Training in progress, step 10

adapter_config.json

@@ -24,12 +24,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "up_proj",
+    "o_proj",
     "down_proj",
+    "v_proj",
     "k_proj",
-    "o_proj",
     "gate_proj",
-    "v_proj"
+    "up_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:cdd99dc63ebcbe730c33f4522daa71eb8092bfe7c235bdf025f98a8fadf9d7be
+oid sha256:12764a7538c8ef7d2c1f575a9125e62cd4b4be397700c8c925d14c1200e61b21
 size 11301520

metrics.json

@@ -1 +1 @@
-{"run_name": "/data-shared/testing-refactored", "train_runtime": 82.5533, "train_samples_per_second": 4.845, "train_steps_per_second": 0.121, "total_flos": 4810910442979328.0, "train_loss": 3.1294017791748048, "epoch": 0.01, "total_training_time": 89.90108489990234, "total_training_time_mins": 1.4983514149983723, "avg_step_time": 6.669609618186951}
+{"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}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6302d7204c11d65102ccfe9a727ca8d3bba190dd19170c0e413b309c5b094043
+oid sha256:a2e090022771ac3844d368491d4b984d9b3516518d4541c26795188f11ad5f5a
 size 8440