Hugging Face's logo

dtorber
/
bert-base-cased

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
dtorber commited on
Commit
de3a7bc
·
verified ·
1 Parent(s): 49a077c

Model save

Browse files
Files changed (1) hide show
  1. README.md +17 -18
README.md CHANGED
@@ -18,15 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.1710
22
- - F1 Macro: 0.8711
23
- - F1: 0.9094
24
- - F1 Neg: 0.8327
25
- - Acc: 0.8825
26
- - Prec: 0.8872
27
- - Recall: 0.9328
28
- - Mcc: 0.7444
29
- - Millor Epoca: 4
30
 
31
  ## Model description
32
 
@@ -57,15 +56,15 @@ The following hyperparameters were used during training:
57
 
58
  ### Training results
59
 
60
- | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc | Millor Epoca |
61
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|:------------:|
62
- | 0.3198 | 1.0 | 1741 | 0.6009 | 0.8481 | 0.8948 | 0.8014 | 0.8625 | 0.8667 | 0.9249 | 0.7000 | 1 |
63
- | 0.1331 | 2.0 | 3482 | 0.8319 | 0.8596 | 0.8929 | 0.8262 | 0.8675 | 0.9132 | 0.8735 | 0.7206 | 2 |
64
- | 0.049 | 3.0 | 5223 | 1.1924 | 0.8587 | 0.9029 | 0.8145 | 0.8725 | 0.8713 | 0.9368 | 0.7221 | 3 |
65
- | 0.0192 | 4.0 | 6964 | 1.1710 | 0.8711 | 0.9094 | 0.8327 | 0.8825 | 0.8872 | 0.9328 | 0.7444 | 4 |
66
- | 0.0141 | 5.0 | 8705 | 1.3624 | 0.8511 | 0.8876 | 0.8146 | 0.86 | 0.9020 | 0.8735 | 0.7029 | 4 |
67
- | 0.0053 | 6.0 | 10446 | 1.4250 | 0.8494 | 0.8844 | 0.8143 | 0.8575 | 0.9083 | 0.8617 | 0.7007 | 4 |
68
- | 0.0032 | 7.0 | 12187 | 1.3777 | 0.8602 | 0.8972 | 0.8231 | 0.87 | 0.8972 | 0.8972 | 0.7204 | 4 |
69
 
70
 
71
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.3175
22
+ - F1 Macro: 0.8663
23
+ - F1: 0.9004
24
+ - F1 Neg: 0.8322
25
+ - Acc: 0.875
26
+ - Prec: 0.9076
27
+ - Recall: 0.8933
28
+ - Mcc: 0.7328
 
29
 
30
  ## Model description
31
 
 
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
60
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
61
+ | 0.2827 | 1.0 | 3822 | 0.5289 | 0.8407 | 0.8841 | 0.7973 | 0.8525 | 0.8789 | 0.8893 | 0.6814 |
62
+ | 0.1343 | 2.0 | 7644 | 0.8134 | 0.8507 | 0.888 | 0.8133 | 0.86 | 0.8988 | 0.8775 | 0.7018 |
63
+ | 0.0375 | 3.0 | 11466 | 0.9465 | 0.8581 | 0.8992 | 0.8169 | 0.87 | 0.8821 | 0.9170 | 0.7174 |
64
+ | 0.0273 | 4.0 | 15288 | 0.9964 | 0.8506 | 0.8928 | 0.8084 | 0.8625 | 0.8808 | 0.9051 | 0.7018 |
65
+ | 0.0165 | 5.0 | 19110 | 1.2194 | 0.8585 | 0.8942 | 0.8227 | 0.8675 | 0.9032 | 0.8854 | 0.7173 |
66
+ | 0.0132 | 6.0 | 22932 | 1.2963 | 0.8531 | 0.8902 | 0.8161 | 0.8625 | 0.8992 | 0.8814 | 0.7066 |
67
+ | 0.0055 | 7.0 | 26754 | 1.3175 | 0.8663 | 0.9004 | 0.8322 | 0.875 | 0.9076 | 0.8933 | 0.7328 |
68
 
69
 
70
  ### Framework versions