Training in progress, step 100

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "LlavaNextForConditionalGeneration",
     "parent_library": "transformers.models.llava_next.modeling_llava_next"
   },
-  "base_model_name_or_path": "looppayments/llava-7b-addresses-only",
+  "base_model_name_or_path": "looppayments/llava-7b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,230 +23,230 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "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.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.22.self_attn.v_proj",
+    "language_model.model.layers.10.self_attn.k_proj",
+    "language_model.model.layers.26.self_attn.o_proj",
+    "language_model.model.layers.22.self_attn.k_proj",
+    "language_model.model.layers.23.mlp.up_proj",
+    "language_model.model.layers.4.mlp.gate_proj",
+    "language_model.model.layers.11.mlp.up_proj",
+    "language_model.model.layers.17.self_attn.q_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.16.mlp.down_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.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.3.self_attn.o_proj",
+    "language_model.model.layers.3.mlp.gate_proj",
+    "language_model.model.layers.20.self_attn.o_proj",
+    "language_model.model.layers.7.self_attn.v_proj",
     "language_model.model.layers.26.mlp.gate_proj",
+    "language_model.model.layers.6.mlp.gate_proj",
+    "language_model.model.layers.16.self_attn.q_proj",
+    "language_model.model.layers.9.mlp.up_proj",
+    "language_model.model.layers.17.self_attn.k_proj",
+    "language_model.model.layers.8.self_attn.k_proj",
+    "language_model.model.layers.18.self_attn.o_proj",
+    "language_model.model.layers.17.mlp.up_proj",
+    "language_model.model.layers.29.self_attn.o_proj",
+    "language_model.model.layers.28.mlp.down_proj",
+    "language_model.model.layers.15.mlp.up_proj",
+    "language_model.model.layers.0.mlp.gate_proj",
+    "language_model.model.layers.9.mlp.gate_proj",
+    "language_model.model.layers.19.mlp.down_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.9.self_attn.o_proj",
+    "language_model.model.layers.5.self_attn.o_proj",
+    "language_model.model.layers.13.self_attn.o_proj",
+    "language_model.model.layers.31.mlp.up_proj",
+    "language_model.model.layers.17.self_attn.v_proj",
+    "language_model.model.layers.31.self_attn.v_proj",
+    "language_model.model.layers.6.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.16.self_attn.o_proj",
+    "language_model.model.layers.7.self_attn.k_proj",
+    "language_model.model.layers.18.self_attn.v_proj",
+    "language_model.model.layers.1.self_attn.q_proj",
+    "language_model.model.layers.2.mlp.gate_proj",
+    "language_model.model.layers.22.mlp.up_proj",
+    "language_model.model.layers.19.self_attn.q_proj",
+    "language_model.model.layers.16.self_attn.k_proj",
+    "language_model.model.layers.30.self_attn.k_proj",
+    "language_model.model.layers.2.self_attn.k_proj",
+    "language_model.model.layers.29.self_attn.v_proj",
+    "language_model.model.layers.26.mlp.down_proj",
+    "language_model.model.layers.0.self_attn.q_proj",
+    "language_model.model.layers.7.mlp.gate_proj",
+    "language_model.model.layers.21.mlp.gate_proj",
+    "language_model.model.layers.30.self_attn.o_proj",
+    "language_model.model.layers.3.self_attn.k_proj",
+    "language_model.model.layers.5.self_attn.q_proj",
+    "language_model.model.layers.5.mlp.gate_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.19.self_attn.v_proj",
+    "language_model.model.layers.4.mlp.up_proj",
+    "language_model.model.layers.8.mlp.down_proj",
+    "language_model.model.layers.25.mlp.up_proj",
+    "language_model.model.layers.26.self_attn.v_proj",
+    "language_model.model.layers.1.mlp.up_proj",
+    "language_model.model.layers.19.mlp.up_proj",
+    "language_model.model.layers.24.mlp.up_proj",
+    "language_model.model.layers.23.self_attn.o_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.3.mlp.up_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.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.7.mlp.down_proj",
+    "language_model.model.layers.26.self_attn.q_proj",
+    "language_model.model.layers.0.self_attn.o_proj",
+    "language_model.model.layers.16.mlp.down_proj",
+    "language_model.model.layers.21.self_attn.q_proj",
+    "language_model.model.layers.18.self_attn.k_proj",
