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: 0.5862
-- F1 Macro: 0.8618
-- F1: 0.9024
-- F1 Neg: 0.8212
-- Acc: 0.8738
-- Prec: 0.8861
-- Recall: 0.9193
-- Mcc: 0.7248
+- Loss: 0.6943
+- F1 Macro: 0.8683
+- F1: 0.9054
+- F1 Neg: 0.8313
+- Acc: 0.8788
+- Prec: 0.8975
+- Recall: 0.9134
+- Mcc: 0.7369
 
 ## 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_12-33-20_tardis/events.out.tfevents.1710243458.tardis.115115.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d5da284ea6ce23ad7e9ee52d6aa7409b055515857e75f5837625d41ce5c305
+size 699