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: 0.5830
-- F1 Macro: 0.8610
-- F1: 0.9010
-- F1 Neg: 0.8211
-- Acc: 0.8725
-- Prec: 0.8872
-- Recall: 0.9152
-- Mcc: 0.7228
+- Loss: 0.7706
+- F1 Macro: 0.8560
+- F1: 0.8944
+- F1 Neg: 0.8177
+- Acc: 0.8662
+- Prec: 0.8953
+- Recall: 0.8935
+- Mcc: 0.7121
 
 ## Model description
 
@@ -50,7 +50,7 @@ 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: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results

runs/Mar12_12-37-46_tardis/events.out.tfevents.1710243730.tardis.115115.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdb2a44b864c2f401d4af5789dcd08d304a784bf86fbda73e3e2e4d413ca528
+size 699