Model save

README.md

@@ -17,14 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.1222
-- F1 Macro: 0.9798
-- F1: 0.9852
-- F1 Neg: 0.9744
-- Acc: 0.9812
-- Prec: 0.9862
-- Recall: 0.9843
-- Mcc: 0.9596
+- Loss: 0.1503
+- F1 Macro: 0.9566
+- F1: 0.9688
+- F1 Neg: 0.9444
+- Acc: 0.96
+- Prec: 0.9612
+- Recall: 0.9764
+- Mcc: 0.9134
 
 ## Model description
 
@@ -50,23 +50,21 @@ The following hyperparameters were used during training:
 - distributed_type: multi-GPU
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1     | F1 Neg | Acc    | Prec   | Recall | Mcc    |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
-| No log        | 1.0   | 400  | 0.0777          | 0.9784   | 0.9843 | 0.9725 | 0.98   | 0.9824 | 0.9862 | 0.9568 |
-| 0.2063        | 2.0   | 800  | 0.1065          | 0.9784   | 0.9843 | 0.9726 | 0.98   | 0.9843 | 0.9843 | 0.9569 |
-| 0.0791        | 3.0   | 1200 | 0.1388          | 0.9743   | 0.9814 | 0.9672 | 0.9762 | 0.9766 | 0.9862 | 0.9487 |
-| 0.0298        | 4.0   | 1600 | 0.1222          | 0.9798   | 0.9852 | 0.9744 | 0.9812 | 0.9862 | 0.9843 | 0.9596 |
-| 0.0052        | 5.0   | 2000 | 0.1608          | 0.9732   | 0.9801 | 0.9663 | 0.975  | 0.9900 | 0.9705 | 0.9468 |
+| No log        | 1.0   | 400  | 0.1503          | 0.9566   | 0.9688 | 0.9444 | 0.96   | 0.9612 | 0.9764 | 0.9134 |
+| 0.2729        | 2.0   | 800  | 0.1966          | 0.9494   | 0.9643 | 0.9345 | 0.9537 | 0.9469 | 0.9823 | 0.9000 |
+| 0.0926        | 3.0   | 1200 | 0.1825          | 0.9565   | 0.9688 | 0.9443 | 0.96   | 0.9595 | 0.9783 | 0.9134 |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
-- Pytorch 2.2.1+cu121
-- Datasets 2.18.0
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.16.1
 - Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5a4f9b072d62ffbcc422fcbc54840f3f0b1db55b309aa20d16da0442c62906
+oid sha256:837b92d1c909ca88a1689356d8edaeab375787162e2c2cf3298da70fa510eaf4
 size 439433208