Hugging Face's logo

mitegvg
/
videomae-base-finetuned-ssv2-finetuned-sports-videos-in-the-wild

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Model card Files
xet
Metrics Community
mitegvg commited on
Commit
7f957a6
·
verified ·
1 Parent(s): a07807d

End of training

Browse files
Files changed (1) hide show
  1. README.md +87 -0
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: MCG-NJU/videomae-base-finetuned-ssv2
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: videomae-base-finetuned-ssv2-finetuned-sports-videos-in-the-wild
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
+ # videomae-base-finetuned-ssv2-finetuned-sports-videos-in-the-wild
18
+
19
+ This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-ssv2](https://huggingface.co/MCG-NJU/videomae-base-finetuned-ssv2) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.1496
22
+ - Accuracy: 0.7594
23
+ - Macro Precision: 0.6910
24
+ - Macro Recall: 0.7199
25
+ - Macro F1: 0.6905
26
+ - Weighted Precision: 0.7833
27
+ - Weighted Recall: 0.7594
28
+ - Weighted F1: 0.7598
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 0.0005
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 8
50
+ - seed: 42
51
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - training_steps: 8400
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro Precision | Macro Recall | Macro F1 | Weighted Precision | Weighted Recall | Weighted F1 |
59
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
60
+ | 1.6313 | 0.0501 | 421 | 1.6631 | 0.5297 | 0.5192 | 0.4451 | 0.4010 | 0.6102 | 0.5297 | 0.4954 |
61
+ | 1.8344 | 1.0501 | 842 | 2.3963 | 0.3274 | 0.4950 | 0.3302 | 0.2925 | 0.6196 | 0.3274 | 0.3216 |
62
+ | 1.9713 | 2.0501 | 1263 | 1.6678 | 0.5111 | 0.5007 | 0.4767 | 0.4215 | 0.6097 | 0.5111 | 0.5061 |
63
+ | 1.7598 | 3.0501 | 1684 | 1.5902 | 0.5275 | 0.5426 | 0.4819 | 0.4417 | 0.6160 | 0.5275 | 0.5152 |
64
+ | 1.5432 | 4.0501 | 2105 | 1.4812 | 0.5603 | 0.5400 | 0.4867 | 0.4513 | 0.6482 | 0.5603 | 0.5514 |
65
+ | 1.3945 | 5.0501 | 2526 | 1.5876 | 0.5286 | 0.5659 | 0.5077 | 0.4697 | 0.6529 | 0.5286 | 0.5421 |
66
+ | 1.2047 | 6.0501 | 2947 | 1.2964 | 0.6376 | 0.5846 | 0.5892 | 0.5527 | 0.6834 | 0.6376 | 0.6361 |
67
+ | 1.2434 | 7.0501 | 3368 | 1.4268 | 0.5793 | 0.5920 | 0.5630 | 0.5116 | 0.6897 | 0.5793 | 0.5842 |
68
+ | 1.1157 | 8.0501 | 3789 | 1.1934 | 0.6533 | 0.6153 | 0.6177 | 0.5837 | 0.7081 | 0.6533 | 0.6504 |
69
+ | 0.9056 | 9.0501 | 4210 | 1.1501 | 0.6551 | 0.6268 | 0.6337 | 0.5984 | 0.7202 | 0.6551 | 0.6658 |
70
+ | 0.7085 | 10.0501 | 4631 | 1.1881 | 0.6810 | 0.6295 | 0.6458 | 0.6101 | 0.7221 | 0.6810 | 0.6826 |
71
+ | 0.6789 | 11.0501 | 5052 | 1.1540 | 0.7043 | 0.6744 | 0.6577 | 0.6396 | 0.7304 | 0.7043 | 0.6959 |
72
+ | 0.5957 | 12.0501 | 5473 | 1.2473 | 0.6832 | 0.6210 | 0.6377 | 0.6077 | 0.7028 | 0.6832 | 0.6759 |
73
+ | 0.4533 | 13.0501 | 5894 | 1.1441 | 0.6927 | 0.6495 | 0.6450 | 0.6278 | 0.7211 | 0.6927 | 0.6924 |
74
+ | 0.4165 | 14.0501 | 6315 | 1.2567 | 0.7116 | 0.6708 | 0.6839 | 0.6468 | 0.7622 | 0.7116 | 0.7094 |
75
+ | 0.2661 | 15.0501 | 6736 | 1.1229 | 0.7204 | 0.6526 | 0.6809 | 0.6417 | 0.7598 | 0.7204 | 0.7226 |
76
+ | 0.2679 | 16.0501 | 7157 | 1.1790 | 0.7382 | 0.6838 | 0.7055 | 0.6717 | 0.7792 | 0.7382 | 0.7397 |
77
+ | 0.1875 | 17.0501 | 7578 | 1.1689 | 0.7506 | 0.6983 | 0.7060 | 0.6894 | 0.7746 | 0.7506 | 0.7529 |
78
+ | 0.2501 | 18.0501 | 7999 | 1.1802 | 0.7557 | 0.6911 | 0.7190 | 0.6883 | 0.7802 | 0.7557 | 0.7537 |
79
+ | 0.1072 | 19.0477 | 8400 | 1.1496 | 0.7594 | 0.6910 | 0.7199 | 0.6905 | 0.7833 | 0.7594 | 0.7598 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.51.3
85
+ - Pytorch 2.1.0+cu118
86
+ - Datasets 3.6.0
87
+ - Tokenizers 0.21.1