Hugging Face's logo

Ivanrs
/
vit-finetune-kidney-stone-Jonathan_El-Beze_-w256_1k_v1-_MIX-finetune

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Ivanrs commited on
Commit
5603adc
·
verified ·
1 Parent(s): 4690f14

vit-finetune-kidney-stone-Jonathan_El-Beze_-w256_1k_v1-_MIX-finetune

Browse files
Files changed (7) hide show
  1. README.md +57 -15
  2. all_results.json +14 -14
  3. model.safetensors +1 -1
  4. test_results.json +9 -9
  5. train_results.json +6 -6
  6. trainer_state.json +0 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.8833333333333333
28
  - name: Precision
29
  type: precision
30
- value: 0.8929214371019096
31
  - name: Recall
32
  type: recall
33
- value: 0.8833333333333333
34
  - name: F1
35
  type: f1
36
- value: 0.8834269042403968
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
43
 
44
  This model was trained from scratch on the imagefolder dataset.
45
  It achieves the following results on the evaluation set:
46
- - Loss: 0.4274
47
- - Accuracy: 0.8833
48
- - Precision: 0.8929
49
- - Recall: 0.8833
50
- - F1: 0.8834
51
 
52
  ## Model description
53
 
@@ -72,16 +72,58 @@ The following hyperparameters were used during training:
72
  - seed: 42
73
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
74
  - lr_scheduler_type: linear
75
- - num_epochs: 1
76
  - mixed_precision_training: Native AMP
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
81
- |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
82
- | 0.1774 | 0.3333 | 100 | 0.5609 | 0.8383 | 0.8610 | 0.8383 | 0.8299 |
83
- | 0.0464 | 0.6667 | 200 | 0.6120 | 0.8196 | 0.8488 | 0.8196 | 0.8165 |
84
- | 0.0126 | 1.0 | 300 | 0.4274 | 0.8833 | 0.8929 | 0.8833 | 0.8834 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
 
86
 
87
  ### Framework versions
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.9025
28
  - name: Precision
29
  type: precision
30
+ value: 0.9064641723426297
31
  - name: Recall
32
  type: recall
33
+ value: 0.9025
34
  - name: F1
35
  type: f1
36
+ value: 0.901111416212371
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
43
 
44
  This model was trained from scratch on the imagefolder dataset.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 0.3739
47
+ - Accuracy: 0.9025
48
+ - Precision: 0.9065
49
+ - Recall: 0.9025
50
+ - F1: 0.9011
51
 
52
  ## Model description
53
 
 
72
  - seed: 42
73
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
74
  - lr_scheduler_type: linear
75
+ - num_epochs: 15
76
  - mixed_precision_training: Native AMP
77
 
