Training in progress, step 100

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42ef37c9508597d911a7646f1d0ef41bd787d6e06e842227929ee6e0ef071112
+oid sha256:261fd77e23c089a8cb121b0e662a5d35a31fd26c3d3c812406352afb532ad0b8
 size 671155888

runs/Aug17_00-00-14_1a98b7359127/events.out.tfevents.1723852817.1a98b7359127.2488.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ae211554fa1401ffa118462445f7bd44300fcf54c395f7c82b8085eafdae7c
+size 6404

runs/Aug17_00-03-44_1a98b7359127/events.out.tfevents.1723853027.1a98b7359127.2488.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2a5576c68d5e9f201a65d71e351728f15482a723c68c2428395506d43a5e29f
+size 6142

runs/Aug17_00-04-16_1a98b7359127/events.out.tfevents.1723853058.1a98b7359127.2488.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c54e5a1deb4f34e64ab108ceeb976bbbb4c49d6ca77cd38d471781175d6757
+size 6615

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae673b3d3e98c8e758204c9af6d4d269cc45fb48b319b18cf2328697f130f9d4
+oid sha256:03dbc6be6f0459f8b572bcdf13cb022d7c9221b740c60e1501d3ff8ac8439fad
 size 5176