Hugging Face's logo

minhah
/
videomae-base-finetuned-elder

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
minhah commited on
Commit
466ea03
·
verified ·
1 Parent(s): b7b6984

Model save

Browse files
Files changed (2) hide show
  1. README.md +64 -13
  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: 1.6635
21
- - Accuracy: 0.3414
22
 
23
  ## Model description
24
 
@@ -38,26 +38,77 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
- - train_batch_size: 16
42
- - eval_batch_size: 16
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: 576
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 1.7389 | 0.13 | 73 | 1.6415 | 0.3422 |
54
- | 1.6564 | 1.13 | 146 | 1.6350 | 0.3254 |
55
- | 1.6835 | 2.13 | 219 | 1.6297 | 0.3478 |
56
- | 1.6586 | 3.13 | 292 | 1.6578 | 0.2889 |
57
- | 1.5774 | 4.13 | 365 | 1.6131 | 0.3296 |
58
- | 1.5861 | 5.13 | 438 | 1.6085 | 0.3429 |
59
- | 1.6262 | 6.13 | 511 | 1.6245 | 0.3156 |
60
- | 1.5688 | 7.11 | 576 | 1.6346 | 0.3142 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### 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: 1.6799
21
+ - Accuracy: 0.3314
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 32
42
+ - eval_batch_size: 32
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: 2160
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.7518 | 0.02 | 37 | 1.6498 | 0.3401 |
54
+ | 1.6435 | 1.02 | 74 | 1.6302 | 0.3436 |
55
+ | 1.6879 | 2.02 | 111 | 1.6198 | 0.3401 |
56
+ | 1.7059 | 3.02 | 148 | 1.7028 | 0.1971 |
57
+ | 1.6555 | 4.02 | 185 | 1.6067 | 0.2903 |
58
+ | 1.616 | 5.02 | 222 | 1.6073 | 0.3163 |
59
+ | 1.6706 | 6.02 | 259 | 1.5843 | 0.3485 |
60
+ | 1.6317 | 7.02 | 296 | 1.6479 | 0.3177 |
61
+ | 1.5798 | 8.02 | 333 | 1.7482 | 0.1985 |
62
+ | 1.5923 | 9.02 | 370 | 1.6529 | 0.2707 |
63
+ | 1.6002 | 10.02 | 407 | 1.6175 | 0.3247 |
64
+ | 1.4946 | 11.02 | 444 | 1.6414 | 0.2945 |
65
+ | 1.5688 | 12.02 | 481 | 1.6062 | 0.3338 |
66
+ | 1.5322 | 13.02 | 518 | 1.6427 | 0.2805 |
67
+ | 1.5078 | 14.02 | 555 | 1.7242 | 0.3135 |
68
+ | 1.5014 | 15.02 | 592 | 1.6587 | 0.3219 |
69
+ | 1.4861 | 16.02 | 629 | 1.8075 | 0.2349 |
70
+ | 1.4983 | 17.02 | 666 | 1.6725 | 0.3072 |
71
+ | 1.4716 | 18.02 | 703 | 1.7466 | 0.2658 |
72
+ | 1.5072 | 19.02 | 740 | 1.7423 | 0.2482 |
73
+ | 1.4874 | 20.02 | 777 | 1.7873 | 0.2447 |
74
+ | 1.4236 | 21.02 | 814 | 1.8282 | 0.2496 |
75
+ | 1.4134 | 22.02 | 851 | 1.8401 | 0.2265 |
76
+ | 1.3889 | 23.02 | 888 | 1.7694 | 0.2714 |
77
+ | 1.436 | 24.02 | 925 | 1.7302 | 0.3022 |
78
+ | 1.3266 | 25.02 | 962 | 1.7449 | 0.3142 |
79
+ | 1.3165 | 26.02 | 999 | 1.7723 | 0.2938 |
80
+ | 1.3522 | 27.02 | 1036 | 1.7750 | 0.3198 |
81
+ | 1.2635 | 28.02 | 1073 | 1.8097 | 0.3015 |
82
+ | 1.5006 | 29.02 | 1110 | 1.7649 | 0.2903 |
83
+ | 1.2839 | 30.02 | 1147 | 1.7946 | 0.2721 |
84
+ | 1.2542 | 31.02 | 1184 | 1.8282 | 0.3065 |
85
+ | 1.2637 | 32.02 | 1221 | 1.9263 | 0.2945 |
86
+ | 1.2725 | 33.02 | 1258 | 1.8878 | 0.2812 |
87
+ | 1.3261 | 34.02 | 1295 | 1.8429 | 0.3240 |
88
+ | 1.2834 | 35.02 | 1332 | 1.9100 | 0.2903 |
89
+ | 1.2953 | 36.02 | 1369 | 1.9537 | 0.3079 |
90
+ | 1.2118 | 37.02 | 1406 | 1.9896 | 0.2637 |
91
+ | 1.1953 | 38.02 | 1443 | 2.0280 | 0.2546 |
92
+ | 1.1522 | 39.02 | 1480 | 2.0114 | 0.2889 |
93
+ | 1.2288 | 40.02 | 1517 | 2.0062 | 0.3050 |
94
+ | 1.2318 | 41.02 | 1554 | 2.0633 | 0.2489 |
95
+ | 1.1571 | 42.02 | 1591 | 2.0472 | 0.2826 |
96
+ | 1.155 | 43.02 | 1628 | 2.0339 | 0.2756 |
97
+ | 1.1448 | 44.02 | 1665 | 2.0285 | 0.2819 |
98
+ | 1.2088 | 45.02 | 1702 | 2.0569 | 0.2917 |
99
+ | 1.1469 | 46.02 | 1739 | 2.1201 | 0.2889 |
100
+ | 1.1332 | 47.02 | 1776 | 2.0940 | 0.2980 |
101
+ | 1.1608 | 48.02 | 1813 | 2.1328 | 0.2742 |
102
+ | 1.0913 | 49.02 | 1850 | 2.1333 | 0.2819 |
103
+ | 1.1204 | 50.02 | 1887 | 2.2017 | 0.2875 |
104
+ | 1.1052 | 51.02 | 1924 | 2.1983 | 0.2910 |
105
+ | 1.0817 | 52.02 | 1961 | 2.1910 | 0.2966 |
106
+ | 1.0696 | 53.02 | 1998 | 2.1994 | 0.2805 |
107
+ | 1.0465 | 54.02 | 2035 | 2.2044 | 0.2854 |
108
+ | 1.0786 | 55.02 | 2072 | 2.1827 | 0.2903 |
109
+ | 1.0293 | 56.02 | 2109 | 2.1847 | 0.2931 |
110
+ | 1.107 | 57.02 | 2146 | 2.1876 | 0.2875 |
111
+ | 1.0571 | 58.01 | 2160 | 2.1889 | 0.2882 |
112
 
113
 
114
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b40c3a5157916ba9e57932a2b11c7039b656b113f8b4590ad8dfa1ffe6182e36
3
  size 344949680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59a043db142be041197a0c1ef402b6e68320722ba614e09554f9224e4b60bf3
3
  size 344949680