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
31c2cb9
·
1 Parent(s): a35591a

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -20
README.md CHANGED
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.3872
18
- - Rouge2 Precision: 0.9167
19
- - Rouge2 Recall: 0.4191
20
- - Rouge2 Fmeasure: 0.5619
21
 
22
  ## Model description
23
 
@@ -42,27 +42,22 @@ The following hyperparameters were used during training:
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 | 2.0397 | 0.0179 | 0.0033 | 0.0055 |
52
- | No log | 2.0 | 22 | 1.1572 | 0.3278 | 0.158 | 0.2048 |
53
- | No log | 3.0 | 33 | 0.8159 | 0.7687 | 0.3739 | 0.4931 |
54
- | No log | 4.0 | 44 | 0.6403 | 0.8662 | 0.4083 | 0.5439 |
55
- | No log | 5.0 | 55 | 0.5431 | 0.8654 | 0.3959 | 0.5348 |
56
- | No log | 6.0 | 66 | 0.4982 | 0.9156 | 0.4199 | 0.5638 |
57
- | No log | 7.0 | 77 | 0.4647 | 0.9008 | 0.4137 | 0.5542 |
58
- | No log | 8.0 | 88 | 0.4433 | 0.8961 | 0.4119 | 0.5527 |
59
- | No log | 9.0 | 99 | 0.4352 | 0.8929 | 0.4073 | 0.547 |
60
- | No log | 10.0 | 110 | 0.4132 | 0.9167 | 0.4191 | 0.5619 |
61
- | No log | 11.0 | 121 | 0.3973 | 0.9167 | 0.4191 | 0.5619 |
62
- | No log | 12.0 | 132 | 0.3918 | 0.9206 | 0.4227 | 0.567 |
63
- | No log | 13.0 | 143 | 0.3861 | 0.9206 | 0.4227 | 0.567 |
64
- | No log | 14.0 | 154 | 0.3869 | 0.9167 | 0.4191 | 0.5619 |
65
- | No log | 15.0 | 165 | 0.3872 | 0.9167 | 0.4191 | 0.5619 |
66
 
67
 
68
  ### Framework versions
 
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: 0.6322
18
+ - Rouge2 Precision: 0.7724
19
+ - Rouge2 Recall: 0.3399
20
+ - Rouge2 Fmeasure: 0.4581
21
 
22
  ## Model description
23
 
 
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 | 2.2055 | 0.0295 | 0.0079 | 0.0125 |
52
+ | No log | 2.0 | 22 | 1.3842 | 0.2474 | 0.12 | 0.1538 |
53
+ | No log | 3.0 | 33 | 0.9508 | 0.5971 | 0.3019 | 0.3938 |
54
+ | No log | 4.0 | 44 | 0.7835 | 0.7738 | 0.3436 | 0.4646 |
55
+ | No log | 5.0 | 55 | 0.7125 | 0.7635 | 0.3364 | 0.4561 |
56
+ | No log | 6.0 | 66 | 0.6709 | 0.7605 | 0.3407 | 0.4582 |
57
+ | No log | 7.0 | 77 | 0.6626 | 0.7868 | 0.3493 | 0.471 |
58
+ | No log | 8.0 | 88 | 0.6443 | 0.7684 | 0.3393 | 0.4578 |
59
+ | No log | 9.0 | 99 | 0.6320 | 0.7724 | 0.3399 | 0.4581 |
60
+ | No log | 10.0 | 110 | 0.6322 | 0.7724 | 0.3399 | 0.4581 |
 
 
 
 
 
61
 
62
 
63
  ### Framework versions