RajuEEE/RewardModel_TrainingOnlyOnAnswer

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: RajuEEE/RewardModel
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # RewardModel
 
-This model is a fine-tuned version of [RajuEEE/RewardModel](https://huggingface.co/RajuEEE/RewardModel) on the None dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4180
-- F1: 0.4938
-- Roc Auc: 0.6200
-- Accuracy: 0.495
+- Loss: 0.6500
+- F1: 0.5343
+- Roc Auc: 0.6487
+- Accuracy: 0.51
 
 ## Model description
 
@@ -46,13 +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: 2
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
-| 0.1595        | 1.94  | 500  | 1.4180          | 0.4938 | 0.6200  | 0.495    |
+| No log        | 1.0   | 258  | 0.6209          | 0.0198 | 0.505   | 0.01     |
+| 0.6053        | 2.0   | 516  | 0.6234          | 0.3785 | 0.5788  | 0.3      |
+| 0.6053        | 3.0   | 774  | 0.5752          | 0.5116 | 0.6375  | 0.495    |
+| 0.4326        | 4.0   | 1032 | 0.6500          | 0.5343 | 0.6487  | 0.51     |
+| 0.4326        | 5.0   | 1290 | 0.7455          | 0.4792 | 0.6062  | 0.435    |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "RajuEEE/RewardModel",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74713d3633ac0405396e9b0a888393f883388c696d9136046d2f549dd0a7cd4c
+oid sha256:40be10dc1f25ed21cf437c365453f348ab2104fca187de1ce23e7983e4b746a8
 size 438006577

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d2e3c2d5b48dc5b2f1b9f2150bb43ff13f5211a9d4a07158b146615db9a9f95
+oid sha256:5b23ab3d5da3ed88439d0f86ca9de87aeecefa7433058c994f706261dddfc270
 size 4027