Training in progress, step 10

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "k_proj",
     "q_proj",
+    "v_proj",
     "o_proj",
+    "gate_proj",
     "up_proj",
-    "down_proj",
-    "k_proj",
-    "gate_proj"
+    "down_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:fe162099dcf87beaaceee4a653cc02983e241634fb98780856f4dfc7477ec413
+oid sha256:4c5d3938f91ef7ff5a58592f8a705a26afc4c0f1c1e0f350a05c9145456d0338
 size 48679352

metrics.json

@@ -1 +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}
+{"run_name": "./output-DeepSeek-R1-Distill-Qwen-7B-squad-nemo-replicaa", "train_runtime": 146.0605, "train_samples_per_second": 10.954, "train_steps_per_second": 0.068, "total_flos": 5.5657843654656e+16, "train_loss": 1.3686250686645507, "epoch": 0.0182648401826484}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed469a065e62c1937a4a9f72a89b3b6af90360091f57a3051f958ad732e82b3
+oid sha256:0b9e2519c0c3ff056cf6df59eb746b4d01d1ac1127d5f848cb93c0c3165f693d
 size 6353