Model save

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [unsloth/tinyllama-chat-bnb-4bit](https://huggingface.co/unsloth/tinyllama-chat-bnb-4bit) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 9.3472
+- Loss: 9.3023
 
 ## Model description
 
@@ -52,16 +52,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 14.9654       | 1.0   | 2    | 9.3475          |
-| 14.9429       | 2.0   | 4    | 9.3475          |
-| 14.9444       | 3.0   | 6    | 9.3475          |
-| 14.8261       | 4.0   | 8    | 9.3475          |
-| 14.8751       | 5.0   | 10   | 9.3475          |
-| 14.8533       | 6.0   | 12   | 9.3475          |
-| 14.9159       | 7.0   | 14   | 9.3475          |
-| 14.9044       | 8.0   | 16   | 9.3473          |
-| 10.5466       | 9.0   | 18   | 9.3471          |
-| 10.0034       | 10.0  | 20   | 9.3472          |
+| 14.9333       | 1.0   | 2    | 9.3022          |
+| 14.8712       | 2.0   | 4    | 9.3022          |
+| 14.8529       | 3.0   | 6    | 9.3022          |
+| 14.8866       | 4.0   | 8    | 9.3022          |
+| 14.8956       | 5.0   | 10   | 9.3022          |
+| 14.9002       | 6.0   | 12   | 9.3022          |
+| 14.9378       | 7.0   | 14   | 9.3022          |
+| 14.9036       | 8.0   | 16   | 9.3021          |
+| 10.3845       | 9.0   | 18   | 9.3023          |
+| 9.9248        | 10.0  | 20   | 9.3023          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf87bcb9990374b60bc454537ab00d67ad541bf0142d65db94470956803dc16
+oid sha256:651211d3a1fe7b25e942f7845094ce3156183786c97820f1d57f9140e509ffbd
 size 18045856