Training in progress, step 50

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "base_model_name_or_path": "Aryanne/Mistral-3B-Instruct-v0.2-init",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,13 +23,13 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "gate_proj",
-    "o_proj",
     "lm_head",
-    "up_proj",
-    "q_proj",
     "k_proj",
-    "down_proj"
+    "q_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 sha256:822e7ee0aec5844b647c56e112acfa2b7f9cc3354c118705fea3b3aa67f70eda
-size 877194832
+oid sha256:179fbeb341cef50ed5d77ed2733f3cafa7289a6af7cbf55e7464ad84367ea914
+size 726101488

runs/Nov23_08-48-58_6d772ef0bc2f/events.out.tfevents.1732351773.6d772ef0bc2f.3058.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7820cbc0980ad1ff295f4026b3bee3368e86810709e3913af36784cd0bf945fd
+size 6931

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
-size 587404
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cec05134c8a0f017ecad9c84150f89db40993b02df070216795e00e6c6ed66b
+oid sha256:58a111d1cbab457ee64f4474cd35098d79f9af3e17b941f83a60d310f1866c91
 size 5560