Training in progress, step 80

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": "llava-hf/llava-v1.6-mistral-7b-hf",
+  "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.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.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.6.mlp.down_proj",
+    "language_model.model.layers.26.mlp.up_proj",
+    "language_model.model.layers.15.self_attn.o_proj",
+    "language_model.model.layers.6.mlp.up_proj",
+    "language_model.model.layers.20.self_attn.v_proj",
+    "language_model.model.layers.20.self_attn.q_proj",
+    "language_model.model.layers.20.self_attn.k_proj",
+    "language_model.model.layers.29.self_attn.k_proj",
+    "language_model.model.layers.25.self_attn.k_proj",
+    "language_model.model.layers.12.self_attn.q_proj",
+    "language_model.model.layers.27.self_attn.v_proj",
+    "language_model.model.layers.14.mlp.up_proj",
+    "language_model.model.layers.2.mlp.down_proj",
+    "language_model.model.layers.2.mlp.gate_proj",
     "language_model.model.layers.14.self_attn.q_proj",
-    "language_model.model.layers.9.mlp.up_proj",
+    "language_model.model.layers.17.self_attn.o_proj",
+    "language_model.model.layers.23.self_attn.q_proj",
+    "language_model.model.layers.5.self_attn.k_proj",
+    "language_model.model.layers.12.mlp.gate_proj",
+    "language_model.model.layers.4.self_attn.q_proj",
+    "language_model.model.layers.22.self_attn.v_proj",
+    "language_model.model.layers.12.self_attn.k_proj",
+    "language_model.model.layers.24.mlp.gate_proj",
+    "language_model.model.layers.18.self_attn.k_proj",
+    "language_model.model.layers.4.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.3.mlp.down_proj",
+    "language_model.model.layers.8.self_attn.v_proj",
+    "language_model.model.layers.11.self_attn.k_proj",
+    "language_model.model.layers.31.self_attn.v_proj",
+    "language_model.model.layers.3.mlp.up_proj",
+    "language_model.model.layers.11.mlp.gate_proj",
+    "language_model.model.layers.14.self_attn.v_proj",
+    "language_model.model.layers.25.mlp.up_proj",
+    "language_model.model.layers.18.self_attn.o_proj",
+    "language_model.model.layers.28.mlp.up_proj",
+    "language_model.model.layers.5.self_attn.v_proj",
+    "language_model.model.layers.12.self_attn.v_proj",
+    "language_model.model.layers.14.self_attn.o_proj",
+    "language_model.model.layers.0.mlp.gate_proj",
+    "language_model.model.layers.22.self_attn.o_proj",
+    "language_model.model.layers.31.self_attn.q_proj",
+    "language_model.model.layers.19.self_attn.o_proj",
+    "language_model.model.layers.19.self_attn.q_proj",
+    "language_model.model.layers.28.mlp.gate_proj",
+    "language_model.model.layers.0.mlp.up_proj",
+    "language_model.model.layers.16.self_attn.v_proj",
+    "language_model.model.layers.15.self_attn.q_proj",
+    "language_model.model.layers.8.self_attn.o_proj",
+    "language_model.model.layers.3.self_attn.v_proj",
+    "language_model.model.layers.10.self_attn.q_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.19.mlp.down_proj",
+    "language_model.model.layers.1.mlp.gate_proj",
+    "language_model.model.layers.18.mlp.gate_proj",
+    "language_model.model.layers.26.mlp.down_proj",
+    "language_model.model.layers.7.mlp.down_proj",
+    "language_model.model.layers.4.mlp.down_proj",
+    "language_model.model.layers.0.mlp.down_proj",
+    "language_model.model.layers.3.self_attn.o_proj",
+    "language_model.model.layers.11.self_attn.o_proj",
+    "language_model.model.layers.18.self_attn.q_proj",
+    "language_model.model.layers.6.self_attn.v_proj",
+    "language_model.model.layers.31.mlp.gate_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.13.mlp.gate_proj",
+    "language_model.model.layers.5.mlp.down_proj",
+    "language_model.model.layers.19.self_attn.v_proj",
+    "language_model.model.layers.24.mlp.up_proj",
+    "language_model.model.layers.6.mlp.gate_proj",
+    "language_model.model.layers.6.self_attn.q_proj",
+    "language_model.model.layers.27.mlp.down_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.25.mlp.down_proj",
+    "language_model.model.layers.18.self_attn.v_proj",
+    "language_model.model.layers.31.self_attn.o_proj",
+    "language_model.model.layers.20.self_attn.o_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.16.self_attn.k_proj",
+    "language_model.model.layers.13.self_attn.o_proj",
+    "language_model.model.layers.15.mlp.down_proj",
+    "language_model.model.layers.26.self_attn.k_proj",