+    "language_model.model.layers.20.self_attn.k_proj",
+    "language_model.model.layers.23.self_attn.k_proj",
+    "language_model.model.layers.26.mlp.up_proj",
+    "language_model.model.layers.0.self_attn.v_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.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.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.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.27.self_attn.q_proj",
+    "language_model.model.layers.29.mlp.up_proj",
+    "language_model.model.layers.31.self_attn.k_proj",
+    "language_model.model.layers.6.mlp.up_proj",
+    "language_model.model.layers.11.self_attn.q_proj",
+    "language_model.model.layers.31.self_attn.q_proj",
+    "language_model.model.layers.25.self_attn.k_proj",
+    "language_model.model.layers.24.self_attn.v_proj",
+    "language_model.model.layers.23.self_attn.v_proj",
+    "language_model.model.layers.7.self_attn.q_proj",
+    "language_model.model.layers.2.self_attn.v_proj",
+    "language_model.model.layers.31.mlp.gate_proj",
+    "language_model.model.layers.10.self_attn.o_proj",
+    "language_model.model.layers.18.mlp.up_proj",
+    "language_model.model.layers.11.self_attn.v_proj",
+    "language_model.model.layers.16.mlp.gate_proj",
+    "language_model.model.layers.20.self_attn.v_proj",
+    "language_model.model.layers.31.self_attn.o_proj",
+    "language_model.model.layers.6.self_attn.q_proj",
+    "language_model.model.layers.17.self_attn.o_proj",
+    "language_model.model.layers.10.self_attn.q_proj",
+    "language_model.model.layers.23.mlp.down_proj",
+    "language_model.model.layers.8.self_attn.o_proj",
+    "language_model.model.layers.0.mlp.down_proj",
+    "language_model.model.layers.22.self_attn.o_proj",
+    "language_model.model.layers.4.self_attn.k_proj",
+    "language_model.model.layers.14.self_attn.k_proj",
+    "language_model.model.layers.24.self_attn.o_proj",
+    "language_model.model.layers.25.self_attn.v_proj",
+    "language_model.model.layers.17.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.17.mlp.up_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.2.self_attn.o_proj",
+    "language_model.model.layers.14.mlp.gate_proj",
+    "language_model.model.layers.25.mlp.gate_proj",
+    "language_model.model.layers.22.mlp.down_proj",
+    "language_model.model.layers.27.mlp.down_proj",
+    "language_model.model.layers.23.self_attn.q_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.8.mlp.gate_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.16.self_attn.v_proj",
+    "language_model.model.layers.29.self_attn.k_proj",
+    "language_model.model.layers.15.mlp.down_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.1.self_attn.q_proj",
+    "language_model.model.layers.30.mlp.up_proj",
+    "language_model.model.layers.24.mlp.gate_proj",
+    "language_model.model.layers.11.mlp.gate_proj",
+    "language_model.model.layers.15.self_attn.q_proj",
+    "language_model.model.layers.24.mlp.down_proj",
+    "language_model.model.layers.28.self_attn.q_proj",
+    "language_model.model.layers.9.mlp.down_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.28.self_attn.o_proj",
+    "language_model.model.layers.27.mlp.gate_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.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.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.27.self_attn.v_proj",
+    "language_model.model.layers.29.mlp.down_proj",
+    "language_model.model.layers.8.self_attn.v_proj",
+    "language_model.model.layers.8.mlp.up_proj",
+    "language_model.model.layers.21.self_attn.v_proj",
+    "language_model.model.layers.14.self_attn.o_proj",
+    "language_model.model.layers.2.mlp.down_proj",
+    "language_model.model.layers.12.self_attn.q_proj",
+    "language_model.model.layers.14.mlp.up_proj",
+    "language_model.model.layers.6.self_attn.v_proj",
+    "language_model.model.layers.11.self_attn.o_proj",
+    "language_model.model.layers.22.self_attn.q_proj",
+    "language_model.model.layers.0.self_attn.k_proj",
+    "language_model.model.layers.14.mlp.down_proj",
+    "language_model.model.layers.28.self_attn.v_proj",
+    "language_model.model.layers.4.self_attn.v_proj",
+    "language_model.model.layers.1.self_attn.v_proj",
+    "language_model.model.layers.5.mlp.down_proj",
+    "language_model.model.layers.15.self_attn.o_proj",
