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
499e48e
·
verified ·
1 Parent(s): 0a950c4

Model save

Browse files
Files changed (2) hide show
  1. README.md +61 -8
  2. model.safetensors +1 -1
README.md CHANGED
@@ -3,6 +3,8 @@ license: cc-by-nc-4.0
3
  base_model: MCG-NJU/videomae-base
4
  tags:
5
  - generated_from_trainer
 
 
6
  model-index:
7
  - name: videomae-base-finetuned-subset-check10
8
  results: []
@@ -15,13 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - eval_loss: 1.3321
19
- - eval_accuracy: 0.6111
20
- - eval_runtime: 175.1786
21
- - eval_samples_per_second: 1.233
22
- - eval_steps_per_second: 0.154
23
- - epoch: 96.01
24
- - step: 5426
25
 
26
  ## Model description
27
 
@@ -47,7 +44,63 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
50
- - training_steps: 5550
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
 
52
  ### Framework versions
53
 
 
3
  base_model: MCG-NJU/videomae-base
4
  tags:
5
  - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
  model-index:
9
  - name: videomae-base-finetuned-subset-check10
10
  results: []
 
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: 0.7703
21
+ - Accuracy: 0.6806
 
 
 
 
 
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: 2775
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.6256 | 0.02 | 56 | 1.6078 | 0.1382 |
54
+ | 1.6131 | 1.02 | 112 | 1.5918 | 0.1797 |
55
+ | 1.5876 | 2.02 | 168 | 1.5945 | 0.3041 |
56
+ | 1.6136 | 3.02 | 224 | 1.5252 | 0.4608 |
57
+ | 1.5186 | 4.02 | 280 | 1.4925 | 0.4378 |
58
+ | 1.3534 | 5.02 | 336 | 1.2406 | 0.5300 |
59
+ | 1.2166 | 6.02 | 392 | 1.1091 | 0.6083 |
60
+ | 1.1799 | 7.02 | 448 | 1.1852 | 0.5253 |
61
+ | 1.0207 | 8.02 | 504 | 1.1372 | 0.5530 |
62
+ | 1.131 | 9.02 | 560 | 1.2174 | 0.4793 |
63
+ | 0.9063 | 10.02 | 616 | 1.0557 | 0.5714 |
64
+ | 1.0308 | 11.02 | 672 | 1.0559 | 0.5945 |
65
+ | 0.8939 | 12.02 | 728 | 1.2659 | 0.4747 |
66
+ | 0.7683 | 13.02 | 784 | 0.9758 | 0.5991 |
67
+ | 0.8586 | 14.02 | 840 | 0.8496 | 0.6728 |
68
+ | 0.7655 | 15.02 | 896 | 0.8555 | 0.6912 |
69
+ | 0.622 | 16.02 | 952 | 1.2835 | 0.5207 |
70
+ | 0.878 | 17.02 | 1008 | 0.7961 | 0.6912 |
71
+ | 0.5976 | 18.02 | 1064 | 0.9144 | 0.6406 |
72
+ | 0.7254 | 19.02 | 1120 | 0.9289 | 0.6175 |
73
+ | 0.7443 | 20.02 | 1176 | 1.2426 | 0.5115 |
74
+ | 0.5463 | 21.02 | 1232 | 1.1711 | 0.5530 |
75
+ | 0.7503 | 22.02 | 1288 | 1.4511 | 0.4793 |
76
+ | 0.6529 | 23.02 | 1344 | 0.9010 | 0.6866 |
77
+ | 0.6001 | 24.02 | 1400 | 0.9718 | 0.6129 |
78
+ | 0.55 | 25.02 | 1456 | 1.3724 | 0.4378 |
79
+ | 0.7328 | 26.02 | 1512 | 1.2509 | 0.4931 |
80
+ | 0.5754 | 27.02 | 1568 | 0.9113 | 0.6636 |
81
+ | 0.6717 | 28.02 | 1624 | 1.0872 | 0.5346 |
82
+ | 0.8697 | 29.02 | 1680 | 0.8411 | 0.6636 |
83
+ | 0.4557 | 30.02 | 1736 | 1.0335 | 0.5853 |
84
+ | 0.4873 | 31.02 | 1792 | 1.1548 | 0.5300 |
85
+ | 0.7812 | 32.02 | 1848 | 1.0361 | 0.5991 |
86
+ | 0.5975 | 33.02 | 1904 | 1.2160 | 0.5253 |
87
+ | 0.6439 | 34.02 | 1960 | 1.0630 | 0.5760 |
88
+ | 0.597 | 35.02 | 2016 | 1.0568 | 0.6083 |
89
+ | 0.5641 | 36.02 | 2072 | 0.9502 | 0.6682 |
90
+ | 0.4992 | 37.02 | 2128 | 1.0643 | 0.5899 |
91
+ | 0.4136 | 38.02 | 2184 | 0.9271 | 0.6083 |
92
+ | 0.5194 | 39.02 | 2240 | 1.0673 | 0.5760 |
93
+ | 0.7653 | 40.02 | 2296 | 0.9899 | 0.6267 |
94
+ | 0.6247 | 41.02 | 2352 | 1.0216 | 0.6313 |
95
+ | 0.6901 | 42.02 | 2408 | 1.1336 | 0.5576 |
96
+ | 0.4731 | 43.02 | 2464 | 1.1248 | 0.5945 |
97
+ | 0.4623 | 44.02 | 2520 | 1.0105 | 0.6359 |
98
+ | 0.5236 | 45.02 | 2576 | 1.2222 | 0.5622 |
99
+ | 0.4865 | 46.02 | 2632 | 1.1390 | 0.5668 |
100
+ | 0.6178 | 47.02 | 2688 | 1.1181 | 0.5806 |
101
+ | 0.6068 | 48.02 | 2744 | 1.0919 | 0.6037 |
102
+ | 0.4835 | 49.01 | 2775 | 1.0933 | 0.5853 |
103
+
104
 
105
  ### Framework versions
106
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93e6b1d07c45c4c6df0e62018ae3201dee25b1d6ae157785aa700e038b6c50c6
3
  size 344946604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28d366431dfd078f8f287c94557bfe1ef95210a23c40a8afb24fb25e64327c52
3
  size 344946604