Hugging Face's logo

rshrott
/
ryan_model314_3

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
rshrott commited on
Commit
ff74d22
•
1 Parent(s): bdcf952

Training in progress, step 100

Browse files
Files changed (5) hide show
  1. README.md +16 -18
  2. model.safetensors +1 -1
  3. runs/Mar26_22-59-37_ryanserver/events.out.tfevents.1711508383.ryanserver.8946.0 +2 -2
  4. runs/Mar26_23-12-19_ryanserver/events.out.tfevents.1711509145.ryanserver.11961.0 +3 -0
  5. training_args.bin +1 -1
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
  model-index:
8
  - name: ryan_model314_3
@@ -14,11 +13,11 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # ryan_model314_3
16
 
17
- 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 beans dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.2547
20
- - Na Accuracy: 0.95
21
- - Ordinal Mae: 1.2090
22
 
23
  ## Model description
24
 
@@ -37,7 +36,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 0.0001
41
  - train_batch_size: 16
42
  - eval_batch_size: 8
43
  - seed: 42
@@ -50,18 +49,17 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Na Accuracy | Ordinal Mae |
52
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|:-----------:|
53
- | 0.4505 | 0.2 | 25 | 0.4262 | 0.9 | 1.0092 |
54
- | 0.3847 | 0.4 | 50 | 0.3676 | 0.935 | 1.3719 |
55
- | 0.3061 | 0.6 | 75 | 0.3262 | 0.945 | 0.7486 |
56
- | 0.2744 | 0.8 | 100 | 0.3524 | 0.905 | 1.1408 |
57
- | 0.2384 | 1.0 | 125 | 0.3611 | 0.93 | 0.6747 |
58
- | 0.2021 | 1.2 | 150 | 0.3105 | 0.95 | 1.0441 |
59
- | 0.2234 | 1.4 | 175 | 0.2738 | 0.955 | 1.4168 |
60
- | 0.187 | 1.6 | 200 | 0.2688 | 0.955 | 1.3653 |
61
- | 0.2008 | 1.8 | 225 | 0.2669 | 0.96 | 0.8936 |
62
- | 0.1541 | 2.0 | 250 | 0.2547 | 0.95 | 1.2090 |
63
- | 0.1201 | 2.2 | 275 | 0.2725 | 0.95 | 0.7955 |
64
- | 0.113 | 2.4 | 300 | 0.2818 | 0.955 | 1.2378 |
65
 
66
 
67
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: google/vit-base-patch16-224-in21k
4
  tags:
 
5
  - generated_from_trainer
6
  model-index:
7
  - name: ryan_model314_3
 
13
 
14
  # ryan_model314_3
15
 
16
+ 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.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.3003
19
+ - Na Accuracy: 0.94
20
+ - Ordinal Mae: 0.8473
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.0002
40
  - train_batch_size: 16
41
  - eval_batch_size: 8
42
  - seed: 42
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Na Accuracy | Ordinal Mae |
51
  |:-------------:|:-----:|:----:|:---------------:|:-----------:|:-----------:|
52
+ | 0.3861 | 0.13 | 25 | 0.3698 | 0.935 | 1.2958 |
53
+ | 0.3197 | 0.27 | 50 | 0.3551 | 0.925 | 1.1263 |
54
+ | 0.33 | 0.4 | 75 | 0.3531 | 0.94 | 0.8691 |
55
+ | 0.4362 | 0.53 | 100 | 0.4501 | 0.93 | 1.7403 |
56
+ | 0.2495 | 0.66 | 125 | 0.3154 | 0.935 | 0.8172 |
57
+ | 0.3961 | 0.8 | 150 | 0.3138 | 0.925 | 0.9720 |
58
+ | 0.2511 | 0.93 | 175 | 0.3231 | 0.925 | 0.8814 |
59
+ | 0.1473 | 1.06 | 200 | 0.3242 | 0.93 | 1.2868 |
60
+ | 0.187 | 1.2 | 225 | 0.2903 | 0.935 | 0.9828 |
61
+ | 0.2475 | 1.33 | 250 | 0.3491 | 0.92 | 1.3949 |
62
+ | 0.232 | 1.46 | 275 | 0.3003 | 0.94 | 0.8473 |
 
63
 
64
 
65
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67360dfa1aaed209ef6fad8539ce2818ad8f4ef273ef7714899f89466dff819f
3
  size 343236280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e20d792bad3d89583c69b952ec418776eb48b5e21d4ec72b0093a4f4eda587
3
  size 343236280
runs/Mar26_22-59-37_ryanserver/events.out.tfevents.1711508383.ryanserver.8946.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f6997b6aef74e91ba43c8c511b896e3aa672a43fdfbe25010f50c6654de334a
3
- size 13745
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6f396eb5605e27a76215a933d78c8798ddc6961e2c73d8a429c33e6c392267
3
+ size 14902
runs/Mar26_23-12-19_ryanserver/events.out.tfevents.1711509145.ryanserver.11961.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc2cf5115929082cd45386c93fb29b0c52a93a9de04dc2fe76b2f894d78f273
3
+ size 5533
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94cb74e7bd6fee735714b3179882bb30407e0838a8cde01a570a003ff4eb106c
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7cb4293f14807c9975fb03312e84c37e6f8cb8bc99b48c39eb337ded0730c6b
3
  size 4920