Hugging Face's logo

beingbatman
/
ctsinov1

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Model card Files
xet
Community
beingbatman commited on
Commit
553755a
·
verified ·
1 Parent(s): 3e58e80

Model save

Browse files
Files changed (2) hide show
  1. README.md +63 -17
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,4 +1,5 @@
1
  ---
 
2
  license: cc-by-nc-4.0
3
  base_model: MCG-NJU/videomae-large-finetuned-kinetics
4
  tags:
@@ -17,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  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.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7402
21
- - Accuracy: 0.8456
22
 
23
  ## Model description
24
 
@@ -38,28 +39,73 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 1e-05
41
- - train_batch_size: 1
42
- - eval_batch_size: 1
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: 3935
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 1.8305 | 0.2 | 787 | 1.2155 | 0.6023 |
54
- | 0.7465 | 1.2 | 1574 | 0.7485 | 0.8339 |
55
- | 0.5066 | 2.2 | 2361 | 0.8862 | 0.8104 |
56
- | 0.0055 | 3.2 | 3148 | 0.7402 | 0.8456 |
57
- | 0.0042 | 4.2 | 3935 | 0.8932 | 0.8104 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
61
 
62
- - Transformers 4.38.2
63
- - Pytorch 2.1.0+cu121
64
- - Datasets 4.1.1
65
- - Tokenizers 0.15.2
 
1
  ---
2
+ library_name: transformers
3
  license: cc-by-nc-4.0
4
  base_model: MCG-NJU/videomae-large-finetuned-kinetics
5
  tags:
 
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: 0.7987
22
+ - Accuracy: 0.8586
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 1e-05
42
+ - train_batch_size: 2
43
+ - eval_batch_size: 2
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: 17500
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
54
+ | 0.5787 | 0.02 | 350 | 0.5787 | 0.7104 |
55
+ | 0.5175 | 1.02 | 700 | 0.7402 | 0.8081 |
56
+ | 0.4062 | 2.02 | 1050 | 0.8532 | 0.8283 |
57
+ | 0.7962 | 3.02 | 1400 | 0.7184 | 0.8114 |
58
+ | 0.8225 | 4.02 | 1750 | 1.6868 | 0.5657 |
59
+ | 0.724 | 5.02 | 2100 | 1.0066 | 0.7508 |
60
+ | 0.1468 | 6.02 | 2450 | 0.7703 | 0.8316 |
61
+ | 0.8406 | 7.02 | 2800 | 0.5863 | 0.8485 |
62
+ | 0.4485 | 8.02 | 3150 | 0.6602 | 0.8384 |
63
+ | 0.0134 | 9.02 | 3500 | 0.6907 | 0.8316 |
64
+ | 0.11 | 10.02 | 3850 | 0.7098 | 0.8316 |
65
+ | 0.6557 | 11.02 | 4200 | 0.6507 | 0.8384 |
66
+ | 0.2642 | 12.02 | 4550 | 0.6555 | 0.8519 |
67
+ | 0.2413 | 13.02 | 4900 | 0.6481 | 0.8519 |
68
+ | 0.6278 | 14.02 | 5250 | 0.6555 | 0.8552 |
69
+ | 0.0107 | 15.02 | 5600 | 0.6550 | 0.8519 |
70
+ | 0.3013 | 16.02 | 5950 | 0.7405 | 0.8485 |
71
+ | 0.5055 | 17.02 | 6300 | 0.6563 | 0.8451 |
72
+ | 0.0059 | 18.02 | 6650 | 0.6917 | 0.8485 |
73
+ | 0.4332 | 19.02 | 7000 | 0.6888 | 0.8384 |
74
+ | 0.2602 | 20.02 | 7350 | 0.7993 | 0.8418 |
75
+ | 0.2142 | 21.02 | 7700 | 0.7131 | 0.8451 |
76
+ | 0.5742 | 22.02 | 8050 | 0.9735 | 0.7980 |
77
+ | 0.2504 | 23.02 | 8400 | 0.8314 | 0.8384 |
78
+ | 0.8514 | 24.02 | 8750 | 0.7481 | 0.8418 |
79
+ | 0.8148 | 25.02 | 9100 | 0.7210 | 0.8384 |
80
+ | 0.2594 | 26.02 | 9450 | 0.9980 | 0.8249 |
81
+ | 0.6742 | 27.02 | 9800 | 0.7987 | 0.8586 |
82
+ | 0.0063 | 28.02 | 10150 | 0.9369 | 0.8316 |
83
+ | 0.5186 | 29.02 | 10500 | 1.0871 | 0.8148 |
84
+ | 0.3076 | 30.02 | 10850 | 0.8931 | 0.8350 |
85
+ | 0.1113 | 31.02 | 11200 | 1.0014 | 0.8384 |
86
+ | 0.2201 | 32.02 | 11550 | 0.8628 | 0.8485 |
87
+ | 0.0324 | 33.02 | 11900 | 0.9972 | 0.8350 |
88
+ | 0.4411 | 34.02 | 12250 | 1.0592 | 0.8350 |
89
+ | 0.0011 | 35.02 | 12600 | 1.0746 | 0.8283 |
90
+ | 0.3917 | 36.02 | 12950 | 0.9696 | 0.8384 |
91
+ | 0.7268 | 37.02 | 13300 | 1.1062 | 0.8182 |
92
+ | 0.3747 | 38.02 | 13650 | 1.0368 | 0.8350 |
93
+ | 0.5584 | 39.02 | 14000 | 1.0149 | 0.8418 |
94
+ | 0.4637 | 40.02 | 14350 | 1.0104 | 0.8316 |
95
+ | 0.0014 | 41.02 | 14700 | 1.0437 | 0.8418 |
96
+ | 0.6253 | 42.02 | 15050 | 1.1687 | 0.8148 |
97
+ | 0.0009 | 43.02 | 15400 | 1.0243 | 0.8418 |
98
+ | 0.0003 | 44.02 | 15750 | 1.0864 | 0.8316 |
99
+ | 0.291 | 45.02 | 16100 | 1.0647 | 0.8384 |
100
+ | 0.4962 | 46.02 | 16450 | 1.1166 | 0.8316 |
101
+ | 0.0919 | 47.02 | 16800 | 1.1209 | 0.8283 |
102
+ | 0.0007 | 48.02 | 17150 | 1.1260 | 0.8316 |
103
+ | 0.0008 | 49.02 | 17500 | 1.1139 | 0.8350 |
104
 
105
 
106
  ### Framework versions
107
 
108
+ - Transformers 4.56.2
109
+ - Pytorch 2.6.0+cu118
110
+ - Datasets 2.2.1
111
+ - Tokenizers 0.22.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7769c3b29bfad8b23378e72bd61bdcb57046a1a473c94445e9d9a867beb2ec1
3
  size 1215496208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02179b6827d86dfba092a3abd7908e8ec8797f107ebd59478f9abf60b35ea24
3
  size 1215496208