Commit
•
3d577f6
1
Parent(s):
437d025
Model save
Browse files
README.md
ADDED
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/deit-base-distilled-patch16-224
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: deit-base-distilled-patch16-224-hasta-55-fold2
|
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: Accuracy
|
24 |
+
type: accuracy
|
25 |
+
value: 0.6111111111111112
|
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 |
+
# deit-base-distilled-patch16-224-hasta-55-fold2
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.0385
|
36 |
+
- Accuracy: 0.6111
|
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: 100
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
70 |
+
| No log | 0.5714 | 1 | 1.3241 | 0.3611 |
|
71 |
+
| No log | 1.7143 | 3 | 1.1598 | 0.3056 |
|
72 |
+
| No log | 2.8571 | 5 | 1.1928 | 0.3889 |
|
73 |
+
| No log | 4.0 | 7 | 1.1229 | 0.3333 |
|
74 |
+
| No log | 4.5714 | 8 | 1.1111 | 0.3333 |
|
75 |
+
| 1.13 | 5.7143 | 10 | 1.1062 | 0.3611 |
|
76 |
+
| 1.13 | 6.8571 | 12 | 1.0655 | 0.4722 |
|
77 |
+
| 1.13 | 8.0 | 14 | 1.0527 | 0.3889 |
|
78 |
+
| 1.13 | 8.5714 | 15 | 1.0448 | 0.4444 |
|
79 |
+
| 1.13 | 9.7143 | 17 | 0.9955 | 0.5556 |
|
80 |
+
| 1.13 | 10.8571 | 19 | 0.9819 | 0.5556 |
|
81 |
+
| 0.9629 | 12.0 | 21 | 0.9722 | 0.5 |
|
82 |
+
| 0.9629 | 12.5714 | 22 | 0.9777 | 0.4444 |
|
83 |
+
| 0.9629 | 13.7143 | 24 | 0.9126 | 0.5556 |
|
84 |
+
| 0.9629 | 14.8571 | 26 | 0.9932 | 0.5556 |
|
85 |
+
| 0.9629 | 16.0 | 28 | 0.9946 | 0.5833 |
|
86 |
+
| 0.9629 | 16.5714 | 29 | 0.9690 | 0.5556 |
|
87 |
+
| 0.822 | 17.7143 | 31 | 0.9163 | 0.5833 |
|
88 |
+
| 0.822 | 18.8571 | 33 | 0.9799 | 0.6389 |
|
89 |
+
| 0.822 | 20.0 | 35 | 0.9273 | 0.6389 |
|
90 |
+
| 0.822 | 20.5714 | 36 | 0.9008 | 0.6389 |
|
91 |
+
| 0.822 | 21.7143 | 38 | 1.0305 | 0.5 |
|
92 |
+
| 0.7066 | 22.8571 | 40 | 0.9330 | 0.5833 |
|
93 |
+
| 0.7066 | 24.0 | 42 | 0.9151 | 0.5833 |
|
94 |
+
| 0.7066 | 24.5714 | 43 | 0.9214 | 0.6111 |
|
95 |
+
| 0.7066 | 25.7143 | 45 | 0.9322 | 0.6111 |
|
96 |
+
| 0.7066 | 26.8571 | 47 | 1.0534 | 0.5833 |
|
97 |
+
| 0.7066 | 28.0 | 49 | 1.1223 | 0.5556 |
|
98 |
+
| 0.5702 | 28.5714 | 50 | 1.0081 | 0.5833 |
|
99 |
+
| 0.5702 | 29.7143 | 52 | 0.8680 | 0.6389 |
|
100 |
+
| 0.5702 | 30.8571 | 54 | 0.9259 | 0.6111 |
|
101 |
+
| 0.5702 | 32.0 | 56 | 0.9936 | 0.6111 |
|
102 |
+
| 0.5702 | 32.5714 | 57 | 0.9762 | 0.6111 |
|
103 |
+
| 0.5702 | 33.7143 | 59 | 0.9298 | 0.6111 |
|
104 |
+
| 0.4903 | 34.8571 | 61 | 0.9352 | 0.6111 |
|
105 |
+
| 0.4903 | 36.0 | 63 | 0.9919 | 0.5833 |
|
106 |
+
| 0.4903 | 36.5714 | 64 | 0.9661 | 0.5833 |
|
107 |
+
| 0.4903 | 37.7143 | 66 | 0.9764 | 0.6389 |
|
108 |
+
| 0.4903 | 38.8571 | 68 | 0.9909 | 0.6389 |
|
109 |
+
| 0.3959 | 40.0 | 70 | 0.9906 | 0.6389 |
|
110 |
+
| 0.3959 | 40.5714 | 71 | 0.9789 | 0.6389 |
|
111 |
+
| 0.3959 | 41.7143 | 73 | 0.9529 | 0.6389 |
|
112 |
+
| 0.3959 | 42.8571 | 75 | 0.9729 | 0.6389 |
|
113 |
+
| 0.3959 | 44.0 | 77 | 1.0425 | 0.6111 |
|
114 |
+
| 0.3959 | 44.5714 | 78 | 1.0531 | 0.6111 |
|
115 |
+
| 0.3792 | 45.7143 | 80 | 0.9800 | 0.5833 |
|
116 |
+
| 0.3792 | 46.8571 | 82 | 0.9609 | 0.5833 |
|
117 |
+
| 0.3792 | 48.0 | 84 | 0.9820 | 0.5833 |
|
118 |
+
| 0.3792 | 48.5714 | 85 | 1.0252 | 0.6389 |
|
119 |
+
| 0.3792 | 49.7143 | 87 | 1.0592 | 0.6111 |
|
120 |
+
| 0.3792 | 50.8571 | 89 | 1.0232 | 0.6667 |
|
121 |
+
| 0.3267 | 52.0 | 91 | 0.9972 | 0.6111 |
|
122 |
+
| 0.3267 | 52.5714 | 92 | 0.9925 | 0.6111 |
|
123 |
+
| 0.3267 | 53.7143 | 94 | 1.0007 | 0.5833 |
|
124 |
+
| 0.3267 | 54.8571 | 96 | 1.0169 | 0.5833 |
|
125 |
+
| 0.3267 | 56.0 | 98 | 1.0304 | 0.5833 |
|
126 |
+
| 0.3267 | 56.5714 | 99 | 1.0360 | 0.6111 |
|
127 |
+
| 0.2959 | 57.1429 | 100 | 1.0385 | 0.6111 |
|
128 |
+
|
129 |
+
|
130 |
+
### Framework versions
|
131 |
+
|
132 |
+
- Transformers 4.41.0
|
133 |
+
- Pytorch 2.3.0+cu121
|
134 |
+
- Datasets 2.19.1
|
135 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343233492
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87ff4f9dc7d51e2637fa7f7f91ef7af2f184f6aa15f7577994f75fe51d91189c
|
3 |
size 343233492
|
runs/May22_13-43-30_927069b479b5/events.out.tfevents.1716385411.927069b479b5.252.8
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2247d4efff8d707f8c930d21d2de0e9952f421ee13c80d9ab0e11c2ab775a227
|
3 |
+
size 25817
|