Hugging Face's logo

ihsanahakiim
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ihsanahakiim commited on
Commit
a9d9650
·
verified ·
1 Parent(s): 971d36f

Model save

Browse files
Files changed (3) hide show
  1. README.md +35 -20
  2. model.safetensors +1 -1
  3. runs/Jan12_17-57-19_GAN-SVR/events.out.tfevents.1736694740.GAN-SVR.3870842.4 +3 -0
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 3.0235
22
- - Accuracy: 0.2575
23
 
24
  ## Model description
25
 
@@ -45,33 +45,48 @@ The following hyperparameters were used during training:
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: 480
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
54
- | 4.2682 | 0.0646 | 31 | 4.2493 | 0.0033 |
55
- | 4.2584 | 1.0646 | 62 | 4.2434 | 0.0134 |
56
- | 4.2518 | 2.0646 | 93 | 4.2246 | 0.0167 |
57
- | 4.2445 | 3.0646 | 124 | 4.2208 | 0.0067 |
58
- | 4.2272 | 4.0646 | 155 | 4.2230 | 0.0100 |
59
- | 4.205 | 5.0646 | 186 | 4.2111 | 0.0234 |
60
- | 4.1238 | 6.0646 | 217 | 4.1112 | 0.0368 |
61
- | 3.9136 | 7.0646 | 248 | 3.8530 | 0.0736 |
62
- | 3.6241 | 8.0646 | 279 | 3.6734 | 0.1171 |
63
- | 3.3103 | 9.0646 | 310 | 3.5261 | 0.1070 |
64
- | 3.0981 | 10.0646 | 341 | 3.3860 | 0.1639 |
65
- | 2.8216 | 11.0646 | 372 | 3.1791 | 0.2140 |
66
- | 2.6108 | 12.0646 | 403 | 3.1618 | 0.2441 |
67
- | 2.598 | 13.0646 | 434 | 3.0793 | 0.2341 |
68
- | 2.5023 | 14.0646 | 465 | 3.0194 | 0.2575 |
69
- | 2.513 | 15.0312 | 480 | 3.0668 | 0.2375 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
 
72
  ### Framework versions
73
 
74
  - Transformers 4.48.0
75
- - Pytorch 2.5.1+cu118
76
  - Datasets 3.2.0
77
  - Tokenizers 0.21.0
 
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: 2.1814
22
+ - Accuracy: 0.4883
23
 
24
  ## Model description
25
 
 
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: 960
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
54
+ | 4.2427 | 0.0323 | 31 | 4.2265 | 0.0033 |
55
+ | 4.2321 | 1.0323 | 62 | 4.2235 | 0.0100 |
56
+ | 4.24 | 2.0323 | 93 | 4.2282 | 0.0100 |
57
+ | 4.2445 | 3.0323 | 124 | 4.2250 | 0.0067 |
58
+ | 4.2327 | 4.0323 | 155 | 4.2244 | 0.0100 |
59
+ | 4.2104 | 5.0323 | 186 | 4.2100 | 0.0201 |
60
+ | 4.2374 | 6.0323 | 217 | 4.2022 | 0.0067 |
61
+ | 4.1597 | 7.0323 | 248 | 4.1188 | 0.0301 |
62
+ | 4.0522 | 8.0323 | 279 | 3.9351 | 0.0702 |
63
+ | 3.768 | 9.0323 | 310 | 3.6800 | 0.1070 |
64
+ | 3.5147 | 10.0323 | 341 | 3.5416 | 0.1104 |
65
+ | 3.2878 | 11.0323 | 372 | 3.7074 | 0.0702 |
66
+ | 2.9491 | 12.0323 | 403 | 3.3954 | 0.1070 |
67
+ | 2.806 | 13.0323 | 434 | 3.2552 | 0.1706 |
68
+ | 2.4568 | 14.0323 | 465 | 3.0654 | 0.2040 |
69
+ | 2.3102 | 15.0323 | 496 | 2.7440 | 0.3010 |
70
+ | 2.2079 | 16.0323 | 527 | 2.6789 | 0.3144 |
71
+ | 1.9638 | 17.0323 | 558 | 2.5920 | 0.3679 |
72
+ | 1.7914 | 18.0323 | 589 | 2.6152 | 0.3378 |
73
+ | 1.6925 | 19.0323 | 620 | 2.5971 | 0.3445 |
74
+ | 1.5124 | 20.0323 | 651 | 2.5767 | 0.3478 |
75
+ | 1.4834 | 21.0323 | 682 | 2.4439 | 0.3880 |
76
+ | 1.4565 | 22.0323 | 713 | 2.4057 | 0.3846 |
77
+ | 1.279 | 23.0323 | 744 | 2.5501 | 0.3545 |
78
+ | 1.1477 | 24.0323 | 775 | 2.3247 | 0.4482 |
79
+ | 1.2573 | 25.0323 | 806 | 2.1776 | 0.4883 |
80
+ | 1.0825 | 26.0323 | 837 | 2.1443 | 0.4783 |
81
+ | 1.2121 | 27.0323 | 868 | 2.1490 | 0.4783 |
82
+ | 1.0887 | 28.0323 | 899 | 2.1516 | 0.4716 |
83
+ | 1.1127 | 29.0323 | 930 | 2.1051 | 0.4883 |
84
+ | 0.9905 | 30.0312 | 960 | 2.1170 | 0.4816 |
85
 
86
 
87
  ### Framework versions
88
 
89
  - Transformers 4.48.0
90
+ - Pytorch 2.5.1+cu124
91
  - Datasets 3.2.0
92
  - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1a68c967b41d0cd54bbe77b740f8913031b4c29c0bde8517afea972aff0420e
3
  size 345137324
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3155a5c8bc5eb79132fdcd2c2179041dfde3dc60b62fe8b263628e2fbac1c2c6
3
  size 345137324
runs/Jan12_17-57-19_GAN-SVR/events.out.tfevents.1736694740.GAN-SVR.3870842.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c0d6d3585cbc49ec1dfb467b11a21b44f1b626da41caf1f23cba4d5c3a7b00a
3
+ size 411