Adzka/reward-model-distilbert-indo

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [w11wo/indonesian-roberta-base-sentiment-classifier](https://huggingface.co/w11wo/indonesian-roberta-base-sentiment-classifier) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4306
-- Accuracy: 0.8197
+- Loss: 0.3383
+- Accuracy: 0.8673
 
 ## Model description
 
@@ -43,33 +43,27 @@ 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: 12
+- num_epochs: 8
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7102        | 0.57  | 50   | 0.6741          | 0.7623   |
-| 0.6583        | 1.15  | 100  | 0.6248          | 0.7705   |
-| 0.5738        | 1.72  | 150  | 0.5009          | 0.8115   |
-| 0.438         | 2.3   | 200  | 0.3925          | 0.8443   |
-| 0.3201        | 2.87  | 250  | 0.3594          | 0.8361   |
-| 0.2535        | 3.45  | 300  | 0.3908          | 0.8361   |
-| 0.1875        | 4.02  | 350  | 0.3669          | 0.8443   |
-| 0.1249        | 4.6   | 400  | 0.3908          | 0.8279   |
-| 0.1205        | 5.17  | 450  | 0.4065          | 0.8525   |
-| 0.1083        | 5.75  | 500  | 0.4077          | 0.8443   |
-| 0.0586        | 6.32  | 550  | 0.3901          | 0.8361   |
-| 0.0998        | 6.9   | 600  | 0.4196          | 0.8525   |
-| 0.0634        | 7.47  | 650  | 0.4174          | 0.8525   |
-| 0.0491        | 8.05  | 700  | 0.4311          | 0.8443   |
-| 0.0354        | 8.62  | 750  | 0.4140          | 0.8279   |
-| 0.0375        | 9.2   | 800  | 0.4205          | 0.8115   |
-| 0.0343        | 9.77  | 850  | 0.4212          | 0.8197   |
-| 0.0372        | 10.34 | 900  | 0.4132          | 0.8197   |
-| 0.0238        | 10.92 | 950  | 0.4306          | 0.8197   |
-| 0.0299        | 11.49 | 1000 | 0.4270          | 0.8197   |
+| 0.711         | 0.54  | 50   | 0.6858          | 0.8061   |
+| 0.6942        | 1.08  | 100  | 0.6390          | 0.8469   |
+| 0.586         | 1.61  | 150  | 0.4498          | 0.8673   |
+| 0.4693        | 2.15  | 200  | 0.3464          | 0.8571   |
+| 0.3404        | 2.69  | 250  | 0.3004          | 0.8673   |
+| 0.3255        | 3.23  | 300  | 0.3514          | 0.8776   |
+| 0.2332        | 3.76  | 350  | 0.3435          | 0.8776   |
+| 0.1865        | 4.3   | 400  | 0.3013          | 0.8673   |
+| 0.1552        | 4.84  | 450  | 0.2979          | 0.8878   |
+| 0.1214        | 5.38  | 500  | 0.3166          | 0.8878   |
+| 0.1284        | 5.91  | 550  | 0.3407          | 0.8673   |
+| 0.0971        | 6.45  | 600  | 0.3490          | 0.8776   |
+| 0.0953        | 6.99  | 650  | 0.3269          | 0.8673   |
+| 0.0728        | 7.53  | 700  | 0.3388          | 0.8673   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf5251b92e4cce40be2458c10cf067c754675d7db719e05fdf416de2db052863
+oid sha256:29ebf7aa843aa3d9ecfadcdb0d749ab028a2f1484a07d6ec9a77fdb5989b1c2c
 size 498615900

runs/Jul23_00-12-35_DESKTOP-HH0RPGN/events.out.tfevents.1721668361.DESKTOP-HH0RPGN.13276.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645078c437a09d4fe16a674bd987382b2a79091db9510efb92d6bc741a4978f0
-size 10244
+oid sha256:4ee23b6693f54f8eb5011261fe1a027c515da3a85e8cbae38e9a933c1cf956a4
+size 12734

runs/Jul23_00-12-35_DESKTOP-HH0RPGN/events.out.tfevents.1721668834.DESKTOP-HH0RPGN.13276.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0475dece1c3cc04e66d55340862f6f61122eb709cbea33ec2ce0e897f9b6d90d
+size 411