Training in progress, step 12

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/Llama-3.2-1B",
+  "base_model_name_or_path": "unsloth/llama-3.2-1b-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "q_proj",
     "v_proj",
-    "up_proj",
-    "o_proj",
     "k_proj",
-    "gate_proj",
     "down_proj",
-    "q_proj"
+    "o_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0322cb3ac433f94a7c8bb7223109bbce2609158cd8102cd8afefdebb84c4bdc6
+oid sha256:7a3049b41c1ac900ac011c2a0fd6512dc77661384d4c23a66b23ff9f2c011951
 size 45118424

runs/Oct08_17-27-36_2785964ec193/events.out.tfevents.1728408460.2785964ec193.262.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deef04f74cc49a1ffd2d54df936ab10d0847d21a99ea179efa3540c8504d9618
+size 8728

tokenizer_config.json

@@ -2058,6 +2058,6 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|finetune_right_pad_id|>",
-  "padding_side": "left",
+  "padding_side": "right",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30114c541ec0691841854ef73d6accd62d00a3847710714261ba478d6ff6b591
+oid sha256:9a4c0d6992a35bdbcef2415458941354f735040ac60632be1fb546f33efa0280
 size 5432