debajyotidasgupta commited on
Commit
0532658
1 Parent(s): 70e901a

Model save

Browse files
Files changed (2) hide show
  1. README.md +87 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/vit-large-patch32-384
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - f1
10
+ model-index:
11
+ - name: vit-large-patch32-384
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: train
21
+ args: default
22
+ metrics:
23
+ - name: F1
24
+ type: f1
25
+ value: 0.9763018966303854
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # vit-large-patch32-384
32
+
33
+ This model is a fine-tuned version of [google/vit-large-patch32-384](https://huggingface.co/google/vit-large-patch32-384) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.0127
36
+ - F1: 0.9763
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 5e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 128
61
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
+ - lr_scheduler_type: linear
63
+ - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 10
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
69
+ |:-------------:|:-----:|:----:|:---------------:|:------:|
70
+ | 0.1312 | 0.99 | 53 | 0.1215 | 0.7860 |
71
+ | 0.0831 | 1.99 | 107 | 0.0570 | 0.9350 |
72
+ | 0.0441 | 3.0 | 161 | 0.0348 | 0.9475 |
73
+ | 0.0423 | 4.0 | 215 | 0.0342 | 0.9186 |
74
+ | 0.0249 | 4.99 | 268 | 0.0232 | 0.9594 |
75
+ | 0.0168 | 5.99 | 322 | 0.0279 | 0.9414 |
76
+ | 0.0098 | 7.0 | 376 | 0.0242 | 0.9460 |
77
+ | 0.0133 | 8.0 | 430 | 0.0181 | 0.9637 |
78
+ | 0.0156 | 8.99 | 483 | 0.0101 | 0.9804 |
79
+ | 0.0114 | 9.86 | 530 | 0.0127 | 0.9763 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.35.2
85
+ - Pytorch 2.1.0+cu121
86
+ - Datasets 2.16.1
87
+ - Tokenizers 0.15.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4ce6ade4b58a81c5b49c094f2061572460dbfe3e10daf54895b87b496bf3e92
3
  size 1222485480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af24572d38a6a99d9fc6e5fa3fbdfeea298da76b0299ce9a15fafc07d3650027
3
  size 1222485480