78
  ### Training results
79
 
80
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
81
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
82
+ | 0.1672 | 0.3333 | 100 | 0.3739 | 0.9025 | 0.9065 | 0.9025 | 0.9011 |
83
+ | 0.1364 | 0.6667 | 200 | 0.7118 | 0.7879 | 0.8371 | 0.7879 | 0.7837 |
84
+ | 0.0603 | 1.0 | 300 | 0.6678 | 0.8275 | 0.8502 | 0.8275 | 0.8257 |
85
+ | 0.0532 | 1.3333 | 400 | 0.6051 | 0.8596 | 0.8785 | 0.8596 | 0.8578 |
86
+ | 0.0195 | 1.6667 | 500 | 0.6989 | 0.8263 | 0.8493 | 0.8263 | 0.8278 |
87
+ | 0.0284 | 2.0 | 600 | 0.7349 | 0.8342 | 0.8608 | 0.8342 | 0.8366 |
88
+ | 0.0145 | 2.3333 | 700 | 0.7102 | 0.8662 | 0.8741 | 0.8662 | 0.8636 |
89
+ | 0.0142 | 2.6667 | 800 | 0.7562 | 0.8583 | 0.8652 | 0.8583 | 0.8554 |
90
+ | 0.0327 | 3.0 | 900 | 0.6251 | 0.87 | 0.8830 | 0.87 | 0.8697 |
91
+ | 0.0014 | 3.3333 | 1000 | 0.6991 | 0.8571 | 0.8772 | 0.8571 | 0.8535 |
92
+ | 0.0015 | 3.6667 | 1100 | 0.4318 | 0.9075 | 0.9117 | 0.9075 | 0.9077 |
93
+ | 0.0022 | 4.0 | 1200 | 0.7833 | 0.8592 | 0.8752 | 0.8592 | 0.8583 |
94
+ | 0.0049 | 4.3333 | 1300 | 0.4950 | 0.9054 | 0.9088 | 0.9054 | 0.9049 |
95
+ | 0.0125 | 4.6667 | 1400 | 0.5476 | 0.8879 | 0.8898 | 0.8879 | 0.8873 |
96
+ | 0.0163 | 5.0 | 1500 | 0.4917 | 0.9096 | 0.9099 | 0.9096 | 0.9087 |
97
+ | 0.003 | 5.3333 | 1600 | 0.8279 | 0.8612 | 0.8665 | 0.8612 | 0.8586 |
98
+ | 0.0027 | 5.6667 | 1700 | 0.9960 | 0.8242 | 0.8615 | 0.8242 | 0.8141 |
99
+ | 0.0015 | 6.0 | 1800 | 0.7634 | 0.8621 | 0.8865 | 0.8621 | 0.8611 |
100
+ | 0.0006 | 6.3333 | 1900 | 0.5313 | 0.9 | 0.9068 | 0.9 | 0.8991 |
101
+ | 0.0005 | 6.6667 | 2000 | 0.4222 | 0.9225 | 0.9243 | 0.9225 | 0.9222 |
102
+ | 0.0322 | 7.0 | 2100 | 0.5260 | 0.9067 | 0.9115 | 0.9067 | 0.9063 |
103
+ | 0.0106 | 7.3333 | 2200 | 0.5679 | 0.8817 | 0.8903 | 0.8817 | 0.8819 |
104
+ | 0.0006 | 7.6667 | 2300 | 0.7876 | 0.8517 | 0.8828 | 0.8517 | 0.8532 |
105
+ | 0.0004 | 8.0 | 2400 | 0.5605 | 0.8992 | 0.9061 | 0.8992 | 0.8987 |
106
+ | 0.0003 | 8.3333 | 2500 | 0.5620 | 0.9021 | 0.9084 | 0.9021 | 0.9016 |
107
+ | 0.0003 | 8.6667 | 2600 | 0.5725 | 0.9004 | 0.9071 | 0.9004 | 0.9001 |
108
+ | 0.0002 | 9.0 | 2700 | 0.5745 | 0.9008 | 0.9074 | 0.9008 | 0.9006 |
109
+ | 0.0002 | 9.3333 | 2800 | 0.5751 | 0.9012 | 0.9074 | 0.9012 | 0.9009 |
110
+ | 0.0002 | 9.6667 | 2900 | 0.5769 | 0.9017 | 0.9078 | 0.9017 | 0.9013 |
111
+ | 0.0002 | 10.0 | 3000 | 0.5792 | 0.9012 | 0.9075 | 0.9012 | 0.9009 |
112
+ | 0.0002 | 10.3333 | 3100 | 0.5812 | 0.9017 | 0.9078 | 0.9017 | 0.9014 |
113
+ | 0.0002 | 10.6667 | 3200 | 0.5832 | 0.9017 | 0.9078 | 0.9017 | 0.9014 |
114
+ | 0.0002 | 11.0 | 3300 | 0.5849 | 0.9017 | 0.9078 | 0.9017 | 0.9014 |
115
+ | 0.0002 | 11.3333 | 3400 | 0.5864 | 0.9021 | 0.9080 | 0.9021 | 0.9018 |
116
+ | 0.0002 | 11.6667 | 3500 | 0.5881 | 0.9021 | 0.9080 | 0.9021 | 0.9018 |
117
+ | 0.0001 | 12.0 | 3600 | 0.5898 | 0.9029 | 0.9086 | 0.9029 | 0.9026 |
118
+ | 0.0002 | 12.3333 | 3700 | 0.5913 | 0.9033 | 0.9089 | 0.9033 | 0.9030 |
119
+ | 0.0001 | 12.6667 | 3800 | 0.5925 | 0.9038 | 0.9093 | 0.9038 | 0.9034 |
120
+ | 0.0001 | 13.0 | 3900 | 0.5936 | 0.9038 | 0.9093 | 0.9038 | 0.9034 |
121
+ | 0.0001 | 13.3333 | 4000 | 0.5945 | 0.9038 | 0.9093 | 0.9038 | 0.9034 |
122
+ | 0.0001 | 13.6667 | 4100 | 0.5953 | 0.9038 | 0.9093 | 0.9038 | 0.9034 |
123
+ | 0.0001 | 14.0 | 4200 | 0.5961 | 0.9038 | 0.9093 | 0.9038 | 0.9034 |
124
+ | 0.0001 | 14.3333 | 4300 | 0.5966 | 0.9038 | 0.9093 | 0.9038 | 0.9034 |
125
+ | 0.0001 | 14.6667 | 4400 | 0.5970 | 0.9038 | 0.9093 | 0.9038 | 0.9034 |
126
+ | 0.0001 | 15.0 | 4500 | 0.5971 | 0.9038 | 0.9093 | 0.9038 | 0.9034 |
127
 
