Hugging Face's logo

bansilp
/
xyz

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
bansilp commited on
Commit
1d0dddd
•
1 Parent(s): 2d10ff5

Model save

Browse files
Files changed (11) hide show
  1. README.md +10 -10
  2. all_results.json +10 -10
  3. eval_results.json +5 -5
  4. model.safetensors +1 -1
  5. runs/Mar18_08-24-00_cd2d1c1da590/events.out.tfevents.1710751038.cd2d1c1da590.4304.2 +3 -0
  6. runs/Mar18_08-37-56_cd2d1c1da590/events.out.tfevents.1710751096.cd2d1c1da590.4304.3 +3 -0
  7. runs/Mar18_08-38-50_cd2d1c1da590/events.out.tfevents.1710751135.cd2d1c1da590.4304.4 +3 -0
  8. runs/Mar18_08-39-19_cd2d1c1da590/events.out.tfevents.1710751167.cd2d1c1da590.4304.5 +3 -0
  9. train_results.json +5 -5
  10. trainer_state.json +0 -0
  11. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8814814814814815
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  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.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.5871
36
- - Accuracy: 0.8815
37
 
38
  ## Model description
39
 
@@ -53,23 +53,23 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0002
56
- - train_batch_size: 4
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
- - num_epochs: 5
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 0.9351 | 0.93 | 1000 | 0.8621 | 0.7194 |
69
- | 0.6665 | 1.85 | 2000 | 0.7748 | 0.7880 |
70
- | 0.0161 | 2.78 | 3000 | 0.6623 | 0.8481 |
71
- | 0.0069 | 3.7 | 4000 | 0.6439 | 0.8583 |
72
- | 0.0071 | 4.63 | 5000 | 0.5871 | 0.8815 |
73
 
74
 
75
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9009259259259259
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  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.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.6789
36
+ - Accuracy: 0.9009
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 0.0002
56
+ - train_batch_size: 8
57
  - eval_batch_size: 8
58
  - seed: 42
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
+ - num_epochs: 10
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 0.1683 | 1.85 | 1000 | 0.7743 | 0.8231 |
69
+ | 0.0361 | 3.7 | 2000 | 0.8477 | 0.8370 |
70
+ | 0.0143 | 5.56 | 3000 | 0.6882 | 0.8815 |
71
+ | 0.0006 | 7.41 | 4000 | 0.7666 | 0.8833 |
72
+ | 0.0132 | 9.26 | 5000 | 0.6789 | 0.9009 |
73
 
74
 
75
  ### Framework versions
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 5.0,
3
- "eval_accuracy": 0.7858333333333334,
4
- "eval_loss": 0.9599547386169434,
5
- "eval_runtime": 17.8384,
6
- "eval_samples_per_second": 67.27,
7
- "eval_steps_per_second": 8.409,
8
- "total_flos": 3.4029172406502605e+18,
9
- "train_loss": 0.2756463099698551,
10
- "train_runtime": 974.1891,
11
- "train_samples_per_second": 45.073,
12
- "train_steps_per_second": 0.939
13
  }
 
1
  {
2
  "epoch": 5.0,
3
+ "eval_accuracy": 0.8481481481481481,
4
+ "eval_loss": 0.662264883518219,
5
+ "eval_runtime": 13.8377,
6
+ "eval_samples_per_second": 78.048,
7
+ "eval_steps_per_second": 9.756,
8
+ "total_flos": 1.6739319895474176e+18,
9
+ "train_loss": 0.41893966080965817,
10
+ "train_runtime": 684.6117,
11
+ "train_samples_per_second": 31.551,
12
+ "train_steps_per_second": 7.888
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
- "eval_accuracy": 0.7858333333333334,
4
- "eval_loss": 0.9599547386169434,
5
- "eval_runtime": 17.8384,
6
- "eval_samples_per_second": 67.27,
7
- "eval_steps_per_second": 8.409
8
  }
 
1
  {
2
  "epoch": 5.0,
3
+ "eval_accuracy": 0.8481481481481481,
4
+ "eval_loss": 0.662264883518219,
5
+ "eval_runtime": 13.8377,
6
+ "eval_samples_per_second": 78.048,
7
+ "eval_steps_per_second": 9.756
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca0df84aca7d1873a6dbfec6dadf3ed4fd3fb5c11e54c3c3e3e6ccdc1e8a9daa
3
  size 343245508
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a05a7f34e1f77ab99564f9ad90a9922343067596af43b7f41e569e654394505
3
  size 343245508
runs/Mar18_08-24-00_cd2d1c1da590/events.out.tfevents.1710751038.cd2d1c1da590.4304.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8303ed316d2caf1a25184375a7791f0d5fbfda32fb45f7e7543f9d8388fb93
3
+ size 411
runs/Mar18_08-37-56_cd2d1c1da590/events.out.tfevents.1710751096.cd2d1c1da590.4304.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292aecbd07f6e554d8c372fdab2f819b4b381f22305fa85ebaa660dc54d8d940
3
+ size 8201
runs/Mar18_08-38-50_cd2d1c1da590/events.out.tfevents.1710751135.cd2d1c1da590.4304.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b69476e36696125928ee22f0e239161970818f26ccc77c63fd93c8a1de16d50
3
+ size 5909
runs/Mar18_08-39-19_cd2d1c1da590/events.out.tfevents.1710751167.cd2d1c1da590.4304.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2beaa85dc0606373fd8b790c8c7889b411ccac46abf9cfddcefc20735e0b978
3
+ size 120734
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 5.0,
3
- "total_flos": 3.4029172406502605e+18,
4
- "train_loss": 0.2756463099698551,
5
- "train_runtime": 974.1891,
6
- "train_samples_per_second": 45.073,
7
- "train_steps_per_second": 0.939
8
  }
 
1
  {
2
  "epoch": 5.0,
3
+ "total_flos": 1.6739319895474176e+18,
4
+ "train_loss": 0.41893966080965817,
5
+ "train_runtime": 684.6117,
6
+ "train_samples_per_second": 31.551,
7
+ "train_steps_per_second": 7.888
8
  }
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 sha256:897770956edfa4fc3ddeb1aa4bdc811303e9bd938f3b3875b34fd7dad0a485b8
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2e556f3908f34ee3b337d23f5ec4c692a0f5d1e8b5b8cc65beb328a000f9427
3
  size 4856