google-play-sentiment-analysis

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: neuralmind/bert-base-portuguese-cased
+base_model: neuralmind/bert-large-portuguese-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # google-play-sentiment-analysis
 
-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.
+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: 1.3737
-- Accuracy: 0.457
+- Loss: 1.0987
+- Accuracy: 0.3229
 
 ## Model description
 
@@ -43,15 +43,22 @@ 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: 3.0
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 125  | 1.3050          | 0.437    |
-| No log        | 2.0   | 250  | 1.2939          | 0.448    |
-| No log        | 3.0   | 375  | 1.3737          | 0.457    |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.8592        | 1.0   | 1200  | 0.8029          | 0.6279   |
+| 0.9076        | 2.0   | 2400  | 1.1314          | 0.3229   |
+| 1.1221        | 3.0   | 3600  | 1.1170          | 0.3229   |
+| 1.1211        | 4.0   | 4800  | 1.1020          | 0.3362   |
+| 1.115         | 5.0   | 6000  | 1.1015          | 0.3408   |
+| 1.12          | 6.0   | 7200  | 1.0989          | 0.3408   |
+| 1.1153        | 7.0   | 8400  | 1.0989          | 0.3408   |
+| 1.1123        | 8.0   | 9600  | 1.0993          | 0.3408   |
+| 1.1125        | 9.0   | 10800 | 1.0987          | 0.3408   |
+| 1.1109        | 10.0  | 12000 | 1.0987          | 0.3229   |
 
 
 ### Framework versions
@@ -59,4 +66,4 @@ The following hyperparameters were used during training:
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.15.1