Hugging Face's logo

Joy28
/
videomae-base-finetuned-subset-check10

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
Joy28 commited on
Commit
9a561cc
·
verified ·
1 Parent(s): ae8671c

Model save

Browse files
Files changed (2) hide show
  1. README.md +43 -23
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.7364
21
- - Accuracy: 0.7130
22
 
23
  ## Model description
24
 
@@ -44,32 +44,52 @@ The following hyperparameters were used during training:
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: 1110
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 1.6285 | 0.05 | 56 | 1.6004 | 0.3687 |
54
- | 1.6056 | 1.05 | 112 | 1.5826 | 0.1982 |
55
- | 1.5254 | 2.05 | 168 | 1.5979 | 0.1475 |
56
- | 1.4239 | 3.05 | 224 | 1.2076 | 0.6359 |
57
- | 1.1884 | 4.05 | 280 | 1.1866 | 0.5576 |
58
- | 1.2336 | 5.05 | 336 | 1.0281 | 0.6406 |
59
- | 1.0726 | 6.05 | 392 | 0.9173 | 0.6636 |
60
- | 1.0966 | 7.05 | 448 | 1.0597 | 0.5991 |
61
- | 0.956 | 8.05 | 504 | 0.9278 | 0.6682 |
62
- | 1.0813 | 9.05 | 560 | 1.0025 | 0.5714 |
63
- | 0.8996 | 10.05 | 616 | 0.7882 | 0.7051 |
64
- | 0.947 | 11.05 | 672 | 0.8638 | 0.7189 |
65
- | 0.9386 | 12.05 | 728 | 0.8192 | 0.7005 |
66
- | 0.8754 | 13.05 | 784 | 0.7741 | 0.6959 |
67
- | 0.8028 | 14.05 | 840 | 0.7482 | 0.7097 |
68
- | 0.7038 | 15.05 | 896 | 0.7464 | 0.7327 |
69
- | 0.6302 | 16.05 | 952 | 0.7733 | 0.7005 |
70
- | 0.8387 | 17.05 | 1008 | 0.7224 | 0.7235 |
71
- | 0.5853 | 18.05 | 1064 | 0.7359 | 0.7143 |
72
- | 0.7482 | 19.04 | 1110 | 0.7370 | 0.7189 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
73
 
74
 
75
  ### Framework versions
 
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: 0.8682
21
+ - Accuracy: 0.6343
22
 
23
  ## Model description
24
 
 
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: 2220
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.5175 | 0.03 | 56 | 1.6041 | 0.2074 |
54
+ | 1.4397 | 1.03 | 112 | 1.4559 | 0.3871 |
55
+ | 1.464 | 2.03 | 168 | 1.3637 | 0.3963 |
56
+ | 1.3404 | 3.03 | 224 | 1.2467 | 0.4470 |
57
+ | 1.3284 | 4.03 | 280 | 1.3115 | 0.3318 |
58
+ | 1.1598 | 5.03 | 336 | 1.2489 | 0.4470 |
59
+ | 0.9615 | 6.03 | 392 | 1.3057 | 0.4009 |
60
+ | 0.9357 | 7.03 | 448 | 0.9201 | 0.6498 |
61
+ | 0.9785 | 8.03 | 504 | 0.8629 | 0.6774 |
62
+ | 1.0862 | 9.03 | 560 | 1.0977 | 0.5069 |
63
+ | 0.9315 | 10.03 | 616 | 0.7868 | 0.7097 |
64
+ | 0.9404 | 11.03 | 672 | 0.8170 | 0.6728 |
65
+ | 0.939 | 12.03 | 728 | 0.9246 | 0.6636 |
66
+ | 0.8205 | 13.03 | 784 | 0.8420 | 0.6866 |
67
+ | 0.6719 | 14.03 | 840 | 1.0725 | 0.5899 |
68
+ | 0.8308 | 15.03 | 896 | 0.8683 | 0.6912 |
69
+ | 0.7554 | 16.03 | 952 | 0.9684 | 0.5991 |
70
+ | 0.6962 | 17.03 | 1008 | 1.1106 | 0.5484 |
71
+ | 0.7995 | 18.03 | 1064 | 0.9751 | 0.6498 |
72
+ | 0.8298 | 19.03 | 1120 | 1.0631 | 0.5300 |
73
+ | 0.6607 | 20.03 | 1176 | 0.9458 | 0.6175 |
74
+ | 0.688 | 21.03 | 1232 | 1.0296 | 0.6037 |
75
+ | 0.5835 | 22.03 | 1288 | 0.8948 | 0.6774 |
76
+ | 0.6987 | 23.03 | 1344 | 0.7883 | 0.7189 |
77
+ | 0.4979 | 24.03 | 1400 | 0.7089 | 0.7189 |
78
+ | 0.6163 | 25.03 | 1456 | 0.7634 | 0.7235 |
79
+ | 0.6754 | 26.03 | 1512 | 0.9444 | 0.6359 |
80
+ | 0.6673 | 27.03 | 1568 | 0.8391 | 0.6544 |
81
+ | 0.4924 | 28.03 | 1624 | 0.8289 | 0.6682 |
82
+ | 0.6438 | 29.03 | 1680 | 0.9605 | 0.6129 |
83
+ | 0.5714 | 30.03 | 1736 | 0.8838 | 0.6452 |
84
+ | 0.6726 | 31.03 | 1792 | 0.8412 | 0.6590 |
85
+ | 0.5027 | 32.03 | 1848 | 0.8439 | 0.6728 |
86
+ | 0.4649 | 33.03 | 1904 | 0.9525 | 0.6267 |
87
+ | 0.6625 | 34.03 | 1960 | 0.7850 | 0.7281 |
88
+ | 0.5793 | 35.03 | 2016 | 0.8481 | 0.6728 |
89
+ | 0.6411 | 36.03 | 2072 | 0.8842 | 0.6590 |
90
+ | 0.6592 | 37.03 | 2128 | 0.8028 | 0.6912 |
91
+ | 0.5524 | 38.03 | 2184 | 0.8216 | 0.6866 |
92
+ | 0.5697 | 39.02 | 2220 | 0.8339 | 0.6774 |
93
 
94
 
95
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3470c15bbc2b909b059d56ffcbc44dddc05a169c8ed41d16398274fa33128cf3
3
  size 344946604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b3a6d883070cb82c358734fae5b00f2f945051be6c25209579aaf974bf5b09
3
  size 344946604