Hugging Face's logo

tinutmap
/
categorAI_img

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
tinutmap commited on
Commit
41b45ad
·
verified ·
1 Parent(s): 193ff34

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -12
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.8376068376068376
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-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 1.1293
37
- - Accuracy: 0.8376
38
 
39
  ## Model description
40
 
@@ -62,20 +62,32 @@ The following hyperparameters were used during training:
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
- - num_epochs: 10
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | No log | 1.0 | 5 | 1.6501 | 0.4872 |
72
- | 6.0814 | 2.0 | 10 | 1.4990 | 0.6667 |
73
- | 6.0814 | 3.0 | 15 | 1.4014 | 0.7607 |
74
- | 5.0295 | 4.0 | 20 | 1.3022 | 0.7778 |
75
- | 5.0295 | 5.0 | 25 | 1.1962 | 0.7863 |
76
- | 4.4113 | 6.0 | 30 | 1.1622 | 0.7863 |
77
- | 4.4113 | 7.0 | 35 | 1.1295 | 0.8120 |
78
- | 4.0869 | 8.0 | 40 | 1.1293 | 0.8376 |
 
 
 
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.8632478632478633
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-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.6588
37
+ - Accuracy: 0.8632
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 25
66
 
67
  ### Training results
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
+ | No log | 1.0 | 5 | 1.7795 | 0.2051 |
72
+ | 6.327 | 2.0 | 10 | 1.6254 | 0.5299 |
73
+ | 6.327 | 3.0 | 15 | 1.4687 | 0.6752 |
74
+ | 5.3126 | 4.0 | 20 | 1.3403 | 0.7265 |
75
+ | 5.3126 | 5.0 | 25 | 1.2073 | 0.7692 |
76
+ | 4.4686 | 6.0 | 30 | 1.1235 | 0.7949 |
77
+ | 4.4686 | 7.0 | 35 | 1.0425 | 0.8034 |
78
+ | 3.7739 | 8.0 | 40 | 0.9767 | 0.8205 |
79
+ | 3.7739 | 9.0 | 45 | 0.9313 | 0.8120 |
80
+ | 3.2018 | 10.0 | 50 | 0.8680 | 0.8462 |
81
+ | 3.2018 | 11.0 | 55 | 0.8402 | 0.8205 |
82
+ | 2.8893 | 12.0 | 60 | 0.7929 | 0.8462 |
83
+ | 2.8893 | 13.0 | 65 | 0.7647 | 0.8632 |
84
+ | 2.4413 | 14.0 | 70 | 0.6951 | 0.8974 |
85
+ | 2.4413 | 15.0 | 75 | 0.7528 | 0.8120 |
86
+ | 2.3622 | 16.0 | 80 | 0.7195 | 0.8547 |
87
+ | 2.3622 | 17.0 | 85 | 0.7054 | 0.8291 |
88
+ | 2.1055 | 18.0 | 90 | 0.6788 | 0.8632 |
89
+ | 2.1055 | 19.0 | 95 | 0.7065 | 0.8291 |
90
+ | 2.0917 | 20.0 | 100 | 0.6588 | 0.8632 |
91
 
92
 
93
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d382dc12971bea2d0de7b7d012f56e27266b99acce6956f334e3febff9d708f
3
  size 343236280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b876a03a62abac47517e5116252df6a33b5950490e35bb73d16e6b2f5d6eb6f
3
  size 343236280
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66f241e474876018b83a3b33bc00040b4cd611f25a00f9b4d30f940221ef3567
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0adbbf64daebc830165113e525776a0de04628d189c6333a709842aa6a43e763
3
  size 5304