Hugging Face's logo

MoGHenry
/
cat_dog_classifier_with_small_datasest

Image Classification
Transformers
Safetensors
resnet
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
MoGHenry commited on
Commit
ca2d649
·
verified ·
1 Parent(s): 2ab5de0

End of training

Browse files
Files changed (3) hide show
  1. README.md +25 -15
  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: 0.8714285714285714
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 [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.3807
37
- - Accuracy: 0.8714
38
 
39
  ## Model description
40
 
@@ -54,28 +54,38 @@ More information needed
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 4e-05
57
- - train_batch_size: 4
58
  - eval_batch_size: 8
59
  - seed: 42
60
  - optimizer: Use 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
  - lr_scheduler_warmup_steps: 500
63
- - num_epochs: 10
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | No log | 1.0 | 140 | 0.6967 | 0.4929 |
70
- | No log | 2.0 | 280 | 0.6870 | 0.5357 |
71
- | No log | 3.0 | 420 | 0.6729 | 0.6214 |
72
- | 0.6818 | 4.0 | 560 | 0.6306 | 0.7429 |
73
- | 0.6818 | 5.0 | 700 | 0.5554 | 0.8714 |
74
- | 0.6818 | 6.0 | 840 | 0.4894 | 0.8429 |
75
- | 0.6818 | 7.0 | 980 | 0.4511 | 0.8286 |
76
- | 0.5676 | 8.0 | 1120 | 0.4113 | 0.8643 |
77
- | 0.5676 | 9.0 | 1260 | 0.4318 | 0.8643 |
78
- | 0.5676 | 10.0 | 1400 | 0.3807 | 0.8714 |
 
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.95
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 [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.1369
37
+ - Accuracy: 0.95
38
 
39
  ## Model description
40
 
 
54
 
55
  The following hyperparameters were used during training:
56
  - learning_rate: 4e-05
57
+ - train_batch_size: 8
58
  - eval_batch_size: 8
59
  - seed: 42
60
  - optimizer: Use 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
  - lr_scheduler_warmup_steps: 500
63
+ - num_epochs: 20
64
 
65
  ### Training results
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 1.0 | 70 | 0.5422 | 0.8571 |
70
+ | No log | 2.0 | 140 | 0.5221 | 0.8786 |
71
+ | No log | 3.0 | 210 | 0.4977 | 0.8571 |
72
+ | No log | 4.0 | 280 | 0.4617 | 0.8786 |
73
+ | No log | 5.0 | 350 | 0.3932 | 0.9143 |
74
+ | No log | 6.0 | 420 | 0.3411 | 0.9143 |
75
+ | No log | 7.0 | 490 | 0.2884 | 0.9143 |
76
+ | 0.4971 | 8.0 | 560 | 0.2429 | 0.9286 |
77
+ | 0.4971 | 9.0 | 630 | 0.2151 | 0.9429 |
78
+ | 0.4971 | 10.0 | 700 | 0.1962 | 0.9286 |
79
+ | 0.4971 | 11.0 | 770 | 0.1727 | 0.9357 |
80
+ | 0.4971 | 12.0 | 840 | 0.1676 | 0.95 |
81
+ | 0.4971 | 13.0 | 910 | 0.1764 | 0.9286 |
82
+ | 0.4971 | 14.0 | 980 | 0.1565 | 0.9429 |
83
+ | 0.2878 | 15.0 | 1050 | 0.1578 | 0.9429 |
84
+ | 0.2878 | 16.0 | 1120 | 0.1577 | 0.9429 |
85
+ | 0.2878 | 17.0 | 1190 | 0.1393 | 0.9429 |
86
+ | 0.2878 | 18.0 | 1260 | 0.1472 | 0.9429 |
87
+ | 0.2878 | 19.0 | 1330 | 0.1315 | 0.95 |
88
+ | 0.2878 | 20.0 | 1400 | 0.1369 | 0.95 |
89
 
90
 
91
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f5be6da4d99047a2e156c46feb110200662ab8e67fc00ae3c356b319052adfb
3
  size 94302952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51b4822cbd2af0aa41f34d060ad0d63b5203fc7b54a2c22f4b0c1cdfcbca056c
3
  size 94302952
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3b105c9791529d7d3bc99849398c4e0806d64bc2799d8b33b2d2bcd061fe01c
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce6a21246969c2eb6d4883179aca356184f11c9d3ed253569ccdfcaae42accc
3
  size 5368