Hugging Face's logo

mousaazari
/
t5-text2sql

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
5
mousaazari commited on
Commit
892d453
·
1 Parent(s): a6df5a7

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +35 -35
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: 0.0486
18
- - Rouge2 Precision: 0.9235
19
- - Rouge2 Recall: 0.253
20
- - Rouge2 Fmeasure: 0.3774
21
 
22
  ## Model description
23
 
@@ -48,41 +48,41 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
50
  |:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
51
- | No log | 1.0 | 11 | 0.6926 | 0.0068 | 0.0008 | 0.0015 |
52
- | No log | 2.0 | 22 | 0.3266 | 0.0264 | 0.0026 | 0.0046 |
53
- | No log | 3.0 | 33 | 0.1675 | 0.678 | 0.2014 | 0.2945 |
54
- | No log | 4.0 | 44 | 0.1130 | 0.8063 | 0.2665 | 0.3779 |
55
- | No log | 5.0 | 55 | 0.0866 | 0.8433 | 0.2267 | 0.3401 |
56
- | No log | 6.0 | 66 | 0.0743 | 0.896 | 0.2525 | 0.3738 |
57
- | No log | 7.0 | 77 | 0.0657 | 0.9045 | 0.2492 | 0.3715 |
58
- | No log | 8.0 | 88 | 0.0590 | 0.9028 | 0.2484 | 0.3703 |
59
- | No log | 9.0 | 99 | 0.0561 | 0.9162 | 0.261 | 0.3849 |
60
- | No log | 10.0 | 110 | 0.0552 | 0.9127 | 0.2602 | 0.3838 |
61
- | No log | 11.0 | 121 | 0.0558 | 0.9068 | 0.2554 | 0.3775 |
62
- | No log | 12.0 | 132 | 0.0515 | 0.9096 | 0.2554 | 0.3776 |
63
- | No log | 13.0 | 143 | 0.0512 | 0.904 | 0.2516 | 0.3733 |
64
- | No log | 14.0 | 154 | 0.0507 | 0.9128 | 0.2546 | 0.3776 |
65
- | No log | 15.0 | 165 | 0.0508 | 0.9156 | 0.2526 | 0.3762 |
66
- | No log | 16.0 | 176 | 0.0476 | 0.9116 | 0.252 | 0.3751 |
67
- | No log | 17.0 | 187 | 0.0502 | 0.9235 | 0.2544 | 0.379 |
68
- | No log | 18.0 | 198 | 0.0487 | 0.9235 | 0.253 | 0.3774 |
69
- | No log | 19.0 | 209 | 0.0474 | 0.9235 | 0.253 | 0.3774 |
70
- | No log | 20.0 | 220 | 0.0503 | 0.9241 | 0.2568 | 0.3813 |
71
- | No log | 21.0 | 231 | 0.0500 | 0.9235 | 0.253 | 0.3774 |
72
- | No log | 22.0 | 242 | 0.0494 | 0.9156 | 0.2515 | 0.3751 |
73
- | No log | 23.0 | 253 | 0.0505 | 0.9235 | 0.253 | 0.3774 |
74
- | No log | 24.0 | 264 | 0.0487 | 0.9235 | 0.253 | 0.3774 |
75
- | No log | 25.0 | 275 | 0.0489 | 0.9235 | 0.2526 | 0.3767 |
76
- | No log | 26.0 | 286 | 0.0485 | 0.9235 | 0.253 | 0.3774 |
77
- | No log | 27.0 | 297 | 0.0479 | 0.9235 | 0.253 | 0.3774 |
78
- | No log | 28.0 | 308 | 0.0482 | 0.9235 | 0.253 | 0.3774 |
79
- | No log | 29.0 | 319 | 0.0486 | 0.9235 | 0.253 | 0.3774 |
80
- | No log | 30.0 | 330 | 0.0486 | 0.9235 | 0.253 | 0.3774 |
81
 
82
 
83
  ### Framework versions
84
 
85
- - Transformers 4.21.1
86
  - Pytorch 1.12.1+cu113
87
  - Datasets 2.4.0
88
  - Tokenizers 0.12.1
 
