Hugging Face's logo

beingbatman
/
CTMAE-P2-V4-S3

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
beingbatman commited on
Commit
a8fd5da
·
verified ·
1 Parent(s): 679b3be

Model save

Browse files
Files changed (2) hide show
  1. README.md +111 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: MCG-NJU/videomae-large-finetuned-kinetics
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: CTMAE-P2-V4-S3
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # CTMAE-P2-V4-S3
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: 1.2190
22
+ - Accuracy: 0.7556
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 1e-05
42
+ - train_batch_size: 1
43
+ - eval_batch_size: 1
44
+ - seed: 42
45
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_ratio: 0.1
48
+ - training_steps: 13050
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
+ | 1.3366 | 0.02 | 261 | 2.0585 | 0.5556 |
55
+ | 0.5958 | 1.02 | 522 | 2.6082 | 0.5556 |
56
+ | 1.5554 | 2.02 | 783 | 2.0270 | 0.5556 |
57
+ | 0.7374 | 3.02 | 1044 | 2.2198 | 0.5556 |
58
+ | 1.6587 | 4.02 | 1305 | 1.6638 | 0.5556 |
59
+ | 0.919 | 5.02 | 1566 | 1.9840 | 0.5556 |
60
+ | 0.744 | 6.02 | 1827 | 2.2229 | 0.5556 |
61
+ | 1.0052 | 7.02 | 2088 | 1.7769 | 0.5556 |
62
+ | 1.0951 | 8.02 | 2349 | 2.0694 | 0.5556 |
63
+ | 0.8525 | 9.02 | 2610 | 1.8791 | 0.5556 |
64
+ | 1.4612 | 10.02 | 2871 | 1.8916 | 0.5556 |
65
+ | 2.0672 | 11.02 | 3132 | 2.0200 | 0.5556 |
66
+ | 0.5479 | 12.02 | 3393 | 0.7173 | 0.7333 |
67
+ | 0.5262 | 13.02 | 3654 | 1.2168 | 0.6444 |
68
+ | 0.0059 | 14.02 | 3915 | 2.5240 | 0.5556 |
69
+ | 0.604 | 15.02 | 4176 | 1.2190 | 0.7556 |
70
+ | 0.6369 | 16.02 | 4437 | 1.9123 | 0.6 |
71
+ | 0.5892 | 17.02 | 4698 | 2.1056 | 0.6444 |
72
+ | 1.2516 | 18.02 | 4959 | 1.6370 | 0.7111 |
73
+ | 1.1725 | 19.02 | 5220 | 1.5740 | 0.6889 |
74
+ | 0.0014 | 20.02 | 5481 | 1.8767 | 0.7111 |
75
+ | 1.0705 | 21.02 | 5742 | 1.9267 | 0.6444 |
76
+ | 0.3808 | 22.02 | 6003 | 1.9165 | 0.6222 |
77
+ | 0.0178 | 23.02 | 6264 | 1.9063 | 0.6222 |
78
+ | 1.6724 | 24.02 | 6525 | 2.3735 | 0.5778 |
79
+ | 0.0002 | 25.02 | 6786 | 2.1002 | 0.6222 |
80
+ | 1.2239 | 26.02 | 7047 | 2.1353 | 0.6222 |
81
+ | 0.001 | 27.02 | 7308 | 2.3725 | 0.6222 |
82
+ | 0.0016 | 28.02 | 7569 | 2.2152 | 0.6889 |
83
+ | 0.0006 | 29.02 | 7830 | 2.1500 | 0.6667 |
84
+ | 0.0002 | 30.02 | 8091 | 2.2028 | 0.6889 |
85
+ | 0.0255 | 31.02 | 8352 | 2.1039 | 0.6889 |
86
+ | 0.0002 | 32.02 | 8613 | 2.0948 | 0.7333 |
87
+ | 0.0002 | 33.02 | 8874 | 2.2476 | 0.6667 |
88
+ | 0.0872 | 34.02 | 9135 | 2.0365 | 0.6889 |
89
+ | 0.5337 | 35.02 | 9396 | 2.1685 | 0.7111 |
90
+ | 0.5087 | 36.02 | 9657 | 2.2672 | 0.6667 |
91
+ | 0.0881 | 37.02 | 9918 | 2.3988 | 0.7111 |
92
+ | 0.0191 | 38.02 | 10179 | 2.4235 | 0.6889 |
93
+ | 0.0073 | 39.02 | 10440 | 2.3860 | 0.7111 |
94
+ | 0.0001 | 40.02 | 10701 | 2.3559 | 0.6667 |
95
+ | 0.0001 | 41.02 | 10962 | 2.4858 | 0.6889 |
96
+ | 0.0 | 42.02 | 11223 | 2.3669 | 0.7111 |
97
+ | 0.0001 | 43.02 | 11484 | 2.7558 | 0.6222 |
98
+ | 0.0001 | 44.02 | 11745 | 2.8272 | 0.6222 |
99
+ | 0.0009 | 45.02 | 12006 | 2.5705 | 0.6667 |
100
+ | 0.0003 | 46.02 | 12267 | 2.4859 | 0.7111 |
101
+ | 0.0 | 47.02 | 12528 | 2.4095 | 0.6667 |
102
+ | 0.0 | 48.02 | 12789 | 2.3988 | 0.6889 |
103
+ | 0.0001 | 49.02 | 13050 | 2.4068 | 0.6889 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.46.2
109
+ - Pytorch 2.0.1+cu117
110
+ - Datasets 3.0.1
111
+ - Tokenizers 0.20.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac76a025e859f8358fc09b0330cdc51582e0211e64ed9b547db43083db293c8b
3
  size 1215496208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c0f7992cbe169dc15a1d93a66a49963c6e234eda9e38b83ab06f56fd5f236c1
3
  size 1215496208