Training in progress, step 75

adapter_config.json

@@ -23,230 +23,230 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "language_model.model.layers.17.self_attn.k_proj",
-    "language_model.model.layers.20.self_attn.q_proj",
+    "language_model.model.layers.0.self_attn.o_proj",
+    "language_model.model.layers.10.self_attn.q_proj",
+    "language_model.model.layers.24.self_attn.v_proj",
+    "language_model.model.layers.3.mlp.down_proj",
+    "language_model.model.layers.27.self_attn.o_proj",
+    "language_model.model.layers.3.mlp.up_proj",
+    "language_model.model.layers.1.mlp.up_proj",
+    "language_model.model.layers.23.self_attn.q_proj",
+    "language_model.model.layers.31.self_attn.k_proj",
+    "language_model.model.layers.20.self_attn.k_proj",
+    "language_model.model.layers.10.mlp.up_proj",
+    "language_model.model.layers.8.self_attn.q_proj",
+    "language_model.model.layers.30.mlp.up_proj",
+    "language_model.model.layers.31.mlp.up_proj",
+    "language_model.model.layers.12.self_attn.v_proj",
+    "language_model.model.layers.15.self_attn.o_proj",
+    "language_model.model.layers.4.self_attn.q_proj",
+    "language_model.model.layers.19.mlp.down_proj",
+    "language_model.model.layers.30.mlp.down_proj",
+    "language_model.model.layers.30.self_attn.o_proj",
     "language_model.model.layers.11.self_attn.k_proj",
-    "language_model.model.layers.14.mlp.down_proj",
+    "language_model.model.layers.21.mlp.gate_proj",
+    "language_model.model.layers.31.self_attn.v_proj",
+    "language_model.model.layers.27.mlp.up_proj",
+    "language_model.model.layers.31.self_attn.o_proj",
+    "language_model.model.layers.11.mlp.down_proj",
+    "language_model.model.layers.11.self_attn.q_proj",
     "language_model.model.layers.3.self_attn.q_proj",
-    "language_model.model.layers.18.mlp.down_proj",
-    "language_model.model.layers.21.self_attn.v_proj",
-    "language_model.model.layers.25.self_attn.k_proj",
-    "language_model.model.layers.2.self_attn.v_proj",
-    "language_model.model.layers.12.mlp.up_proj",
-    "language_model.model.layers.12.self_attn.q_proj",
-    "language_model.model.layers.15.self_attn.k_proj",
     "language_model.model.layers.16.mlp.down_proj",
-    "language_model.model.layers.15.mlp.down_proj",
-    "language_model.model.layers.6.mlp.down_proj",
-    "language_model.model.layers.1.self_attn.v_proj",
+    "language_model.model.layers.5.mlp.gate_proj",
+    "language_model.model.layers.21.self_attn.q_proj",
+    "language_model.model.layers.21.self_attn.v_proj",
+    "language_model.model.layers.15.mlp.up_proj",
+    "language_model.model.layers.29.self_attn.v_proj",
     "language_model.model.layers.0.self_attn.q_proj",
-    "language_model.model.layers.17.mlp.down_proj",
-    "language_model.model.layers.14.mlp.gate_proj",
-    "language_model.model.layers.18.self_attn.k_proj",
-    "language_model.model.layers.16.self_attn.q_proj",
-    "language_model.model.layers.7.mlp.gate_proj",
-    "language_model.model.layers.0.mlp.gate_proj",
-    "language_model.model.layers.28.self_attn.o_proj",
-    "language_model.model.layers.25.self_attn.o_proj",
-    "language_model.model.layers.8.self_attn.o_proj",
-    "language_model.model.layers.31.mlp.up_proj",
-    "language_model.model.layers.3.self_attn.o_proj",
+    "language_model.model.layers.7.mlp.up_proj",
+    "language_model.model.layers.13.self_attn.q_proj",
+    "language_model.model.layers.23.mlp.gate_proj",
+    "language_model.model.layers.26.mlp.gate_proj",
+    "language_model.model.layers.6.self_attn.o_proj",
+    "language_model.model.layers.26.mlp.down_proj",
+    "language_model.model.layers.29.mlp.down_proj",
+    "language_model.model.layers.19.self_attn.o_proj",
+    "language_model.model.layers.27.self_attn.q_proj",
+    "language_model.model.layers.26.self_attn.q_proj",
+    "language_model.model.layers.30.self_attn.v_proj",
