alexsha commited on
Commit
bc4fac1
1 Parent(s): 82f1c16

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -8
README.md CHANGED
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [alexsha/t5-large-finetuned-English-to-BASH](https://huggingface.co/alexsha/t5-large-finetuned-English-to-BASH) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.6790
18
- - Nl2bash M: 0.8878
19
- - Gen Len: 13.5207
20
 
21
  ## Model description
22
 
@@ -35,21 +35,23 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 6e-05
39
  - train_batch_size: 5
40
  - eval_batch_size: 5
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
- - num_epochs: 3
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Nl2bash M | Gen Len |
49
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
50
- | No log | 1.0 | 387 | 0.6405 | 0.8927 | 13.3223 |
51
- | 0.0699 | 2.0 | 774 | 0.6508 | 0.8898 | 13.5207 |
52
- | 0.0578 | 3.0 | 1161 | 0.6790 | 0.8878 | 13.5207 |
 
 
53
 
54
 
55
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [alexsha/t5-large-finetuned-English-to-BASH](https://huggingface.co/alexsha/t5-large-finetuned-English-to-BASH) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.7159
18
+ - Nl2bash M: 0.8822
19
+ - Gen Len: 13.4256
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 3e-05
39
  - train_batch_size: 5
40
  - eval_batch_size: 5
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 5
45
 
46
  ### Training results
47
 
48
  | Training Loss | Epoch | Step | Validation Loss | Nl2bash M | Gen Len |
49
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
50
+ | No log | 1.0 | 387 | 0.7666 | 0.8897 | 13.2314 |
51
+ | 0.0177 | 2.0 | 774 | 0.7878 | 0.887 | 13.3512 |
52
+ | 0.0188 | 3.0 | 1161 | 0.7580 | 0.8872 | 13.5661 |
53
+ | 0.0461 | 4.0 | 1548 | 0.7121 | 0.8846 | 13.3926 |
54
+ | 0.0461 | 5.0 | 1935 | 0.7159 | 0.8822 | 13.4256 |
55
 
56
 
57
  ### Framework versions