Hugging Face's logo

Michelvh
/
flan-small-mc-question-options-generation

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
Michelvh commited on
Commit
f0d0c9f
•
1 Parent(s): 741b093

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +101 -0
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: google/flan-t5-small
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - race
8
+ model-index:
9
+ - name: flan-small-mc-question-options-generation
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # flan-small-mc-question-options-generation
17
+
18
+ This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the race dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 1.5747
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 4
41
+ - eval_batch_size: 4
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 16
44
+ - total_train_batch_size: 64
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: linear
47
+ - num_epochs: 3
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 4.3811 | 0.07 | 100 | 2.4007 |
54
+ | 2.5622 | 0.15 | 200 | 2.0431 |
55
+ | 2.2498 | 0.22 | 300 | 1.9139 |
56
+ | 2.1136 | 0.29 | 400 | 1.8218 |
57
+ | 2.0392 | 0.36 | 500 | 1.7739 |
58
+ | 1.9984 | 0.44 | 600 | 1.7237 |
59
+ | 1.9519 | 0.51 | 700 | 1.7058 |
60
+ | 1.928 | 0.58 | 800 | 1.6900 |
61
+ | 1.9075 | 0.66 | 900 | 1.6687 |
62
+ | 1.8968 | 0.73 | 1000 | 1.6631 |
63
+ | 1.8758 | 0.8 | 1100 | 1.6519 |
64
+ | 1.8863 | 0.87 | 1200 | 1.6431 |
65
+ | 1.869 | 0.95 | 1300 | 1.6409 |
66
+ | 1.8483 | 1.02 | 1400 | 1.6313 |
67
+ | 1.8344 | 1.09 | 1500 | 1.6279 |
68
+ | 1.8398 | 1.17 | 1600 | 1.6183 |
69
+ | 1.8247 | 1.24 | 1700 | 1.6223 |
70
+ | 1.8131 | 1.31 | 1800 | 1.6072 |
71
+ | 1.8024 | 1.38 | 1900 | 1.6096 |
72
+ | 1.8038 | 1.46 | 2000 | 1.6056 |
73
+ | 1.8051 | 1.53 | 2100 | 1.6030 |
74
+ | 1.7875 | 1.6 | 2200 | 1.6008 |
75
+ | 1.7983 | 1.68 | 2300 | 1.5923 |
76
+ | 1.7922 | 1.75 | 2400 | 1.5917 |
77
+ | 1.7892 | 1.82 | 2500 | 1.5903 |
78
+ | 1.784 | 1.89 | 2600 | 1.5891 |
79
+ | 1.7844 | 1.97 | 2700 | 1.5867 |
80
+ | 1.7678 | 2.04 | 2800 | 1.5837 |
81
+ | 1.7558 | 2.11 | 2900 | 1.5826 |
82
+ | 1.7702 | 2.19 | 3000 | 1.5820 |
83
+ | 1.7669 | 2.26 | 3100 | 1.5802 |
84
+ | 1.7715 | 2.33 | 3200 | 1.5763 |
85
+ | 1.7724 | 2.4 | 3300 | 1.5799 |
86
+ | 1.757 | 2.48 | 3400 | 1.5783 |
87
+ | 1.7648 | 2.55 | 3500 | 1.5763 |
88
+ | 1.7691 | 2.62 | 3600 | 1.5772 |
89
+ | 1.7607 | 2.69 | 3700 | 1.5758 |
90
+ | 1.7574 | 2.77 | 3800 | 1.5745 |
91
+ | 1.7586 | 2.84 | 3900 | 1.5748 |
92
+ | 1.7583 | 2.91 | 4000 | 1.5745 |
93
+ | 1.7611 | 2.99 | 4100 | 1.5747 |
94
+
95
+
96
+ ### Framework versions
97
+
98
+ - Transformers 4.31.0
99
+ - Pytorch 2.0.0
100
+ - Datasets 2.1.0
101
+ - Tokenizers 0.13.3