RajuEEE/RewardModel_RobertaBase_Test_GPT_Data

README.md

@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0437
-- F1: 1.0
-- Roc Auc: 1.0
-- Accuracy: 1.0
+- Loss: 0.2827
+- F1: 0.9076
+- Roc Auc: 0.9420
+- Accuracy: 0.8393
 
 ## Model description
 
@@ -46,22 +46,17 @@ 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: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
-| No log        | 1.0   | 16   | 0.6214          | 0.0    | 0.5     | 0.0      |
-| No log        | 2.0   | 32   | 0.4624          | 0.7473 | 0.7991  | 0.6071   |
-| No log        | 3.0   | 48   | 0.2786          | 0.8496 | 0.8884  | 0.8393   |
-| No log        | 4.0   | 64   | 0.1602          | 0.9739 | 0.9866  | 0.9464   |
-| No log        | 5.0   | 80   | 0.1413          | 0.9381 | 0.9554  | 0.9286   |
-| No log        | 6.0   | 96   | 0.0814          | 0.9825 | 0.9911  | 0.9643   |
-| 0.3385        | 7.0   | 112  | 0.0524          | 0.9912 | 0.9955  | 0.9821   |
-| 0.3385        | 8.0   | 128  | 0.0437          | 1.0    | 1.0     | 1.0      |
-| 0.3385        | 9.0   | 144  | 0.0476          | 0.9912 | 0.9955  | 0.9821   |
-| 0.3385        | 10.0  | 160  | 0.0438          | 1.0    | 1.0     | 1.0      |
+| No log        | 1.0   | 16   | 0.6224          | 0.0    | 0.5     | 0.0      |
+| No log        | 2.0   | 32   | 0.5112          | 0.4658 | 0.6518  | 0.3036   |
+| No log        | 3.0   | 48   | 0.3407          | 0.8235 | 0.8571  | 0.75     |
+| No log        | 4.0   | 64   | 0.3243          | 0.85   | 0.8973  | 0.7679   |
+| No log        | 5.0   | 80   | 0.2827          | 0.9076 | 0.9420  | 0.8393   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5cfe155bc0046046d475c82732e5b9e9ef7e44b83e751cace628963a5cfa6f8
+oid sha256:c891f6288d4637008522ca9b3780174c52a4b28ab59e0033d4ff1e779204207e
 size 498615900

runs/Jun10_19-06-54_e0ec895ef285/events.out.tfevents.1718046422.e0ec895ef285.185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46dee49a6adbd6428a420207b35e127b158b0a1928cf1cae61080f1648a83efa
+size 7453

runs/Jun10_19-06-54_e0ec895ef285/events.out.tfevents.1718046598.e0ec895ef285.185.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9b69f312c5d4c6d6c85832400ff897cdf5ca71653040556100c8d2d2620a004
+size 500

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e27ff6b07173cdd64131ea137d8ea7a4109d661b458f222199db3345923832
+oid sha256:9dc61c3f16a2e61559eb86a0c9cef692d9319359e15328aaf016d6ce3587a35c
 size 5112