Hugging Face's logo

OSRSEnthusiast
/
trainer_output

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
OSRSEnthusiast commited on
Commit
dbfffc8
·
verified ·
1 Parent(s): 7efc5e0

Model save

Browse files
Files changed (3) hide show
  1. README.md +25 -20
  2. model.safetensors +1 -1
  3. runs/May02_18-51-00_a900858303fe/events.out.tfevents.1746212766.a900858303fe.211.1 +3 -0
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.8673469387755102
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  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.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.3077
37
- - Accuracy: 0.8673
38
 
39
  ## Model description
40
 
@@ -54,32 +54,37 @@ More information needed
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 0.001
57
- - train_batch_size: 8
58
  - eval_batch_size: 8
59
  - seed: 42
60
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
  - lr_scheduler_type: linear
62
- - num_epochs: 15
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
- | No log | 1.0 | 98 | 0.3828 | 0.8660 |
69
- | 0.5393 | 2.0 | 196 | 0.3853 | 0.8041 |
70
- | 0.3564 | 3.0 | 294 | 0.3401 | 0.8351 |
71
- | 0.2952 | 4.0 | 392 | 0.3732 | 0.8144 |
72
- | 0.2444 | 5.0 | 490 | 0.3522 | 0.8144 |
73
- | 0.2353 | 6.0 | 588 | 0.3187 | 0.8660 |
74
- | 0.2157 | 7.0 | 686 | 0.3247 | 0.8557 |
75
- | 0.1952 | 8.0 | 784 | 0.3762 | 0.8041 |
76
- | 0.1813 | 9.0 | 882 | 0.3644 | 0.8351 |
77
- | 0.1782 | 10.0 | 980 | 0.3399 | 0.8557 |
78
- | 0.1598 | 11.0 | 1078 | 0.3398 | 0.8454 |
79
- | 0.1677 | 12.0 | 1176 | 0.3493 | 0.8454 |
80
- | 0.1404 | 13.0 | 1274 | 0.3584 | 0.8351 |
81
- | 0.1532 | 14.0 | 1372 | 0.3594 | 0.8454 |
82
- | 0.1372 | 15.0 | 1470 | 0.3557 | 0.8454 |
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.8775510204081632
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  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.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.3427
37
+ - Accuracy: 0.8776
38
 
39
  ## Model description
40
 
 
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 0.001
57
+ - train_batch_size: 20
58
  - eval_batch_size: 8
59
  - seed: 42
60
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
61
  - lr_scheduler_type: linear
62
+ - num_epochs: 20
63
 
64
  ### Training results
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | No log | 1.0 | 39 | 0.4124 | 0.7938 |
69
+ | No log | 2.0 | 78 | 0.3294 | 0.8454 |
70
+ | 0.4497 | 3.0 | 117 | 0.2932 | 0.8454 |
71
+ | 0.4497 | 4.0 | 156 | 0.2799 | 0.8557 |
72
+ | 0.4497 | 5.0 | 195 | 0.2692 | 0.8969 |
73
+ | 0.2764 | 6.0 | 234 | 0.2604 | 0.8969 |
74
+ | 0.2764 | 7.0 | 273 | 0.2583 | 0.9175 |
75
+ | 0.2192 | 8.0 | 312 | 0.2546 | 0.9072 |
76
+ | 0.2192 | 9.0 | 351 | 0.2506 | 0.9072 |
77
+ | 0.2192 | 10.0 | 390 | 0.2536 | 0.9072 |
78
+ | 0.1936 | 11.0 | 429 | 0.2530 | 0.8866 |
79
+ | 0.1936 | 12.0 | 468 | 0.2503 | 0.9072 |
80
+ | 0.1731 | 13.0 | 507 | 0.2480 | 0.9072 |
81
+ | 0.1731 | 14.0 | 546 | 0.2496 | 0.9072 |
82
+ | 0.1731 | 15.0 | 585 | 0.2498 | 0.9072 |
83
+ | 0.155 | 16.0 | 624 | 0.2498 | 0.9072 |
84
+ | 0.155 | 17.0 | 663 | 0.2495 | 0.9072 |
85
+ | 0.1442 | 18.0 | 702 | 0.2488 | 0.9072 |
86
+ | 0.1442 | 19.0 | 741 | 0.2493 | 0.9072 |
87
+ | 0.1442 | 20.0 | 780 | 0.2490 | 0.9072 |
88
 
89
 
90
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb7bfd3003407b9f9f4fc02094354172e9f6c354837ebb75fb9ac1819bb6a25d
3
  size 343223968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34765d2c8826458a8b62fa240cd389d1c7edd0168bd48c1f07ebd3174c52ce80
3
  size 343223968
runs/May02_18-51-00_a900858303fe/events.out.tfevents.1746212766.a900858303fe.211.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25aa386dbd490db9849ac2d760500ccb3c5355349e1658a6ed482163f8393278
3
+ size 411