Hugging Face's logo

Shawon16
/
working

Safetensors
videomae
Generated from Trainer
Model card Files
xet
Community
Shawon16 commited on
Commit
831a01a
·
verified ·
1 Parent(s): 8c2b550

Upload trained VideoMAE with metrics and all figures

Browse files
Files changed (8) hide show
  1. README.md +15 -15
  2. confusion_matrix_test_50.png +0 -0
  3. confusion_matrix_train_50.png +0 -0
  4. confusion_matrix_valid_50.png +0 -0
  5. longtail_f1_vs_freq.png +0 -0
  6. model.safetensors +1 -1
  7. per_class_report.csv +5 -5
  8. training_args.bin +1 -1
README.md CHANGED
@@ -17,14 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.3668
21
  - Accuracy: 0.1562
22
  - Top 1 Accuracy: 0.1562
23
- - Top 5 Accuracy: 0.5625
24
  - Top 10 Accuracy: 1.0
25
- - Macro Precision: 0.0867
26
- - Macro Recall: 0.1417
27
- - Macro F1: 0.0938
28
 
29
  ## Model description
30
 
@@ -58,16 +58,16 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Top 1 Accuracy | Top 5 Accuracy | Top 10 Accuracy | Macro Precision | Macro Recall | Macro F1 |
60
  |:-------------:|:------:|:----:|:---------------:|:--------:|:--------------:|:--------------:|:---------------:|:---------------:|:------------:|:--------:|
61
- | No log | 0.0941 | 8 | 2.3280 | 0.125 | 0.125 | 0.5312 | 1.0 | 0.0125 | 0.1 | 0.0222 |
62
- | No log | 1.0971 | 17 | 2.3426 | 0.0938 | 0.0938 | 0.5625 | 1.0 | 0.0414 | 0.0917 | 0.0533 |
63
- | No log | 2.1 | 26 | 2.3333 | 0.125 | 0.125 | 0.5625 | 1.0 | 0.0261 | 0.1167 | 0.0426 |
64
- | No log | 3.1029 | 35 | 2.3628 | 0.0 | 0.0 | 0.5 | 1.0 | 0.0 | 0.0 | 0.0 |
65
- | No log | 4.0941 | 43 | 2.3573 | 0.0625 | 0.0625 | 0.5312 | 1.0 | 0.0211 | 0.0583 | 0.0308 |
66
- | No log | 5.0971 | 52 | 2.3469 | 0.0938 | 0.0938 | 0.5625 | 1.0 | 0.0618 | 0.0833 | 0.0590 |
67
- | No log | 6.1 | 61 | 2.3522 | 0.125 | 0.125 | 0.5312 | 1.0 | 0.0380 | 0.1083 | 0.0508 |
68
- | No log | 7.1029 | 70 | 2.3630 | 0.0625 | 0.0625 | 0.5312 | 1.0 | 0.0133 | 0.05 | 0.0211 |
69
- | No log | 8.0941 | 78 | 2.3658 | 0.0938 | 0.0938 | 0.5625 | 1.0 | 0.02 | 0.075 | 0.0316 |
70
- | No log | 9.0735 | 85 | 2.3668 | 0.1562 | 0.1562 | 0.5625 | 1.0 | 0.0867 | 0.1417 | 0.0938 |
71
 
72
 
73
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.3920
21
  - Accuracy: 0.1562
22
  - Top 1 Accuracy: 0.1562
23
+ - Top 5 Accuracy: 0.5
24
  - Top 10 Accuracy: 1.0
25
+ - Macro Precision: 0.0468
26
+ - Macro Recall: 0.1583
27
+ - Macro F1: 0.0701
28
 
