End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.8955
+- Loss: 4.5233
 
 ## Model description
 
@@ -47,13 +47,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss |
-|:-------------:|:-----:|:-----:|:---------------:|
-| 5.2019        | 1.0   | 13552 | 5.0209          |
-| 4.9385        | 2.0   | 27104 | 4.9308          |
-| 4.7585        | 3.0   | 40656 | 4.8992          |
-| 4.7002        | 4.0   | 54208 | 4.8884          |
-| 4.5711        | 5.0   | 67760 | 4.8955          |
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 4.8278        | 1.0   | 53477  | 4.6484          |
+| 4.5936        | 2.0   | 106954 | 4.5639          |
+| 4.4633        | 3.0   | 160431 | 4.5362          |
+| 4.4055        | 4.0   | 213908 | 4.5222          |
+| 4.3132        | 5.0   | 267385 | 4.5233          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f99b53a3d5c8d90f71809e7ab35381532e7a2f5c1489227ee67910c61a6c127f
+oid sha256:8f034b223771953e756bb6c734e65002b1e381cddfa563fb02ee0184fe6abab1
 size 497774208