Training in progress, step 100

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "up_proj",
     "down_proj",
-    "k_proj",
-    "q_proj",
-    "o_proj",
     "v_proj",
-    "up_proj",
-    "gate_proj"
+    "q_proj",
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e0812b83370a5a177e759f6465acc559f39c1631d4bacea8c8a66db10ad5534
+oid sha256:3779d03e73bd9b73d4268af962dfa3307b5332a9b18d0e6504191d42a786a574
 size 1600399848

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2860f9b00233f91042fd553a0fa8b569cafca9e8c37faafd3704283a0384bf7c
+oid sha256:3afd02736941985ae3087f3aa6c7710bf0ea6a079f511d1da527f801d8af43d2
 size 5496