29
  ## Model description
30
 
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Top 1 Accuracy | Top 5 Accuracy | Top 10 Accuracy | Macro Precision | Macro Recall | Macro F1 |
60
  |:-------------:|:------:|:----:|:---------------:|:--------:|:--------------:|:--------------:|:---------------:|:---------------:|:------------:|:--------:|
61
+ | 2.6054 | 0.0941 | 8 | 2.3462 | 0.125 | 0.125 | 0.4375 | 1.0 | 0.0125 | 0.1 | 0.0222 |
62
+ | 2.2755 | 1.0971 | 17 | 2.3085 | 0.125 | 0.125 | 0.5625 | 1.0 | 0.0674 | 0.1250 | 0.0784 |
63
+ | 2.2306 | 2.1 | 26 | 2.3664 | 0.0938 | 0.0938 | 0.5312 | 1.0 | 0.0343 | 0.1 | 0.0485 |
64
+ | 2.231 | 3.1029 | 35 | 2.3689 | 0.0625 | 0.0625 | 0.4375 | 1.0 | 0.0202 | 0.0583 | 0.0299 |
65
+ | 2.4323 | 4.0941 | 43 | 2.3849 | 0.0625 | 0.0625 | 0.5 | 1.0 | 0.0205 | 0.0583 | 0.0300 |
66
+ | 2.1676 | 5.0971 | 52 | 2.3948 | 0.0625 | 0.0625 | 0.5312 | 1.0 | 0.0225 | 0.0667 | 0.0322 |
67
+ | 2.1075 | 6.1 | 61 | 2.3912 | 0.1562 | 0.1562 | 0.5312 | 1.0 | 0.0583 | 0.1500 | 0.0826 |
68
+ | 2.0926 | 7.1029 | 70 | 2.3955 | 0.125 | 0.125 | 0.5625 | 1.0 | 0.0413 | 0.125 | 0.0621 |
69
+ | 2.3112 | 8.0941 | 78 | 2.3913 | 0.125 | 0.125 | 0.5312 | 1.0 | 0.0404 | 0.125 | 0.0598 |
70
+ | 1.8385 | 9.0735 | 85 | 2.3920 | 0.1562 | 0.1562 | 0.5 | 1.0 | 0.0468 | 0.1583 | 0.0701 |
71
 
72
 
73
  ### Framework versions
confusion_matrix_test_50.png CHANGED
confusion_matrix_train_50.png CHANGED
confusion_matrix_valid_50.png CHANGED
longtail_f1_vs_freq.png CHANGED
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5ce06b1f01f43b2555193057f80a0810f2c4addc451bde598f149ae80095e26
3
  size 344961984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f0d6a26057fd44cb46f7aeeda8820864a69e21ca4cfa45e2914430c4126591
3
  size 344961984
per_class_report.csv CHANGED
@@ -3,11 +3,11 @@ accident,0.0,0.0,0.0,3
3
  africa,0.0,0.0,0.0,3
4
  all,0.0,0.0,0.0,3
5
  apple,0.0,0.0,0.0,2
6
- basketball,0.3333333333333333,0.5,0.4,2
7
  bed,0.0,0.0,0.0,2
8
- before,0.07142857142857142,0.25,0.11111111111111112,4
9
  bird,0.0,0.0,0.0,2
10
  birthday,0.0,0.0,0.0,3
11
- black,0.0,0.0,0.0,3
12
- macro avg,0.04047619047619048,0.075,0.05111111111111112,27
13
- weighted avg,0.03527336860670194,0.07407407407407407,0.04609053497942387,27
 
3
  africa,0.0,0.0,0.0,3
4
  all,0.0,0.0,0.0,3
5
  apple,0.0,0.0,0.0,2
6
+ basketball,0.0,0.0,0.0,2
7
  bed,0.0,0.0,0.0,2
8
+ before,0.058823529411764705,0.25,0.09523809523809523,4
9
  bird,0.0,0.0,0.0,2
10
  birthday,0.0,0.0,0.0,3
11
+ black,0.125,0.3333333333333333,0.18181818181818182,3
12
+ macro avg,0.01838235294117647,0.05833333333333333,0.027705627705627706,27
13
+ weighted avg,0.022603485838779958,0.07407407407407407,0.034311367644700975,27
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0e6676eb862b85fbca3ae366e12c9fbde3675159e6b678a55b8b148d4ca31a8
3
  size 4719
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2f47b213999dc480f529ccb9a6229a3201ce91464f8056c6d5bc979ae52c3c
3
  size 4719