+    "language_model.model.layers.30.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.10.self_attn.v_proj",
+    "language_model.model.layers.28.self_attn.k_proj",
+    "language_model.model.layers.12.self_attn.k_proj",
     "language_model.model.layers.12.self_attn.o_proj",
+    "language_model.model.layers.12.self_attn.v_proj",
+    "language_model.model.layers.15.self_attn.v_proj",
+    "language_model.model.layers.10.mlp.up_proj",
+    "language_model.model.layers.13.self_attn.k_proj",
+    "language_model.model.layers.9.self_attn.v_proj",
+    "language_model.model.layers.19.mlp.gate_proj",
+    "language_model.model.layers.12.mlp.gate_proj",
+    "language_model.model.layers.25.mlp.down_proj",
+    "language_model.model.layers.10.mlp.down_proj",
+    "language_model.model.layers.24.self_attn.k_proj",
+    "language_model.model.layers.30.mlp.down_proj",
+    "language_model.model.layers.20.self_attn.q_proj",
+    "language_model.model.layers.13.mlp.up_proj",
+    "language_model.model.layers.12.mlp.down_proj",
+    "language_model.model.layers.31.mlp.down_proj",
+    "language_model.model.layers.13.self_attn.q_proj",
     "language_model.model.layers.14.self_attn.q_proj",
     "language_model.model.layers.18.mlp.gate_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.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.6.self_attn.k_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.29.self_attn.q_proj",
+    "language_model.model.layers.1.self_attn.k_proj",
+    "language_model.model.layers.11.self_attn.k_proj",
+    "language_model.model.layers.23.mlp.gate_proj",
+    "language_model.model.layers.1.mlp.gate_proj",
+    "language_model.model.layers.30.self_attn.q_proj",
+    "language_model.model.layers.2.self_attn.q_proj",
+    "language_model.model.layers.3.self_attn.q_proj",
+    "language_model.model.layers.27.mlp.up_proj",
+    "language_model.model.layers.7.mlp.up_proj",
+    "language_model.model.layers.9.self_attn.k_proj",
+    "language_model.model.layers.21.mlp.down_proj",
     "language_model.model.layers.13.self_attn.v_proj",
+    "language_model.model.layers.20.mlp.down_proj",
+    "language_model.model.layers.15.mlp.gate_proj",
+    "language_model.model.layers.27.self_attn.o_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.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.22.self_attn.o_proj",
+    "language_model.model.layers.7.self_attn.o_proj",
+    "language_model.model.layers.13.mlp.down_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.1.mlp.gate_proj",
+    "language_model.model.layers.30.self_attn.v_proj",
+    "language_model.model.layers.2.mlp.up_proj",
+    "language_model.model.layers.18.self_attn.q_proj",
+    "language_model.model.layers.1.mlp.down_proj",
+    "language_model.model.layers.5.self_attn.v_proj",
     "language_model.model.layers.0.mlp.up_proj",
+    "language_model.model.layers.13.mlp.gate_proj",
+    "language_model.model.layers.24.self_attn.q_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"
+    "language_model.model.layers.22.mlp.gate_proj",
+    "language_model.model.layers.14.self_attn.v_proj",
+    "language_model.model.layers.29.mlp.gate_proj",
+    "language_model.model.layers.17.mlp.gate_proj",
+    "language_model.model.layers.8.self_attn.q_proj",
+    "language_model.model.layers.3.mlp.down_proj",
+    "language_model.model.layers.9.self_attn.q_proj",
+    "language_model.model.layers.16.mlp.up_proj",
+    "language_model.model.layers.26.self_attn.k_proj",
+    "language_model.model.layers.5.mlp.up_proj",
+    "language_model.model.layers.10.self_attn.v_proj",
+    "language_model.model.layers.25.self_attn.q_proj",
+    "language_model.model.layers.21.self_attn.k_proj",
+    "language_model.model.layers.4.self_attn.q_proj",
+    "language_model.model.layers.28.mlp.gate_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2699a27696db6970a43823f257b459046898f9766be25adf8d25e35e81e47e4f
+oid sha256:bfe2e7286bf87e3f1ac51f31ddb19c8b01dd81b833044b2e9dc76df918a3b2b5
 size 671155888

runs/Aug24_20-50-27_30c7f4b99727/events.out.tfevents.1724532628.30c7f4b99727.1120.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096c1cf2ced19922515f006f8ac69066b4cb17523186ad408920e435d74d6677
+size 6603

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a8d9de4cd00985d3660611a3666d607106ed387826f43ee1d0767bc5f4dd52d
+oid sha256:a9705c43870aab9b4f8f7430c4101dad026bcdc2e4f05126d3ac42f0e87f23b3
 size 5176