lmazzon70 commited on
Commit
2bb6644
1 Parent(s): 9d0612c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +77 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-short-finetuned-ssv2-finetuned-rwf2000-epochs8-batch8
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-short-finetuned-ssv2-finetuned-rwf2000-epochs8-batch8
16
+
17
+ This model is a fine-tuned version of [MCG-NJU/videomae-base-short-finetuned-ssv2](https://huggingface.co/MCG-NJU/videomae-base-short-finetuned-ssv2) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.7821
20
+ - Accuracy: 0.6713
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: 2
41
+ - eval_batch_size: 2
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 8
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: 3200
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
54
+ | 0.4247 | 0.06 | 200 | 0.4205 | 0.8063 |
55
+ | 0.4125 | 1.06 | 400 | 0.6749 | 0.72 |
56
+ | 0.3265 | 2.06 | 600 | 1.3838 | 0.5763 |
57
+ | 0.2204 | 3.06 | 800 | 0.6725 | 0.7275 |
58
+ | 0.2965 | 4.06 | 1000 | 0.4583 | 0.8263 |
59
+ | 0.1883 | 5.06 | 1200 | 0.3786 | 0.8488 |
60
+ | 0.1321 | 6.06 | 1400 | 1.6632 | 0.5962 |
61
+ | 0.369 | 7.06 | 1600 | 0.6018 | 0.8063 |
62
+ | 0.3764 | 8.06 | 1800 | 0.8546 | 0.74 |
63
+ | 0.2401 | 9.06 | 2000 | 0.5422 | 0.825 |
64
+ | 0.1943 | 10.06 | 2200 | 0.5868 | 0.8113 |
65
+ | 0.1352 | 11.06 | 2400 | 0.7111 | 0.8063 |
66
+ | 0.2276 | 12.06 | 2600 | 0.8847 | 0.7812 |
67
+ | 0.149 | 13.06 | 2800 | 0.8581 | 0.7837 |
68
+ | 0.0848 | 14.06 | 3000 | 0.8707 | 0.7788 |
69
+ | 0.046 | 15.06 | 3200 | 0.7914 | 0.7963 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.25.1
75
+ - Pytorch 1.13.1+cu117
76
+ - Datasets 2.8.0
77
+ - Tokenizers 0.13.2