Hugging Face's logo

beingbatman
/
MAE-CT-CPC-Dicotomized-v8-n0-m1

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
beingbatman commited on
Commit
8b78b87
•
1 Parent(s): 7db5e06

Model save

Browse files
Files changed (2) hide show
  1. README.md +55 -55
  2. model.safetensors +1 -1
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-large-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-large-finetuned-kinetics) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.5946
22
- - Accuracy: 0.5753
23
 
24
  ## Model description
25
 
@@ -45,62 +45,62 @@ The following hyperparameters were used during training:
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
- - training_steps: 2500
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
- |:-------------:|:-------:|:----:|:---------------:|:--------:|
54
- | 0.6826 | 0.0204 | 51 | 0.6157 | 0.7625 |
55
- | 0.6549 | 1.0204 | 102 | 0.5930 | 0.7625 |
56
- | 0.6486 | 2.0204 | 153 | 0.6797 | 0.5125 |
57
- | 0.5595 | 3.0204 | 204 | 0.4902 | 0.6625 |
58
- | 0.5586 | 4.0204 | 255 | 0.8195 | 0.475 |
59
- | 0.4565 | 5.0204 | 306 | 0.5872 | 0.75 |
60
- | 0.3697 | 6.0204 | 357 | 0.5017 | 0.775 |
61
- | 0.6201 | 7.0204 | 408 | 0.6555 | 0.7 |
62
- | 0.4333 | 8.0204 | 459 | 1.2277 | 0.6125 |
63
- | 0.2148 | 9.0204 | 510 | 0.8115 | 0.7625 |
64
- | 0.9458 | 10.0204 | 561 | 0.9873 | 0.6625 |
65
- | 0.0651 | 11.0204 | 612 | 1.0840 | 0.7625 |
66
- | 0.5756 | 12.0204 | 663 | 1.0489 | 0.8 |
67
- | 0.354 | 13.0204 | 714 | 1.1601 | 0.7875 |
68
- | 0.2888 | 14.0204 | 765 | 1.8144 | 0.625 |
69
- | 0.2449 | 15.0204 | 816 | 1.3988 | 0.7125 |
70
- | 0.1326 | 16.0204 | 867 | 1.7152 | 0.7125 |
71
- | 0.0018 | 17.0204 | 918 | 2.1475 | 0.6375 |
72
- | 0.3631 | 18.0204 | 969 | 1.8957 | 0.65 |
73
- | 0.1252 | 19.0204 | 1020 | 1.1246 | 0.825 |
74
- | 0.0943 | 20.0204 | 1071 | 1.9498 | 0.6625 |
75
- | 0.3488 | 21.0204 | 1122 | 1.3457 | 0.7875 |
76
- | 0.0008 | 22.0204 | 1173 | 1.7872 | 0.7125 |
77
- | 0.009 | 23.0204 | 1224 | 1.5437 | 0.75 |
78
- | 0.0274 | 24.0204 | 1275 | 1.9865 | 0.6875 |
79
- | 0.0004 | 25.0204 | 1326 | 1.5100 | 0.7625 |
80
- | 0.1007 | 26.0204 | 1377 | 1.9590 | 0.6875 |
81
- | 0.0006 | 27.0204 | 1428 | 1.8346 | 0.7125 |
82
- | 0.0006 | 28.0204 | 1479 | 1.4669 | 0.825 |
83
- | 0.0001 | 29.0204 | 1530 | 1.5396 | 0.7875 |
84
- | 0.0002 | 30.0204 | 1581 | 1.5716 | 0.7875 |
85
- | 0.0001 | 31.0204 | 1632 | 1.6614 | 0.7625 |
86
- | 0.0002 | 32.0204 | 1683 | 1.6356 | 0.7625 |
87
- | 0.0001 | 33.0204 | 1734 | 1.5731 | 0.8 |
88
- | 0.0001 | 34.0204 | 1785 | 2.0020 | 0.725 |
89
- | 0.0001 | 35.0204 | 1836 | 1.8886 | 0.75 |
90
- | 0.0001 | 36.0204 | 1887 | 1.8363 | 0.75 |
91
- | 0.0001 | 37.0204 | 1938 | 1.6848 | 0.7625 |
92
- | 0.0001 | 38.0204 | 1989 | 1.7188 | 0.75 |
93
- | 0.0001 | 39.0204 | 2040 | 1.5820 | 0.8 |
94
- | 0.0001 | 40.0204 | 2091 | 1.6061 | 0.7875 |
95
- | 0.0001 | 41.0204 | 2142 | 2.2817 | 0.7 |
96
- | 0.0001 | 42.0204 | 2193 | 2.1015 | 0.725 |
97
- | 0.0001 | 43.0204 | 2244 | 1.6356 | 0.775 |
98
- | 0.0001 | 44.0204 | 2295 | 1.5849 | 0.8125 |
99
- | 0.0001 | 45.0204 | 2346 | 1.6463 | 0.775 |
100
- | 0.0001 | 46.0204 | 2397 | 1.6641 | 0.775 |
101
- | 0.0001 | 47.0204 | 2448 | 1.6123 | 0.7875 |
102
- | 0.0001 | 48.0204 | 2499 | 1.6145 | 0.7875 |
103
- | 0.0001 | 49.0004 | 2500 | 1.6145 | 0.7875 |
104
 
