Hugging Face's logo

Shawon16
/
VideoMAE_WLASL_250_epochs

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Model card Files
xet
 Community
Shawon16 commited on
Commit
0032530
·
verified ·
1 Parent(s): ccd01cb

Model save

Browse files
Files changed (2) hide show
  1. README.md +96 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: MCG-NJU/videomae-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - precision
10
+ - recall
11
+ - f1
12
+ model-index:
13
+ - name: VideoMAE_WLASL_250_epochs
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # VideoMAE_WLASL_250_epochs
21
+
22
+ This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 4.9119
25
+ - Top 1 Accuracy: 0.1622
26
+ - Top 5 Accuracy: 0.4086
27
+ - Top 10 Accuracy: 0.5301
28
+ - Accuracy: 0.1624
29
+ - Precision: 0.1508
30
+ - Recall: 0.1624
31
+ - F1: 0.1418
32
+
33
+ ## Model description
34
+
35
+ More information needed
36
+
37
+ ## Intended uses & limitations
38
+
39
+ More information needed
40
+
41
+ ## Training and evaluation data
42
+
43
+ More information needed
44
+
45
+ ## Training procedure
46
+
47
+ ### Training hyperparameters
48
+
49
+ The following hyperparameters were used during training:
50
+ - learning_rate: 5e-05
51
+ - train_batch_size: 2
52
+ - eval_batch_size: 2
53
+ - seed: 42
54
+ - gradient_accumulation_steps: 4
55
+ - total_train_batch_size: 8
56
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
57
+ - lr_scheduler_type: linear
58
+ - lr_scheduler_warmup_ratio: 0.1
59
+ - training_steps: 893000
60
+ - mixed_precision_training: Native AMP
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Top 1 Accuracy | Top 5 Accuracy | Top 10 Accuracy | Accuracy | Precision | Recall | F1 |
65
+ |:-------------:|:-------:|:-----:|:---------------:|:--------------:|:--------------:|:---------------:|:--------:|:---------:|:------:|:------:|
66
+ | 30.4991 | 0.004 | 3572 | 7.6318 | 0.0008 | 0.0026 | 0.0054 | 0.0008 | 0.0000 | 0.0008 | 0.0001 |
67
+ | 30.456 | 1.0040 | 7144 | 7.6069 | 0.0015 | 0.0054 | 0.0092 | 0.0013 | 0.0000 | 0.0013 | 0.0000 |
68
+ | 30.2884 | 2.0040 | 10716 | 7.5924 | 0.0015 | 0.0059 | 0.0105 | 0.0015 | 0.0000 | 0.0015 | 0.0000 |
69
+ | 30.1254 | 3.0040 | 14289 | 7.5970 | 0.0015 | 0.0072 | 0.0102 | 0.0015 | 0.0000 | 0.0015 | 0.0000 |
70
+ | 29.9334 | 4.004 | 17861 | 7.5835 | 0.0033 | 0.0100 | 0.0166 | 0.0033 | 0.0000 | 0.0033 | 0.0001 |
71
+ | 28.9209 | 5.0040 | 21433 | 7.4102 | 0.0028 | 0.0140 | 0.0232 | 0.0028 | 0.0001 | 0.0028 | 0.0001 |
72
+ | 27.4124 | 6.0040 | 25005 | 7.0850 | 0.0072 | 0.0301 | 0.0554 | 0.0072 | 0.0013 | 0.0072 | 0.0013 |
73
+ | 25.7784 | 7.0040 | 28578 | 6.7483 | 0.0156 | 0.0600 | 0.1009 | 0.0158 | 0.0021 | 0.0158 | 0.0034 |
74
+ | 23.5018 | 8.004 | 32150 | 6.3460 | 0.0289 | 0.1055 | 0.1665 | 0.0291 | 0.0080 | 0.0291 | 0.0095 |
75
+ | 20.905 | 9.0040 | 35722 | 5.9416 | 0.0544 | 0.1647 | 0.2428 | 0.0544 | 0.0178 | 0.0544 | 0.0218 |
76
+ | 17.9146 | 10.0040 | 39294 | 5.5082 | 0.0792 | 0.2265 | 0.3279 | 0.0792 | 0.0374 | 0.0792 | 0.0414 |
77
+ | 14.3734 | 11.0040 | 42867 | 5.0939 | 0.1152 | 0.2939 | 0.4109 | 0.1152 | 0.0683 | 0.1152 | 0.0740 |
78
+ | 10.1724 | 12.004 | 46439 | 4.7246 | 0.1402 | 0.3432 | 0.4727 | 0.1399 | 0.0938 | 0.1399 | 0.1001 |
79
+ | 6.4722 | 13.0040 | 50011 | 4.3776 | 0.1675 | 0.4053 | 0.5426 | 0.1675 | 0.1327 | 0.1675 | 0.1338 |
80
+ | 3.9864 | 14.0040 | 53583 | 4.2916 | 0.1652 | 0.4346 | 0.5531 | 0.1655 | 0.1414 | 0.1655 | 0.1393 |
81
+ | 2.2789 | 15.0040 | 57156 | 4.2496 | 0.1724 | 0.4298 | 0.5590 | 0.1724 | 0.1497 | 0.1724 | 0.1460 |
82
+ | 1.8662 | 16.004 | 60728 | 4.3586 | 0.1688 | 0.4303 | 0.5523 | 0.1691 | 0.1509 | 0.1691 | 0.1451 |
83
+ | 1.3092 | 17.0040 | 64300 | 4.4090 | 0.1744 | 0.4336 | 0.5641 | 0.1744 | 0.1558 | 0.1744 | 0.1498 |
84
+ | 1.2238 | 18.0040 | 67872 | 4.4967 | 0.1680 | 0.4336 | 0.5575 | 0.1678 | 0.1544 | 0.1678 | 0.1453 |
85
+ | 1.3316 | 19.0040 | 71445 | 4.6016 | 0.1685 | 0.4213 | 0.5493 | 0.1685 | 0.1463 | 0.1685 | 0.1415 |
86
+ | 1.3673 | 20.004 | 75017 | 4.7247 | 0.1591 | 0.4139 | 0.5411 | 0.1588 | 0.1476 | 0.1588 | 0.1380 |
87
+ | 1.2106 | 21.0040 | 78589 | 4.8187 | 0.1629 | 0.4122 | 0.5291 | 0.1629 | 0.1396 | 0.1629 | 0.1362 |
88
+ | 1.2995 | 22.0040 | 82161 | 4.9119 | 0.1622 | 0.4086 | 0.5301 | 0.1624 | 0.1508 | 0.1624 | 0.1418 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.46.1
94
+ - Pytorch 2.5.1+cu124
95
+ - Datasets 3.1.0
96
+ - Tokenizers 0.20.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caadaa4f2f1f4ef847843d057351ae9b69a27bc8fa9c09ec62f4edf03bf5fd51
3
  size 351083264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6221e6d07524420bf826cf820388eda7d3e73ccbdb27ed5a35da7bd9c2cecac
3
  size 351083264