.86 | 600 | 0.0544 | 0.9854 |
 
 
73
 
74
 
75
  ### Framework versions
76
 
77
- - Transformers 4.25.1
78
- - Pytorch 1.13.0+cu116
79
- - Datasets 2.8.0
80
  - Tokenizers 0.13.2
 
16
  name: imagefolder
17
  type: imagefolder
18
  config: MaxP--agro_riego
19
+ split: test
20
  args: MaxP--agro_riego
21
  metrics:
22
  - name: F1
23
  type: f1
24
+ value: 0.9885057471264367
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.0410
35
+ - F1: 0.9885
36
 
37
  ## Model description
38
 
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | F1 |
66
  |:-------------:|:-----:|:----:|:---------------:|:------:|
67
+ | 0.4811 | 0.34 | 100 | 0.4447 | 0.7468 |
68
+ | 0.2985 | 0.67 | 200 | 0.2198 | 0.8793 |
69
+ | 0.1199 | 1.01 | 300 | 0.0846 | 0.9709 |
70
+ | 0.128 | 1.35 | 400 | 0.1119 | 0.9574 |
71
+ | 0.1387 | 1.68 | 500 | 0.1222 | 0.9496 |
72
+ | 0.0899 | 2.02 | 600 | 0.0800 | 0.9765 |
73
+ | 0.0048 | 2.36 | 700 | 0.0731 | 0.9769 |
74
+ | 0.0195 | 2.69 | 800 | 0.0410 | 0.9885 |
75
 
76
 
77
  ### Framework versions
78
 
79
+ - Transformers 4.26.1
80
+ - Pytorch 1.13.1+cu116
81
+ - Datasets 2.10.1
82
  - Tokenizers 0.13.2