105
 
106
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [MCG-NJU/videomae-large-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-large-finetuned-kinetics) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4681
22
+ - Accuracy: 0.7907
23
 
24
  ## Model description
25
 
 
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
+ - training_steps: 3500
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 0.6769 | 0.02 | 70 | 0.6814 | 0.5938 |
55
+ | 0.7223 | 1.02 | 140 | 0.6953 | 0.5938 |
56
+ | 0.6628 | 2.02 | 210 | 0.6335 | 0.625 |
57
+ | 0.5096 | 3.02 | 280 | 0.6514 | 0.625 |
58
+ | 0.4739 | 4.02 | 350 | 0.6358 | 0.6562 |
59
+ | 0.4554 | 5.02 | 420 | 0.6272 | 0.6562 |
60
+ | 0.4818 | 6.02 | 490 | 0.7727 | 0.5938 |
61
+ | 0.4129 | 7.02 | 560 | 0.8222 | 0.6875 |
62
+ | 0.6301 | 8.02 | 630 | 0.8041 | 0.625 |
63
+ | 0.3809 | 9.02 | 700 | 0.8721 | 0.625 |
64
+ | 0.8071 | 10.02 | 770 | 1.1092 | 0.625 |
65
+ | 0.1888 | 11.02 | 840 | 1.1556 | 0.625 |
66
+ | 0.3762 | 12.02 | 910 | 1.3499 | 0.625 |
67
+ | 0.3502 | 13.02 | 980 | 1.5333 | 0.6562 |
68
+ | 0.1027 | 14.02 | 1050 | 1.6249 | 0.6562 |
69
+ | 0.177 | 15.02 | 1120 | 1.3758 | 0.6562 |
70
+ | 0.0998 | 16.02 | 1190 | 1.9514 | 0.6562 |
71
+ | 0.1749 | 17.02 | 1260 | 1.9120 | 0.6562 |
72
+ | 0.0145 | 18.02 | 1330 | 2.1036 | 0.625 |
73
+ | 0.0038 | 19.02 | 1400 | 2.0288 | 0.625 |
74
+ | 0.1262 | 20.02 | 1470 | 2.0193 | 0.6875 |
75
+ | 0.0203 | 21.02 | 1540 | 2.1937 | 0.6562 |
76
+ | 0.0002 | 22.02 | 1610 | 2.2922 | 0.625 |
77
+ | 0.0017 | 23.02 | 1680 | 2.1569 | 0.6562 |
78
+ | 0.0049 | 24.02 | 1750 | 2.2573 | 0.625 |
79
+ | 0.0231 | 25.02 | 1820 | 2.1460 | 0.6875 |
80
+ | 0.0001 | 26.02 | 1890 | 2.3566 | 0.6562 |
81
+ | 0.0001 | 27.02 | 1960 | 2.3822 | 0.5938 |
82
+ | 0.0001 | 28.02 | 2030 | 2.3178 | 0.6562 |
83
+ | 0.0004 | 29.02 | 2100 | 2.5492 | 0.625 |
84
+ | 0.0003 | 30.02 | 2170 | 2.7648 | 0.625 |
85
+ | 0.0001 | 31.02 | 2240 | 2.3949 | 0.625 |
86
+ | 0.0001 | 32.02 | 2310 | 2.4107 | 0.6562 |
87
+ | 0.0001 | 33.02 | 2380 | 2.6099 | 0.5938 |
88
+ | 0.0001 | 34.02 | 2450 | 2.8574 | 0.5625 |
89
+ | 0.0001 | 35.02 | 2520 | 2.5808 | 0.5938 |
90
+ | 0.0001 | 36.02 | 2590 | 2.6246 | 0.5938 |
91
+ | 0.0001 | 37.02 | 2660 | 2.7051 | 0.5938 |
92
+ | 0.0001 | 38.02 | 2730 | 2.5046 | 0.5938 |
93
+ | 0.0001 | 39.02 | 2800 | 2.5003 | 0.5938 |
94
+ | 0.0 | 40.02 | 2870 | 2.5460 | 0.625 |
95
+ | 0.0 | 41.02 | 2940 | 2.5397 | 0.625 |
96
+ | 0.0 | 42.02 | 3010 | 2.5384 | 0.625 |
97
+ | 0.0 | 43.02 | 3080 | 2.4849 | 0.625 |
98
+ | 0.0 | 44.02 | 3150 | 2.5847 | 0.6562 |
99
+ | 0.0 | 45.02 | 3220 | 2.5829 | 0.6562 |
100
+ | 0.0 | 46.02 | 3290 | 2.5809 | 0.6562 |
101
+ | 0.0 | 47.02 | 3360 | 2.5756 | 0.625 |
102
+ | 0.0001 | 48.02 | 3430 | 2.4744 | 0.6562 |
103
+ | 0.0 | 49.02 | 3500 | 2.4720 | 0.6562 |
104
 
105
 
106
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4a2075f035b7bf1efb94de6141888a9d0e963b00d73a570501124bab3e73691
3
  size 1215496208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a84a97793c6033522291d7b5773d08bbd253aa4f4cd19614c65008bf5af2860
3
  size 1215496208