Hugging Face's logo

yale-cultural-heritage
/
name-parser-model

Transformers
TensorBoard
Safetensors
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
wjbmattingly commited on
Commit
b93c8b8
·
verified ·
1 Parent(s): 833ab96

End of training

Browse files
Files changed (2) hide show
  1. README.md +17 -57
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
- base_model: t5-base
5
  tags:
6
  - generated_from_trainer
7
  metrics:
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # name-parser-model
18
 
19
- This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0113
22
- - Accuracy: 0.9924
23
 
24
  ## Model description
25
 
@@ -47,63 +47,23 @@ The following hyperparameters were used during training:
47
  - optimizer: Use adafactor and the args are:
48
  No additional optimizer arguments
49
  - lr_scheduler_type: linear
50
- - training_steps: 1000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
- |:-------------:|:-------:|:----:|:---------------:|:--------:|
57
- | No log | 1.2540 | 20 | 5.6788 | 0.4187 |
58
- | No log | 2.5079 | 40 | 0.6299 | 0.5176 |
59
- | No log | 3.7619 | 60 | 0.2964 | 0.6436 |
60
- | No log | 5.0 | 80 | 0.1270 | 0.8712 |
61
- | No log | 6.2540 | 100 | 0.0709 | 0.9502 |
62
- | No log | 7.5079 | 120 | 0.0490 | 0.9617 |
63
- | No log | 8.7619 | 140 | 0.0349 | 0.9704 |
64
- | No log | 10.0 | 160 | 0.0259 | 0.9855 |
65
- | No log | 11.2540 | 180 | 0.0222 | 0.9862 |
66
- | No log | 12.5079 | 200 | 0.0206 | 0.9873 |
67
- | No log | 13.7619 | 220 | 0.0194 | 0.9872 |
68
- | No log | 15.0 | 240 | 0.0177 | 0.9885 |
69
- | No log | 16.2540 | 260 | 0.0168 | 0.9888 |
70
- | No log | 17.5079 | 280 | 0.0161 | 0.9898 |
71
- | No log | 18.7619 | 300 | 0.0157 | 0.9899 |
72
- | No log | 20.0 | 320 | 0.0149 | 0.9903 |
73
- | No log | 21.2540 | 340 | 0.0148 | 0.9908 |
74
- | No log | 22.5079 | 360 | 0.0143 | 0.9903 |
75
- | No log | 23.7619 | 380 | 0.0138 | 0.9902 |
76
- | No log | 25.0 | 400 | 0.0137 | 0.9904 |
77
- | No log | 26.2540 | 420 | 0.0134 | 0.9907 |
78
- | No log | 27.5079 | 440 | 0.0131 | 0.9911 |
79
- | No log | 28.7619 | 460 | 0.0130 | 0.9913 |
80
- | No log | 30.0 | 480 | 0.0128 | 0.9915 |
81
- | 0.6611 | 31.2540 | 500 | 0.0128 | 0.9913 |
82
- | 0.6611 | 32.5079 | 520 | 0.0124 | 0.9915 |
83
- | 0.6611 | 33.7619 | 540 | 0.0125 | 0.9913 |
84
- | 0.6611 | 35.0 | 560 | 0.0123 | 0.9915 |
85
- | 0.6611 | 36.2540 | 580 | 0.0122 | 0.9913 |
86
- | 0.6611 | 37.5079 | 600 | 0.0121 | 0.9915 |
87
- | 0.6611 | 38.7619 | 620 | 0.0121 | 0.9916 |
88
- | 0.6611 | 40.0 | 640 | 0.0120 | 0.9918 |
89
- | 0.6611 | 41.2540 | 660 | 0.0118 | 0.9918 |
90
- | 0.6611 | 42.5079 | 680 | 0.0118 | 0.9918 |
91
- | 0.6611 | 43.7619 | 700 | 0.0117 | 0.9920 |
92
- | 0.6611 | 45.0 | 720 | 0.0115 | 0.9922 |
93
- | 0.6611 | 46.2540 | 740 | 0.0114 | 0.9924 |
94
- | 0.6611 | 47.5079 | 760 | 0.0114 | 0.9921 |
95
- | 0.6611 | 48.7619 | 780 | 0.0115 | 0.9922 |
96
- | 0.6611 | 50.0 | 800 | 0.0115 | 0.9921 |
97
- | 0.6611 | 51.2540 | 820 | 0.0115 | 0.9921 |
98
- | 0.6611 | 52.5079 | 840 | 0.0114 | 0.9922 |
99
- | 0.6611 | 53.7619 | 860 | 0.0114 | 0.9923 |
100
- | 0.6611 | 55.0 | 880 | 0.0114 | 0.9925 |
101
- | 0.6611 | 56.2540 | 900 | 0.0113 | 0.9923 |
102
- | 0.6611 | 57.5079 | 920 | 0.0113 | 0.9923 |
103
- | 0.6611 | 58.7619 | 940 | 0.0113 | 0.9924 |
104
- | 0.6611 | 60.0 | 960 | 0.0113 | 0.9924 |
105
- | 0.6611 | 61.2540 | 980 | 0.0113 | 0.9924 |
106
- | 0.0127 | 62.5079 | 1000 | 0.0113 | 0.9924 |
107
 
108
 
109
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
  license: apache-2.0
4
+ base_model: yale-cultural-heritage/name-parser-model
5
  tags:
6
  - generated_from_trainer
7
  metrics:
 
16
 
17
  # name-parser-model
18
 
19
+ This model is a fine-tuned version of [yale-cultural-heritage/name-parser-model](https://huggingface.co/yale-cultural-heritage/name-parser-model) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0332
22
+ - Accuracy: 0.9921
23
 
24
  ## Model description
25
 
 
47
  - optimizer: Use adafactor and the args are:
48
  No additional optimizer arguments
49
  - lr_scheduler_type: linear
50
+ - training_steps: 10000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
56
+ |:-------------:|:-------:|:-----:|:---------------:|:--------:|
57
+ | 0.041 | 3.1952 | 1000 | 0.0352 | 0.9912 |
58
+ | 0.0369 | 6.3904 | 2000 | 0.0345 | 0.9915 |
59
+ | 0.0358 | 9.5856 | 3000 | 0.0336 | 0.9917 |
60
+ | 0.0349 | 12.7808 | 4000 | 0.0333 | 0.9919 |
61
+ | 0.0337 | 15.9760 | 5000 | 0.0331 | 0.9920 |
62
+ | 0.0332 | 19.1696 | 6000 | 0.0334 | 0.9919 |
63
+ | 0.0328 | 22.3648 | 7000 | 0.0332 | 0.9921 |
64
+ | 0.0323 | 25.56 | 8000 | 0.0333 | 0.9921 |
65
+ | 0.0318 | 28.7552 | 9000 | 0.0333 | 0.9921 |
66
+ | 0.032 | 31.9504 | 10000 | 0.0332 | 0.9921 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b6d1e98e5d68c56f5cfe40d34b8161c0fd3a135415d24df9c2abce9d05791fd
3
  size 893005608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c76fbc12bcc6f5b0364f8128097328350695117abed032fb801d14c5161fbc3
3
  size 893005608