Training in progress, step 10

adapter_config.json

@@ -26,12 +26,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "k_proj",
-    "gate_proj",
-    "up_proj",
+    "q_proj",
     "o_proj",
+    "up_proj",
     "down_proj",
-    "q_proj"
+    "k_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd2989f33ebd32b9aceafdb6c9caa591d9ba0540e93915421e5d9122ed7c6c6
+oid sha256:fe162099dcf87beaaceee4a653cc02983e241634fb98780856f4dfc7477ec413
 size 48679352

metrics.json

@@ -0,0 +1 @@
+{"run_name": "./output-DeepSeek-R1-Distill-Qwen-7B-squad-nemo-replicaa", "train_runtime": 143.4567, "train_samples_per_second": 11.153, "train_steps_per_second": 0.07, "total_flos": 5.5657843654656e+16, "train_loss": 1.3610095977783203, "epoch": 0.0182648401826484}