Training in progress, step 25

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "./llama8B_reasoning_3_{data_type}",
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "v_proj",
     "up_proj",
-    "down_proj",
     "o_proj",
-    "gate_proj",
     "q_proj",
-    "k_proj"
+    "down_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:cd395b1392157d37262f1189fcf99d78ea0e9600b94c3342aa2de93f584efa4b
+oid sha256:c5964a880983bb534cfd355d6a13e2fffba8623b29b5e3519432fc650cb79cff
 size 335604696

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:561fd51993c1e944d5b6a0f413ba94fcdb29f488661042e4630b2bdca7aaee7b
+oid sha256:e92a5bb1020f9223a5005a9b924ed3b40444ae9d9187f6afdc6366c1504f20fc
 size 5560