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: 0.0593
18
+ - Rouge2 Precision: 0.7821
19
+ - Rouge2 Recall: 0.1774
20
+ - Rouge2 Fmeasure: 0.2845
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
50
  |:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
51
+ | No log | 1.0 | 50 | 0.1988 | 0.5696 | 0.141 | 0.2222 |
52
+ | No log | 2.0 | 100 | 0.1259 | 0.6107 | 0.1385 | 0.2226 |
53
+ | No log | 3.0 | 150 | 0.0957 | 0.6533 | 0.1461 | 0.2352 |
54
+ | No log | 4.0 | 200 | 0.0822 | 0.665 | 0.1494 | 0.2402 |
55
+ | No log | 5.0 | 250 | 0.0776 | 0.691 | 0.1569 | 0.2518 |
56
+ | No log | 6.0 | 300 | 0.0693 | 0.6893 | 0.1544 | 0.2486 |
57
+ | No log | 7.0 | 350 | 0.0676 | 0.6966 | 0.1614 | 0.2583 |
58
+ | No log | 8.0 | 400 | 0.0653 | 0.7006 | 0.1578 | 0.2537 |
59
+ | No log | 9.0 | 450 | 0.0628 | 0.6784 | 0.152 | 0.2445 |
60
+ | 0.1876 | 10.0 | 500 | 0.0612 | 0.7203 | 0.1628 | 0.2615 |
61
+ | 0.1876 | 11.0 | 550 | 0.0615 | 0.7378 | 0.1673 | 0.2688 |
62
+ | 0.1876 | 12.0 | 600 | 0.0595 | 0.7161 | 0.1599 | 0.2573 |
63
+ | 0.1876 | 13.0 | 650 | 0.0588 | 0.7317 | 0.1659 | 0.2661 |
64
+ | 0.1876 | 14.0 | 700 | 0.0595 | 0.6959 | 0.1589 | 0.2542 |
65
+ | 0.1876 | 15.0 | 750 | 0.0576 | 0.74 | 0.167 | 0.2686 |
66
+ | 0.1876 | 16.0 | 800 | 0.0590 | 0.7149 | 0.1611 | 0.2587 |
67
+ | 0.1876 | 17.0 | 850 | 0.0574 | 0.7398 | 0.1664 | 0.2674 |
68
+ | 0.1876 | 18.0 | 900 | 0.0574 | 0.7557 | 0.171 | 0.2749 |
69
+ | 0.1876 | 19.0 | 950 | 0.0618 | 0.7366 | 0.1671 | 0.2676 |
70
+ | 0.0344 | 20.0 | 1000 | 0.0583 | 0.7692 | 0.1764 | 0.2821 |
71
+ | 0.0344 | 21.0 | 1050 | 0.0606 | 0.7757 | 0.1762 | 0.2823 |
72
+ | 0.0344 | 22.0 | 1100 | 0.0582 | 0.7622 | 0.1747 | 0.2795 |
73
+ | 0.0344 | 23.0 | 1150 | 0.0595 | 0.7677 | 0.1747 | 0.2798 |
74
+ | 0.0344 | 24.0 | 1200 | 0.0589 | 0.767 | 0.1726 | 0.2763 |
75
+ | 0.0344 | 25.0 | 1250 | 0.0587 | 0.7797 | 0.1769 | 0.2836 |
76
+ | 0.0344 | 26.0 | 1300 | 0.0584 | 0.7713 | 0.1748 | 0.2803 |
77
+ | 0.0344 | 27.0 | 1350 | 0.0583 | 0.7854 | 0.1779 | 0.2854 |
78
+ | 0.0344 | 28.0 | 1400 | 0.0590 | 0.7829 | 0.1783 | 0.2857 |
79
+ | 0.0344 | 29.0 | 1450 | 0.0592 | 0.7876 | 0.1786 | 0.2864 |
80
+ | 0.0227 | 30.0 | 1500 | 0.0593 | 0.7821 | 0.1774 | 0.2845 |
81
 
82
 
83
  ### Framework versions
84
 
85
+ - Transformers 4.21.2
86
  - Pytorch 1.12.1+cu113
87
  - Datasets 2.4.0
88
  - Tokenizers 0.12.1