Hugging Face's logo

mousaazari
/
t5-text2sql

Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
5
mousaazari commited on
Commit
13b272b
·
1 Parent(s): 6016c8f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -17
README.md CHANGED
@@ -12,12 +12,12 @@ should probably proofread and complete it, then remove this comment. -->
12
 
13
  # t5-text2sql
14
 
15
- This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.4421
18
- - Rouge2 Precision: 0.8492
19
- - Rouge2 Recall: 0.37
20
- - Rouge2 Fmeasure: 0.5022
21
 
22
  ## Model description
23
 
@@ -36,28 +36,33 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 0.0002
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
- - num_epochs: 10
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
50
  |:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
51
- | No log | 1.0 | 11 | 1.2891 | 0.3239 | 0.1492 | 0.198 |
52
- | No log | 2.0 | 22 | 0.7482 | 0.728 | 0.3254 | 0.4383 |
53
- | No log | 3.0 | 33 | 0.6458 | 0.7737 | 0.3366 | 0.459 |
54
- | No log | 4.0 | 44 | 0.5512 | 0.8333 | 0.356 | 0.4878 |
55
- | No log | 5.0 | 55 | 0.5363 | 0.8333 | 0.3622 | 0.4925 |
56
- | No log | 6.0 | 66 | 0.4863 | 0.8492 | 0.3702 | 0.5021 |
57
- | No log | 7.0 | 77 | 0.4715 | 0.8413 | 0.3663 | 0.4985 |
58
- | No log | 8.0 | 88 | 0.4629 | 0.8413 | 0.3663 | 0.4985 |
59
- | No log | 9.0 | 99 | 0.4397 | 0.8492 | 0.37 | 0.5022 |
60
- | No log | 10.0 | 110 | 0.4421 | 0.8492 | 0.37 | 0.5022 |
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
12
 
13
  # t5-text2sql
14
 
15
+ This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.3871
18
+ - Rouge2 Precision: 0.8193
19
+ - Rouge2 Recall: 0.3626
20
+ - Rouge2 Fmeasure: 0.4892
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
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
+ - num_epochs: 15
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
50
  |:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
51
+ | No log | 1.0 | 11 | 0.9569 | 0.5762 | 0.2782 | 0.3687 |
52
+ | No log | 2.0 | 22 | 0.6312 | 0.7367 | 0.3368 | 0.4544 |
53
+ | No log | 3.0 | 33 | 0.5001 | 0.7897 | 0.3453 | 0.4689 |
54
+ | No log | 4.0 | 44 | 0.4478 | 0.8433 | 0.3766 | 0.5072 |
55
+ | No log | 5.0 | 55 | 0.4313 | 0.8294 | 0.3669 | 0.4949 |
56
+ | No log | 6.0 | 66 | 0.3951 | 0.837 | 0.3681 | 0.4973 |
57
+ | No log | 7.0 | 77 | 0.4019 | 0.8413 | 0.3713 | 0.5007 |
58
+ | No log | 8.0 | 88 | 0.4036 | 0.8452 | 0.3726 | 0.5026 |
59
+ | No log | 9.0 | 99 | 0.4190 | 0.8452 | 0.3726 | 0.5026 |
60
+ | No log | 10.0 | 110 | 0.4127 | 0.8093 | 0.3531 | 0.4801 |
61
+ | No log | 11.0 | 121 | 0.3723 | 0.8193 | 0.3626 | 0.4892 |
62
+ | No log | 12.0 | 132 | 0.3776 | 0.8093 | 0.3531 | 0.4801 |
63
+ | No log | 13.0 | 143 | 0.3837 | 0.8193 | 0.3626 | 0.4892 |
64
+ | No log | 14.0 | 154 | 0.3880 | 0.8193 | 0.3626 | 0.4892 |
65
+ | No log | 15.0 | 165 | 0.3871 | 0.8193 | 0.3626 | 0.4892 |
66
 
67
 
68
  ### Framework versions