+    "language_model.model.layers.1.self_attn.o_proj",
+    "language_model.model.layers.24.self_attn.q_proj",
+    "language_model.model.layers.26.mlp.up_proj",
+    "language_model.model.layers.13.mlp.down_proj",
+    "language_model.model.layers.20.mlp.down_proj",
     "language_model.model.layers.14.self_attn.v_proj",
-    "language_model.model.layers.0.mlp.down_proj",
-    "language_model.model.layers.7.self_attn.k_proj",
-    "language_model.model.layers.3.self_attn.k_proj",
-    "language_model.model.layers.5.mlp.up_proj",
-    "language_model.model.layers.10.self_attn.o_proj",
-    "language_model.model.layers.12.self_attn.k_proj",
-    "language_model.model.layers.21.self_attn.k_proj",
+    "language_model.model.layers.27.self_attn.k_proj",
+    "language_model.model.layers.6.self_attn.v_proj",
+    "language_model.model.layers.9.mlp.gate_proj",
+    "language_model.model.layers.17.mlp.down_proj",
+    "language_model.model.layers.26.self_attn.o_proj",
+    "language_model.model.layers.4.mlp.down_proj",
+    "language_model.model.layers.12.self_attn.q_proj",
     "language_model.model.layers.28.self_attn.v_proj",
-    "language_model.model.layers.28.mlp.gate_proj",
-    "language_model.model.layers.20.self_attn.v_proj",
-    "language_model.model.layers.30.mlp.gate_proj",
-    "language_model.model.layers.9.self_attn.v_proj",
-    "language_model.model.layers.10.mlp.gate_proj",
-    "language_model.model.layers.20.mlp.up_proj",
-    "language_model.model.layers.26.mlp.down_proj",
+    "language_model.model.layers.25.self_attn.v_proj",
+    "language_model.model.layers.28.self_attn.k_proj",
+    "language_model.model.layers.7.self_attn.o_proj",
+    "language_model.model.layers.17.mlp.gate_proj",
+    "language_model.model.layers.15.self_attn.q_proj",
     "language_model.model.layers.14.self_attn.o_proj",
-    "language_model.model.layers.10.self_attn.q_proj",
-    "language_model.model.layers.11.mlp.down_proj",
-    "language_model.model.layers.19.self_attn.q_proj",
-    "language_model.model.layers.22.mlp.gate_proj",
-    "language_model.model.layers.13.self_attn.k_proj",
-    "language_model.model.layers.4.mlp.gate_proj",
-    "language_model.model.layers.24.self_attn.k_proj",
-    "language_model.model.layers.24.self_attn.o_proj",
-    "language_model.model.layers.4.self_attn.o_proj",
+    "language_model.model.layers.3.self_attn.v_proj",
+    "language_model.model.layers.5.self_attn.v_proj",
+    "language_model.model.layers.0.mlp.gate_proj",
+    "language_model.model.layers.18.self_attn.q_proj",
+    "language_model.model.layers.2.self_attn.k_proj",
     "language_model.model.layers.29.self_attn.k_proj",
+    "language_model.model.layers.22.self_attn.k_proj",
+    "language_model.model.layers.1.self_attn.v_proj",
     "language_model.model.layers.8.self_attn.k_proj",
-    "language_model.model.layers.8.self_attn.q_proj",
-    "language_model.model.layers.26.mlp.gate_proj",
-    "language_model.model.layers.8.mlp.gate_proj",
-    "language_model.model.layers.17.self_attn.v_proj",
-    "language_model.model.layers.27.self_attn.v_proj",
-    "language_model.model.layers.5.mlp.down_proj",
+    "language_model.model.layers.10.self_attn.k_proj",
+    "language_model.model.layers.5.self_attn.o_proj",
     "language_model.model.layers.4.self_attn.v_proj",
-    "language_model.model.layers.0.self_attn.o_proj",
-    "language_model.model.layers.25.mlp.down_proj",
-    "language_model.model.layers.6.self_attn.o_proj",
-    "language_model.model.layers.21.self_attn.q_proj",
-    "language_model.model.layers.22.self_attn.o_proj",
-    "language_model.model.layers.11.mlp.gate_proj",
-    "language_model.model.layers.16.self_attn.v_proj",
-    "language_model.model.layers.19.self_attn.o_proj",
-    "language_model.model.layers.25.self_attn.q_proj",
-    "language_model.model.layers.24.self_attn.q_proj",
-    "language_model.model.layers.23.mlp.up_proj",
