selmamalak commited on
Commit
88479c6
·
verified ·
1 Parent(s): 617ed65

Model save

Browse files
Files changed (1) hide show
  1. README.md +82 -0
README.md ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - generated_from_trainer
6
+ base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
7
+ datasets:
8
+ - medmnist-v2
9
+ metrics:
10
+ - accuracy
11
+ - precision
12
+ - recall
13
+ - f1
14
+ model-index:
15
+ - name: organsmnist-beit-base-finetuned
16
+ results: []
17
+ ---
18
+
19
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
+ should probably proofread and complete it, then remove this comment. -->
21
+
22
+ # organsmnist-beit-base-finetuned
23
+
24
+ This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the medmnist-v2 dataset.
25
+ It achieves the following results on the evaluation set:
26
+ - Loss: 0.2590
27
+ - Accuracy: 0.9050
28
+ - Precision: 0.8524
29
+ - Recall: 0.8468
30
+ - F1: 0.8468
31
+
32
+ ## Model description
33
+
34
+ More information needed
35
+
36
+ ## Intended uses & limitations
37
+
38
+ More information needed
39
+
40
+ ## Training and evaluation data
41
+
42
+ More information needed
43
+
44
+ ## Training procedure
45
+
46
+ ### Training hyperparameters
47
+
48
+ The following hyperparameters were used during training:
49
+ - learning_rate: 0.005
50
+ - train_batch_size: 16
51
+ - eval_batch_size: 16
52
+ - seed: 42
53
+ - gradient_accumulation_steps: 4
54
+ - total_train_batch_size: 64
55
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
56
+ - lr_scheduler_type: linear
57
+ - num_epochs: 10
58
+ - mixed_precision_training: Native AMP
59
+
60
+ ### Training results
61
+
62
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
63
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
64
+ | 0.9608 | 1.0 | 218 | 0.6055 | 0.7765 | 0.7235 | 0.7233 | 0.7007 |
65
+ | 0.9984 | 2.0 | 436 | 0.4812 | 0.8067 | 0.7265 | 0.7321 | 0.7114 |
66
+ | 0.8265 | 3.0 | 654 | 0.3726 | 0.8520 | 0.8005 | 0.7713 | 0.7683 |
67
+ | 0.7938 | 4.0 | 872 | 0.3913 | 0.8507 | 0.7812 | 0.7831 | 0.7554 |
68
+ | 0.8149 | 5.0 | 1090 | 0.3676 | 0.8532 | 0.7687 | 0.8002 | 0.7702 |
69
+ | 0.6737 | 6.0 | 1308 | 0.3305 | 0.8675 | 0.8306 | 0.8117 | 0.7934 |
70
+ | 0.5695 | 7.0 | 1526 | 0.2481 | 0.9029 | 0.8546 | 0.8469 | 0.8321 |
71
+ | 0.5857 | 8.0 | 1744 | 0.2912 | 0.8923 | 0.8464 | 0.8356 | 0.8340 |
72
+ | 0.4834 | 9.0 | 1962 | 0.2658 | 0.8997 | 0.8428 | 0.8410 | 0.8286 |
73
+ | 0.5287 | 10.0 | 2180 | 0.2590 | 0.9050 | 0.8524 | 0.8468 | 0.8468 |
74
+
75
+
76
+ ### Framework versions
77
+
78
+ - PEFT 0.11.1
79
+ - Transformers 4.39.3
80
+ - Pytorch 2.1.2
81
+ - Datasets 2.18.0
82
+ - Tokenizers 0.15.2