[sft] Qwen3-0.6B | e1 | 13.9k samples | lr=2e-05

Metrics:
- train_loss: 2.4142
- val_loss: 2.3905

W&B: https://wandb.ai/run/p8xonerz

adapter_config.json

@@ -30,12 +30,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "gate_proj",
-    "down_proj",
-    "up_proj",
     "v_proj",
+    "k_proj",
     "q_proj",
-    "k_proj"
+    "up_proj",
+    "gate_proj",
+    "down_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:feabe87a4afe0e16bced7642a8952e4b2d56e593505a0eaf7918434d5574243c
+oid sha256:e5291e93e62b72caad86ab0477904bae30f91c2d34bdb5a58801153e95290bea
 size 20237256

metrics.json

@@ -1,6 +1,6 @@
 {
-  "train_loss": 2.0744,
-  "val_loss": 2.0531225204467773,
+  "train_loss": 2.4142,
+  "val_loss": 2.3904521465301514,
   "accuracy": null,
   "epochs": 1,
   "max_steps": 10,
@@ -8,8 +8,8 @@
   "learning_rate": 2e-05,
   "model_name": "Qwen/Qwen3-0.6B",
   "method": "sft",
-  "run_number": "003",
+  "run_number": "004",
   "experiment_name": "aimo3-exp-1",
-  "wandb_run_id": "0pkyx3cq",
-  "timestamp": "2026-01-12T22:37:21.523229"
+  "wandb_run_id": "p8xonerz",
+  "timestamp": "2026-01-16T14:11:54.096241"
 }