-    "language_model.model.layers.20.mlp.gate_proj",
-    "language_model.model.layers.24.mlp.gate_proj",
-    "language_model.model.layers.26.self_attn.k_proj",
+    "language_model.model.layers.20.self_attn.o_proj",
+    "language_model.model.layers.5.mlp.up_proj",
+    "language_model.model.layers.8.mlp.up_proj",
+    "language_model.model.layers.14.mlp.down_proj",
+    "language_model.model.layers.20.self_attn.q_proj",
+    "language_model.model.layers.28.self_attn.o_proj",
+    "language_model.model.layers.17.self_attn.v_proj",
+    "language_model.model.layers.2.mlp.up_proj",
+    "language_model.model.layers.22.self_attn.v_proj",
+    "language_model.model.layers.30.self_attn.q_proj",
+    "language_model.model.layers.24.self_attn.k_proj",
+    "language_model.model.layers.11.self_attn.o_proj",
+    "language_model.model.layers.22.mlp.down_proj",
+    "language_model.model.layers.11.mlp.up_proj",
+    "language_model.model.layers.9.self_attn.o_proj",
+    "language_model.model.layers.28.mlp.gate_proj",
+    "language_model.model.layers.15.mlp.gate_proj",
+    "language_model.model.layers.2.mlp.down_proj",
+    "language_model.model.layers.14.mlp.gate_proj",
+    "language_model.model.layers.1.self_attn.k_proj",
+    "language_model.model.layers.22.self_attn.q_proj",
+    "language_model.model.layers.8.mlp.gate_proj",
     "language_model.model.layers.2.self_attn.q_proj",
-    "language_model.model.layers.7.self_attn.o_proj",
-    "language_model.model.layers.5.self_attn.k_proj",
     "language_model.model.layers.19.mlp.up_proj",
+    "language_model.model.layers.1.mlp.down_proj",
+    "language_model.model.layers.3.self_attn.o_proj",
+    "language_model.model.layers.18.mlp.down_proj",
+    "language_model.model.layers.25.self_attn.o_proj",
+    "language_model.model.layers.8.mlp.down_proj",
+    "language_model.model.layers.13.mlp.up_proj",
+    "language_model.model.layers.4.mlp.up_proj",
+    "language_model.model.layers.30.mlp.gate_proj",
+    "language_model.model.layers.6.mlp.down_proj",
     "language_model.model.layers.23.self_attn.o_proj",
-    "language_model.model.layers.13.mlp.gate_proj",
-    "language_model.model.layers.3.self_attn.v_proj",
-    "language_model.model.layers.25.self_attn.v_proj",
-    "language_model.model.layers.2.mlp.gate_proj",
-    "language_model.model.layers.8.self_attn.v_proj",
-    "language_model.model.layers.1.mlp.gate_proj",
-    "language_model.model.layers.27.mlp.gate_proj",
-    "language_model.model.layers.27.mlp.up_proj",
-    "language_model.model.layers.29.self_attn.q_proj",
-    "language_model.model.layers.6.self_attn.q_proj",
-    "language_model.model.layers.29.mlp.down_proj",
-    "language_model.model.layers.12.mlp.down_proj",
-    "language_model.model.layers.16.mlp.up_proj",
     "language_model.model.layers.17.mlp.up_proj",
-    "language_model.model.layers.23.self_attn.k_proj",
-    "language_model.model.layers.2.self_attn.k_proj",
-    "language_model.model.layers.6.mlp.gate_proj",
-    "language_model.model.layers.11.self_attn.q_proj",
-    "language_model.model.layers.17.self_attn.o_proj",
-    "language_model.model.layers.4.self_attn.k_proj",
-    "language_model.model.layers.17.mlp.gate_proj",
+    "language_model.model.layers.3.self_attn.k_proj",
+    "language_model.model.layers.22.mlp.up_proj",
+    "language_model.model.layers.13.self_attn.k_proj",
+    "language_model.model.layers.21.self_attn.o_proj",
+    "language_model.model.layers.24.mlp.gate_proj",
+    "language_model.model.layers.27.mlp.gate_proj",
+    "language_model.model.layers.29.mlp.up_proj",
+    "language_model.model.layers.5.self_attn.k_proj",
+    "language_model.model.layers.10.self_attn.o_proj",
+    "language_model.model.layers.16.self_attn.k_proj",
     "language_model.model.layers.24.mlp.up_proj",
-    "language_model.model.layers.24.mlp.down_proj",
-    "language_model.model.layers.2.mlp.down_proj",