+    "language_model.model.layers.11.self_attn.v_proj",
+    "language_model.model.layers.3.self_attn.k_proj",
     "language_model.model.layers.9.self_attn.o_proj",
+    "language_model.model.layers.8.mlp.up_proj",
+    "language_model.model.layers.6.self_attn.k_proj",
+    "language_model.model.layers.13.self_attn.k_proj",
+    "language_model.model.layers.13.mlp.up_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.v_proj",
+    "language_model.model.layers.28.mlp.down_proj",
+    "language_model.model.layers.17.self_attn.v_proj",
+    "language_model.model.layers.24.self_attn.q_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.29.self_attn.o_proj",
+    "language_model.model.layers.7.self_attn.v_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.10.self_attn.k_proj",
+    "language_model.model.layers.30.mlp.down_proj",
     "language_model.model.layers.29.mlp.up_proj",
-    "language_model.model.layers.13.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.28.self_attn.q_proj",
+    "language_model.model.layers.30.self_attn.v_proj",
     "language_model.model.layers.7.self_attn.o_proj",
+    "language_model.model.layers.21.mlp.up_proj",
+    "language_model.model.layers.17.self_attn.q_proj",
+    "language_model.model.layers.0.self_attn.q_proj",
+    "language_model.model.layers.25.self_attn.o_proj",
+    "language_model.model.layers.3.self_attn.q_proj",
+    "language_model.model.layers.0.self_attn.v_proj",
+    "language_model.model.layers.2.mlp.up_proj",
     "language_model.model.layers.21.self_attn.k_proj",
-    "language_model.model.layers.12.self_attn.v_proj",
-    "language_model.model.layers.20.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.6.mlp.gate_proj",
-    "language_model.model.layers.10.mlp.gate_proj",
+    "language_model.model.layers.24.self_attn.o_proj",
+    "language_model.model.layers.14.self_attn.k_proj",
+    "language_model.model.layers.15.mlp.up_proj",
+    "language_model.model.layers.29.mlp.down_proj",
     "language_model.model.layers.16.mlp.gate_proj",
-    "language_model.model.layers.23.mlp.up_proj",
+    "language_model.model.layers.2.self_attn.k_proj",
+    "language_model.model.layers.23.self_attn.v_proj",
+    "language_model.model.layers.30.self_attn.o_proj",
+    "language_model.model.layers.30.self_attn.k_proj",
+    "language_model.model.layers.4.self_attn.v_proj",
+    "language_model.model.layers.6.self_attn.o_proj",
+    "language_model.model.layers.15.self_attn.k_proj",
+    "language_model.model.layers.18.mlp.up_proj",
+    "language_model.model.layers.12.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.10.self_attn.o_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.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.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.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.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.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.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.23.mlp.down_proj",
+    "language_model.model.layers.29.self_attn.q_proj",
+    "language_model.model.layers.29.mlp.gate_proj",
+    "language_model.model.layers.12.mlp.down_proj",
+    "language_model.model.layers.15.self_attn.v_proj",
+    "language_model.model.layers.25.mlp.gate_proj",
+    "language_model.model.layers.21.self_attn.q_proj",
+    "language_model.model.layers.26.self_attn.q_proj",
+    "language_model.model.layers.22.mlp.down_proj",
+    "language_model.model.layers.27.self_attn.q_proj",
     "language_model.model.layers.4.mlp.gate_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.0.self_attn.k_proj",
+    "language_model.model.layers.30.self_attn.q_proj",
+    "language_model.model.layers.7.mlp.gate_proj",
+    "language_model.model.layers.2.self_attn.q_proj",
+    "language_model.model.layers.10.mlp.gate_proj",
+    "language_model.model.layers.0.self_attn.o_proj",
+    "language_model.model.layers.9.self_attn.q_proj",
+    "language_model.model.layers.1.mlp.down_proj",
+    "language_model.model.layers.30.mlp.gate_proj",
+    "language_model.model.layers.27.mlp.gate_proj",
+    "language_model.model.layers.10.mlp.up_proj",
+    "language_model.model.layers.27.mlp.up_proj",
+    "language_model.model.layers.4.self_attn.k_proj",
+    "language_model.model.layers.17.mlp.down_proj",
     "language_model.model.layers.17.mlp.gate_proj",
+    "language_model.model.layers.9.self_attn.v_proj",
     "language_model.model.layers.20.mlp.up_proj",
