Hugging Face's logo

Shawon16
/
working

Safetensors
videomae
Generated from Trainer
Model card Files
xet
Community
Shawon16 commited on
Commit
045b532
·
verified ·
1 Parent(s): 831a01a

Upload trained VideoMAE with metrics and all figures

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. README.md +18 -16
  3. confusion_matrix_test_50.png +0 -0
  4. confusion_matrix_train_50.png +0 -0
  5. confusion_matrix_valid_50.png +0 -0
  6. longtail_f1_vs_freq.png +0 -0
  7. model.safetensors +1 -1
  8. per_class_report.csv +13 -13
  9. training_args.bin +1 -1
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  sample.gif filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  sample.gif filter=lfs diff=lfs merge=lfs -text
37
+ longtail_f1_vs_freq.png filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -17,14 +17,16 @@ 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: 2.3920
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
 
@@ -56,18 +58,18 @@ The following hyperparameters were used during training:
56
 
57
  ### Training results
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
 
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: 2.3765
21
  - Accuracy: 0.1562
22
  - Top 1 Accuracy: 0.1562
23
+ - Top 5 Accuracy: 0.5938
24
  - Top 10 Accuracy: 1.0
25
+ - Macro Precision: 0.0827
26
  - Macro Recall: 0.1583
27
+ - Macro F1: 0.1037
28
+ - Pearson Corr: 0.0111
29
+ - Spearman Corr: 0.1465
30
 
31
  ## Model description
32
 
 
58
 
59
  ### Training results
60
 
61
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Top 1 Accuracy | Top 5 Accuracy | Top 10 Accuracy | Macro Precision | Macro Recall | Macro F1 | Pearson Corr | Spearman Corr |
62
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:--------------:|:--------------:|:---------------:|:---------------:|:------------:|:--------:|:------------:|:-------------:|
63
+ | 2.5873 | 0.0941 | 8 | 2.3233 | 0.125 | 0.125 | 0.5312 | 1.0 | 0.0301 | 0.1083 | 0.0461 | 0.5410 | 0.2784 |
64
+ | 2.2865 | 1.0971 | 17 | 2.3180 | 0.1562 | 0.1562 | 0.5625 | 1.0 | 0.0616 | 0.1417 | 0.0776 | 0.4324 | 0.3429 |
65
+ | 2.2539 | 2.1 | 26 | 2.3145 | 0.125 | 0.125 | 0.5312 | 1.0 | 0.0462 | 0.125 | 0.0658 | 0.3799 | 0.5867 |
66
+ | 2.239 | 3.1029 | 35 | 2.3378 | 0.0938 | 0.0938 | 0.4688 | 1.0 | 0.0309 | 0.0917 | 0.0459 | 0.4058 | 0.6497 |
67
+ | 2.4775 | 4.0941 | 43 | 2.3220 | 0.125 | 0.125 | 0.5938 | 1.0 | 0.0444 | 0.125 | 0.0643 | 0.4936 | 0.5486 |
68
+ | 2.1767 | 5.0971 | 52 | 2.3478 | 0.125 | 0.125 | 0.5938 | 1.0 | 0.0325 | 0.125 | 0.05 | 0.3733 | 0.4066 |
69
+ | 2.1349 | 6.1 | 61 | 2.3552 | 0.0938 | 0.0938 | 0.5312 | 1.0 | 0.0475 | 0.0917 | 0.0610 | 0.4551 | 0.5486 |
70
+ | 2.1092 | 7.1029 | 70 | 2.3407 | 0.1875 | 0.1875 | 0.5312 | 1.0 | 0.0861 | 0.1917 | 0.1109 | 0.0687 | 0.1465 |
71
+ | 2.3306 | 8.0941 | 78 | 2.3750 | 0.1562 | 0.1562 | 0.5938 | 1.0 | 0.0821 | 0.1583 | 0.1030 | 0.0000 | 0.1465 |
72
+ | 1.8384 | 9.0735 | 85 | 2.3765 | 0.1562 | 0.1562 | 0.5938 | 1.0 | 0.0827 | 0.1583 | 0.1037 | 0.0111 | 0.1465 |
73
 
74
 
75
  ### 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

Git LFS Details

  • SHA256: 190fa4f3769116cc1fac11fc600ae73b1512cfbd8fe6423a6529631f31c18e58
  • Pointer size: 131 Bytes
  • Size of remote file: 159 kB
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71f0d6a26057fd44cb46f7aeeda8820864a69e21ca4cfa45e2914430c4126591
3
  size 344961984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652620e69d4dc9f58a839ed63d1dfb622e217da6e69d0b162825cc01096feab9
3
  size 344961984
per_class_report.csv CHANGED
@@ -1,13 +1,13 @@
1
- ,precision,recall,f1-score,support
2
- 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,0.0,0.0,0.0,2
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
 
1
+ ,precision,recall,f1-score,support,train_freq,pearson_corr,spearman_corr
2
+ accident,0.0,0.0,0.0,3,13.0,0.1992047682223989,0.35578403348241
3
+ africa,0.0,0.0,0.0,3,12.0,0.1992047682223989,0.35578403348241
4
+ all,0.0,0.0,0.0,3,14.0,0.1992047682223989,0.35578403348241
5
+ apple,0.0,0.0,0.0,2,14.0,0.1992047682223989,0.35578403348241
6
+ basketball,0.0,0.0,0.0,2,13.0,0.1992047682223989,0.35578403348241
7
+ bed,0.0,0.0,0.0,2,15.0,0.1992047682223989,0.35578403348241
8
+ before,0.0,0.0,0.0,4,18.0,0.1992047682223989,0.35578403348241
9
+ bird,0.0,0.0,0.0,2,14.0,0.1992047682223989,0.35578403348241
10
+ birthday,0.0,0.0,0.0,3,12.0,0.1992047682223989,0.35578403348241
11
+ black,0.1111111111111111,0.3333333333333333,0.16666666666666666,3,15.0,0.1992047682223989,0.35578403348241
12
+ macro avg,0.01111111111111111,0.03333333333333333,0.016666666666666666,27,,0.1992047682223989,0.35578403348241
13
+ weighted avg,0.012345679012345678,0.037037037037037035,0.018518518518518517,27,,0.1992047682223989,0.35578403348241
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea2f47b213999dc480f529ccb9a6229a3201ce91464f8056c6d5bc979ae52c3c
3
  size 4719
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7344cbe498f844be8cc78304fae6a185ca0fb9cf017424d082a2be8c520738f2
3
  size 4719