Hugging Face's logo

anvaldesg
/
videomae-base-finetuned-ucf101-subset

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
anvaldesg commited on
Commit
2beaacb
•
1 Parent(s): 14233b8

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -9
  2. runs/Sep24_21-08-44_18bbd82beced/events.out.tfevents.1727212125.18bbd82beced.13077.0 +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.1396
20
 
21
  ## Model description
22
 
@@ -35,25 +35,29 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 5e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_ratio: 0.1
45
- - training_steps: 222
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:------:|:----:|:---------------:|
51
- | 2.1576 | 0.1712 | 38 | 1.9715 |
52
- | 1.1372 | 1.1712 | 76 | 0.8458 |
53
- | 0.4724 | 2.1712 | 114 | 0.4988 |
54
- | 0.2455 | 3.1712 | 152 | 0.2680 |
55
- | 0.0681 | 4.1712 | 190 | 0.1476 |
56
- | 0.0682 | 5.1441 | 222 | 0.1396 |
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.8688
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
  - train_batch_size: 8
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_ratio: 0.1
45
+ - training_steps: 370
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:------:|:----:|:---------------:|
51
+ | 2.3516 | 0.1027 | 38 | 2.2951 |
52
+ | 2.1851 | 1.1027 | 76 | 2.1559 |
53
+ | 1.9452 | 2.1027 | 114 | 1.9531 |
54
+ | 1.6471 | 3.1027 | 152 | 1.6395 |
55
+ | 1.255 | 4.1027 | 190 | 1.3609 |
56
+ | 1.0922 | 5.1027 | 228 | 1.1511 |
57
+ | 0.7825 | 6.1027 | 266 | 1.0092 |
58
+ | 0.7033 | 7.1027 | 304 | 0.9361 |
59
+ | 0.5924 | 8.1027 | 342 | 0.8911 |
60
+ | 0.616 | 9.0757 | 370 | 0.8688 |
61
 
62
 
63
  ### Framework versions
runs/Sep24_21-08-44_18bbd82beced/events.out.tfevents.1727212125.18bbd82beced.13077.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bd7be967af17b20e081c97a3772a93878d60441abde12fb6de1a96db89fda3e
3
- size 15780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87f8a886d7ee2f47d0c5f959dd0309fab3d1b5894ca52c12e93afd7004ea9aba
3
+ size 16405