Model save

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9035
-- Acc: 0.729
-- F1: 0.7215
+- Loss: 0.6976
+- Acc: 0.724
+- F1: 0.7107
 
 ## Model description
 
@@ -51,11 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Acc   | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:-----:|:------:|
-| 0.5586        | 1.0   | 63   | 0.6102          | 0.682 | 0.7171 |
-| 0.4488        | 2.0   | 126  | 0.6046          | 0.71  | 0.7222 |
-| 0.3006        | 3.0   | 189  | 0.6438          | 0.726 | 0.7319 |
-| 0.1351        | 4.0   | 252  | 0.8477          | 0.733 | 0.7114 |
-| 0.078         | 5.0   | 315  | 0.9035          | 0.729 | 0.7215 |
+| 0.5746        | 1.0   | 63   | 0.6290          | 0.685 | 0.7091 |
+| 0.4933        | 2.0   | 126  | 0.5979          | 0.711 | 0.7375 |
+| 0.3049        | 3.0   | 189  | 0.6137          | 0.735 | 0.6929 |
+| 0.2006        | 4.0   | 252  | 0.6976          | 0.724 | 0.7107 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420feb0223679190966649f4f5d8e3eab534b1ec70a780ca7e94861bc80da118
+oid sha256:ae9d255b1745998b827a8d3931070e68786c5a4793a977c5f675c87dadbc6e91
 size 435722224