End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8731
+- Loss: 1.8753
 
 ## Model description
 
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.0283        | 0.9999 | 3912 | 1.9877          |
-| 1.8342        | 1.9999 | 7824 | 1.8731          |
+| 2.0282        | 0.9999 | 3912 | 1.9913          |
+| 1.8359        | 1.9999 | 7824 | 1.8753          |
 
 
 ### Framework versions

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "gate_proj",
-    "v_proj",
     "q_proj",
-    "up_proj",
     "k_proj",
-    "down_proj"
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2865cbe6c61197fb3216c4f09b3a30e02100a3abc1dfc0e75081e74056590000
+oid sha256:f8da6f3dbe733ac47c06fba7bda016d5e584db81408cf04b053b5744923fd057
 size 41581360

runs/Dec17_09-36-49_d3fe6e2dc7c3/events.out.tfevents.1734428210.d3fe6e2dc7c3.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa40959aed067dc1aa2f0f7d08b684256ce9c29b3f8ca8e2efdff5717c4d360
+size 9734

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9187f89902527abfcfd7b5e59ab9ba41ccddb2bfe9eea937531bf5080eada94
+oid sha256:7d611d6b33680a34110ae1dab24d1a2f0c00ad68343156f4d624282967675b6c
 size 5240