End of training

README.md

@@ -105,7 +105,7 @@ xformers_attention: true
 
 This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B](https://huggingface.co/NousResearch/Meta-Llama-3-8B) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4887
+- Loss: 1.4829
 
 ## Model description
 
@@ -137,7 +137,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.6074        | 0.0004 | 10   | 1.4887          |
+| 0.613         | 0.0004 | 10   | 1.4829          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "up_proj",
     "k_proj",
-    "q_proj",
     "down_proj",
-    "o_proj",
+    "gate_proj",
     "v_proj",
-    "gate_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d72f9530c3c208b65637ff4588cfd7038c8562c94e15b56149dab8130049510
+oid sha256:a67f34e3193610fccc82a56c88037c8655fef765f63c452c43544fc8e33af302
 size 167934026

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3018685903934df639a1db3680380a19b52a8197667bcf5f0c724b3cdaeb53d2
+oid sha256:95df842d00237254ec59fca08f4bf8601d32cb12c208d5e6f1b889691ab99ca5
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd14db595c435da48a0fafe0d555659d04382320200e6be6a65171b5f44586b
+oid sha256:c8628ef1db7300bb3ffaad062b924755b9d00772aed8a33fc2fb16b1b054e446
 size 6776