Hugging Face's logo

khaingsmon
/
test-hasy-6

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
khaingsmon commited on
Commit
e842d45
•
1 Parent(s): 51cfa65

Model save

Browse files
Files changed (4) hide show
  1. README.md +6 -6
  2. all_results.json +5 -5
  3. eval_results.json +5 -5
  4. runs/Mar12_18-55-56_30303fe9e772/events.out.tfevents.1710269882.30303fe9e772.1893.5 +3 -0
README.md CHANGED
@@ -2,7 +2,6 @@
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
5
- - image-classification
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
@@ -16,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # test-hasy-6
18
 
19
- 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 HASY dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 3.4460
22
- - Accuracy: 0.4200
23
 
24
  ## Model description
25
 
@@ -45,13 +44,14 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - num_epochs: 2
 
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 4.227 | 1.0 | 541 | 3.6833 | 0.3846 |
54
- | 3.756 | 2.0 | 1082 | 3.4460 | 0.4200 |
55
 
56
 
57
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
 
5
  - generated_from_trainer
6
  metrics:
7
  - accuracy
 
15
 
16
  # test-hasy-6
17
 
18
+ 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 None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.8365
21
+ - Accuracy: 0.4969
22
 
23
  ## Model description
24
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - num_epochs: 2
47
+ - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 3.5095 | 1.0 | 541 | 2.9905 | 0.4636 |
54
+ | 2.8453 | 2.0 | 1082 | 2.8365 | 0.4969 |
55
 
56
 
57
  ### Framework versions
all_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
  "epoch": 2.0,
3
- "eval_accuracy": 0.41995841995842,
4
- "eval_loss": 3.446028709411621,
5
- "eval_runtime": 2.0615,
6
- "eval_samples_per_second": 233.32,
7
- "eval_steps_per_second": 29.589,
8
  "total_flos": 6.710386542096384e+17,
9
  "train_loss": 3.966065468497285,
10
  "train_runtime": 108.0206,
 
1
  {
2
  "epoch": 2.0,
3
+ "eval_accuracy": 0.4968814968814969,
4
+ "eval_loss": 2.8364877700805664,
5
+ "eval_runtime": 1.534,
6
+ "eval_samples_per_second": 313.565,
7
+ "eval_steps_per_second": 39.766,
8
  "total_flos": 6.710386542096384e+17,
9
  "train_loss": 3.966065468497285,
10
  "train_runtime": 108.0206,
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
- "eval_accuracy": 0.41995841995842,
4
- "eval_loss": 3.446028709411621,
5
- "eval_runtime": 2.0615,
6
- "eval_samples_per_second": 233.32,
7
- "eval_steps_per_second": 29.589
8
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "eval_accuracy": 0.4968814968814969,
4
+ "eval_loss": 2.8364877700805664,
5
+ "eval_runtime": 1.534,
6
+ "eval_samples_per_second": 313.565,
7
+ "eval_steps_per_second": 39.766
8
  }
runs/Mar12_18-55-56_30303fe9e772/events.out.tfevents.1710269882.30303fe9e772.1893.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21a81fa815c3f7eb8413024b034f1ef9b22073d3be21d06edd9fc85def810dc7
3
+ size 411