+    "language_model.model.layers.21.self_attn.v_proj",
+    "language_model.model.layers.7.self_attn.q_proj",
+    "language_model.model.layers.31.self_attn.k_proj",
+    "language_model.model.layers.9.mlp.up_proj",
+    "language_model.model.layers.11.self_attn.q_proj",
+    "language_model.model.layers.23.self_attn.k_proj",
+    "language_model.model.layers.25.self_attn.v_proj",
+    "language_model.model.layers.26.mlp.gate_proj",
+    "language_model.model.layers.10.self_attn.v_proj",
+    "language_model.model.layers.5.mlp.up_proj",
+    "language_model.model.layers.1.self_attn.v_proj",
+    "language_model.model.layers.1.self_attn.q_proj",
+    "language_model.model.layers.27.self_attn.k_proj",
+    "language_model.model.layers.28.self_attn.v_proj",
+    "language_model.model.layers.21.self_attn.o_proj",
     "language_model.model.layers.31.mlp.down_proj",
-    "language_model.model.layers.30.self_attn.k_proj",
+    "language_model.model.layers.8.self_attn.q_proj",
+    "language_model.model.layers.22.mlp.gate_proj",
+    "language_model.model.layers.23.mlp.gate_proj",
+    "language_model.model.layers.24.mlp.down_proj",
+    "language_model.model.layers.14.mlp.down_proj",
+    "language_model.model.layers.3.mlp.gate_proj",
+    "language_model.model.layers.27.self_attn.o_proj",
+    "language_model.model.layers.1.self_attn.o_proj",
+    "language_model.model.layers.13.self_attn.q_proj",
+    "language_model.model.layers.21.mlp.down_proj",
     "language_model.model.layers.16.mlp.up_proj",
-    "language_model.model.layers.17.mlp.down_proj",
-    "language_model.model.layers.22.self_attn.v_proj",
+    "language_model.model.layers.9.mlp.down_proj",
+    "language_model.model.layers.23.mlp.up_proj",
+    "language_model.model.layers.31.mlp.up_proj",
+    "language_model.model.layers.5.self_attn.q_proj",
+    "language_model.model.layers.7.self_attn.k_proj",
+    "language_model.model.layers.25.self_attn.q_proj",
+    "language_model.model.layers.16.self_attn.o_proj",
+    "language_model.model.layers.22.mlp.up_proj",
+    "language_model.model.layers.7.mlp.up_proj",
+    "language_model.model.layers.12.self_attn.o_proj",
+    "language_model.model.layers.20.mlp.gate_proj",
+    "language_model.model.layers.5.mlp.gate_proj",
     "language_model.model.layers.1.mlp.up_proj",
+    "language_model.model.layers.5.self_attn.o_proj",
+    "language_model.model.layers.17.self_attn.k_proj",
+    "language_model.model.layers.19.mlp.up_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.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.11.mlp.down_proj",
+    "language_model.model.layers.13.self_attn.v_proj",
+    "language_model.model.layers.16.mlp.down_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.9.self_attn.k_proj",
+    "language_model.model.layers.1.self_attn.k_proj",
+    "language_model.model.layers.9.mlp.gate_proj",
     "language_model.model.layers.8.self_attn.k_proj",
-    "language_model.model.layers.29.self_attn.k_proj",
-    "language_model.model.layers.18.self_attn.v_proj",
-    "language_model.model.layers.30.mlp.down_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.23.self_attn.v_proj",
+    "language_model.model.layers.22.self_attn.q_proj",
+    "language_model.model.layers.4.self_attn.o_proj",
+    "language_model.model.layers.2.self_attn.v_proj",
+    "language_model.model.layers.18.mlp.down_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.7.self_attn.k_proj"
+    "language_model.model.layers.10.mlp.down_proj",
+    "language_model.model.layers.24.self_attn.k_proj",
+    "language_model.model.layers.19.self_attn.k_proj",
+    "language_model.model.layers.14.mlp.gate_proj",
+    "language_model.model.layers.17.mlp.up_proj",
+    "language_model.model.layers.15.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:a6403422e5460845a2fbeb6c3339a84b6186e5d57b28404cac1618f75ab9d5c7
+oid sha256:1eb0de7f0a051b926bf7e52f72eaf134f6db9eb4ba8ff8d5b35686ceb1f8c5cf
 size 671155888

runs/Aug20_01-46-25_b9da09b5d9ef/events.out.tfevents.1724118403.b9da09b5d9ef.452.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c59e2b4f20dfac1159e17a715c885aaf6b800b3339fda3c88b55cf11a7b7db9
+size 6599

tokenizer.json

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Left",
+    "pad_to_multiple_of": null,
+    "pad_id": 32001,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03dbc6be6f0459f8b572bcdf13cb022d7c9221b740c60e1501d3ff8ac8439fad
+oid sha256:f2156d4e72def29decfe6c554fd404ac954538d65b87e9616e2edae1cab2477f
 size 5176