Model save

README.md

@@ -3,8 +3,6 @@ license: mit
 base_model: neuralmind/bert-base-portuguese-cased
 tags:
 - generated_from_trainer
-datasets:
-- assin2
 model-index:
 - name: model_dir
   results: []
@@ -15,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # model_dir
 
-This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the assin2 dataset.
+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.
 
 ## Model description
 
@@ -40,14 +38,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 125  | 0.4393          | 0.81     |
-
+- num_epochs: 10
 
 ### Framework versions
 

config.json

@@ -24,7 +24,6 @@
   "pooler_size_per_head": 128,
   "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
   "type_vocab_size": 2,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f928eee80efabdf08188810e3176951e09fdcecf0e5e6040f0c5b2e83a3d5af8
+oid sha256:334a77a03746e1636e38ea1c8c826466dd195e654cacd8a29be336d6442a07bd
 size 435764718

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd4c902953aec375cb43579e9d69e319a6d5d1a9b7b9ffecd60ed15e6804e421
+oid sha256:25e8e0348e4063182cc1f977bc3f2ad4a86909ebd2735ec16aced4a6b0e5162c
 size 4472