End of training
Browse files- README.md +127 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google/vit-base-patch16-224-in21k
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
metrics:
|
9 |
+
- accuracy
|
10 |
+
model-index:
|
11 |
+
- name: emotion_model
|
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: 0.6
|
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 |
+
# emotion_model
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.3497
|
36 |
+
- Accuracy: 0.6
|
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: 0.0001
|
56 |
+
- train_batch_size: 16
|
57 |
+
- eval_batch_size: 16
|
58 |
+
- seed: 42
|
59 |
+
- gradient_accumulation_steps: 4
|
60 |
+
- total_train_batch_size: 64
|
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: 50
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
70 |
+
| 2.0823 | 1.0 | 10 | 2.0560 | 0.1625 |
|
71 |
+
| 2.0479 | 2.0 | 20 | 2.0218 | 0.2812 |
|
72 |
+
| 1.9636 | 3.0 | 30 | 1.8882 | 0.4062 |
|
73 |
+
| 1.7902 | 4.0 | 40 | 1.6881 | 0.4313 |
|
74 |
+
| 1.5792 | 5.0 | 50 | 1.6159 | 0.3688 |
|
75 |
+
| 1.4429 | 6.0 | 60 | 1.3871 | 0.5687 |
|
76 |
+
| 1.2854 | 7.0 | 70 | 1.2973 | 0.5437 |
|
77 |
+
| 1.1487 | 8.0 | 80 | 1.2303 | 0.6 |
|
78 |
+
| 1.0374 | 9.0 | 90 | 1.2661 | 0.5375 |
|
79 |
+
| 0.9584 | 10.0 | 100 | 1.1662 | 0.5563 |
|
80 |
+
| 0.8108 | 11.0 | 110 | 1.2135 | 0.5312 |
|
81 |
+
| 0.7402 | 12.0 | 120 | 1.2117 | 0.5813 |
|
82 |
+
| 0.6349 | 13.0 | 130 | 1.1176 | 0.6062 |
|
83 |
+
| 0.5674 | 14.0 | 140 | 1.1794 | 0.575 |
|
84 |
+
| 0.5103 | 15.0 | 150 | 1.0948 | 0.6375 |
|
85 |
+
| 0.4826 | 16.0 | 160 | 1.1833 | 0.5875 |
|
86 |
+
| 0.4128 | 17.0 | 170 | 1.2601 | 0.5375 |
|
87 |
+
| 0.3664 | 18.0 | 180 | 1.3378 | 0.55 |
|
88 |
+
| 0.3112 | 19.0 | 190 | 1.2789 | 0.5437 |
|
89 |
+
| 0.335 | 20.0 | 200 | 1.2913 | 0.5625 |
|
90 |
+
| 0.3261 | 21.0 | 210 | 1.1114 | 0.6 |
|
91 |
+
| 0.3443 | 22.0 | 220 | 1.2177 | 0.5938 |
|
92 |
+
| 0.2642 | 23.0 | 230 | 1.2299 | 0.5938 |
|
93 |
+
| 0.2895 | 24.0 | 240 | 1.2339 | 0.5813 |
|
94 |
+
| 0.266 | 25.0 | 250 | 1.2384 | 0.5875 |
|
95 |
+
| 0.2725 | 26.0 | 260 | 1.2100 | 0.6062 |
|
96 |
+
| 0.2725 | 27.0 | 270 | 1.3073 | 0.575 |
|
97 |
+
| 0.2637 | 28.0 | 280 | 1.3019 | 0.5875 |
|
98 |
+
| 0.2561 | 29.0 | 290 | 1.3597 | 0.5437 |
|
99 |
+
| 0.2375 | 30.0 | 300 | 1.3404 | 0.5563 |
|
100 |
+
| 0.2188 | 31.0 | 310 | 1.2922 | 0.5813 |
|
101 |
+
| 0.2141 | 32.0 | 320 | 1.3778 | 0.5312 |
|
102 |
+
| 0.198 | 33.0 | 330 | 1.3473 | 0.5875 |
|
103 |
+
| 0.1805 | 34.0 | 340 | 1.3984 | 0.5437 |
|
104 |
+
| 0.1888 | 35.0 | 350 | 1.3508 | 0.5813 |
|
105 |
+
| 0.1867 | 36.0 | 360 | 1.3531 | 0.575 |
|
106 |
+
| 0.1596 | 37.0 | 370 | 1.5846 | 0.4875 |
|
107 |
+
| 0.1564 | 38.0 | 380 | 1.3380 | 0.5687 |
|
108 |
+
| 0.1719 | 39.0 | 390 | 1.5206 | 0.5312 |
|
109 |
+
| 0.1678 | 40.0 | 400 | 1.2929 | 0.5875 |
|
110 |
+
| 0.136 | 41.0 | 410 | 1.5031 | 0.55 |
|
111 |
+
| 0.1602 | 42.0 | 420 | 1.3855 | 0.5625 |
|
112 |
+
| 0.174 | 43.0 | 430 | 1.4385 | 0.5875 |
|
113 |
+
| 0.179 | 44.0 | 440 | 1.3153 | 0.575 |
|
114 |
+
| 0.1284 | 45.0 | 450 | 1.4295 | 0.5875 |
|
115 |
+
| 0.1419 | 46.0 | 460 | 1.4126 | 0.575 |
|
116 |
+
| 0.1425 | 47.0 | 470 | 1.3760 | 0.5687 |
|
117 |
+
| 0.1602 | 48.0 | 480 | 1.4374 | 0.5875 |
|
118 |
+
| 0.1473 | 49.0 | 490 | 1.3126 | 0.5813 |
|
119 |
+
| 0.153 | 50.0 | 500 | 1.3497 | 0.6 |
|
120 |
+
|
121 |
+
|
122 |
+
### Framework versions
|
123 |
+
|
124 |
+
- Transformers 4.33.2
|
125 |
+
- Pytorch 2.0.1+cu118
|
126 |
+
- Datasets 2.14.5
|
127 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343287149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee761c784e7c7a88604760e8591f5b8e934504a59297dd60f5b38c37f34c8f4e
|
3 |
size 343287149
|