Training in progress, step 10

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "q_proj",
+    "up_proj",
     "down_proj",
-    "o_proj",
     "k_proj",
-    "up_proj",
-    "gate_proj"
+    "o_proj",
+    "gate_proj",
+    "v_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:d035c7d217578a4cf81b6f3d9058e6b661d834dc982c560bb61d99f7eb41ab0b
+oid sha256:cdd99dc63ebcbe730c33f4522daa71eb8092bfe7c235bdf025f98a8fadf9d7be
 size 11301520

metrics.json

@@ -1 +1 @@
-{"run_name": "./custom_deepspeed", "train_runtime": 267.2762, "train_samples_per_second": 11.973, "train_steps_per_second": 0.075, "total_flos": 3.848728354383462e+16, "train_loss": 1.5882408142089843, "epoch": 0.0365296803652968}
+{"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}