JayShah07/reporting-reward-model

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0070
+- Loss: 0.0027
 
 ## Model description
 
@@ -41,15 +41,22 @@ 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: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1343        | 1.0   | 36   | 0.0188          |
-| 0.025         | 2.0   | 72   | 0.0099          |
-| 0.0176        | 3.0   | 108  | 0.0070          |
+| 0.1158        | 1.0   | 37   | 0.0163          |
+| 0.0196        | 2.0   | 74   | 0.0118          |
+| 0.013         | 3.0   | 111  | 0.0075          |
+| 0.0075        | 4.0   | 148  | 0.0049          |
+| 0.006         | 5.0   | 185  | 0.0037          |
+| 0.0049        | 6.0   | 222  | 0.0035          |
+| 0.0054        | 7.0   | 259  | 0.0035          |
+| 0.0041        | 8.0   | 296  | 0.0023          |
+| 0.0033        | 9.0   | 333  | 0.0023          |
+| 0.004         | 10.0  | 370  | 0.0027          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a511e17f040050045c67127d5d05021ea5bd5186853e0587a73ffd63f5acf39
+oid sha256:ee9ed55f4e8ff44730f0fd1449e0a0927a24cf7671ede1043d1db6921833c5a3
 size 267829484

runs/Feb13_04-43-14_2212d2f3b74b/events.out.tfevents.1739421800.2212d2f3b74b.256.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eb69b13a47ef94c9aa1b6ffe6d0f1fffd24ecbd5cc447fbabf8908871455ee7
-size 9319
+oid sha256:a50a2981798ee45ef84ba65dfec561e6ef26cff2d2111c546120f6a1403615be
+size 10155