RajuEEE/Paper_RewardModel_RobertaBase

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: 0.1047
-- F1: 0.9722
-- Roc Auc: 0.9792
-- Accuracy: 0.9722
+- Loss: 0.5050
+- F1: 0.7522
+- Roc Auc: 0.7526
+- Accuracy: 0.7509
 
 ## 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   | 15   | 0.6256          | 0.0    | 0.5     | 0.0      |
-| No log        | 2.0   | 30   | 0.5210          | 0.3448 | 0.6042  | 0.2083   |
-| No log        | 3.0   | 45   | 0.3479          | 0.8143 | 0.8576  | 0.7639   |
-| No log        | 4.0   | 60   | 0.2431          | 0.9241 | 0.9444  | 0.9167   |
-| No log        | 5.0   | 75   | 0.1917          | 0.9315 | 0.9514  | 0.9167   |
-| No log        | 6.0   | 90   | 0.1364          | 0.9655 | 0.9757  | 0.9583   |
-| 0.3628        | 7.0   | 105  | 0.1120          | 0.9583 | 0.9688  | 0.9583   |
-| 0.3628        | 8.0   | 120  | 0.0967          | 0.9655 | 0.9757  | 0.9583   |
-| 0.3628        | 9.0   | 135  | 0.1047          | 0.9722 | 0.9792  | 0.9722   |
-| 0.3628        | 10.0  | 150  | 0.0928          | 0.9722 | 0.9792  | 0.9722   |
+| 0.6464        | 1.0   | 100  | 0.6186          | 0.6772 | 0.6772  | 0.6737   |
+| 0.5776        | 2.0   | 200  | 0.5439          | 0.7298 | 0.7298  | 0.7298   |
+| 0.4806        | 3.0   | 300  | 0.5050          | 0.7522 | 0.7526  | 0.7509   |
+| 0.3909        | 4.0   | 400  | 0.8594          | 0.6690 | 0.6684  | 0.6667   |
+| 0.331         | 5.0   | 500  | 0.7766          | 0.7206 | 0.7211  | 0.7193   |
 
 
 ### Framework versions

config.json

@@ -12,15 +12,13 @@
   "hidden_size": 768,
   "id2label": {
     "0": "Bad",
-    "1": "Average",
-    "2": "Good"
+    "1": "Good"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "Average": 1,
     "Bad": 0,
-    "Good": 2
+    "Good": 1
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3da063902d706260f2b9ae6ccc0dd54f70b774ae06cb0645d5953581e3773d
-size 498615900
+oid sha256:61dc313b9b0cb871020ca02bab5b800d6b72a310ca90a2e670d097c505503af5
+size 498612824

runs/Jul16_20-53-27_6f833c65d347/events.out.tfevents.1721163210.6f833c65d347.209.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a461c3cdafcafc2bac11e6083941cfdc961e8523c323fd48d967ad7b05af87e
+size 8477

runs/Jul16_20-53-27_6f833c65d347/events.out.tfevents.1721164167.6f833c65d347.209.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f34a441a1cf6dce382147f8d6655f877efe622bb93d7efeffd39fd632877020
+size 508

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098e46c5a702d34bdec66651e59afcacd001f2ed02dd90e9c149968cd82803f1
+oid sha256:9c32164d7d1fbb4be5ff1def9ff4334ea1b25181842232dbc60d27fe502bc651
 size 5112