Hugging Face's logo

Gausar
/
roberta-base-ner-demo

Token Classification
Transformers
TensorBoard
Safetensors
Mongolian
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Gausar commited on
Commit
6293e9b
·
verified ·
1 Parent(s): eb50037

End of training

Browse files
Files changed (3) hide show
  1. README.md +17 -16
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [bayartsogt/mongolian-roberta-base](https://huggingface.co/bayartsogt/mongolian-roberta-base) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.1370
25
- - Precision: 0.9277
26
- - Recall: 0.9369
27
- - F1: 0.9323
28
- - Accuracy: 0.9806
29
 
30
  ## Model description
31
 
@@ -50,27 +50,28 @@ The following hyperparameters were used during training:
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
 
53
  - num_epochs: 10
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
- | 0.1695 | 1.0 | 477 | 0.0763 | 0.9044 | 0.9179 | 0.9111 | 0.9775 |
60
- | 0.0524 | 2.0 | 954 | 0.0772 | 0.9221 | 0.9290 | 0.9255 | 0.9799 |
61
- | 0.0272 | 3.0 | 1431 | 0.0964 | 0.9167 | 0.9313 | 0.9240 | 0.9783 |
62
- | 0.0145 | 4.0 | 1908 | 0.1009 | 0.9217 | 0.9340 | 0.9278 | 0.9801 |
63
- | 0.0081 | 5.0 | 2385 | 0.1093 | 0.9244 | 0.9320 | 0.9282 | 0.9802 |
64
- | 0.0057 | 6.0 | 2862 | 0.1210 | 0.9289 | 0.9369 | 0.9329 | 0.9810 |
65
- | 0.0031 | 7.0 | 3339 | 0.1273 | 0.9275 | 0.9366 | 0.9320 | 0.9805 |
66
- | 0.0021 | 8.0 | 3816 | 0.1356 | 0.9249 | 0.9348 | 0.9298 | 0.9797 |
67
- | 0.0015 | 9.0 | 4293 | 0.1360 | 0.9299 | 0.9381 | 0.9340 | 0.9806 |
68
- | 0.001 | 10.0 | 4770 | 0.1370 | 0.9277 | 0.9369 | 0.9323 | 0.9806 |
69
 
70
 
71
  ### Framework versions
72
 
73
  - Transformers 4.38.2
74
  - Pytorch 2.2.1+cu121
75
- - Datasets 2.18.0
76
  - Tokenizers 0.15.2
 
21
 
22
  This model is a fine-tuned version of [bayartsogt/mongolian-roberta-base](https://huggingface.co/bayartsogt/mongolian-roberta-base) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.1205
25
+ - Precision: 0.9307
26
+ - Recall: 0.9389
27
+ - F1: 0.9348
28
+ - Accuracy: 0.9816
29
 
30
  ## Model description
31
 
 
50
  - seed: 42
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 500
54
  - num_epochs: 10
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
59
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
60
+ | 0.3889 | 1.0 | 477 | 0.0832 | 0.8808 | 0.8987 | 0.8897 | 0.9743 |
61
+ | 0.0736 | 2.0 | 954 | 0.0703 | 0.9170 | 0.9226 | 0.9198 | 0.9796 |
62
+ | 0.0361 | 3.0 | 1431 | 0.0784 | 0.9227 | 0.9321 | 0.9274 | 0.9801 |
63
+ | 0.0216 | 4.0 | 1908 | 0.0863 | 0.9235 | 0.9328 | 0.9281 | 0.9801 |
64
+ | 0.0116 | 5.0 | 2385 | 0.0977 | 0.9292 | 0.9371 | 0.9332 | 0.9809 |
65
+ | 0.007 | 6.0 | 2862 | 0.1071 | 0.9270 | 0.9356 | 0.9313 | 0.9808 |
66
+ | 0.0046 | 7.0 | 3339 | 0.1123 | 0.9322 | 0.9378 | 0.9350 | 0.9818 |
67
+ | 0.0029 | 8.0 | 3816 | 0.1179 | 0.9310 | 0.9371 | 0.9340 | 0.9814 |
68
+ | 0.0021 | 9.0 | 4293 | 0.1187 | 0.9293 | 0.9375 | 0.9334 | 0.9812 |
69
+ | 0.0013 | 10.0 | 4770 | 0.1205 | 0.9307 | 0.9389 | 0.9348 | 0.9816 |
70
 
71
 
72
  ### Framework versions
73
 
74
  - Transformers 4.38.2
75
  - Pytorch 2.2.1+cu121
76
+ - Datasets 2.19.0
77
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ac8a246380818545b9e0982f9f925fadb4c56b233b7a11533250662710416e4
3
  size 496259468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3eec4ca1aad45b7dd01819e60c1d98e13a5ddbe5b3c538130ff47a87393cada
3
  size 496259468
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b0b2132efd09c80ee75885e37741c93dd2fbf1edd49ae7e0bc7cc662b404c97
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9999d4d4da2ff4d2b3c926121249fdbe8bb204ed19f94218628bac1c3745ea9
3
  size 4856