Training in progress, step 10

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12764a7538c8ef7d2c1f575a9125e62cd4b4be397700c8c925d14c1200e61b21
+oid sha256:5daeb91e434a58778dcd3ffe039957062df01da905dbd9656e16d83fe2b84f74
 size 11301520

metrics.json

@@ -1 +1 @@
-{"run_name": "/data-shared/testing-refactored", "train_runtime": 74.9153, "train_samples_per_second": 5.339, "train_steps_per_second": 0.133, "total_flos": 4810910442979328.0, "train_loss": 3.104553985595703, "epoch": 0.01, "total_training_time": 82.03439784049988, "total_training_time_mins": 1.3672399640083313, "avg_step_time": 6.863372492790222}
+{"run_name": "/data-shared/testing-refactored", "train_runtime": 72.2149, "train_samples_per_second": 5.539, "train_steps_per_second": 0.138, "total_flos": 4810910442979328.0, "train_loss": 3.2091583251953124, "epoch": 0.01, "total_training_time": 80.47256731987, "total_training_time_mins": 1.3412094553311666, "avg_step_time": 6.693000960350036}