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
a607e32
·
verified ·
1 Parent(s): 23cffc3

Model save

Browse files
Files changed (3) hide show
  1. README.md +16 -16
  2. model.safetensors +1 -1
  3. runs/Apr26_12-32-32_tardis/events.out.tfevents.1714128936.tardis.179540.1 +3 -0
README.md CHANGED
@@ -18,15 +18,15 @@ 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: 0.6080
22
- - F1 Macro: 0.9169
23
- - F1: 0.9466
24
- - F1 Neg: 0.8872
25
- - Acc: 0.9275
26
- - Prec: 0.9380
27
- - Recall: 0.9554
28
- - Mcc: 0.8341
29
- - Millor Epoca: 3
30
 
31
  ## Model description
32
 
@@ -59,13 +59,13 @@ The following hyperparameters were used during training:
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc | Millor Epoca |
61
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|:------------:|
62
- | 0.2756 | 1.0 | 1698 | 0.3780 | 0.9135 | 0.9451 | 0.8819 | 0.925 | 0.9314 | 0.9591 | 0.8279 | 1 |
63
- | 0.119 | 2.0 | 3396 | 0.5107 | 0.9158 | 0.9436 | 0.8881 | 0.925 | 0.9544 | 0.9331 | 0.8322 | 2 |
64
- | 0.0398 | 3.0 | 5094 | 0.6080 | 0.9169 | 0.9466 | 0.8872 | 0.9275 | 0.9380 | 0.9554 | 0.8341 | 3 |
65
- | 0.022 | 4.0 | 6792 | 0.7176 | 0.9152 | 0.9440 | 0.8864 | 0.925 | 0.9476 | 0.9405 | 0.8305 | 3 |
66
- | 0.0124 | 5.0 | 8490 | 0.8219 | 0.9122 | 0.9423 | 0.8821 | 0.9225 | 0.9440 | 0.9405 | 0.8244 | 3 |
67
- | 0.0 | 6.0 | 10188 | 1.0603 | 0.9046 | 0.9397 | 0.8696 | 0.9175 | 0.9245 | 0.9554 | 0.8104 | 3 |
68
- | 0.0018 | 7.0 | 11886 | 0.9280 | 0.9058 | 0.9390 | 0.8726 | 0.9175 | 0.9338 | 0.9442 | 0.8117 | 3 |
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: 0.8345
22
+ - F1 Macro: 0.9216
23
+ - F1: 0.9508
24
+ - F1 Neg: 0.8924
25
+ - Acc: 0.9325
26
+ - Prec: 0.9321
27
+ - Recall: 0.9703
28
+ - Mcc: 0.8451
29
+ - Millor Epoca: 5
30
 
31
  ## Model description
32
 
 
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc | Millor Epoca |
61
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|:------------:|
62
+ | 0.2657 | 1.0 | 1698 | 0.3480 | 0.9031 | 0.9370 | 0.8692 | 0.915 | 0.9336 | 0.9405 | 0.8063 | 1 |
63
+ | 0.0983 | 2.0 | 3396 | 0.5281 | 0.9039 | 0.9366 | 0.8712 | 0.915 | 0.9401 | 0.9331 | 0.8078 | 2 |
64
+ | 0.043 | 3.0 | 5094 | 0.5741 | 0.9016 | 0.9343 | 0.8689 | 0.9125 | 0.9432 | 0.9257 | 0.8036 | 2 |
65
+ | 0.0239 | 4.0 | 6792 | 0.8465 | 0.9115 | 0.9460 | 0.8770 | 0.925 | 0.9164 | 0.9777 | 0.8282 | 4 |
66
+ | 0.0134 | 5.0 | 8490 | 0.8345 | 0.9216 | 0.9508 | 0.8924 | 0.9325 | 0.9321 | 0.9703 | 0.8451 | 5 |
67
+ | 0.0104 | 6.0 | 10188 | 0.9451 | 0.9108 | 0.9431 | 0.8784 | 0.9225 | 0.9312 | 0.9554 | 0.8223 | 5 |
68
+ | 0.0 | 7.0 | 11886 | 0.9742 | 0.9081 | 0.9412 | 0.875 | 0.92 | 0.9309 | 0.9517 | 0.8167 | 5 |
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afc67f04da988e8924c43781ab0ff9edd766d43930840f5c337712aa8f3bb8c8
3
  size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd257c9665947c6c5677e703992d6cbe4a31360f0ff68edc35a32ef69ffdae1f
3
  size 433270768
runs/Apr26_12-32-32_tardis/events.out.tfevents.1714128936.tardis.179540.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48cffa23536430a0783f9fd41be080417e738d2cc0384c6a786b2e116c8a6b19
3
+ size 755