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
5275b83
·
verified ·
1 Parent(s): aabf578

Model save

Browse files
Files changed (4) hide show
  1. README.md +28 -28
  2. model.safetensors +1 -1
  3. runs/Sep26_20-08-57_hmudgx/events.out.tfevents.1727370538.hmudgx.1191814.2 +2 -2
  4. runs/Sep26_20-09-22_hmudgx/events.out.tfevents.1727370563.hmudgx.1191083.2 +2 -2
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: 5.5496
25
- - Accuracy: 0.4667
26
- - Precision: 0.2178
27
- - Recall: 0.4667
28
- - F1: 0.2970
29
 
30
  ## Model description
31
 
@@ -51,32 +51,32 @@ The following hyperparameters were used during training:
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
- | 0.5155 | 1.0 | 256 | 0.8595 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
61
- | 0.4699 | 2.0 | 512 | 0.8589 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
62
- | 0.3445 | 3.0 | 768 | 2.6585 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
63
- | 0.0819 | 4.0 | 1024 | 3.9389 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
64
- | 0.099 | 5.0 | 1280 | 3.2142 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
65
- | 0.0531 | 6.0 | 1536 | 4.8094 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
66
- | 0.0032 | 7.0 | 1792 | 4.8235 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
67
- | 0.0001 | 8.0 | 2048 | 5.0010 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
68
- | 0.0214 | 9.0 | 2304 | 5.2360 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
69
- | 0.0 | 10.0 | 2560 | 5.3494 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
70
- | 0.0417 | 11.0 | 2816 | 5.2447 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
71
- | 0.0014 | 12.0 | 3072 | 5.3666 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
72
- | 0.0001 | 13.0 | 3328 | 5.1025 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
73
- | 0.0001 | 14.0 | 3584 | 5.0775 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
74
- | 0.0001 | 15.0 | 3840 | 5.2954 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
75
- | 0.0 | 16.0 | 4096 | 5.3913 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
76
- | 0.0 | 17.0 | 4352 | 5.4632 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
77
- | 0.0 | 18.0 | 4608 | 5.5113 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
78
- | 0.0 | 19.0 | 4864 | 5.5407 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
79
- | 0.0 | 19.9219 | 5100 | 5.5496 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
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: 4.5354
25
+ - Accuracy: 0.4615
26
+ - Precision: 0.3357
27
+ - Recall: 0.4615
28
+ - F1: 0.3887
29
 
30
  ## Model description
31
 
 
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: 5120
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
+ | 0.4474 | 1.0 | 256 | 0.5837 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
61
+ | 0.3522 | 2.0 | 512 | 1.3421 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
62
+ | 0.6541 | 3.0 | 768 | 2.2046 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
63
+ | 0.1653 | 4.0 | 1024 | 2.4049 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
64
+ | 0.0007 | 5.0 | 1280 | 3.4085 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
65
+ | 0.0477 | 6.0 | 1536 | 3.0247 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
66
+ | 0.0019 | 7.0 | 1792 | 3.3402 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
67
+ | 0.0002 | 8.0 | 2048 | 3.6162 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
68
+ | 0.0001 | 9.0 | 2304 | 3.8473 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
69
+ | 0.0001 | 10.0 | 2560 | 3.8232 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
70
+ | 0.0008 | 11.0 | 2816 | 3.8918 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
71
+ | 0.0428 | 12.0 | 3072 | 4.4917 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
72
+ | 0.0 | 13.0 | 3328 | 3.9737 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
73
+ | 0.0 | 14.0 | 3584 | 4.2064 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
74
+ | 0.0 | 15.0 | 3840 | 4.3017 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
75
+ | 0.0 | 16.0 | 4096 | 4.3791 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
76
+ | 0.0 | 17.0 | 4352 | 4.4430 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
77
+ | 0.0 | 18.0 | 4608 | 4.4936 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
78
+ | 0.0 | 19.0 | 4864 | 4.5252 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
79
+ | 0.0 | 20.0 | 5120 | 4.5354 | 0.4615 | 0.3357 | 0.4615 | 0.3887 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c312cf522c0459398bbe7ff6de74831a05ccc7c69a62bd4b975d0144aa780ae5
3
  size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428736c076e29a28243b914e21c77e5247926394e707143e8637145b1f240d3c
3
  size 344937368
runs/Sep26_20-08-57_hmudgx/events.out.tfevents.1727370538.hmudgx.1191814.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55061e12da59ea1ffd1b8056222bfe7053533684d8674ef2c300f675cabd7aa7
3
- size 122549
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05e28933807d0811065f24fabfa60f0a0a2f5e0d3a2c0ecc574e32c25758a8a
3
+ size 122903
runs/Sep26_20-09-22_hmudgx/events.out.tfevents.1727370563.hmudgx.1191083.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f351694e3dc5ed73179bcf3aa5d68b2b908c2673da0de3049841d883b859539
3
- size 222303
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77cdadb5f78f32365a9d317a22403deda412359dfdf2cafe9f78e3854322b630
3
+ size 223569