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: 0.1528
+- Loss: 0.1153
 
 ## Model description
 
@@ -51,14 +51,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.2317        | 0.1246 | 20   | 0.3990          |
-| 0.3324        | 0.2492 | 40   | 0.2884          |
-| 0.2665        | 0.3738 | 60   | 0.2478          |
-| 0.2326        | 0.4983 | 80   | 0.2174          |
-| 0.2072        | 0.6229 | 100  | 0.1941          |
-| 0.1818        | 0.7475 | 120  | 0.1687          |
-| 0.1631        | 0.8721 | 140  | 0.1555          |
-| 0.1543        | 0.9967 | 160  | 0.1528          |
+| 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          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12ac22bba7490e37ed9784769714d9b6253b1e5b38f9536df4e96909f089dbab
-size 6834904
+oid sha256:d19fd8b275141c2cd72d0fc45b7597ea6fe2c46506fdea60abe2a819a92d9a80
+size 6832728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b17beb214a9143f2befed0a63928bdeddafa1fe89cacf297ce36eb0396eee0a8
-size 5560
+oid sha256:90bc6e73feded14695ff73155bb67b2938f7678a71a8c2897cd30f395075122e
+size 5496