-    "language_model.model.layers.17.self_attn.q_proj",
+    "language_model.model.layers.21.mlp.up_proj",
+    "language_model.model.layers.19.mlp.gate_proj",
     "language_model.model.layers.12.mlp.gate_proj",
-    "language_model.model.layers.23.self_attn.v_proj",
-    "language_model.model.layers.0.self_attn.k_proj",
-    "language_model.model.layers.3.mlp.up_proj",
-    "language_model.model.layers.28.mlp.up_proj",
-    "language_model.model.layers.12.self_attn.v_proj",
-    "language_model.model.layers.20.mlp.down_proj",
+    "language_model.model.layers.1.self_attn.q_proj",
+    "language_model.model.layers.12.mlp.up_proj",
+    "language_model.model.layers.7.mlp.down_proj",
+    "language_model.model.layers.10.mlp.down_proj",
+    "language_model.model.layers.13.self_attn.o_proj",
+    "language_model.model.layers.25.self_attn.q_proj",
+    "language_model.model.layers.26.self_attn.v_proj",
+    "language_model.model.layers.16.mlp.up_proj",
+    "language_model.model.layers.8.self_attn.o_proj",
+    "language_model.model.layers.10.mlp.gate_proj",
+    "language_model.model.layers.16.self_attn.o_proj",
+    "language_model.model.layers.17.self_attn.k_proj",
+    "language_model.model.layers.23.mlp.up_proj",
+    "language_model.model.layers.25.mlp.down_proj",
     "language_model.model.layers.25.mlp.up_proj",
-    "language_model.model.layers.9.self_attn.o_proj",
-    "language_model.model.layers.14.self_attn.k_proj",
-    "language_model.model.layers.30.self_attn.q_proj",
-    "language_model.model.layers.6.self_attn.v_proj",
+    "language_model.model.layers.7.self_attn.v_proj",
+    "language_model.model.layers.7.self_attn.k_proj",
+    "language_model.model.layers.19.self_attn.k_proj",
+    "language_model.model.layers.27.mlp.down_proj",
+    "language_model.model.layers.7.mlp.gate_proj",
     "language_model.model.layers.15.self_attn.v_proj",
-    "language_model.model.layers.19.self_attn.v_proj",
-    "language_model.model.layers.19.mlp.gate_proj",
+    "language_model.model.layers.7.self_attn.q_proj",
+    "language_model.model.layers.6.mlp.up_proj",
+    "language_model.model.layers.23.mlp.down_proj",
+    "language_model.model.layers.24.mlp.down_proj",
+    "language_model.model.layers.9.self_attn.k_proj",
+    "language_model.model.layers.16.mlp.gate_proj",
+    "language_model.model.layers.4.self_attn.o_proj",
+    "language_model.model.layers.11.mlp.gate_proj",
+    "language_model.model.layers.23.self_attn.k_proj",
+    "language_model.model.layers.11.self_attn.v_proj",
+    "language_model.model.layers.22.mlp.gate_proj",
+    "language_model.model.layers.5.self_attn.q_proj",
+    "language_model.model.layers.4.mlp.gate_proj",
+    "language_model.model.layers.20.self_attn.v_proj",
+    "language_model.model.layers.17.self_attn.q_proj",
+    "language_model.model.layers.4.self_attn.k_proj",
+    "language_model.model.layers.26.self_attn.k_proj",
     "language_model.model.layers.21.mlp.down_proj",
-    "language_model.model.layers.19.mlp.down_proj",
-    "language_model.model.layers.26.self_attn.q_proj",
-    "language_model.model.layers.31.self_attn.v_proj",
-    "language_model.model.layers.29.mlp.gate_proj",
+    "language_model.model.layers.10.self_attn.v_proj",
+    "language_model.model.layers.12.self_attn.o_proj",
+    "language_model.model.layers.14.self_attn.q_proj",
     "language_model.model.layers.18.mlp.gate_proj",
-    "language_model.model.layers.0.self_attn.v_proj",
-    "language_model.model.layers.30.self_attn.v_proj",
-    "language_model.model.layers.4.mlp.up_proj",
-    "language_model.model.layers.28.self_attn.q_proj",
-    "language_model.model.layers.1.mlp.down_proj",
-    "language_model.model.layers.26.mlp.up_proj",
-    "language_model.model.layers.28.mlp.down_proj",
+    "language_model.model.layers.25.mlp.gate_proj",
+    "language_model.model.layers.23.self_attn.v_proj",
     "language_model.model.layers.2.self_attn.o_proj",
