Hugging Face's logo

pkr7098
/
food101-vit-base-patch16-224-in21k

Image Classification
TensorBoard
Safetensors
vit
vision
Generated from Trainer
Model card Files Metrics Community
pkr7098 commited on
Commit
5e989b5
•
1 Parent(s): dbbfdc7

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. README.md +16 -16
  2. all_results.json +9 -9
  3. eval_results.json +5 -5
  4. model.safetensors +1 -1
  5. runs/Aug13_11-17-46_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723515475.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.1052785.0 +3 -0
  6. runs/Aug13_11-17-46_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723518728.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.1052785.1 +3 -0
  7. runs/Aug13_12-20-18_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723519227.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.1093622.0 +3 -0
  8. train_results.json +4 -4
  9. trainer_state.json +0 -0
  10. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
  - image-classification
6
  - vision
@@ -8,19 +8,19 @@ tags:
8
  metrics:
9
  - accuracy
10
  model-index:
11
- - name: food101-vit-base-patch16-224-in21k
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
- # food101-vit-base-patch16-224-in21k
19
 
20
- 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.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.3873
23
- - Accuracy: 0.9035
24
 
25
  ## Model description
26
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
- | 0.9431 | 1.0 | 9469 | 0.6777 | 0.8593 |
55
- | 0.617 | 2.0 | 18938 | 0.4546 | 0.8802 |
56
- | 0.9109 | 3.0 | 28407 | 0.4086 | 0.8899 |
57
- | 1.0346 | 4.0 | 37876 | 0.3911 | 0.8968 |
58
- | 0.2142 | 5.0 | 47345 | 0.4098 | 0.8913 |
59
- | 0.7247 | 6.0 | 56814 | 0.3904 | 0.9008 |
60
- | 0.3935 | 7.0 | 66283 | 0.3873 | 0.9035 |
61
- | 0.552 | 8.0 | 75752 | 0.3915 | 0.9053 |
62
- | 0.4012 | 9.0 | 85221 | 0.3955 | 0.9052 |
63
- | 0.2699 | 10.0 | 94690 | 0.3894 | 0.9072 |
64
 
65
 
66
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: facebook/deit-tiny-patch16-224
4
  tags:
5
  - image-classification
6
  - vision
 
8
  metrics:
9
  - accuracy
10
  model-index:
11
+ - name: food101-deit-tiny-patch16-224
12
  results: []
13
  ---
14
 
15
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
  should probably proofread and complete it, then remove this comment. -->
17
 
18
+ # food101-deit-tiny-patch16-224
19
 
20
+ This model is a fine-tuned version of [facebook/deit-tiny-patch16-224](https://huggingface.co/facebook/deit-tiny-patch16-224) on the food101 dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.6538
23
+ - Accuracy: 0.8204
24
 
25
  ## Model description
26
 
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
+ | 1.7988 | 1.0 | 9469 | 1.4392 | 0.6555 |
55
+ | 1.5581 | 2.0 | 18938 | 1.1165 | 0.7145 |
56
+ | 1.2981 | 3.0 | 28407 | 0.9254 | 0.7558 |
57
+ | 1.4347 | 4.0 | 37876 | 0.8343 | 0.7739 |
58
+ | 0.9679 | 5.0 | 47345 | 0.7731 | 0.7922 |
59
+ | 0.9975 | 6.0 | 56814 | 0.7378 | 0.7998 |
60
+ | 1.0269 | 7.0 | 66283 | 0.7022 | 0.8073 |
61
+ | 0.8969 | 8.0 | 75752 | 0.6865 | 0.8117 |
62
+ | 0.8152 | 9.0 | 85221 | 0.6641 | 0.8194 |
63
+ | 0.7437 | 10.0 | 94690 | 0.6538 | 0.8204 |
64
 
65
 
66
  ### Framework versions
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 10.0,
3
- "eval_accuracy": 0.9035247524752476,
4
- "eval_loss": 0.38733184337615967,
5
- "eval_runtime": 228.3973,
6
- "eval_samples_per_second": 110.553,
7
- "eval_steps_per_second": 13.822,
8
- "train_loss": 0.6563277260213383,
9
- "train_runtime": 13063.3743,
10
- "train_samples_per_second": 57.987,
11
- "train_steps_per_second": 7.249
12
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "eval_accuracy": 0.8204356435643564,
4
+ "eval_loss": 0.6538042426109314,
5
+ "eval_runtime": 37.4035,
6
+ "eval_samples_per_second": 675.071,
7
+ "eval_steps_per_second": 84.404,
8
+ "train_loss": 1.2358400564811112,
9
+ "train_runtime": 3207.066,
10
+ "train_samples_per_second": 236.197,
11
+ "train_steps_per_second": 29.525
12
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 10.0,
3
- "eval_accuracy": 0.9035247524752476,
4
- "eval_loss": 0.38733184337615967,
5
- "eval_runtime": 228.3973,
6
- "eval_samples_per_second": 110.553,
7
- "eval_steps_per_second": 13.822
8
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "eval_accuracy": 0.8204356435643564,
4
+ "eval_loss": 0.6538042426109314,
5
+ "eval_runtime": 37.4035,
6
+ "eval_samples_per_second": 675.071,
7
+ "eval_steps_per_second": 84.404
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:279649f0384739453d81f52c14db03537b0f080ade4b5567844e76316e9f11df
3
  size 343528508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b71412d7c434692360a243d23bd206029523b5c0b937b47209e4d50bc69664b9
3
  size 343528508
runs/Aug13_11-17-46_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723515475.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.1052785.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:451eb57fcd068cf3b6bac42dce793c02a16c453a01dd49e69ac58311952081d2
3
+ size 2042495
runs/Aug13_11-17-46_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723518728.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.1052785.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0a7fba4ef31888417657d517013b9c2da43359f535138cf1d8b07dde24f5c6
3
+ size 417
runs/Aug13_12-20-18_kwangryeol-OMEN-30L-Desktop-GT13-1xxx/events.out.tfevents.1723519227.kwangryeol-OMEN-30L-Desktop-GT13-1xxx.1093622.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe35b94db8478744f32a33fca1b9e1693388f1877d1ba0eb33f9f736013009d9
3
+ size 209706
train_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 10.0,
3
- "train_loss": 0.6563277260213383,
4
- "train_runtime": 13063.3743,
5
- "train_samples_per_second": 57.987,
6
- "train_steps_per_second": 7.249
7
  }
 
1
  {
2
  "epoch": 10.0,
3
+ "train_loss": 1.2358400564811112,
4
+ "train_runtime": 3207.066,
5
+ "train_samples_per_second": 236.197,
6
+ "train_steps_per_second": 29.525
7
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e20e2ec6ac05af5d074b4bf2d1c6ed2480155f648dcacbcc03640ea344c8c44
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9325ad33a512ccd7c6f44c7050ab82d97a980a78d164b7adef5450e838f1853
3
  size 5048