Hugging Face's logo

HaileyJu
/
videomae-base-finetuned-ucf101-subset-SBDtoy

Video Classification
Transformers
PyTorch
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
HaileyJu commited on
Commit
228d6d3
•
1 Parent(s): 88d0ce8

Model save

Browse files
Files changed (2) hide show
  1. README.md +39 -18
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,5 +1,6 @@
1
  ---
2
  license: cc-by-nc-4.0
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
@@ -16,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.4955
20
- - Accuracy: 1.0
21
 
22
  ## Model description
23
 
@@ -37,33 +38,53 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 5e-05
40
- - train_batch_size: 1
41
- - eval_batch_size: 1
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_ratio: 0.1
46
- - training_steps: 20
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | No log | 0.1 | 2 | 0.6590 | 0.5 |
53
- | No log | 1.1 | 4 | 0.5487 | 0.5 |
54
- | No log | 2.1 | 6 | 0.4955 | 1.0 |
55
- | No log | 3.1 | 8 | 0.5463 | 0.5 |
56
- | 0.4651 | 4.1 | 10 | 0.5728 | 0.5 |
57
- | 0.4651 | 5.1 | 12 | 0.5635 | 0.5 |
58
- | 0.4651 | 6.1 | 14 | 0.6040 | 0.5 |
59
- | 0.4651 | 7.1 | 16 | 0.6417 | 0.5 |
60
- | 0.4651 | 8.1 | 18 | 0.6531 | 0.5 |
61
- | 0.122 | 9.1 | 20 | 0.6686 | 0.5 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
 
63
 
64
  ### Framework versions
65
 
66
- - Transformers 4.29.2
67
- - Pytorch 2.0.0+cu117
68
  - Datasets 2.18.0
69
- - Tokenizers 0.13.3
 
1
  ---
2
  license: cc-by-nc-4.0
3
+ base_model: MCG-NJU/videomae-base
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
17
 
18
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.8332
21
+ - Accuracy: 0.6078
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_ratio: 0.1
47
+ - training_steps: 1200
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.7634 | 0.03 | 41 | 0.6320 | 0.5882 |
54
+ | 0.7445 | 1.03 | 82 | 1.4198 | 0.5686 |
55
+ | 0.4931 | 2.03 | 123 | 1.3689 | 0.5686 |
56
+ | 0.7206 | 3.03 | 164 | 1.3282 | 0.5882 |
57
+ | 0.735 | 4.03 | 205 | 2.0849 | 0.5686 |
58
+ | 1.769 | 5.03 | 246 | 1.0332 | 0.6078 |
59
+ | 0.9494 | 6.03 | 287 | 2.1307 | 0.6078 |
60
+ | 0.3857 | 7.03 | 328 | 2.5985 | 0.6078 |
61
+ | 0.3639 | 8.03 | 369 | 2.2300 | 0.6078 |
62
+ | 0.6456 | 9.03 | 410 | 1.8992 | 0.6078 |
63
+ | 0.9483 | 10.03 | 451 | 1.9556 | 0.6078 |
64
+ | 0.4518 | 11.03 | 492 | 1.8346 | 0.6275 |
65
+ | 0.9109 | 12.03 | 533 | 1.9937 | 0.6078 |
66
+ | 0.5441 | 13.03 | 574 | 1.4013 | 0.6078 |
67
+ | 0.4035 | 14.03 | 615 | 1.9078 | 0.6078 |
68
+ | 0.1713 | 15.03 | 656 | 2.0803 | 0.5882 |
69
+ | 0.0542 | 16.03 | 697 | 2.5432 | 0.6078 |
70
+ | 0.3084 | 17.03 | 738 | 2.5753 | 0.6078 |
71
+ | 0.2476 | 18.03 | 779 | 2.4253 | 0.6275 |
72
+ | 0.006 | 19.03 | 820 | 2.4320 | 0.6078 |
73
+ | 0.0021 | 20.03 | 861 | 2.7182 | 0.6078 |
74
+ | 0.008 | 21.03 | 902 | 2.7711 | 0.5882 |
75
+ | 0.0011 | 22.03 | 943 | 2.8089 | 0.5882 |
76
+ | 0.7546 | 23.03 | 984 | 2.8142 | 0.6078 |
77
+ | 0.0006 | 24.03 | 1025 | 2.8796 | 0.6078 |
78
+ | 0.0008 | 25.03 | 1066 | 2.8486 | 0.6078 |
79
+ | 0.1745 | 26.03 | 1107 | 2.8475 | 0.6078 |
80
+ | 0.5421 | 27.03 | 1148 | 2.8462 | 0.6078 |
81
+ | 0.1233 | 28.03 | 1189 | 2.8324 | 0.6078 |
82
+ | 0.1298 | 29.01 | 1200 | 2.8332 | 0.6078 |
83
 
84
 
85
  ### Framework versions
86
 
87
+ - Transformers 4.38.2
88
+ - Pytorch 2.0.1
89
  - Datasets 2.18.0
90
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0aab9aef97a1cc7d12ca847170cc3f1435f652e0c1c879d06543d32c17ead9c
3
  size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5304c547714071ec55fd0fa716f78cec566fb1f4b57240719c7246167deca62d
3
  size 344937368