monideep2255 commited on
Commit
26529cb
·
1 Parent(s): 1d0de5f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: spell_correction_M04_LM
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # spell_correction_M04_LM
14
+
15
+ This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.0178
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 1e-05
37
+ - train_batch_size: 16
38
+ - eval_batch_size: 16
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - num_epochs: 30
43
+
44
+ ### Training results
45
+
46
+ | Training Loss | Epoch | Step | Validation Loss |
47
+ |:-------------:|:-----:|:----:|:---------------:|
48
+ | No log | 1.0 | 269 | 0.2687 |
49
+ | 1.8467 | 2.0 | 538 | 0.0361 |
50
+ | 1.8467 | 3.0 | 807 | 0.0241 |
51
+ | 0.0357 | 4.0 | 1076 | 0.0198 |
52
+ | 0.0357 | 5.0 | 1345 | 0.0199 |
53
+ | 0.0159 | 6.0 | 1614 | 0.0175 |
54
+ | 0.0159 | 7.0 | 1883 | 0.0179 |
55
+ | 0.0077 | 8.0 | 2152 | 0.0189 |
56
+ | 0.0077 | 9.0 | 2421 | 0.0183 |
57
+ | 0.006 | 10.0 | 2690 | 0.0183 |
58
+ | 0.006 | 11.0 | 2959 | 0.0191 |
59
+ | 0.0044 | 12.0 | 3228 | 0.0186 |
60
+ | 0.0044 | 13.0 | 3497 | 0.0192 |
61
+ | 0.0033 | 14.0 | 3766 | 0.0189 |
62
+ | 0.0024 | 15.0 | 4035 | 0.0173 |
63
+ | 0.0024 | 16.0 | 4304 | 0.0171 |
64
+ | 0.0026 | 17.0 | 4573 | 0.0183 |
65
+ | 0.0026 | 18.0 | 4842 | 0.0181 |
66
+ | 0.0021 | 19.0 | 5111 | 0.0177 |
67
+ | 0.0021 | 20.0 | 5380 | 0.0174 |
68
+ | 0.0015 | 21.0 | 5649 | 0.0173 |
69
+ | 0.0015 | 22.0 | 5918 | 0.0174 |
70
+ | 0.0016 | 23.0 | 6187 | 0.0178 |
71
+ | 0.0016 | 24.0 | 6456 | 0.0180 |
72
+ | 0.0018 | 25.0 | 6725 | 0.0175 |
73
+ | 0.0018 | 26.0 | 6994 | 0.0171 |
74
+ | 0.0017 | 27.0 | 7263 | 0.0175 |
75
+ | 0.0014 | 28.0 | 7532 | 0.0177 |
76
+ | 0.0014 | 29.0 | 7801 | 0.0178 |
77
+ | 0.0013 | 30.0 | 8070 | 0.0178 |
78
+
79
+
80
+ ### Framework versions
81
+
82
+ - Transformers 4.28.0
83
+ - Pytorch 1.12.1+cu102
84
+ - Datasets 2.13.1
85
+ - Tokenizers 0.13.3