Training in progress, step 20

adapter_config.json

@@ -26,130 +26,130 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "model.layers.2.self_attn.v_proj",
-    "model.layers.26.self_attn.k_proj",
     "model.layers.22.self_attn.k_proj",
-    "model.layers.13.self_attn.v_proj",
-    "36.self_attn.k_proj",
-    "model.layers.16.self_attn.k_proj",
-    "down_proj",
-    "model.layers.0.self_attn.v_proj",
-    "model.layers.25.self_attn.k_proj",
-    "model.layers.5.self_attn.k_proj",
-    "o_proj",
-    "model.layers.1.self_attn.q_proj",
-    "model.layers.14.self_attn.k_proj",
-    "33.self_attn.q_proj",
-    "model.layers.10.self_attn.v_proj",
-    "34.self_attn.v_proj",
-    "model.layers.6.self_attn.k_proj",
-    "model.layers.18.self_attn.k_proj",
-    "29.self_attn.v_proj",
     "model.layers.14.self_attn.q_proj",
-    "model.layers.7.self_attn.q_proj",
-    "model.layers.23.self_attn.k_proj",
-    "model.layers.16.self_attn.v_proj",
-    "model.layers.20.self_attn.k_proj",
-    "model.layers.12.self_attn.v_proj",
-    "33.self_attn.v_proj",
-    "model.layers.17.self_attn.k_proj",
-    "model.layers.10.self_attn.q_proj",
-    "38.self_attn.k_proj",
+    "model.layers.9.self_attn.k_proj",
+    "34.self_attn.v_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.8.self_attn.q_proj",
+    "37.self_attn.k_proj",
     "39.self_attn.v_proj",
-    "model.layers.2.self_attn.k_proj",
-    "model.layers.17.self_attn.v_proj",
+    "29.self_attn.q_proj",
+    "31.self_attn.k_proj",
+    "32.self_attn.v_proj",
+    "model.layers.2.self_attn.q_proj",
+    "33.self_attn.v_proj",
+    "model.layers.16.self_attn.k_proj",
     "33.self_attn.k_proj",
-    "model.layers.7.self_attn.v_proj",
-    "model.layers.23.self_attn.q_proj",
-    "model.layers.21.self_attn.q_proj",
-    "model.layers.1.self_attn.v_proj",
-    "28.self_attn.k_proj",
-    "27.self_attn.q_proj",
-    "model.layers.1.self_attn.k_proj",
-    "model.layers.0.self_attn.q_proj",
-    "model.layers.6.self_attn.q_proj",
-    "model.layers.16.self_attn.q_proj",
-    "37.self_attn.v_proj",
-    "model.layers.13.self_attn.k_proj",
-    "model.layers.17.self_attn.q_proj",
+    "28.self_attn.v_proj",
+    "model.layers.15.self_attn.k_proj",
+    "36.self_attn.k_proj",
+    "model.layers.10.self_attn.q_proj",
     "model.layers.25.self_attn.q_proj",
-    "model.layers.11.self_attn.v_proj",
-    "up_proj",
-    "30.self_attn.v_proj",
-    "35.self_attn.v_proj",
-    "model.layers.26.self_attn.v_proj",
-    "32.self_attn.k_proj",
-    "model.layers.14.self_attn.v_proj",
-    "27.self_attn.v_proj",
-    "model.layers.18.self_attn.q_proj",
-    "35.self_attn.k_proj",
-    "model.layers.13.self_attn.q_proj",
-    "model.layers.24.self_attn.q_proj",
+    "model.layers.0.self_attn.q_proj",
     "model.layers.5.self_attn.q_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.19.self_attn.k_proj",
+    "model.layers.23.self_attn.k_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.3.self_attn.k_proj",
+    "model.layers.21.self_attn.v_proj",
+    "38.self_attn.v_proj",
+    "37.self_attn.q_proj",
+    "model.layers.9.self_attn.q_proj",
+    "down_proj",
+    "model.layers.13.self_attn.q_proj",
     "model.layers.20.self_attn.v_proj",
-    "28.self_attn.q_proj",
-    "32.self_attn.v_proj",
-    "model.layers.15.self_attn.k_proj",
-    "model.layers.19.self_attn.q_proj",
-    "36.self_attn.v_proj",
+    "model.layers.17.self_attn.k_proj",
+    "38.self_attn.k_proj",
+    "model.layers.5.self_attn.k_proj",
     "model.layers.22.self_attn.q_proj",
-    "31.self_attn.v_proj",
-    "model.layers.4.self_attn.v_proj",
-    "34.self_attn.q_proj",
-    "model.layers.6.self_attn.v_proj",
+    "o_proj",
+    "28.self_attn.q_proj",
+    "model.layers.13.self_attn.v_proj",
+    "35.self_attn.v_proj",
+    "model.layers.1.self_attn.k_proj",
+    "27.self_attn.v_proj",
+    "29.self_attn.k_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.8.self_attn.k_proj",
+    "39.self_attn.q_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.24.self_attn.q_proj",
