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: 0.6752
-- F1 Macro: 0.8719
-- F1: 0.9108
-- F1 Neg: 0.8330
-- Acc: 0.8838
-- Prec: 0.8862
-- Recall: 0.9369
-- Mcc: 0.7466
+- Loss: 0.9938
+- F1 Macro: 0.8622
+- F1: 0.9042
+- F1 Neg: 0.8201
+- Acc: 0.875
+- Prec: 0.8790
+- Recall: 0.9310
+- Mcc: 0.7273
 
 ## 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: 5
+- num_epochs: 10
 - mixed_precision_training: Native AMP
 
 ### Training results

runs/Mar12_14-02-02_tardis/events.out.tfevents.1710249020.tardis.118975.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666804b51d7e790aa39189afe425d1227ac03ff8fcb2834b4443a72d212c20e4
+size 699