Model save

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 8.4661
+- Loss: 8.0373
 
 ## Model description
 
@@ -44,9 +44,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 9.252         | 0.83  | 50   | 8.9995          |
-| 8.575         | 1.67  | 100  | 8.5798          |
-| 8.3224        | 2.5   | 150  | 8.4661          |
+| 9.1867        | 0.28  | 50   | 8.9209          |
+| 8.4695        | 0.56  | 100  | 8.4576          |
+| 8.2953        | 0.84  | 150  | 8.3795          |
+| 8.2062        | 1.12  | 200  | 8.3186          |
+| 8.1031        | 1.4   | 250  | 8.2218          |
+| 8.0537        | 1.69  | 300  | 8.1561          |
+| 7.9833        | 1.97  | 350  | 8.0899          |
+| 7.9868        | 2.25  | 400  | 8.0718          |
+| 7.964         | 2.53  | 450  | 8.0367          |
+| 7.9028        | 2.81  | 500  | 8.0373          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d452b0a2e6ee79ed43c9f89d25eded6367fc0c1a86aed360f1dff07a5bbae432
+oid sha256:01432c0ab4a5496648ced18274d4e81cb6d973d91de4147a6e19cfb232fc9591
 size 504144664