Hugging Face's logo

shellypeng
/
bert-base-cased-finetuned-ner5

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
shellypeng commited on
Commit
f4a4033
·
verified ·
1 Parent(s): 93a270a

Training complete

Browse files
Files changed (2) hide show
  1. README.md +20 -16
  2. model.safetensors +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 [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.1446
25
- - Precision: 0.8226
26
- - Recall: 0.8378
27
- - F1: 0.8302
28
- - Accuracy: 0.9628
29
 
30
  ## Model description
31
 
@@ -44,24 +44,28 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 5e-05
48
- - train_batch_size: 64
49
- - eval_batch_size: 64
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
- - lr_scheduler_type: linear
53
- - lr_scheduler_warmup_ratio: 0.05
54
- - num_epochs: 5
 
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
59
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
60
- | 0.334 | 1.0 | 594 | 0.1321 | 0.7944 | 0.8025 | 0.7984 | 0.9569 |
61
- | 0.1127 | 2.0 | 1188 | 0.1206 | 0.8151 | 0.8132 | 0.8141 | 0.9606 |
62
- | 0.0849 | 3.0 | 1782 | 0.1218 | 0.8168 | 0.8321 | 0.8244 | 0.9623 |
63
- | 0.0663 | 4.0 | 2376 | 0.1313 | 0.8227 | 0.8367 | 0.8297 | 0.9626 |
64
- | 0.0511 | 5.0 | 2970 | 0.1446 | 0.8226 | 0.8378 | 0.8302 | 0.9628 |
 
 
 
65
 
66
 
67
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.6873
25
+ - Precision: 0.8196
26
+ - Recall: 0.8344
27
+ - F1: 0.8269
28
+ - Accuracy: 0.9611
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 3e-05
48
+ - train_batch_size: 32
49
+ - eval_batch_size: 32
50
  - seed: 42
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
+ - lr_scheduler_type: cosine_with_restarts
53
+ - lr_scheduler_warmup_ratio: 0.1
54
+ - num_epochs: 8
55
+ - label_smoothing_factor: 0.1
56
 
57
  ### Training results
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
+ | 0.726 | 1.0 | 1188 | 0.7145 | 0.7742 | 0.7897 | 0.7819 | 0.9525 |
62
+ | 0.6889 | 2.0 | 2376 | 0.6936 | 0.8085 | 0.8085 | 0.8085 | 0.9573 |
63
+ | 0.6676 | 3.0 | 3564 | 0.6818 | 0.8023 | 0.8239 | 0.8129 | 0.9584 |
64
+ | 0.6569 | 4.0 | 4752 | 0.6792 | 0.8154 | 0.8293 | 0.8223 | 0.9610 |
65
+ | 0.6452 | 5.0 | 5940 | 0.6883 | 0.8182 | 0.8254 | 0.8218 | 0.9600 |
66
+ | 0.6371 | 6.0 | 7128 | 0.6876 | 0.8237 | 0.8336 | 0.8286 | 0.9615 |
67
+ | 0.6342 | 7.0 | 8316 | 0.6863 | 0.8194 | 0.8370 | 0.8281 | 0.9615 |
68
+ | 0.6298 | 8.0 | 9504 | 0.6873 | 0.8196 | 0.8344 | 0.8269 | 0.9611 |
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7b9916f0bf090e5a326baf7a68d1b0e23406a9250c0bf8a9baaea07cd8a4454
3
  size 430954348
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec4815679f04b5e6d917eca4a53acbcbeb84f609132ffde4f98f22152800e245
3
  size 430954348