Training in progress, step 10

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
-    "v_proj",
     "q_proj",
+    "up_proj",
     "down_proj",
+    "v_proj",
+    "k_proj",
     "o_proj",
-    "k_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:961b3bc732c9250003cd79f09bd79c8fc5eac2b968fcf520dae28541bb818f7a
+oid sha256:90b210ecde44172b100c85514e15d846d6378ff877f2b9324b16db986faa2208
 size 11301520

metrics.json

@@ -1 +1 @@
-{"run_name": "/data-shared/testing-refactored", "train_runtime": 80.5488, "train_samples_per_second": 9.932, "train_steps_per_second": 0.124, "total_flos": 9621820885958656.0, "train_loss": 3.1137392044067385, "epoch": 0.02, "total_training_time": 90.58460640907288, "total_training_time_mins": 1.5097434401512146, "avg_step_time": 7.272610497474671}
+{"run_name": "/data-shared/testing-refactored", "train_runtime": 75.826, "train_samples_per_second": 10.55, "train_steps_per_second": 0.132, "total_flos": 9621820885958656.0, "train_loss": 2.993947219848633, "epoch": 0.02, "total_training_time": 87.23009157180786, "total_training_time_mins": 1.453834859530131, "avg_step_time": 6.869749426841736}