brad1141 commited on
Commit
00e5fbc
·
1 Parent(s): 12e4be0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +20 -18
README.md CHANGED
@@ -1,5 +1,4 @@
1
  ---
2
- license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
  metrics:
@@ -17,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # bert-finetuned-ner
19
 
20
- This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5907
23
- - Precision: 0.5789
24
- - Recall: 0.9167
25
- - F1: 0.7097
26
- - Accuracy: 0.8091
27
 
28
  ## Model description
29
 
@@ -42,28 +41,31 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 2e-05
46
- - train_batch_size: 8
47
- - eval_batch_size: 8
48
  - seed: 42
 
 
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
 
51
  - num_epochs: 5
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
- | 0.631 | 1.0 | 1747 | 0.5743 | 0.5789 | 0.9167 | 0.7097 | 0.7985 |
58
- | 0.5177 | 2.0 | 3494 | 0.5425 | 0.3810 | 0.8889 | 0.5333 | 0.8088 |
59
- | 0.4494 | 3.0 | 5241 | 0.5425 | 0.5652 | 0.9286 | 0.7027 | 0.8113 |
60
- | 0.3763 | 4.0 | 6988 | 0.5653 | 0.5882 | 0.9091 | 0.7143 | 0.8080 |
61
- | 0.335 | 5.0 | 8735 | 0.5907 | 0.5789 | 0.9167 | 0.7097 | 0.8091 |
62
 
63
 
64
  ### Framework versions
65
 
66
- - Transformers 4.16.1
67
  - Pytorch 1.10.0+cu111
68
- - Datasets 1.18.2
69
- - Tokenizers 0.11.0
 
1
  ---
 
2
  tags:
3
  - generated_from_trainer
4
  metrics:
 
16
 
17
  # bert-finetuned-ner
18
 
19
+ This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.6434
22
+ - Precision: 0.8589
23
+ - Recall: 0.8686
24
+ - F1: 0.8637
25
+ - Accuracy: 0.8324
26
 
27
  ## Model description
28
 
 
41
  ### Training hyperparameters
42
 
43
  The following hyperparameters were used during training:
44
+ - learning_rate: 5e-05
45
+ - train_batch_size: 1
46
+ - eval_batch_size: 1
47
  - seed: 42
48
+ - gradient_accumulation_steps: 8
49
+ - total_train_batch_size: 8
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_ratio: 0.1
53
  - num_epochs: 5
54
 
55
  ### Training results
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.615 | 1.0 | 1741 | 0.6111 | 0.8200 | 0.8652 | 0.8420 | 0.8046 |
60
+ | 0.4795 | 2.0 | 3482 | 0.5366 | 0.8456 | 0.8803 | 0.8626 | 0.8301 |
61
+ | 0.3705 | 3.0 | 5223 | 0.5412 | 0.8527 | 0.8786 | 0.8655 | 0.8339 |
62
+ | 0.2749 | 4.0 | 6964 | 0.5906 | 0.8559 | 0.8711 | 0.8634 | 0.8316 |
63
+ | 0.2049 | 5.0 | 8705 | 0.6434 | 0.8589 | 0.8686 | 0.8637 | 0.8324 |
64
 
65
 
66
  ### Framework versions
67
 
68
+ - Transformers 4.17.0
69
  - Pytorch 1.10.0+cu111
70
+ - Datasets 1.18.4
71
+ - Tokenizers 0.11.6