Hugging Face's logo

JEdward7777
/
finetuned-xlm-r-masakhaner-swa-whole-word-phonetic

Fill-Mask
Transformers
PyTorch
TensorBoard
xlm-roberta
Generated from Trainer
Model card Files Metrics Community
1
JEdward7777 commited on
Commit
f9db674
·
1 Parent(s): 8278626

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +53 -13
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 8.1903
18
 
19
  ## Model description
20
 
@@ -33,28 +33,68 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - learning_rate: 2e-05
37
  - train_batch_size: 8
38
  - eval_batch_size: 8
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
- - num_epochs: 10
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
- | No log | 1.0 | 84 | 8.4449 |
49
- | No log | 2.0 | 168 | 8.2529 |
50
- | No log | 3.0 | 252 | 8.0750 |
51
- | No log | 4.0 | 336 | 8.1452 |
52
- | No log | 5.0 | 420 | 8.1334 |
53
- | 8.2835 | 6.0 | 504 | 8.1795 |
54
- | 8.2835 | 7.0 | 588 | 8.3774 |
55
- | 8.2835 | 8.0 | 672 | 8.2166 |
56
- | 8.2835 | 9.0 | 756 | 8.1744 |
57
- | 8.2835 | 10.0 | 840 | 8.1903 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 11.2301
18
 
19
  ## Model description
20
 
 
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
+ - learning_rate: 2e-07
37
  - train_batch_size: 8
38
  - eval_batch_size: 8
39
  - seed: 42
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: linear
42
+ - num_epochs: 50
43
 
44
  ### Training results
45
 
46
  | Training Loss | Epoch | Step | Validation Loss |
47
  |:-------------:|:-----:|:----:|:---------------:|
48
+ | No log | 1.0 | 62 | 38.7304 |
49
+ | No log | 2.0 | 124 | 37.1806 |
50
+ | No log | 3.0 | 186 | 33.3488 |
51
+ | No log | 4.0 | 248 | 28.7715 |
52
+ | No log | 5.0 | 310 | 24.8965 |
53
+ | No log | 6.0 | 372 | 21.4066 |
54
+ | No log | 7.0 | 434 | 19.1665 |
55
+ | No log | 8.0 | 496 | 17.3087 |
56
+ | 29.5022 | 9.0 | 558 | 15.5323 |
57
+ | 29.5022 | 10.0 | 620 | 14.4497 |
58
+ | 29.5022 | 11.0 | 682 | 14.1622 |
59
+ | 29.5022 | 12.0 | 744 | 13.7512 |
60
+ | 29.5022 | 13.0 | 806 | 13.3941 |
61
+ | 29.5022 | 14.0 | 868 | 13.0215 |
62
+ | 29.5022 | 15.0 | 930 | 12.8363 |
63
+ | 29.5022 | 16.0 | 992 | 12.6596 |
64
+ | 13.2409 | 17.0 | 1054 | 12.5914 |
65
+ | 13.2409 | 18.0 | 1116 | 12.2895 |
66
+ | 13.2409 | 19.0 | 1178 | 12.2700 |
67
+ | 13.2409 | 20.0 | 1240 | 12.1427 |
68
+ | 13.2409 | 21.0 | 1302 | 12.1344 |
69
+ | 13.2409 | 22.0 | 1364 | 12.0623 |
70
+ | 13.2409 | 23.0 | 1426 | 12.0630 |
71
+ | 13.2409 | 24.0 | 1488 | 12.0983 |
72
+ | 11.0242 | 25.0 | 1550 | 11.7902 |
73
+ | 11.0242 | 26.0 | 1612 | 11.8626 |
74
+ | 11.0242 | 27.0 | 1674 | 11.9154 |
75
+ | 11.0242 | 28.0 | 1736 | 11.6483 |
76
+ | 11.0242 | 29.0 | 1798 | 11.8620 |
77
+ | 11.0242 | 30.0 | 1860 | 11.5987 |
78
+ | 11.0242 | 31.0 | 1922 | 11.7633 |
79
+ | 11.0242 | 32.0 | 1984 | 11.7000 |
80
+ | 10.5931 | 33.0 | 2046 | 11.6631 |
81
+ | 10.5931 | 34.0 | 2108 | 11.4315 |
82
+ | 10.5931 | 35.0 | 2170 | 11.5619 |
83
+ | 10.5931 | 36.0 | 2232 | 11.5930 |
84
+ | 10.5931 | 37.0 | 2294 | 11.5537 |
85
+ | 10.5931 | 38.0 | 2356 | 11.6703 |
86
+ | 10.5931 | 39.0 | 2418 | 11.5488 |
87
+ | 10.5931 | 40.0 | 2480 | 11.4440 |
88
+ | 10.4503 | 41.0 | 2542 | 11.3210 |
89
+ | 10.4503 | 42.0 | 2604 | 11.4373 |
90
+ | 10.4503 | 43.0 | 2666 | 11.4868 |
91
+ | 10.4503 | 44.0 | 2728 | 11.3895 |
92
+ | 10.4503 | 45.0 | 2790 | 11.4097 |
93
+ | 10.4503 | 46.0 | 2852 | 11.5567 |
94
+ | 10.4503 | 47.0 | 2914 | 11.3519 |
95
+ | 10.4503 | 48.0 | 2976 | 11.3263 |
96
+ | 10.4239 | 49.0 | 3038 | 11.4049 |
97
+ | 10.4239 | 50.0 | 3100 | 11.2301 |
98
 
99
 
100
  ### Framework versions