Hugging Face's logo

beingbatman
/
CTMAE2_CS_V7_3

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
beingbatman commited on
Commit
fdd7a8b
·
verified ·
1 Parent(s): 51943e8

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: CTMAE2_CS_V7_3
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
+ # CTMAE2_CS_V7_3
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: 1.0930
22
+ - Accuracy: 0.8261
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: 3
43
+ - eval_batch_size: 3
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: 13000
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
+ | 0.6166 | 0.02 | 260 | 0.7472 | 0.4565 |
55
+ | 0.5113 | 1.02 | 520 | 0.9421 | 0.4565 |
56
+ | 0.4538 | 2.02 | 780 | 0.9290 | 0.4783 |
57
+ | 0.4927 | 3.02 | 1040 | 0.6694 | 0.5870 |
58
+ | 0.5214 | 4.02 | 1300 | 0.7649 | 0.7174 |
59
+ | 1.0967 | 5.02 | 1560 | 0.9229 | 0.6739 |
60
+ | 0.6237 | 6.02 | 1820 | 0.8940 | 0.7174 |
61
+ | 0.2162 | 7.02 | 2080 | 0.8480 | 0.7609 |
62
+ | 0.4234 | 8.02 | 2340 | 1.3532 | 0.6304 |
63
+ | 0.4629 | 9.02 | 2600 | 0.7409 | 0.7391 |
64
+ | 0.4631 | 10.02 | 2860 | 0.8471 | 0.7609 |
65
+ | 0.548 | 11.02 | 3120 | 0.9673 | 0.6957 |
66
+ | 0.355 | 12.02 | 3380 | 0.9122 | 0.7609 |
67
+ | 0.6545 | 13.02 | 3640 | 1.0228 | 0.7391 |
68
+ | 0.6703 | 14.02 | 3900 | 0.9249 | 0.7174 |
69
+ | 0.561 | 15.02 | 4160 | 1.1688 | 0.7174 |
70
+ | 0.3788 | 16.02 | 4420 | 1.9633 | 0.6522 |
71
+ | 0.3055 | 17.02 | 4680 | 1.1960 | 0.6957 |
72
+ | 0.2223 | 18.02 | 4940 | 1.0511 | 0.7609 |
73
+ | 0.4324 | 19.02 | 5200 | 1.5567 | 0.6957 |
74
+ | 0.3022 | 20.02 | 5460 | 1.6864 | 0.6304 |
75
+ | 0.4434 | 21.02 | 5720 | 1.7834 | 0.6304 |
76
+ | 0.2485 | 22.02 | 5980 | 1.4761 | 0.6739 |
77
+ | 0.3882 | 23.02 | 6240 | 1.8617 | 0.6522 |
78
+ | 0.0128 | 24.02 | 6500 | 1.6289 | 0.6739 |
79
+ | 0.4251 | 25.02 | 6760 | 1.5492 | 0.6957 |
80
+ | 0.0128 | 26.02 | 7020 | 2.4527 | 0.5652 |
81
+ | 0.2468 | 27.02 | 7280 | 1.8335 | 0.6739 |
82
+ | 0.1681 | 28.02 | 7540 | 1.0796 | 0.8043 |
83
+ | 0.4033 | 29.02 | 7800 | 2.3945 | 0.6087 |
84
+ | 0.1556 | 30.02 | 8060 | 1.7049 | 0.6739 |
85
+ | 0.3012 | 31.02 | 8320 | 1.0930 | 0.8261 |
86
+ | 0.0585 | 32.02 | 8580 | 1.5270 | 0.7174 |
87
+ | 0.0005 | 33.02 | 8840 | 1.1852 | 0.8261 |
88
+ | 0.0008 | 34.02 | 9100 | 1.6258 | 0.7609 |
89
+ | 0.117 | 35.02 | 9360 | 1.4406 | 0.7826 |
90
+ | 0.1401 | 36.02 | 9620 | 1.7366 | 0.7174 |
91
+ | 0.2498 | 37.02 | 9880 | 2.4993 | 0.6304 |
92
+ | 0.2411 | 38.02 | 10140 | 2.2741 | 0.6522 |
93
+ | 0.0004 | 39.02 | 10400 | 2.0468 | 0.6957 |
94
+ | 0.0001 | 40.02 | 10660 | 2.0636 | 0.6522 |
95
+ | 0.331 | 41.02 | 10920 | 2.1473 | 0.6522 |
96
+ | 0.0112 | 42.02 | 11180 | 1.8257 | 0.6957 |
97
+ | 0.2408 | 43.02 | 11440 | 2.2235 | 0.6522 |
98
+ | 0.0002 | 44.02 | 11700 | 2.2065 | 0.6739 |
99
+ | 0.0001 | 45.02 | 11960 | 2.4907 | 0.6522 |
100
+ | 0.0055 | 46.02 | 12220 | 2.2836 | 0.6304 |
101
+ | 0.0001 | 47.02 | 12480 | 2.6007 | 0.6304 |
102
+ | 0.0003 | 48.02 | 12740 | 2.2538 | 0.6304 |
103
+ | 0.0334 | 49.02 | 13000 | 2.3751 | 0.6304 |
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 sha256:77c001b78483555baaae64a39ba24ecb27e68a42666fcbebbb3d3ddc4c2599a7
3
  size 1215496208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3feb65058718ff499bfa3a636e4c4f5b2d248d293c9d83ae4fbb6977f624eff4
3
  size 1215496208