End of training

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1111
-- Precision: 0.7322
-- Recall: 0.7331
-- F1: 0.7327
-- Accuracy: 0.9623
+- Loss: 0.1070
+- Precision: 0.7385
+- Recall: 0.7487
+- F1: 0.7435
+- Accuracy: 0.9633
 
 ## Model description
 
@@ -58,7 +58,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0459        | 4.0   | 500  | 0.1248          | 0.6919    | 0.6787 | 0.6852 | 0.9536   |
+| 0.0472        | 4.0   | 500  | 0.1219          | 0.6859    | 0.6990 | 0.6924 | 0.9558   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f2f861244c6c037af411d6b96d879fd07ce47ceb92f003775d2dda9f4141867
+oid sha256:85619eb0d2e1ad91f905b03be16be625cedf7c5856dbde0dde7e1f6c98475680
 size 1333442272

tokenizer_config.json

@@ -1,5 +1,4 @@
 {
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "[PAD]",