Hugging Face's logo

nomis15
/
checkpoint-100

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
nomis15 commited on
Commit
52c3327
·
verified ·
1 Parent(s): cff6585

End of training

Browse files
Files changed (7) hide show
  1. README.md +19 -25
  2. model.safetensors +1 -1
  3. runs/Jan22_21-57-18_Simon-PC/events.out.tfevents.1705957039.Simon-PC +3 -0
  4. runs/Jan22_22-06-11_Simon-PC/events.out.tfevents.1705957572.Simon-PC +3 -0
  5. runs/Jan22_22-17-19_Simon-PC/events.out.tfevents.1705958239.Simon-PC +3 -0
  6. runs/Jan22_22-33-10_Simon-PC/events.out.tfevents.1705959191.Simon-PC +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.7850931677018633
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.7801
36
- - Accuracy: 0.7851
37
 
38
  ## Model description
39
 
@@ -53,38 +53,32 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
- - train_batch_size: 2
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
  - lr_scheduler_warmup_ratio: 0.1
62
- - num_epochs: 2
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | 1.1884 | 0.06 | 100 | 0.9288 | 0.6224 |
69
- | 0.8421 | 0.12 | 200 | 0.8327 | 0.6758 |
70
- | 0.9707 | 0.19 | 300 | 0.7705 | 0.7093 |
71
- | 0.7771 | 0.25 | 400 | 0.9362 | 0.6683 |
72
- | 0.9801 | 0.31 | 500 | 0.8751 | 0.7043 |
73
- | 0.8177 | 0.37 | 600 | 1.2225 | 0.6733 |
74
- | 0.9605 | 0.44 | 700 | 0.6644 | 0.7602 |
75
- | 0.888 | 0.5 | 800 | 1.3271 | 0.6273 |
76
- | 1.0219 | 0.56 | 900 | 0.7537 | 0.7416 |
77
- | 0.9151 | 0.62 | 1000 | 0.7985 | 0.7553 |
78
- | 0.7776 | 0.68 | 1100 | 0.9170 | 0.7180 |
79
- | 0.9209 | 0.75 | 1200 | 0.7193 | 0.7764 |
80
- | 0.6937 | 0.81 | 1300 | 1.0005 | 0.7627 |
81
- | 1.0967 | 0.87 | 1400 | 0.6136 | 0.7876 |
82
- | 0.8685 | 0.93 | 1500 | 0.6815 | 0.7876 |
83
- | 0.7504 | 1.0 | 1600 | 0.9254 | 0.7429 |
84
- | 0.6551 | 1.06 | 1700 | 0.7449 | 0.7839 |
85
- | 0.3893 | 1.12 | 1800 | 1.0150 | 0.7516 |
86
- | 0.7936 | 1.18 | 1900 | 0.7813 | 0.7764 |
87
- | 0.7074 | 1.24 | 2000 | 0.7801 | 0.7851 |
88
 
89
 
90
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8111801242236025
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.8076
36
+ - Accuracy: 0.8112
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 20
57
  - eval_batch_size: 8
58
  - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 80
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 15
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.9834 | 1.24 | 50 | 0.6206 | 0.7404 |
71
+ | 0.4926 | 2.48 | 100 | 0.5090 | 0.7938 |
72
+ | 0.3246 | 3.73 | 150 | 0.5237 | 0.7988 |
73
+ | 0.184 | 4.97 | 200 | 0.5277 | 0.8075 |
74
+ | 0.092 | 6.21 | 250 | 0.6270 | 0.8050 |
75
+ | 0.0527 | 7.45 | 300 | 0.6963 | 0.7950 |
76
+ | 0.0276 | 8.7 | 350 | 0.7653 | 0.7938 |
77
+ | 0.0187 | 9.94 | 400 | 0.7748 | 0.8050 |
78
+ | 0.0139 | 11.18 | 450 | 0.7550 | 0.8012 |
79
+ | 0.0059 | 12.42 | 500 | 0.7755 | 0.8161 |
80
+ | 0.0072 | 13.66 | 550 | 0.7944 | 0.8161 |
81
+ | 0.0039 | 14.91 | 600 | 0.8076 | 0.8112 |
 
 
 
 
 
 
 
 
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3862902694d160b9c6942091e557cc3a0881f74decc8b82e9b121fee4b517b2
3
  size 343230128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b74e916600b15a3209ebed95c9e1677897bbbb1bacdd91e18ec5fe20b13760
3
  size 343230128
runs/Jan22_21-57-18_Simon-PC/events.out.tfevents.1705957039.Simon-PC ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdff42b78210cf9339c76f9eda89788a01d4eb1bfd7155d523758ada183faceb
3
+ size 16437
runs/Jan22_22-06-11_Simon-PC/events.out.tfevents.1705957572.Simon-PC ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7e785774208a0358e54c1d505da783e8cfaf6cff82f35f0ebfa10ca1376fb7
3
+ size 18837
runs/Jan22_22-17-19_Simon-PC/events.out.tfevents.1705958239.Simon-PC ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5d0f3d8566977111cbcbda17f5935f80535e578a8e123fb6e98210dce2e71b4
3
+ size 7319
runs/Jan22_22-33-10_Simon-PC/events.out.tfevents.1705959191.Simon-PC ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c0f17061f69bb16d52636a929823396b8472b1ab0e27de67b4700084f1f46f9
3
+ size 10542
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34b92435f6d3609efaa85c44a37d90dce494132bf8633ee61d9a04c979fcfe71
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db432a27a920f953d28d47696f6ece9d5017aa28beb3a7a1f8a996a04516e2e
3
  size 4728