Hugging Face's logo

InfAI
/
flan-t5-text2sparql-custom-tokenizer

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
1
felixb85 commited on
Commit
0bbe640
•
1 Parent(s): 3662a82

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +109 -0
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - lc_quad
7
+ model-index:
8
+ - name: flan-t5-text2sparql-custom-tokenizer
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # flan-t5-text2sparql-custom-tokenizer
16
+
17
+ This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the lc_quad dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.8039
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 16
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 64
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 50
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:-----:|:---------------:|
52
+ | No log | 1.0 | 301 | 2.6503 |
53
+ | 3.2271 | 2.0 | 602 | 2.3894 |
54
+ | 3.2271 | 3.0 | 903 | 2.2532 |
55
+ | 2.3957 | 4.0 | 1204 | 2.1631 |
56
+ | 2.18 | 5.0 | 1505 | 2.0788 |
57
+ | 2.18 | 6.0 | 1806 | 2.0195 |
58
+ | 2.0209 | 7.0 | 2107 | 1.9681 |
59
+ | 2.0209 | 8.0 | 2408 | 1.9353 |
60
+ | 1.9087 | 9.0 | 2709 | 1.8936 |
61
+ | 1.8114 | 10.0 | 3010 | 1.8683 |
62
+ | 1.8114 | 11.0 | 3311 | 1.8556 |
63
+ | 1.7254 | 12.0 | 3612 | 1.8284 |
64
+ | 1.7254 | 13.0 | 3913 | 1.8099 |
65
+ | 1.6556 | 14.0 | 4214 | 1.7932 |
66
+ | 1.5891 | 15.0 | 4515 | 1.7823 |
67
+ | 1.5891 | 16.0 | 4816 | 1.7691 |
68
+ | 1.528 | 17.0 | 5117 | 1.7569 |
69
+ | 1.528 | 18.0 | 5418 | 1.7578 |
70
+ | 1.4784 | 19.0 | 5719 | 1.7561 |
71
+ | 1.4288 | 20.0 | 6020 | 1.7514 |
72
+ | 1.4288 | 21.0 | 6321 | 1.7372 |
73
+ | 1.3793 | 22.0 | 6622 | 1.7318 |
74
+ | 1.3793 | 23.0 | 6923 | 1.7244 |
75
+ | 1.3436 | 24.0 | 7224 | 1.7382 |
76
+ | 1.3073 | 25.0 | 7525 | 1.7254 |
77
+ | 1.3073 | 26.0 | 7826 | 1.7494 |
78
+ | 1.2692 | 27.0 | 8127 | 1.7378 |
79
+ | 1.2692 | 28.0 | 8428 | 1.7387 |
80
+ | 1.242 | 29.0 | 8729 | 1.7290 |
81
+ | 1.2107 | 30.0 | 9030 | 1.7391 |
82
+ | 1.2107 | 31.0 | 9331 | 1.7458 |
83
+ | 1.1817 | 32.0 | 9632 | 1.7528 |
84
+ | 1.1817 | 33.0 | 9933 | 1.7521 |
85
+ | 1.1661 | 34.0 | 10234 | 1.7672 |
86
+ | 1.136 | 35.0 | 10535 | 1.7594 |
87
+ | 1.136 | 36.0 | 10836 | 1.7564 |
88
+ | 1.1216 | 37.0 | 11137 | 1.7670 |
89
+ | 1.1216 | 38.0 | 11438 | 1.7724 |
90
+ | 1.1031 | 39.0 | 11739 | 1.7766 |
91
+ | 1.0834 | 40.0 | 12040 | 1.7756 |
92
+ | 1.0834 | 41.0 | 12341 | 1.7786 |
93
+ | 1.0707 | 42.0 | 12642 | 1.7947 |
94
+ | 1.0707 | 43.0 | 12943 | 1.7931 |
95
+ | 1.058 | 44.0 | 13244 | 1.7925 |
96
+ | 1.0489 | 45.0 | 13545 | 1.7939 |
97
+ | 1.0489 | 46.0 | 13846 | 1.7969 |
98
+ | 1.0421 | 47.0 | 14147 | 1.7982 |
99
+ | 1.0421 | 48.0 | 14448 | 1.7994 |
100
+ | 1.0357 | 49.0 | 14749 | 1.8018 |
101
+ | 1.03 | 50.0 | 15050 | 1.8039 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.18.0
107
+ - Pytorch 1.10.2+cu102
108
+ - Datasets 2.4.0
109
+ - Tokenizers 0.12.1