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: 1.2942
-- F1 Macro: 0.8259
-- F1: 0.8755
-- F1 Neg: 0.7762
-- Acc: 0.84
-- Prec: 0.8637
-- Recall: 0.8876
-- Mcc: 0.6523
+- Loss: 1.3790
+- F1 Macro: 0.8425
+- F1: 0.8931
+- F1 Neg: 0.7919
+- Acc: 0.8588
+- Prec: 0.8582
+- Recall: 0.9310
+- Mcc: 0.6910
 
 ## 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: 10
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results