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
91e85c5
•
1 Parent(s): 3713feb

Model save

Browse files
Files changed (3) hide show
  1. README.md +13 -13
  2. model.safetensors +1 -1
  3. runs/Sep26_11-30-17_hmudgx/events.out.tfevents.1727339419.hmudgx.658204.2 +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: 1.0497
25
- - Accuracy: 0.6667
26
- - Precision: 0.8056
27
- - Recall: 0.6667
28
- - F1: 0.6348
29
 
30
  ## Model description
31
 
@@ -51,17 +51,17 @@ 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: 1275
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
- |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
- | 0.4685 | 1.0 | 256 | 0.2059 | 1.0 | 1.0 | 1.0 | 1.0 |
61
- | 0.4451 | 2.0 | 512 | 0.1075 | 0.9333 | 0.9407 | 0.9333 | 0.9327 |
62
- | 0.1107 | 3.0 | 768 | 3.2224 | 0.4667 | 0.2178 | 0.4667 | 0.2970 |
63
- | 0.0004 | 4.0 | 1024 | 0.7245 | 0.7333 | 0.8303 | 0.7333 | 0.7185 |
64
- | 0.0002 | 4.9805 | 1275 | 1.0497 | 0.6667 | 0.8056 | 0.6667 | 0.6348 |
65
 
66
 
67
  ### 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: 2.5186
25
+ - Accuracy: 0.5385
26
+ - Precision: 0.3590
27
+ - Recall: 0.5385
28
+ - F1: 0.4308
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: 1280
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
59
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
60
+ | 0.5101 | 1.0 | 256 | 0.2698 | 0.8462 | 0.8769 | 0.8462 | 0.8355 |
61
+ | 0.1872 | 2.0 | 512 | 1.7595 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
62
+ | 0.0715 | 3.0 | 768 | 2.3471 | 0.6154 | 0.3787 | 0.6154 | 0.4689 |
63
+ | 0.0003 | 4.0 | 1024 | 2.3920 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
64
+ | 0.0002 | 5.0 | 1280 | 2.5186 | 0.5385 | 0.3590 | 0.5385 | 0.4308 |
65
 
66
 
67
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c49121768cf794974efbce18a4332f48b22f35f95cf2586b5ee2ce9cd4004a6
3
  size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279b2a2aadf8f6e94afa8b413b641491e24d1c3a2a72d2b7e65fcf81ea81914c
3
  size 344937368
runs/Sep26_11-30-17_hmudgx/events.out.tfevents.1727339419.hmudgx.658204.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e60b5744ca65e4931a82e28dba74508855c2e706d77fd44af8a0e2a58886ee7f
3
- size 28487
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7997ae92cb2bef2056370424eb40cf2c16ee2184c704e928f3c818f70b0c85
3
+ size 34799