Ymanz commited on
Commit
fda8bcd
1 Parent(s): 0e66009

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: videomae-base-finetuned-ucf101-subset
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # videomae-base-finetuned-ucf101-subset
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: 0.4846
20
+ - Accuracy: 0.8516
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_ratio: 0.1
46
+ - training_steps: 148
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 2.1377 | 0.26 | 38 | 1.8102 | 0.4714 |
53
+ | 0.8527 | 1.26 | 76 | 0.8992 | 0.7143 |
54
+ | 0.4023 | 2.26 | 114 | 0.4369 | 0.8429 |
55
+ | 0.2852 | 3.23 | 148 | 0.3679 | 0.9143 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.28.1
61
+ - Pytorch 2.0.0+cu117
62
+ - Datasets 2.11.0
63
+ - Tokenizers 0.13.3