+    "36.self_attn.q_proj",
+    "model.layers.12.self_attn.k_proj",
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.25.self_attn.k_proj",
     "model.layers.4.self_attn.k_proj",
+    "27.self_attn.k_proj",
+    "model.layers.14.self_attn.k_proj",
     "model.layers.9.self_attn.v_proj",
-    "model.layers.24.self_attn.k_proj",
+    "model.layers.0.self_attn.k_proj",
+    "34.self_attn.q_proj",
+    "37.self_attn.v_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.4.self_attn.q_proj",
+    "34.self_attn.k_proj",
+    "gate_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.11.self_attn.k_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.20.self_attn.k_proj",
+    "31.self_attn.q_proj",
+    "30.self_attn.k_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.21.self_attn.k_proj",
+    "model.layers.12.self_attn.v_proj",
+    "30.self_attn.v_proj",
     "model.layers.8.self_attn.v_proj",
+    "30.self_attn.q_proj",
+    "model.layers.25.self_attn.v_proj",
     "model.layers.10.self_attn.k_proj",
-    "36.self_attn.q_proj",
-    "29.self_attn.k_proj",
+    "up_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.16.self_attn.v_proj",
+    "33.self_attn.q_proj",
+    "model.layers.15.self_attn.q_proj",
+    "28.self_attn.k_proj",
     "model.layers.11.self_attn.q_proj",
-    "model.layers.19.self_attn.k_proj",
+    "model.layers.26.self_attn.k_proj",
+    "model.layers.21.self_attn.q_proj",
+    "32.self_attn.k_proj",
+    "27.self_attn.q_proj",
+    "36.self_attn.v_proj",
     "32.self_attn.q_proj",
-    "model.layers.21.self_attn.v_proj",
-    "model.layers.3.self_attn.v_proj",
-    "model.layers.4.self_attn.q_proj",
+    "38.self_attn.q_proj",
     "model.layers.18.self_attn.v_proj",
+    "model.layers.19.self_attn.v_proj",
+    "35.self_attn.q_proj",
+    "model.layers.13.self_attn.k_proj",
+    "model.layers.24.self_attn.k_proj",
+    "model.layers.1.self_attn.q_proj",
+    "31.self_attn.v_proj",
     "39.self_attn.k_proj",
-    "model.layers.24.self_attn.v_proj",
-    "model.layers.25.self_attn.v_proj",
-    "38.self_attn.v_proj",
-    "model.layers.22.self_attn.v_proj",
-    "model.layers.12.self_attn.q_proj",
-    "model.layers.8.self_attn.q_proj",
-    "37.self_attn.k_proj",
-    "model.layers.9.self_attn.k_proj",
-    "model.layers.3.self_attn.q_proj",
-    "model.layers.11.self_attn.k_proj",
-    "model.layers.7.self_attn.k_proj",
-    "model.layers.15.self_attn.v_proj",
-    "30.self_attn.k_proj",
-    "gate_proj",
-    "model.layers.0.self_attn.k_proj",
-    "34.self_attn.k_proj",
-    "model.layers.12.self_attn.k_proj",
-    "37.self_attn.q_proj",
+    "29.self_attn.v_proj",
     "model.layers.5.self_attn.v_proj",
-    "31.self_attn.q_proj",
-    "38.self_attn.q_proj",
-    "30.self_attn.q_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.17.self_attn.q_proj",
+    "35.self_attn.k_proj",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.1.self_attn.v_proj",
     "model.layers.20.self_attn.q_proj",
-    "29.self_attn.q_proj",
-    "model.layers.21.self_attn.k_proj",
-    "model.layers.9.self_attn.q_proj",
-    "27.self_attn.k_proj",
-    "39.self_attn.q_proj",
-    "model.layers.26.self_attn.q_proj",
-    "model.layers.23.self_attn.v_proj",
-    "model.layers.2.self_attn.q_proj",
-    "model.layers.8.self_attn.k_proj",
-    "35.self_attn.q_proj",
-    "model.layers.3.self_attn.k_proj",
-    "model.layers.19.self_attn.v_proj",
-    "31.self_attn.k_proj",
-    "model.layers.15.self_attn.q_proj",
-    "28.self_attn.v_proj"
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.18.self_attn.k_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e097b974edb384445d105536bef3cd9d171ac97a4bc387ef13b77a7c6b8b0bde
+oid sha256:adfe7d857b414e65875f7ea543ac156f599be09e829f9eba5754d2252768d31b
 size 60254184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74eddc4b5d7b7e60cd45e0ff4d6167b60d2b92757c4e9f61283c80f963f2a221
+oid sha256:ae745f414c3075ec5a4cd6702fc2580d47b8f42d4bd1912da426a70948ab6483
 size 5560