Hugging Face's logo

dtorber
/
bert-base-spanish-wwm-cased_K3

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
dtorber commited on
Commit
6e59e94
·
verified ·
1 Parent(s): fccc881

Model save

Browse files
Files changed (2) hide show
  1. README.md +15 -17
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,14 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0402
21
- - F1 Macro: 0.9946
22
- - F1: 0.9960
23
- - F1 Neg: 0.9932
24
- - Acc: 0.995
25
- - Prec: 1.0
26
- - Recall: 0.9921
27
- - Mcc: 0.9893
28
 
29
  ## Model description
30
 
@@ -50,23 +50,21 @@ The following hyperparameters were used during training:
50
  - distributed_type: multi-GPU
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
- - num_epochs: 5
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
60
- | No log | 1.0 | 400 | 0.0466 | 0.9919 | 0.9941 | 0.9898 | 0.9925 | 1.0 | 0.9882 | 0.9840 |
61
- | 0.0844 | 2.0 | 800 | 0.0804 | 0.9853 | 0.9891 | 0.9815 | 0.9862 | 0.9980 | 0.9803 | 0.9708 |
62
- | 0.0297 | 3.0 | 1200 | 0.0397 | 0.9933 | 0.9951 | 0.9915 | 0.9938 | 1.0 | 0.9902 | 0.9867 |
63
- | 0.0186 | 4.0 | 1600 | 0.0402 | 0.9946 | 0.9960 | 0.9932 | 0.995 | 1.0 | 0.9921 | 0.9893 |
64
- | 0.0059 | 5.0 | 2000 | 0.0405 | 0.9946 | 0.9960 | 0.9932 | 0.995 | 1.0 | 0.9921 | 0.9893 |
65
 
66
 
67
  ### Framework versions
68
 
69
- - Transformers 4.38.2
70
- - Pytorch 2.2.1+cu121
71
- - Datasets 2.18.0
72
  - Tokenizers 0.15.2
 
17
 
18
  This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-cased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-cased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1211
21
+ - F1 Macro: 0.9718
22
+ - F1: 0.9792
23
+ - F1 Neg: 0.9645
24
+ - Acc: 0.9738
25
+ - Prec: 0.9860
26
+ - Recall: 0.9724
27
+ - Mcc: 0.9438
28
 
29
  ## Model description
30
 
 
50
  - distributed_type: multi-GPU
51
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
  - lr_scheduler_type: linear
53
+ - num_epochs: 3
54
  - mixed_precision_training: Native AMP
55
 
56
  ### Training results
57
 
58
  | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
59
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
60
+ | No log | 1.0 | 400 | 0.1211 | 0.9718 | 0.9792 | 0.9645 | 0.9738 | 0.9860 | 0.9724 | 0.9438 |
61
+ | 0.1763 | 2.0 | 800 | 0.1186 | 0.9691 | 0.9773 | 0.9608 | 0.9712 | 0.9802 | 0.9744 | 0.9381 |
62
+ | 0.0669 | 3.0 | 1200 | 0.1388 | 0.9704 | 0.9783 | 0.9625 | 0.9725 | 0.9802 | 0.9764 | 0.9408 |
 
 
63
 
64
 
65
  ### Framework versions
66
 
67
+ - Transformers 4.37.2
68
+ - Pytorch 2.2.0+cu121
69
+ - Datasets 2.16.1
70
  - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27e1e7426fa1a8e5972d467a25bfd80cf4e8fde834add8a260e41d17ddef7c1a
3
  size 439433208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dde30158b67f76c073443061c88cbfef8b0f12eeedc40638326cd76f475e63c
3
  size 439433208