Hugging Face's logo

billskar23
/
videomae-base-videoMAE

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
billskar23 commited on
Commit
a14c515
·
verified ·
1 Parent(s): 4a7d3e6

Model save

Browse files
Files changed (6) hide show
  1. README.md +28 -28
  2. model.safetensors +1 -1
  3. runs/Sep26_15-08-55_hmudgx/events.out.tfevents.1727352538.hmudgx.917888.0 +2 -2
  4. runs/Sep26_15-09-12_hmudgx/events.out.tfevents.1727352554.hmudgx.918034.0 +2 -2
  5. runs/Sep26_15-09-35_hmudgx/events.out.tfevents.1727355542.hmudgx.918204.1 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.2891
25
- - Accuracy: 0.8667
26
- - Precision: 0.8963
27
- - Recall: 0.8667
28
- - F1: 0.8655
29
 
30
  ## Model description
31
 
@@ -45,38 +45,38 @@ More information needed
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 5e-05
48
- - train_batch_size: 16
49
- - eval_batch_size: 16
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_ratio: 0.1
54
- - training_steps: 2540
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
- | 0.6522 | 1.0 | 128 | 0.7264 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
61
- | 0.4319 | 2.0 | 256 | 0.9222 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
62
- | 0.2615 | 3.0 | 384 | 0.0733 | 1.0 | 1.0 | 1.0 | 1.0 |
63
- | 0.1503 | 4.0 | 512 | 0.1158 | 0.9333 | 0.9407 | 0.9333 | 0.9327 |
64
- | 0.0783 | 5.0 | 640 | 0.0430 | 1.0 | 1.0 | 1.0 | 1.0 |
65
- | 0.058 | 6.0 | 768 | 1.7061 | 0.5333 | 0.7667 | 0.5333 | 0.4296 |
66
- | 0.0002 | 7.0 | 896 | 0.2261 | 0.8 | 0.8600 | 0.8 | 0.7946 |
67
- | 0.0002 | 8.0 | 1024 | 0.0097 | 1.0 | 1.0 | 1.0 | 1.0 |
68
- | 0.0001 | 9.0 | 1152 | 0.9089 | 0.7333 | 0.8303 | 0.7333 | 0.7185 |
69
- | 0.0012 | 10.0 | 1280 | 0.1646 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
70
- | 0.0001 | 11.0 | 1408 | 0.1737 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
71
- | 0.0001 | 12.0 | 1536 | 0.2599 | 0.8667 | 0.8963 | 0.8667 | 0.8655 |
72
- | 0.0 | 13.0 | 1664 | 0.5901 | 0.8667 | 0.8963 | 0.8667 | 0.8655 |
73
- | 0.0 | 14.0 | 1792 | 0.4810 | 0.8667 | 0.8963 | 0.8667 | 0.8655 |
74
- | 0.0 | 15.0 | 1920 | 0.4107 | 0.8667 | 0.8963 | 0.8667 | 0.8655 |
75
- | 0.0 | 16.0 | 2048 | 0.3579 | 0.8667 | 0.8963 | 0.8667 | 0.8655 |
76
- | 0.0 | 17.0 | 2176 | 0.3290 | 0.8667 | 0.8963 | 0.8667 | 0.8655 |
77
- | 0.0 | 18.0 | 2304 | 0.3053 | 0.8667 | 0.8963 | 0.8667 | 0.8655 |
78
- | 0.0 | 19.0 | 2432 | 0.2919 | 0.8667 | 0.8963 | 0.8667 | 0.8655 |
79
- | 0.0 | 19.8438 | 2540 | 0.2891 | 0.8667 | 0.8963 | 0.8667 | 0.8655 |
80
 
81
 
82
  ### Framework versions
 
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: 0.5414
25
+ - Accuracy: 0.9333
26
+ - Precision: 0.9417
27
+ - Recall: 0.9333
28
+ - F1: 0.9333
29
 
30
  ## Model description
31
 
 
45
 
46
  The following hyperparameters were used during training:
47
  - learning_rate: 5e-05
48
+ - train_batch_size: 8
49
+ - eval_batch_size: 8
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_ratio: 0.1
54
+ - training_steps: 5100
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
  |:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
+ | 0.5349 | 1.0 | 256 | 0.3605 | 1.0 | 1.0 | 1.0 | 1.0 |
61
+ | 0.5233 | 2.0 | 512 | 0.2742 | 1.0 | 1.0 | 1.0 | 1.0 |
62
+ | 0.37 | 3.0 | 768 | 0.0803 | 1.0 | 1.0 | 1.0 | 1.0 |
63
+ | 0.1911 | 4.0 | 1024 | 0.4367 | 0.7333 | 0.8303 | 0.7333 | 0.7185 |
64
+ | 0.2191 | 5.0 | 1280 | 0.2463 | 0.8667 | 0.8963 | 0.8667 | 0.8655 |
65
+ | 0.0005 | 6.0 | 1536 | 4.2895 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
66
+ | 0.0002 | 7.0 | 1792 | 0.0111 | 1.0 | 1.0 | 1.0 | 1.0 |
67
+ | 0.1025 | 8.0 | 2048 | 0.0439 | 1.0 | 1.0 | 1.0 | 1.0 |
68
+ | 0.0001 | 9.0 | 2304 | 0.2776 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
69
+ | 0.0 | 10.0 | 2560 | 0.2759 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
70
+ | 0.0 | 11.0 | 2816 | 0.3329 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
71
+ | 0.0 | 12.0 | 3072 | 0.3789 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
72
+ | 0.0 | 13.0 | 3328 | 0.4144 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
73
+ | 0.0 | 14.0 | 3584 | 0.4435 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
74
+ | 0.0 | 15.0 | 3840 | 0.4708 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
75
+ | 0.0 | 16.0 | 4096 | 0.4930 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
76
+ | 0.0 | 17.0 | 4352 | 0.5132 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
77
+ | 0.0 | 18.0 | 4608 | 0.5288 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
78
+ | 0.0 | 19.0 | 4864 | 0.5386 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
79
+ | 0.0 | 19.9219 | 5100 | 0.5414 | 0.9333 | 0.9417 | 0.9333 | 0.9333 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74bdbec0cde985ab479b52ec9b83418363070294226af47b4dc364ac55ce531b
3
  size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729fb4e76e4d4c019ed6a73ba0ecf19a08404c5bcf41d6fbc77d86b8bd10f5f6
3
  size 344937368
runs/Sep26_15-08-55_hmudgx/events.out.tfevents.1727352538.hmudgx.917888.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bda44db78f835a33152df677878247f1a7c56bac450e91aefae0bb729bfde60
3
- size 118701
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9887724024eea5d9c8adf726e8a74169f076acfd04d85681c11e3bcb635bc3ec
3
+ size 122481
runs/Sep26_15-09-12_hmudgx/events.out.tfevents.1727352554.hmudgx.918034.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00cbcce318cbfc2b7c274ab74a16d942a87f69df374e7e97d7cdeba608e99ca9
3
- size 220615
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798805775c56e87680fc20830b705168da5f6ee2a5551cb1a012732253c84f97
3
+ size 227789
runs/Sep26_15-09-35_hmudgx/events.out.tfevents.1727355542.hmudgx.918204.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b24890b2038af23cdefecee8917abcd2d203381f526208a9986d7c5baaed8430
3
+ size 560
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c41629e4679173ffcfa5684b89f9aad56e82ee883d71ec420057c6646d584692
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988b456cfb6fff6fa9f831d139102ec1cc46e431ef867e7a619d30816a5ff241
3
  size 5176