Hugging Face's logo

dtorber
/
bert-base-spanish-wwm-cased

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
dtorber commited on
Commit
7cd9a08
·
verified ·
1 Parent(s): b7516f2

Model save

Browse files
Files changed (3) hide show
  1. README.md +15 -19
  2. model.safetensors +1 -1
  3. runs/May16_20-26-10_tardis/events.out.tfevents.1715888589.tardis.5553.3 +3 -0
README.md CHANGED
@@ -17,15 +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 the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5748
21
- - F1 Macro: 0.8848
22
- - F1: 0.9231
23
- - F1 Neg: 0.8464
24
  - Acc: 0.8975
25
- - Prec: 0.8786
26
- - Recall: 0.9723
27
- - Mcc: 0.7796
28
- - Millor Epoca: 1
29
 
30
  ## Model description
31
 
@@ -48,23 +47,20 @@ The following hyperparameters were used during training:
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
  - seed: 42
51
- - distributed_type: multi-GPU
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
- - num_epochs: 7
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc | Millor Epoca |
60
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|:------------:|
61
- | 0.2917 | 1.0 | 1748 | 0.5748 | 0.8848 | 0.9231 | 0.8464 | 0.8975 | 0.8786 | 0.9723 | 0.7796 | 1 |
62
- | 0.1003 | 2.0 | 3496 | 0.9085 | 0.8698 | 0.9105 | 0.8291 | 0.8825 | 0.8787 | 0.9447 | 0.7443 | 1 |
63
- | 0.0285 | 3.0 | 5244 | 0.9081 | 0.8762 | 0.9136 | 0.8387 | 0.8875 | 0.8881 | 0.9407 | 0.7553 | 1 |
64
- | 0.0235 | 4.0 | 6992 | 0.9270 | 0.8740 | 0.9112 | 0.8369 | 0.885 | 0.8906 | 0.9328 | 0.7499 | 1 |
65
- | 0.0186 | 5.0 | 8740 | 1.1838 | 0.8681 | 0.9034 | 0.8328 | 0.8775 | 0.9016 | 0.9051 | 0.7361 | 1 |
66
- | 0.0053 | 6.0 | 10488 | 1.1457 | 0.8806 | 0.9141 | 0.8472 | 0.89 | 0.9035 | 0.9249 | 0.7617 | 1 |
67
- | 0.0008 | 7.0 | 12236 | 1.0345 | 0.8788 | 0.9112 | 0.8464 | 0.8875 | 0.9094 | 0.9130 | 0.7577 | 1 |
68
 
69
 
70
  ### Framework versions
 
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 the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.9387
21
+ - F1 Macro: 0.8879
22
+ - F1: 0.9207
23
+ - F1 Neg: 0.8551
24
  - Acc: 0.8975
25
+ - Prec: 0.9015
26
+ - Recall: 0.9407
27
+ - Mcc: 0.7774
 
28
 
29
  ## Model description
30
 
 
47
  - train_batch_size: 8
48
  - eval_batch_size: 8
49
  - seed: 42
 
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 5
53
  - mixed_precision_training: Native AMP
54
 
55
  ### Training results
56
 
57
+ | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
58
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
59
+ | 0.2306 | 1.0 | 2061 | 0.5481 | 0.8775 | 0.9167 | 0.8382 | 0.89 | 0.88 | 0.9565 | 0.7614 |
60
+ | 0.0717 | 2.0 | 4122 | 0.7879 | 0.8615 | 0.8903 | 0.8328 | 0.8675 | 0.9348 | 0.8498 | 0.7293 |
61
+ | 0.0203 | 3.0 | 6183 | 0.9309 | 0.8795 | 0.9105 | 0.8485 | 0.8875 | 0.916 | 0.9051 | 0.7591 |
62
+ | 0.0146 | 4.0 | 8244 | 0.9387 | 0.8879 | 0.9207 | 0.8551 | 0.8975 | 0.9015 | 0.9407 | 0.7774 |
63
+ | 0.0103 | 5.0 | 10305 | 1.0163 | 0.8774 | 0.9126 | 0.8421 | 0.8875 | 0.8969 | 0.9289 | 0.7558 |
 
 
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a079c71b64139984c421599247e1fe1f0a9e32920c7105ce22bf80b9479cc19
3
  size 439433208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c09783ab517ed46d02aca8e989b16abead8592f236ce16213a88de1d2b61f1
3
  size 439433208
runs/May16_20-26-10_tardis/events.out.tfevents.1715888589.tardis.5553.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24d62e3ba2ece638da8b5bddb98c8365dff4838e2180f9007e1866ae9e3cdbc4
3
+ size 699