vignesh2404/shawgpt-ft

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.3263
+- Loss: 2.9096
 
 ## Model description
 
@@ -49,18 +49,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 5.1488        | 0.9231 | 3    | 4.3509          |
-| 5.1158        | 1.8462 | 6    | 4.3486          |
-| 5.1306        | 2.7692 | 9    | 4.3430          |
-| 3.8451        | 4.0    | 13   | 4.3394          |
-| 5.143         | 4.9231 | 16   | 4.3357          |
-| 5.1448        | 5.8462 | 19   | 4.3339          |
-| 5.1081        | 6.7692 | 22   | 4.3313          |
-| 3.8084        | 8.0    | 26   | 4.3275          |
-| 5.0699        | 8.9231 | 29   | 4.3276          |
-| 3.4863        | 9.2308 | 30   | 4.3263          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.5412        | 1.0   | 138  | 3.1697          |
+| 3.3721        | 2.0   | 276  | 3.0695          |
+| 3.2929        | 3.0   | 414  | 2.9924          |
+| 3.2278        | 4.0   | 552  | 2.9467          |
+| 3.1929        | 5.0   | 690  | 2.9341          |
+| 3.181         | 6.0   | 828  | 2.9238          |
+| 3.1635        | 7.0   | 966  | 2.9183          |
+| 3.1524        | 8.0   | 1104 | 2.9131          |
+| 3.1492        | 9.0   | 1242 | 2.9101          |
+| 3.1411        | 10.0  | 1380 | 2.9096          |
 
 
 ### Framework versions

runs/Dec02_13-09-54_519ab6cbdc23/events.out.tfevents.1733145509.519ab6cbdc23.1609.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab61daa19ea500689649ca0780e2b39a371d5f64e3ad92a842fe5ab464de7f32
+size 10474

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74377ff53feb22c465fb13cb90d81868d24266d3498bfe4e3aa29f45c89feec7
+oid sha256:ee54dff7cf71a25378a45c32ae0161a2999ae6339b64b345a947ff0616a4b820
 size 5240