Training in progress, step 60

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -23,19 +23,19 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.0",
+  "peft_version": "0.18.1",
   "qalora_group_size": 16,
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "k_proj",
     "v_proj",
+    "up_proj",
     "gate_proj",
     "q_proj",
-    "up_proj",
-    "down_proj"
+    "down_proj",
+    "o_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:252741f4631f439a8d497d3a4532d8b56f2b6797e0951776defa2488582f3cd4
-size 45118424
+oid sha256:a46734372061604a6e6466c0bc295b646dda3901d12187e2df36138ed4a8a362
+size 97307544

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbca85ea4c3d0a1b4b05d40de76274366294701881b1d5b3ac234523bcee896
-size 5905
+oid sha256:93f7e165beba639d6ea8abfa9c37075e31b404b3d50b3b26709cc7e354992509
+size 5265