Training in progress, step 10

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb995fc96df85d46d015c0ae36e86d50566788ed4569be1528215b051754757
+oid sha256:9de510a2c0eaf42458ff46d7dc5cc66b33b161fa653ee929be3fc2716c5b7069
 size 11301520

metrics.json

@@ -1 +1 @@
-{"run_name": "/data-shared/testing-refactored", "train_runtime": 76.5183, "train_samples_per_second": 5.228, "train_steps_per_second": 0.131, "total_flos": 4810910442979328.0, "train_loss": 3.0876850128173827, "epoch": 0.01, "total_training_time": 82.92802095413208, "total_training_time_mins": 1.382133682568868, "avg_step_time": 7.034697532653809}
+{"run_name": "/data-shared/testing-refactored", "train_runtime": 82.321, "train_samples_per_second": 4.859, "train_steps_per_second": 0.121, "total_flos": 4810910442979328.0, "train_loss": 3.214849853515625, "epoch": 0.01, "total_training_time": 89.5426573753357, "total_training_time_mins": 1.4923776229222616, "avg_step_time": 7.553769207000732}