onarganogun commited on
Commit
ff073da
1 Parent(s): b8d5f1e

Model save

Browse files
Files changed (1) hide show
  1. README.md +65 -0
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ base_model: MCG-NJU/videomae-large
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: videomae-large-cctv-brawl_extended_v1
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # videomae-large-cctv-brawl_extended_v1
17
+
18
+ This model is a fine-tuned version of [MCG-NJU/videomae-large](https://huggingface.co/MCG-NJU/videomae-large) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.4430
21
+ - Accuracy: 0.8252
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 3e-07
41
+ - train_batch_size: 4
42
+ - eval_batch_size: 4
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: 12565
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|
53
+ | 0.4193 | 0.2 | 2514 | 0.4839 | 0.6985 |
54
+ | 0.3542 | 1.2 | 5028 | 0.4445 | 0.7593 |
55
+ | 0.2673 | 2.2 | 7542 | 0.4344 | 0.7993 |
56
+ | 0.3185 | 3.2 | 10056 | 0.4328 | 0.8201 |
57
+ | 0.4006 | 4.2 | 12565 | 0.4430 | 0.8252 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.34.1
63
+ - Pytorch 2.1.0+cu118
64
+ - Datasets 2.14.6
65
+ - Tokenizers 0.14.1