Fine-tune model

README.md

@@ -19,9 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [flax-community/indonesian-roberta-base](https://huggingface.co/flax-community/indonesian-roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6531
-- Accuracy: 0.8407
-- F1: 0.8419
+- Loss: 0.6418
+- Accuracy: 0.8413
+- F1: 0.8421
 
 ## Model description
 
@@ -46,16 +46,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 4
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
-| 0.4905        | 1.0   | 3415  | 0.4725          | 0.8202   | 0.8222 |
-| 0.3484        | 2.0   | 6830  | 0.5202          | 0.8413   | 0.8427 |
-| 0.2316        | 3.0   | 10245 | 0.6581          | 0.8488   | 0.8490 |
+| 0.4906        | 1.0   | 3415  | 0.4751          | 0.8155   | 0.8197 |
+| 0.353         | 2.0   | 6830  | 0.5212          | 0.8391   | 0.8409 |
+| 0.2384        | 3.0   | 10245 | 0.6594          | 0.8457   | 0.8449 |
+| 0.1574        | 4.0   | 13660 | 0.9253          | 0.8435   | 0.8421 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85eadab4b8020cdc1d732371f4f576ac1380577a4e28392acbe2fd11e2fbf9f5
+oid sha256:7351289836bdabc3bd54a82b2aa8414ecc29263bef90ab4038f073f9a596b067
 size 498615900

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4abf26b3d0f7a006837ee0b727cf65810de82be82444105b92685048adc036
+oid sha256:b6628c63bf932b831b3930acee84e4c734c34657d95a85c9b3762ab21fd2f8bd
 size 5304