llama3.1_8b_bwgenerator

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1084
+- Loss: 0.1186
 
 ## Model description
 
@@ -51,13 +51,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.7243        | 0.1373 | 40   | 0.2700          |
-| 0.2306        | 0.2746 | 80   | 0.2057          |
-| 0.1693        | 0.4120 | 120  | 0.1377          |
-| 0.1284        | 0.5493 | 160  | 0.1213          |
-| 0.1176        | 0.6866 | 200  | 0.1148          |
-| 0.1127        | 0.8239 | 240  | 0.1100          |
-| 0.1098        | 0.9613 | 280  | 0.1084          |
+| 0.7241        | 0.1680 | 40   | 0.2744          |
+| 0.2351        | 0.3359 | 80   | 0.2017          |
+| 0.1739        | 0.5039 | 120  | 0.1441          |
+| 0.1311        | 0.6718 | 160  | 0.1237          |
+| 0.1209        | 0.8398 | 200  | 0.1186          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:987586eaa7ace46f9b524d80439f7d9ac7b82c3ac62fd9de5c0a10543badf75e
+oid sha256:0e0380df0d905857a3171aeda366c6a4c4f1503ce0d4bdc2edfd80a93827689b
 size 6832728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e45cc6a309dc82431d6beb2afc7335d77e080beeff9b6107b8b430968f6b24
+oid sha256:7a710a6747144cf8d1ed16b3ec2ea09cf75c98242fdae29be6ac20248f7d4dc3
 size 5496