ShuaHousetable commited on
Commit
1a736bf
1 Parent(s): 6ade82b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -9
README.md CHANGED
@@ -14,8 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 3.5140
18
- - Rmse: 1.8746
19
 
20
  ## Model description
21
 
@@ -34,24 +34,27 @@ More information needed
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
- - learning_rate: 1e-05
38
  - train_batch_size: 16
39
  - eval_batch_size: 64
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 500
44
- - num_epochs: 5
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Rmse |
49
  |:-------------:|:-----:|:----:|:---------------:|:------:|
50
- | No log | 1.0 | 134 | 3.5140 | 1.8746 |
51
- | No log | 2.0 | 268 | 1.6198 | 1.2727 |
52
- | No log | 3.0 | 402 | 0.9386 | 0.9688 |
53
- | 8.1621 | 4.0 | 536 | 0.8200 | 0.9056 |
54
- | 8.1621 | 5.0 | 670 | 0.7409 | 0.8607 |
 
 
 
55
 
56
 
57
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 1.1685
18
+ - Rmse: 1.0810
19
 
20
  ## Model description
21
 
 
34
  ### Training hyperparameters
35
 
36
  The following hyperparameters were used during training:
37
+ - learning_rate: 0.0002
38
  - train_batch_size: 16
39
  - eval_batch_size: 64
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
  - lr_scheduler_warmup_steps: 500
44
+ - num_epochs: 8
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Rmse |
49
  |:-------------:|:-----:|:----:|:---------------:|:------:|
50
+ | No log | 1.0 | 101 | 1.2101 | 1.1001 |
51
+ | No log | 2.0 | 202 | 0.7917 | 0.8898 |
52
+ | No log | 3.0 | 303 | 1.0430 | 1.0213 |
53
+ | No log | 4.0 | 404 | 0.9290 | 0.9639 |
54
+ | 2.8472 | 5.0 | 505 | 0.6923 | 0.8321 |
55
+ | 2.8472 | 6.0 | 606 | 0.8079 | 0.8989 |
56
+ | 2.8472 | 7.0 | 707 | 0.7159 | 0.8461 |
57
+ | 2.8472 | 8.0 | 808 | 0.6934 | 0.8327 |
58
 
59
 
60
  ### Framework versions