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: 0.1153
+- Loss: 0.1032
 
 ## Model description
 
@@ -51,12 +51,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.7197        | 0.1536 | 40   | 0.2706          |
-| 0.233         | 0.3071 | 80   | 0.2020          |
-| 0.1719        | 0.4607 | 120  | 0.1414          |
-| 0.1317        | 0.6142 | 160  | 0.1239          |
-| 0.1209        | 0.7678 | 200  | 0.1179          |
-| 0.1168        | 0.9213 | 240  | 0.1153          |
+| 0.7124        | 0.1216 | 40   | 0.2698          |
+| 0.2279        | 0.2433 | 80   | 0.1875          |
+| 0.1546        | 0.3649 | 120  | 0.1293          |
+| 0.1242        | 0.4865 | 160  | 0.1168          |
+| 0.1144        | 0.6081 | 200  | 0.1103          |
+| 0.1097        | 0.7298 | 240  | 0.1064          |
+| 0.107         | 0.8514 | 280  | 0.1043          |
+| 0.105         | 0.9730 | 320  | 0.1032          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d19fd8b275141c2cd72d0fc45b7597ea6fe2c46506fdea60abe2a819a92d9a80
+oid sha256:93de4bf57aab1828667bacd328921a78ab4e52d693f424d7d0ba794e8a949deb
 size 6832728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90bc6e73feded14695ff73155bb67b2938f7678a71a8c2897cd30f395075122e
+oid sha256:94b7f1252de2ef7de0ca1f0f926c6ab823e3b4e41e07becfca600b0eb3228a3e
 size 5496