128
 
129
  ### Framework versions
all_results.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "epoch": 1.0,
3
- "eval_accuracy": 0.8833333333333333,
4
- "eval_f1": 0.8834269042403968,
5
- "eval_loss": 0.4274447560310364,
6
- "eval_precision": 0.8929214371019096,
7
- "eval_recall": 0.8833333333333333,
8
- "eval_runtime": 19.6495,
9
- "eval_samples_per_second": 122.14,
10
- "eval_steps_per_second": 15.268,
11
- "total_flos": 7.43949770489856e+17,
12
- "train_loss": 0.18607434034347534,
13
- "train_runtime": 150.3491,
14
- "train_samples_per_second": 63.851,
15
- "train_steps_per_second": 1.995
16
  }
 
1
  {
2
+ "epoch": 15.0,
3
+ "eval_accuracy": 0.9025,
4
+ "eval_f1": 0.901111416212371,
5
+ "eval_loss": 0.3738570213317871,
6
+ "eval_precision": 0.9064641723426297,
7
+ "eval_recall": 0.9025,
8
+ "eval_runtime": 18.707,
9
+ "eval_samples_per_second": 128.294,
10
+ "eval_steps_per_second": 16.037,
11
+ "total_flos": 1.115924655734784e+19,
12
+ "train_loss": 0.023723256637652713,
13
+ "train_runtime": 2160.7868,
14
+ "train_samples_per_second": 66.642,
15
+ "train_steps_per_second": 2.083
16
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07ffef9f0ef2705bc879ed3de73c342099224552b5d93ceeae3919a10f9ed501
3
  size 343236280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:744366f7b34f8f6c3448099ab05891d5e26925617d924fe86505b0220838b184
3
  size 343236280
test_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 1.0,
3
- "eval_accuracy": 0.8833333333333333,
4
- "eval_f1": 0.8834269042403968,
5
- "eval_loss": 0.4274447560310364,
6
- "eval_precision": 0.8929214371019096,
7
- "eval_recall": 0.8833333333333333,
8
- "eval_runtime": 19.6495,
9
- "eval_samples_per_second": 122.14,
10
- "eval_steps_per_second": 15.268
11
  }
 
1
  {
2
+ "epoch": 15.0,
3
+ "eval_accuracy": 0.9025,
4
+ "eval_f1": 0.901111416212371,
5
+ "eval_loss": 0.3738570213317871,
6
+ "eval_precision": 0.9064641723426297,
7
+ "eval_recall": 0.9025,
8
+ "eval_runtime": 18.707,
9
+ "eval_samples_per_second": 128.294,
10
+ "eval_steps_per_second": 16.037
11
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "total_flos": 7.43949770489856e+17,
4
- "train_loss": 0.18607434034347534,
5
- "train_runtime": 150.3491,
6
- "train_samples_per_second": 63.851,
7
- "train_steps_per_second": 1.995
8
  }
 
1
  {
2
+ "epoch": 15.0,
3
+ "total_flos": 1.115924655734784e+19,
4
+ "train_loss": 0.023723256637652713,
5
+ "train_runtime": 2160.7868,
6
+ "train_samples_per_second": 66.642,
7
+ "train_steps_per_second": 2.083
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc8ad42322898a1a326f925bdacf37abdec1377dd120e58766dc6f896756cab0
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f896627b92317e13c25dfd0ebadc0d31da08b0eb5af76db06c21c5d66c54ff66
3
  size 5432