-    "language_model.model.layers.15.mlp.gate_proj",
-    "language_model.model.layers.8.mlp.up_proj",
-    "language_model.model.layers.4.self_attn.q_proj",
-    "language_model.model.layers.27.self_attn.q_proj",
-    "language_model.model.layers.1.self_attn.q_proj",
-    "language_model.model.layers.9.self_attn.q_proj",
+    "language_model.model.layers.15.mlp.down_proj",
+    "language_model.model.layers.12.self_attn.k_proj",
+    "language_model.model.layers.13.mlp.gate_proj",
+    "language_model.model.layers.16.self_attn.v_proj",
+    "language_model.model.layers.27.self_attn.v_proj",
+    "language_model.model.layers.16.self_attn.q_proj",
+    "language_model.model.layers.19.self_attn.q_proj",
+    "language_model.model.layers.21.self_attn.k_proj",
+    "language_model.model.layers.18.self_attn.o_proj",
+    "language_model.model.layers.0.mlp.down_proj",
+    "language_model.model.layers.31.mlp.gate_proj",
+    "language_model.model.layers.6.self_attn.q_proj",
     "language_model.model.layers.31.mlp.down_proj",
-    "language_model.model.layers.5.self_attn.v_proj",
-    "language_model.model.layers.21.mlp.gate_proj",
-    "language_model.model.layers.12.self_attn.o_proj",
-    "language_model.model.layers.30.mlp.up_proj",
-    "language_model.model.layers.1.self_attn.k_proj",
-    "language_model.model.layers.26.self_attn.v_proj",
-    "language_model.model.layers.31.self_attn.o_proj",
-    "language_model.model.layers.8.mlp.down_proj",
-    "language_model.model.layers.7.mlp.up_proj",
-    "language_model.model.layers.13.self_attn.q_proj",
-    "language_model.model.layers.25.mlp.gate_proj",
-    "language_model.model.layers.6.mlp.up_proj",
-    "language_model.model.layers.5.self_attn.o_proj",
-    "language_model.model.layers.10.mlp.up_proj",
-    "language_model.model.layers.16.mlp.gate_proj",
-    "language_model.model.layers.19.self_attn.k_proj",
-    "language_model.model.layers.7.mlp.down_proj",
-    "language_model.model.layers.3.mlp.gate_proj",
-    "language_model.model.layers.15.self_attn.q_proj",
-    "language_model.model.layers.22.self_attn.v_proj",
-    "language_model.model.layers.22.mlp.up_proj",
-    "language_model.model.layers.6.self_attn.k_proj",
-    "language_model.model.layers.1.self_attn.o_proj",
-    "language_model.model.layers.15.self_attn.o_proj",
+    "language_model.model.layers.28.mlp.up_proj",
+    "language_model.model.layers.9.mlp.down_proj",
+    "language_model.model.layers.17.self_attn.o_proj",
+    "language_model.model.layers.28.mlp.down_proj",
+    "language_model.model.layers.0.self_attn.k_proj",
     "language_model.model.layers.13.self_attn.v_proj",
-    "language_model.model.layers.31.self_attn.k_proj",
+    "language_model.model.layers.20.mlp.up_proj",
+    "language_model.model.layers.29.self_attn.o_proj",
+    "language_model.model.layers.2.mlp.gate_proj",
     "language_model.model.layers.14.mlp.up_proj",
-    "language_model.model.layers.23.self_attn.q_proj",
-    "language_model.model.layers.23.mlp.down_proj",
-    "language_model.model.layers.23.mlp.gate_proj",
-    "language_model.model.layers.5.mlp.gate_proj",
-    "language_model.model.layers.18.self_attn.q_proj",
-    "language_model.model.layers.13.mlp.down_proj",
-    "language_model.model.layers.13.mlp.up_proj",
-    "language_model.model.layers.10.mlp.down_proj",
+    "language_model.model.layers.18.self_attn.k_proj",
+    "language_model.model.layers.9.self_attn.q_proj",
+    "language_model.model.layers.3.mlp.gate_proj",
+    "language_model.model.layers.9.self_attn.v_proj",
+    "language_model.model.layers.0.self_attn.v_proj",
+    "language_model.model.layers.6.self_attn.k_proj",
+    "language_model.model.layers.6.mlp.gate_proj",
+    "language_model.model.layers.12.mlp.down_proj",
+    "language_model.model.layers.24.self_attn.o_proj",
     "language_model.model.layers.18.mlp.up_proj",
