Hugging Face's logo

chandc
/
distilbert-base-uncased-finetuned-ner

Token Classification
Transformers
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Community
chandc commited on
Commit
60a9f43
•
1 Parent(s): e0a1b9e

End of training

Browse files
Files changed (3) hide show
  1. README.md +18 -10
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: nan
24
- - Precision: 0.9222
25
- - Recall: 0.9253
26
- - F1: 0.9237
27
- - Accuracy: 0.9811
28
 
29
  ## Model description
30
 
@@ -43,21 +43,29 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 2e-05
47
  - train_batch_size: 16
48
  - eval_batch_size: 16
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 3
 
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | 0.262 | 1.0 | 878 | nan | 0.8873 | 0.9168 | 0.9018 | 0.9778 |
59
- | 0.0607 | 2.0 | 1756 | nan | 0.9156 | 0.9192 | 0.9174 | 0.9807 |
60
- | 0.0433 | 3.0 | 2634 | nan | 0.9203 | 0.9262 | 0.9232 | 0.9814 |
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.2228
24
+ - Precision: 0.8030
25
+ - Recall: 0.8093
26
+ - F1: 0.8061
27
+ - Accuracy: 0.9545
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 0.0005
47
  - train_batch_size: 16
48
  - eval_batch_size: 16
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_ratio: 0.06
53
+ - num_epochs: 10
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.3032 | 1.0 | 878 | 0.3241 | 0.6979 | 0.5912 | 0.6401 | 0.9168 |
60
+ | 0.2666 | 2.0 | 1756 | 0.2822 | 0.6475 | 0.6577 | 0.6525 | 0.9221 |
61
+ | 0.2025 | 3.0 | 2634 | 0.2402 | 0.7021 | 0.7273 | 0.7144 | 0.9369 |
62
+ | 0.1421 | 4.0 | 3512 | 0.2158 | 0.7283 | 0.7331 | 0.7307 | 0.9390 |
63
+ | 0.111 | 5.0 | 4390 | 0.2189 | 0.7442 | 0.7395 | 0.7418 | 0.9417 |
64
+ | 0.0813 | 6.0 | 5268 | 0.2196 | 0.7307 | 0.7812 | 0.7551 | 0.9442 |
65
+ | 0.0538 | 7.0 | 6146 | 0.2169 | 0.7594 | 0.8049 | 0.7815 | 0.9497 |
66
+ | 0.0389 | 8.0 | 7024 | 0.2133 | 0.7929 | 0.7991 | 0.7960 | 0.9520 |
67
+ | 0.0263 | 9.0 | 7902 | 0.2192 | 0.8002 | 0.7991 | 0.7996 | 0.9530 |
68
+ | 0.0141 | 10.0 | 8780 | 0.2224 | 0.8029 | 0.8097 | 0.8063 | 0.9546 |
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9b2679f3399a1f6a517674a098d3ce570b5c461e54ae3d70ba05d9a08596eae
3
  size 265491548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a09abf074c00db120d4d5ba2110ce0db55a8e6a894de90b6b6810ca0257eed4d
3
  size 265491548
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2461ffee80f3bb689cdd4373a377360c4a8fb93d7cf62daaa97b5e61460fdf8e
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:732f878bbfd8fcbb9d1b27030365097afd563122d4e9a67cb4400c1f29ee9d3d
3
  size 4728