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
f5e276a
·
verified ·
1 Parent(s): 551acb4

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. README.md +16 -16
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
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: 0.2979
22
- - F1 Macro: 0.9199
23
- - F1: 0.9483
24
- - F1 Neg: 0.8915
25
- - Acc: 0.93
26
- - Prec: 0.9414
27
- - Recall: 0.9554
28
- - Mcc: 0.8401
29
- - Millor Epoca: 1
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
- | 0.265 | 1.0 | 3803 | 0.2979 | 0.9199 | 0.9483 | 0.8915 | 0.93 | 0.9414 | 0.9554 | 0.8401 | 1 |
63
- | 0.1156 | 2.0 | 7606 | 0.4891 | 0.9034 | 0.9331 | 0.8736 | 0.9125 | 0.9606 | 0.9071 | 0.8098 | 1 |
64
- | 0.0723 | 3.0 | 11409 | 0.6325 | 0.8975 | 0.9295 | 0.8655 | 0.9075 | 0.9531 | 0.9071 | 0.7973 | 1 |
65
- | 0.0243 | 4.0 | 15212 | 0.7340 | 0.9076 | 0.9379 | 0.8773 | 0.9175 | 0.9504 | 0.9257 | 0.8159 | 1 |
66
- | 0.0113 | 5.0 | 19015 | 0.7790 | 0.8930 | 0.9249 | 0.8612 | 0.9025 | 0.96 | 0.8922 | 0.7909 | 1 |
67
- | 0.0065 | 6.0 | 22818 | 0.8293 | 0.9046 | 0.9361 | 0.8731 | 0.915 | 0.9468 | 0.9257 | 0.8097 | 1 |
68
- | 0.0001 | 7.0 | 26621 | 0.7992 | 0.9069 | 0.9383 | 0.8755 | 0.9175 | 0.9436 | 0.9331 | 0.8139 | 1 |
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: 0.7600
22
+ - F1 Macro: 0.9004
23
+ - F1: 0.9270
24
+ - F1 Neg: 0.8737
25
+ - Acc: 0.9075
26
+ - Prec: 0.9252
27
+ - Recall: 0.9289
28
+ - Mcc: 0.8008
29
+ - Millor Epoca: 3
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
+ | 0.3296 | 1.0 | 3491 | 0.5448 | 0.8612 | 0.9088 | 0.8137 | 0.8775 | 0.8592 | 0.9644 | 0.7356 | 1 |
63
+ | 0.1282 | 2.0 | 6982 | 0.7060 | 0.8791 | 0.9154 | 0.8429 | 0.89 | 0.8914 | 0.9407 | 0.7608 | 2 |
64
+ | 0.0531 | 3.0 | 10473 | 0.7600 | 0.9004 | 0.9270 | 0.8737 | 0.9075 | 0.9252 | 0.9289 | 0.8008 | 3 |
65
+ | 0.0285 | 4.0 | 13964 | 0.8815 | 0.8606 | 0.8916 | 0.8296 | 0.8675 | 0.9237 | 0.8617 | 0.7246 | 3 |
66
+ | 0.0171 | 5.0 | 17455 | 1.2115 | 0.8589 | 0.8984 | 0.8194 | 0.87 | 0.8880 | 0.9091 | 0.7183 | 3 |
67
+ | 0.0086 | 6.0 | 20946 | 1.3128 | 0.8686 | 0.9073 | 0.8298 | 0.88 | 0.8868 | 0.9289 | 0.7390 | 3 |
68
+ | 0.0042 | 7.0 | 24437 | 1.3447 | 0.8734 | 0.9073 | 0.8396 | 0.8825 | 0.9055 | 0.9091 | 0.7469 | 3 |
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76ee6ea2b30713cda46c5f947bbff32709c1633cc72ad230a3df0c2e378a6581
3
  size 433270768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7feb07b3f31f948fb5148235ea702ed5f45ca3b1237da0074304b8b0c8caf7d
3
  size 433270768
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75bc44dc5ee6cc585438d8f95663fee6dae017ec53ce78ca12789c8bd7c60f5d
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6d6272654c2cb295d0ca164609a5840d0a3fc84ca09157fdf248f817e83bbfa
3
  size 5112