Hugging Face's logo

alexgrigore
/
videomae-base-finetuned-gesturePhasev2

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
alexgrigore commited on
Commit
9662f4e
•
1 Parent(s): 866167b

Model save

Browse files
Files changed (2) hide show
  1. README.md +11 -8
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ 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: 0.8752
21
  - Accuracy: 0.7633
22
 
23
  ## Model description
@@ -37,23 +37,26 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 1e-05
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
- - lr_scheduler_type: linear
46
- - lr_scheduler_warmup_ratio: 0.1
47
  - training_steps: 376
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
- | 0.806 | 0.2527 | 95 | 0.8249 | 0.7875 |
54
- | 0.8453 | 1.2527 | 190 | 0.8071 | 0.7875 |
55
- | 0.8814 | 2.2527 | 285 | 0.8308 | 0.7875 |
56
- | 0.8272 | 3.2420 | 376 | 0.8260 | 0.7875 |
 
57
 
58
 
59
  ### 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: 0.8172
21
  - Accuracy: 0.7633
22
 
23
  ## Model description
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 5e-06
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 16
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.2
49
  - training_steps: 376
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
+ | 1.1665 | 0.125 | 47 | 1.0642 | 0.775 |
56
+ | 0.7316 | 1.1263 | 95 | 0.7826 | 0.7875 |
57
+ | 0.7259 | 2.125 | 142 | 0.8042 | 0.7875 |
58
+ | 0.6643 | 3.1263 | 190 | 0.8023 | 0.7875 |
59
+ | 0.761 | 4.125 | 237 | 0.8077 | 0.7875 |
60
 
61
 
62
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:090f07f23b7e9f29ab49692102e9c4e7ddb9c3b41d5ccbb608c74898747bca7f
3
  size 344943528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ea40bf1ab9193d59b1777dfc4559525167a9c4afbac4392212962a047f39ba4
3
  size 344943528