Hugging Face's logo

ihsanabdulhakim
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Model card Files
xet
Metrics Community
ihsanabdulhakim commited on
Commit
a110b90
·
verified ·
1 Parent(s): 9751d4d

Model save

Browse files
Files changed (4) hide show
  1. README.md +94 -0
  2. model.safetensors +1 -1
  3. runs/Jun28_02-01-44_GAN-SVR/events.out.tfevents.1751043728.GAN-SVR.323061.0 +2 -2
  4. runs/Jun28_02-01-44_GAN-SVR/events.out.tfevents.1751043961.GAN-SVR.323061.1 +3 -0
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: MCG-NJU/videomae-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: videomae-base-finetuned-ucf101-subset
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # videomae-base-finetuned-ucf101-subset
18
+
19
+ This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.5786
22
+ - Accuracy: 0.8852
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 5e-05
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
+ - seed: 42
45
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - training_steps: 130
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
54
+ | No log | 0.0308 | 4 | 3.0569 | 0.0492 |
55
+ | No log | 1.0308 | 8 | 3.0837 | 0.0328 |
56
+ | 3.0022 | 2.0308 | 12 | 3.0679 | 0.0984 |
57
+ | 3.0022 | 3.0308 | 16 | 3.0689 | 0.0820 |
58
+ | 2.9588 | 4.0308 | 20 | 3.0206 | 0.0656 |
59
+ | 2.9588 | 5.0308 | 24 | 2.9201 | 0.1803 |
60
+ | 2.9588 | 6.0308 | 28 | 2.8711 | 0.1475 |
61
+ | 2.7723 | 7.0308 | 32 | 2.7757 | 0.1803 |
62
+ | 2.7723 | 8.0308 | 36 | 2.4966 | 0.3934 |
63
+ | 2.3535 | 9.0308 | 40 | 2.3920 | 0.2951 |
64
+ | 2.3535 | 10.0308 | 44 | 2.1505 | 0.4754 |
65
+ | 2.3535 | 11.0308 | 48 | 2.0541 | 0.5082 |
66
+ | 1.7855 | 12.0308 | 52 | 1.8269 | 0.5902 |
67
+ | 1.7855 | 13.0308 | 56 | 1.6477 | 0.6557 |
68
+ | 1.2907 | 14.0308 | 60 | 1.5733 | 0.7049 |
69
+ | 1.2907 | 15.0308 | 64 | 1.3482 | 0.8033 |
70
+ | 1.2907 | 16.0308 | 68 | 1.2642 | 0.7705 |
71
+ | 0.8499 | 17.0308 | 72 | 1.1296 | 0.8689 |
72
+ | 0.8499 | 18.0308 | 76 | 1.1052 | 0.8197 |
73
+ | 0.5723 | 19.0308 | 80 | 1.0154 | 0.8197 |
74
+ | 0.5723 | 20.0308 | 84 | 0.8964 | 0.8525 |
75
+ | 0.5723 | 21.0308 | 88 | 0.8365 | 0.8689 |
76
+ | 0.3825 | 22.0308 | 92 | 0.7722 | 0.8525 |
77
+ | 0.3825 | 23.0308 | 96 | 0.7270 | 0.8689 |
78
+ | 0.2545 | 24.0308 | 100 | 0.7209 | 0.8525 |
79
+ | 0.2545 | 25.0308 | 104 | 0.6553 | 0.8689 |
80
+ | 0.2545 | 26.0308 | 108 | 0.6224 | 0.8689 |
81
+ | 0.1936 | 27.0308 | 112 | 0.6002 | 0.8852 |
82
+ | 0.1936 | 28.0308 | 116 | 0.5698 | 0.8852 |
83
+ | 0.1622 | 29.0308 | 120 | 0.5786 | 0.8689 |
84
+ | 0.1622 | 30.0308 | 124 | 0.5775 | 0.8689 |
85
+ | 0.1622 | 31.0308 | 128 | 0.5436 | 0.8689 |
86
+ | 0.1456 | 32.0154 | 130 | 0.5694 | 0.8689 |
87
+
88
+
89
+ ### Framework versions
90
+
91
+ - Transformers 4.48.0
92
+ - Pytorch 2.0.1+cu118
93
+ - Datasets 3.2.0
94
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08ca0b7783b4f4f8aba5fd3949ea6ad116cc6e22afecfd81e9b20724cfb083b2
3
  size 344995820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb546effcd2eb43558f10b5a53e33d28920935e16e1489bdf693b1b658ef7b0
3
  size 344995820
runs/Jun28_02-01-44_GAN-SVR/events.out.tfevents.1751043728.GAN-SVR.323061.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa891829f798ceac5f9e44002368b2309354e151930562afb474b9246a38dd07
3
- size 18495
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dbfb724d1fef4da58e7623f1f75f71a3ec3b9b3d8a180f4626bc2c8c1bd2a81
3
+ size 20023
runs/Jun28_02-01-44_GAN-SVR/events.out.tfevents.1751043961.GAN-SVR.323061.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44cf220a559b0114748aa4f766eba837233aa113daa08ca928e2e4d9abdb7683
3
+ size 411