Model save

README.md

@@ -17,8 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
 # spam-llama3.1-8B-teacher-2
 
 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 the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.6740
 
 ## Model description
 
@@ -49,16 +47,6 @@ The following hyperparameters were used during training:
 - num_epochs: 1
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.6576        | 0.2009 | 91   | 1.8055          |
-| 1.5242        | 0.4019 | 182  | 1.7284          |
-| 1.5695        | 0.6028 | 273  | 1.6887          |
-| 1.3364        | 0.8038 | 364  | 1.6740          |
-
-
 ### Framework versions
 
 - PEFT 0.12.0

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bab7ccfea159a00fd9baa91f267b4cd4661d5e1fb68a2bd0582dd571ba2a889
+oid sha256:cde1a66817dddf0d9289c1ce9fe5c154c8e8b40700cff8b94e290a6e55d9dee1
 size 671149168

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f67439908f4c503200f661217ea4e257664e11cc5ac1067da2d2ca1d0599f467
+oid sha256:5dded637a70887f4e9f53837ff0525a6fa2e6f12cd3d0b05f1c26302cff590c9
 size 5560