Hugging Face's logo

Salvatore
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
Salvatore commited on
Commit
1186329
•
1 Parent(s): 82f6cfe

Model save

Browse files
Files changed (2) hide show
  1. README.md +24 -8
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.4163
22
- - Accuracy: 0.2368
23
 
24
  ## Model description
25
 
@@ -38,23 +38,39 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 5e-05
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
- - training_steps: 96
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
- | 1.4528 | 1.0 | 25 | 1.4396 | 0.2625 |
55
- | 1.4244 | 2.0 | 50 | 1.4033 | 0.25 |
56
- | 1.4495 | 3.0 | 75 | 1.3919 | 0.25 |
57
- | 1.3912 | 3.84 | 96 | 1.3885 | 0.25 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.4025
22
+ - Accuracy: 0.2237
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 5e-06
42
  - train_batch_size: 8
43
  - eval_batch_size: 8
44
  - seed: 42
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_ratio: 0.1
48
+ - training_steps: 480
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 1.3855 | 1.0 | 25 | 1.3973 | 0.275 |
55
+ | 1.4151 | 2.0 | 50 | 1.4034 | 0.1875 |
56
+ | 1.4342 | 3.0 | 75 | 1.4028 | 0.2 |
57
+ | 1.4189 | 4.0 | 100 | 1.3967 | 0.1625 |
58
+ | 1.3925 | 5.0 | 125 | 1.4030 | 0.2375 |
59
+ | 1.406 | 6.0 | 150 | 1.3974 | 0.1875 |
60
+ | 1.3868 | 7.0 | 175 | 1.4011 | 0.175 |
61
+ | 1.3969 | 8.0 | 200 | 1.4019 | 0.15 |
62
+ | 1.4233 | 9.0 | 225 | 1.3985 | 0.2125 |
63
+ | 1.4011 | 10.0 | 250 | 1.4081 | 0.25 |
64
+ | 1.3994 | 11.0 | 275 | 1.4037 | 0.175 |
65
+ | 1.3945 | 12.0 | 300 | 1.4094 | 0.2625 |
66
+ | 1.3844 | 13.0 | 325 | 1.4050 | 0.175 |
67
+ | 1.378 | 14.0 | 350 | 1.4081 | 0.275 |
68
+ | 1.3965 | 15.0 | 375 | 1.4095 | 0.275 |
69
+ | 1.3982 | 16.0 | 400 | 1.4116 | 0.275 |
70
+ | 1.385 | 17.0 | 425 | 1.4114 | 0.275 |
71
+ | 1.3735 | 18.0 | 450 | 1.4103 | 0.275 |
72
+ | 1.3817 | 19.0 | 475 | 1.4106 | 0.275 |
73
+ | 1.3785 | 19.2 | 480 | 1.4106 | 0.275 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b75927341e5e7c34c1c50b64396b602e70a2240fcdfe74e32147d3082ec3a500
3
  size 344943528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62747386e6f24aaad4a71ac6525420647d87d595cb7c38184637a87f13548f3
3
  size 344943528