Model save

README.md

@@ -3,8 +3,6 @@ license: mit
 base_model: neuralmind/bert-base-portuguese-cased
 tags:
 - generated_from_trainer
-datasets:
-- lener_br
 metrics:
 - precision
 - recall
@@ -12,29 +10,7 @@ metrics:
 - accuracy
 model-index:
 - name: bert-base-portuguese-cased-finetuned-ner
-  results:
-  - task:
-      name: Token Classification
-      type: token-classification
-    dataset:
-      name: lener_br
-      type: lener_br
-      config: lener_br
-      split: test
-      args: lener_br
-    metrics:
-    - name: Precision
-      type: precision
-      value: 0.8649122807017544
-    - name: Recall
-      type: recall
-      value: 0.8885169927909372
-    - name: F1
-      type: f1
-      value: 0.8765557531115061
-    - name: Accuracy
-      type: accuracy
-      value: 0.9821930095431353
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-portuguese-cased-finetuned-ner
 
-This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the lener_br dataset.
+This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0679
-- Precision: 0.8649
-- Recall: 0.8885
-- F1: 0.8766
-- Accuracy: 0.9822
+- Loss: 0.0947
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.9821
 
 ## Model description
 
@@ -77,11 +53,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 490  | 0.0795          | 0.8185    | 0.7907 | 0.8043 | 0.9753   |
-| 0.1925        | 2.0   | 980  | 0.0683          | 0.8475    | 0.8602 | 0.8538 | 0.9803   |
-| 0.0422        | 3.0   | 1470 | 0.0679          | 0.8649    | 0.8885 | 0.8766 | 0.9822   |
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1  | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| No log        | 1.0   | 35   | 0.1217          | 0.0       | 0.0    | 0.0 | 0.9817   |
+| No log        | 2.0   | 70   | 0.0992          | 0.0       | 0.0    | 0.0 | 0.9817   |
+| No log        | 3.0   | 105  | 0.0947          | 0.0       | 0.0    | 0.0 | 0.9821   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d23f52b27db44bf709602cec62ada6f7fe023b6fdb20aaa14b76daaa7ac9d7
+oid sha256:05164ebd997f030d665ac595474f254d72b270962e7c626251f5e37971b801ea
 size 433438310

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d71ee62db0ee4867024fb30fea6e3ecb0b7399d765f4982990e16dabacc7750
+oid sha256:ad27df5562e577b5ed4a74c9fc32c18b292ef85ae6cafe0b507dfb659149cb70
 size 4536