google-play-sentiment-analysis

README.md

@@ -17,8 +17,8 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3877
-- Accuracy: 0.5328
+- Loss: 1.5489
+- Accuracy: 0.5245
 
 ## Model description
 
@@ -37,33 +37,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 2.5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 1.2365        | 1.0   | 1275  | 1.1915          | 0.5056   |
-| 1.0717        | 2.0   | 2550  | 1.2020          | 0.5133   |
-| 0.8201        | 3.0   | 3825  | 1.3425          | 0.5017   |
-| 0.5824        | 4.0   | 5100  | 1.5890          | 0.5294   |
-| 0.4379        | 5.0   | 6375  | 1.9669          | 0.5128   |
-| 0.3143        | 6.0   | 7650  | 2.4700          | 0.5361   |
-| 0.2556        | 7.0   | 8925  | 2.9751          | 0.5211   |
-| 0.1924        | 8.0   | 10200 | 3.2435          | 0.5211   |
-| 0.1494        | 9.0   | 11475 | 3.3190          | 0.5278   |
-| 0.1293        | 10.0  | 12750 | 3.3877          | 0.5328   |
+| 1.0972        | 1.0   | 10625 | 1.0835          | 0.5356   |
+| 1.0084        | 2.0   | 21250 | 1.1163          | 0.5313   |
+| 0.8658        | 3.0   | 31875 | 1.1971          | 0.5328   |
+| 0.7153        | 4.0   | 42500 | 1.3433          | 0.5264   |
+| 0.6015        | 5.0   | 53125 | 1.5489          | 0.5245   |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu118
+- Transformers 4.36.1
+- Pytorch 2.0.1+cu118
 - Datasets 2.15.0
 - Tokenizers 0.15.0

config.json

@@ -40,7 +40,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 29794

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7216b00be6d39cf15b4a673999607c388d293101b58a73dea9d7551e79eb319
+oid sha256:1279bd50d27c7dc076fc4597e148d5567f2f5fdf26138fbd5a518420ea4c7234
 size 435731452

runs/Dec17_13-54-26_597f983f089b/events.out.tfevents.1702821276.597f983f089b.136.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f13e16cb8827b064442c6b6acaa7bc9a14bb97e965d9ed90854e5ad31757c99
+size 23705

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875f07b306d69871ffb81036dc2a5e2d6c150fe1a1949906b4b3996bc31b9fe9
-size 4600
+oid sha256:8d572784b4ca468807c0cfe3735b0300779a681d481650ccf6428dedb7a8df30
+size 4283