sayakpaul HF staff commited on
Commit
f14c543
1 Parent(s): fa98540

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -8
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.854
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 food101 dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 2.6021
35
- - Accuracy: 0.854
36
 
37
  ## Model description
38
 
@@ -59,17 +59,18 @@ The following hyperparameters were used during training:
59
  - total_train_batch_size: 512
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
- - lr_scheduler_warmup_ratio: 0.1
63
- - num_epochs: 3
64
  - mixed_precision_training: Native AMP
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 1.0 | 9 | 3.5563 | 0.508 |
71
- | 4.1714 | 2.0 | 18 | 2.8400 | 0.842 |
72
- | 3.1127 | 3.0 | 27 | 2.6021 | 0.854 |
 
 
73
 
74
 
75
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.96
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 food101 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.1448
35
+ - Accuracy: 0.96
36
 
37
  ## Model description
38
 
 
59
  - total_train_batch_size: 512
60
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
  - lr_scheduler_type: linear
62
+ - num_epochs: 5
 
63
  - mixed_precision_training: Native AMP
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 1.0 | 9 | 0.5069 | 0.896 |
70
+ | 2.1627 | 2.0 | 18 | 0.1891 | 0.946 |
71
+ | 0.3451 | 3.0 | 27 | 0.1448 | 0.96 |
72
+ | 0.2116 | 4.0 | 36 | 0.1509 | 0.958 |
73
+ | 0.1711 | 5.0 | 45 | 0.1498 | 0.958 |
74
 
75
 
76
  ### Framework versions