Training in progress, step 100

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "unsloth/Llama-3.2-1B-Instruct-bnb-4bit",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
+  "lora_bias": false,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
     "v_proj",
-    "gate_proj",
+    "up_proj",
+    "down_proj",
     "q_proj",
     "k_proj",
-    "down_proj"
+    "gate_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 sha256:256725f4bcce4e984baacd7981f4282112c9ff2032e7ca683cb9d04989afeca0
+oid sha256:a92839096cdccaad56ee91ea5f7994c6be6ba9d33a99134e5ed273129ef18ef0
 size 45118424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6fb6b6e3adc261d0a7885521544cee5190193ba91f162fdd596a9773bd61697
+oid sha256:e21f2a882f703e54677b6d29c5166af27a38da370fe6b9685b41d457c46a3d9d
 size 5688