-    "language_model.model.layers.18.self_attn.o_proj",
-    "language_model.model.layers.20.self_attn.o_proj",
-    "language_model.model.layers.21.self_attn.o_proj",
-    "language_model.model.layers.1.mlp.up_proj",
-    "language_model.model.layers.18.self_attn.v_proj",
-    "language_model.model.layers.3.mlp.down_proj",
-    "language_model.model.layers.31.mlp.gate_proj",
-    "language_model.model.layers.7.self_attn.v_proj",
-    "language_model.model.layers.14.self_attn.q_proj",
-    "language_model.model.layers.16.self_attn.k_proj",
-    "language_model.model.layers.10.self_attn.k_proj",
-    "language_model.model.layers.26.self_attn.o_proj",
-    "language_model.model.layers.27.mlp.down_proj",
+    "language_model.model.layers.22.self_attn.o_proj",
+    "language_model.model.layers.15.self_attn.k_proj",
+    "language_model.model.layers.8.self_attn.v_proj",
+    "language_model.model.layers.9.mlp.up_proj",
+    "language_model.model.layers.29.mlp.gate_proj",
+    "language_model.model.layers.25.self_attn.k_proj",
+    "language_model.model.layers.29.self_attn.q_proj",
     "language_model.model.layers.30.self_attn.k_proj",
-    "language_model.model.layers.22.mlp.down_proj",
-    "language_model.model.layers.31.self_attn.q_proj",
-    "language_model.model.layers.27.self_attn.k_proj",
+    "language_model.model.layers.1.mlp.gate_proj",
     "language_model.model.layers.0.mlp.up_proj",
-    "language_model.model.layers.2.mlp.up_proj",
-    "language_model.model.layers.4.mlp.down_proj",
-    "language_model.model.layers.29.mlp.up_proj",
-    "language_model.model.layers.30.self_attn.o_proj",
-    "language_model.model.layers.29.self_attn.v_proj",
-    "language_model.model.layers.9.self_attn.k_proj",
-    "language_model.model.layers.15.mlp.up_proj",
-    "language_model.model.layers.20.self_attn.k_proj",
-    "language_model.model.layers.10.self_attn.v_proj",
-    "language_model.model.layers.28.self_attn.k_proj",
-    "language_model.model.layers.24.self_attn.v_proj",
-    "language_model.model.layers.16.self_attn.o_proj",
-    "language_model.model.layers.9.mlp.up_proj",
-    "language_model.model.layers.21.mlp.up_proj",
-    "language_model.model.layers.7.self_attn.q_proj",
-    "language_model.model.layers.29.self_attn.o_proj",
-    "language_model.model.layers.22.self_attn.k_proj",
-    "language_model.model.layers.11.mlp.up_proj",
-    "language_model.model.layers.30.mlp.down_proj",
-    "language_model.model.layers.9.mlp.down_proj",
-    "language_model.model.layers.11.self_attn.o_proj",
-    "language_model.model.layers.27.self_attn.o_proj",
-    "language_model.model.layers.13.self_attn.o_proj",
-    "language_model.model.layers.5.self_attn.q_proj",
-    "language_model.model.layers.22.self_attn.q_proj",
-    "language_model.model.layers.11.self_attn.v_proj",
-    "language_model.model.layers.9.mlp.gate_proj"
+    "language_model.model.layers.20.mlp.gate_proj",
+    "language_model.model.layers.2.self_attn.v_proj",
+    "language_model.model.layers.14.self_attn.k_proj",
+    "language_model.model.layers.28.self_attn.q_proj",
+    "language_model.model.layers.31.self_attn.q_proj",
+    "language_model.model.layers.5.mlp.down_proj",
+    "language_model.model.layers.19.self_attn.v_proj",
+    "language_model.model.layers.18.self_attn.v_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0c1f28ef1e24fac37be348d9382b1c320467b278afad6ede8d35c106b5d07e0
+oid sha256:b0ccf8b933c533e5044ca2d54fa35294a3aca9e61063bc6ad8084f89ddec82bd
 size 671155888

runs/Aug23_00-06-57_489e51884fd6/events.out.tfevents.1724371634.489e51884fd6.1728.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8fb87dd42d14f4c2463fee0208395ec13faede8058e4eb1b76dd6bdcf1a1beb
+size 6615

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b7f7c7218d67a7f38a892ef27202d938bb2fbc03e1ad21cbf4f781ff04c0e7
+oid sha256:5a8d9de4cd00985d3660611a3666d607106ed387826f43ee1d0767bc5f4dd52d
 size 5176