Hugging Face's logo

prathameshdalal
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
PyTorch
TensorBoard
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
prathameshdalal commited on
Commit
f73e1e7
•
1 Parent(s): c9b811a

Training in progress, epoch 0

Browse files
Files changed (3) hide show
  1. README.md +9 -21
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ 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: 0.0273
21
- - Accuracy: 0.9857
22
 
23
  ## Model description
24
 
@@ -38,8 +38,8 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-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
@@ -50,27 +50,15 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | 2.2553 | 0.06 | 38 | 2.2822 | 0.1429 |
54
- | 1.5918 | 1.06 | 76 | 1.2300 | 0.6286 |
55
- | 0.7251 | 2.06 | 114 | 0.7309 | 0.6857 |
56
- | 0.3999 | 3.06 | 152 | 0.4062 | 0.8 |
57
- | 0.1734 | 4.06 | 190 | 0.4396 | 0.8286 |
58
- | 0.3278 | 5.06 | 228 | 0.4385 | 0.8143 |
59
- | 0.1175 | 6.06 | 266 | 0.5018 | 0.8571 |
60
- | 0.1994 | 7.06 | 304 | 0.1652 | 0.9429 |
61
- | 0.0323 | 8.06 | 342 | 0.0887 | 0.9714 |
62
- | 0.025 | 9.06 | 380 | 0.4416 | 0.8714 |
63
- | 0.0207 | 10.06 | 418 | 0.1090 | 0.9571 |
64
- | 0.0656 | 11.06 | 456 | 0.2511 | 0.9571 |
65
- | 0.004 | 12.06 | 494 | 0.1440 | 0.9571 |
66
- | 0.004 | 13.06 | 532 | 0.0313 | 0.9857 |
67
- | 0.0057 | 14.06 | 570 | 0.0367 | 0.9857 |
68
- | 0.0057 | 15.05 | 600 | 0.0273 | 0.9857 |
69
 
70
 
71
  ### Framework versions
72
 
73
- - Transformers 4.33.1
74
  - Pytorch 1.10.0+cu113
75
  - Datasets 2.14.5
76
  - Tokenizers 0.13.3
 
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: 0.1896
21
+ - Accuracy: 0.9429
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 2
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 1.5443 | 0.25 | 150 | 1.2805 | 0.4714 |
54
+ | 0.7116 | 1.25 | 300 | 0.6705 | 0.7 |
55
+ | 0.122 | 2.25 | 450 | 0.3157 | 0.8857 |
56
+ | 0.0669 | 3.25 | 600 | 0.1896 | 0.9429 |
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
60
 
61
+ - Transformers 4.33.2
62
  - Pytorch 1.10.0+cu113
63
  - Datasets 2.14.5
64
  - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c940d4842db0f0c7a8436eef2f28a5b4219e54d9edb3b1d8f66b1697588c98b
3
  size 345001805
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfb10539a7920d959deb559797b19ab5141ce6794d238476be59a0396d35f598
3
  size 345001805
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f6c75975917b83b9b6fd83c74fa9f5eadc8ccf79ce893c59dadc73072c3a0b2
3
  size 4079
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d1adf7dbad82887a60c198c84e5017cf2cbcad545732394ee9dd0812e874224
3
  size 4079