Hugging Face's logo

MaryDatascientist
/
modelA_1_12_2023

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
MaryDatascientist commited on
Commit
f5923f5
•
1 Parent(s): a5e1986

MaryDatascientist/modelA_1_12_2023

Browse files
Files changed (3) hide show
  1. README.md +14 -14
  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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0689
24
- - Precision: 0.8784
25
- - Recall: 0.8915
26
- - F1: 0.8849
27
- - Accuracy: 0.9760
28
 
29
  ## Model description
30
 
@@ -43,7 +43,7 @@ More information needed
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
- - learning_rate: 0.00019616920113351048
47
  - train_batch_size: 64
48
  - eval_batch_size: 16
49
  - seed: 42
@@ -55,14 +55,14 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | 0.0976 | 0.12 | 500 | 0.1055 | 0.8047 | 0.8025 | 0.8036 | 0.9641 |
59
- | 0.0849 | 0.24 | 1000 | 0.0974 | 0.8186 | 0.8479 | 0.8330 | 0.9667 |
60
- | 0.0788 | 0.37 | 1500 | 0.0865 | 0.8623 | 0.8274 | 0.8444 | 0.9695 |
61
- | 0.0678 | 0.49 | 2000 | 0.0831 | 0.8860 | 0.8092 | 0.8459 | 0.9705 |
62
- | 0.0555 | 0.61 | 2500 | 0.0790 | 0.8401 | 0.8899 | 0.8643 | 0.9718 |
63
- | 0.0468 | 0.73 | 3000 | 0.0745 | 0.8727 | 0.8769 | 0.8748 | 0.9739 |
64
- | 0.0417 | 0.85 | 3500 | 0.0704 | 0.8684 | 0.8942 | 0.8811 | 0.9751 |
65
- | 0.0359 | 0.97 | 4000 | 0.0689 | 0.8784 | 0.8915 | 0.8849 | 0.9760 |
66
 
67
 
68
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0875
24
+ - Precision: 0.8761
25
+ - Recall: 0.8916
26
+ - F1: 0.8838
27
+ - Accuracy: 0.9756
28
 
29
  ## Model description
30
 
 
43
  ### Training hyperparameters
44
 
45
  The following hyperparameters were used during training:
46
+ - learning_rate: 4.46211583196084e-05
47
  - train_batch_size: 64
48
  - eval_batch_size: 16
49
  - seed: 42
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.0236 | 0.12 | 500 | 0.0804 | 0.8719 | 0.8856 | 0.8787 | 0.9747 |
59
+ | 0.0235 | 0.24 | 1000 | 0.0840 | 0.8461 | 0.9056 | 0.8749 | 0.9735 |
60
+ | 0.0193 | 0.37 | 1500 | 0.0869 | 0.8572 | 0.8990 | 0.8776 | 0.9745 |
61
+ | 0.0174 | 0.49 | 2000 | 0.0853 | 0.8689 | 0.8912 | 0.8799 | 0.9749 |
62
+ | 0.0136 | 0.61 | 2500 | 0.0899 | 0.8750 | 0.8923 | 0.8835 | 0.9754 |
63
+ | 0.0119 | 0.73 | 3000 | 0.0954 | 0.8685 | 0.8964 | 0.8822 | 0.9751 |
64
+ | 0.0126 | 0.85 | 3500 | 0.0919 | 0.8711 | 0.8932 | 0.8820 | 0.9754 |
65
+ | 0.0197 | 0.97 | 4000 | 0.0875 | 0.8761 | 0.8916 | 0.8838 | 0.9756 |
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57f141627249df2f4b21193e16b5dcfd50f540ee13e378597a8457b9c82d1a13
3
  size 435685292
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79fcf21b7acc4d0c8f3c275d56c058a28929367502ec3a1158c4c02682b9d178
3
  size 435685292
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:583075ab3fa09307788db0eb59ec74dfbcf530fb2147e5e4554c66e68c3ee1a8
3
  size 4536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bddeb5e20146070012e3223ba87d892944cf9149f4253fa77a9322e1d8e0e183
3
  size 4536