Training in progress, step 500

adapter_config.json

@@ -13,387 +13,387 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 64,
   "lora_dropout": 0.2,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "language_model.model.layers.31.self_attn.v_proj",
-    "language_model.model.layers.4.self_attn.o_proj",
-    "language_model.model.layers.1.self_attn.o_proj",
-    "language_model.model.layers.6.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.6.mlp.fc1",
-    "language_model.model.layers.2.mlp.down_proj",
-    "language_model.model.layers.28.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
-    "language_model.model.layers.27.mlp.up_proj",
+    "language_model.model.layers.23.self_attn.k_proj",
     "language_model.model.layers.26.mlp.up_proj",
-    "language_model.model.layers.3.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.13.mlp.fc2",
-    "language_model.model.layers.6.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
-    "language_model.model.layers.29.mlp.up_proj",
-    "language_model.model.layers.7.mlp.up_proj",
-    "language_model.model.layers.30.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
-    "language_model.model.layers.8.self_attn.o_proj",
-    "language_model.model.layers.15.mlp.up_proj",
-    "language_model.model.layers.20.mlp.up_proj",
-    "language_model.model.layers.24.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.22.mlp.fc2",
-    "language_model.model.layers.21.self_attn.k_proj",
-    "language_model.model.layers.24.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
-    "language_model.model.layers.16.self_attn.o_proj",
-    "language_model.model.layers.27.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
-    "language_model.model.layers.24.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.16.mlp.fc1",
-    "multi_modal_projector.linear_1",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
-    "language_model.model.layers.22.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.9.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.8.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
+    "language_model.model.layers.28.self_attn.o_proj",
+    "language_model.model.layers.22.mlp.up_proj",
+    "language_model.model.layers.15.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
+    "language_model.model.layers.6.mlp.gate_proj",
     "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
-    "language_model.model.layers.29.mlp.gate_proj",
-    "language_model.model.layers.4.self_attn.q_proj",
-    "language_model.model.layers.25.mlp.gate_proj",
-    "language_model.model.layers.30.mlp.up_proj",
-    "language_model.model.layers.15.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
-    "language_model.model.layers.24.self_attn.q_proj",
-    "language_model.model.layers.11.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.7.mlp.fc2",
-    "language_model.model.layers.14.mlp.gate_proj",
+    "language_model.model.layers.27.mlp.down_proj",
+    "language_model.model.layers.30.self_attn.q_proj",
+    "language_model.model.layers.18.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
+    "language_model.model.layers.30.self_attn.o_proj",
+    "language_model.model.layers.30.self_attn.v_proj",
+    "language_model.model.layers.20.self_attn.o_proj",
+    "language_model.model.layers.25.self_attn.o_proj",
+    "language_model.model.layers.23.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
+    "language_model.model.layers.12.self_attn.o_proj",
     "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
-    "language_model.model.layers.31.mlp.gate_proj",
-    "language_model.model.layers.31.self_attn.o_proj",
-    "language_model.model.layers.19.mlp.up_proj",
-    "language_model.model.layers.23.self_attn.k_proj",
-    "language_model.model.layers.29.self_attn.v_proj",
-    "language_model.model.layers.8.self_attn.k_proj",
-    "language_model.model.layers.26.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.17.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
-    "language_model.model.layers.27.self_attn.o_proj",
+    "language_model.model.layers.12.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
+    "language_model.model.layers.31.mlp.up_proj",
+    "language_model.model.layers.17.mlp.down_proj",
+    "language_model.model.layers.0.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
+    "language_model.model.layers.11.self_attn.k_proj",
     "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
-    "language_model.model.layers.12.self_attn.v_proj",
-    "language_model.model.layers.16.self_attn.q_proj",
+    "language_model.model.layers.17.self_attn.v_proj",
+    "language_model.model.layers.28.mlp.up_proj",
+    "language_model.model.layers.8.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc2",
+    "language_model.model.layers.5.self_attn.o_proj",
+    "language_model.model.layers.21.self_attn.v_proj",
+    "language_model.model.layers.1.self_attn.o_proj",
+    "language_model.model.layers.25.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
+    "language_model.model.layers.4.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc2",
+    "language_model.model.layers.20.mlp.up_proj",
+    "language_model.model.layers.22.self_attn.k_proj",
+    "language_model.model.layers.4.self_attn.k_proj",
+    "language_model.model.layers.8.self_attn.v_proj",
+    "language_model.model.layers.10.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.3.mlp.fc1",
+    "language_model.model.layers.19.mlp.down_proj",
+    "language_model.model.layers.14.mlp.up_proj",
+    "language_model.model.layers.28.mlp.down_proj",
+    "language_model.model.layers.10.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
+    "language_model.model.layers.29.self_attn.v_proj",
     "language_model.model.layers.13.mlp.gate_proj",
-    "language_model.model.layers.11.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.16.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
-    "language_model.model.layers.25.self_attn.v_proj",
-    "language_model.model.layers.18.self_attn.v_proj",
-    "language_model.model.layers.13.mlp.up_proj",
-    "language_model.model.layers.3.self_attn.k_proj",
-    "language_model.model.layers.16.self_attn.k_proj",
+    "language_model.model.layers.3.mlp.up_proj",
+    "language_model.model.layers.24.mlp.gate_proj",
     "vision_tower.vision_model.encoder.layers.5.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
-    "language_model.model.layers.12.mlp.up_proj",
-    "language_model.model.layers.29.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.14.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.19.mlp.fc1",
-    "language_model.model.layers.9.self_attn.o_proj",
-    "language_model.model.layers.14.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
-    "language_model.model.layers.11.self_attn.v_proj",
-    "language_model.model.layers.28.self_attn.k_proj",
-    "language_model.model.layers.15.mlp.down_proj",
-    "language_model.model.layers.2.self_attn.k_proj",
-    "language_model.model.layers.5.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
-    "language_model.model.layers.17.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.4.mlp.fc1",
-    "language_model.model.layers.1.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
-    "language_model.model.layers.3.self_attn.q_proj",
-    "language_model.model.layers.9.mlp.up_proj",
-    "language_model.model.layers.17.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.2.mlp.fc1",
-    "language_model.model.layers.9.self_attn.k_proj",
     "language_model.model.layers.7.self_attn.v_proj",
-    "language_model.model.layers.26.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
+    "language_model.model.layers.3.self_attn.k_proj",
+    "language_model.model.layers.16.self_attn.q_proj",
+    "language_model.model.layers.17.self_attn.k_proj",
+    "language_model.model.layers.3.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
     "language_model.model.layers.20.mlp.gate_proj",
-    "language_model.model.layers.6.self_attn.o_proj",
-    "language_model.model.layers.7.mlp.down_proj",
-    "language_model.model.layers.16.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.5.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
-    "language_model.model.layers.0.mlp.down_proj",
-    "language_model.model.layers.18.mlp.down_proj",
-    "language_model.model.layers.28.mlp.up_proj",
-    "language_model.model.layers.16.mlp.up_proj",
+    "language_model.model.layers.30.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
     "vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.11.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
-    "language_model.model.layers.14.self_attn.q_proj",
-    "multi_modal_projector.linear_2",
+    "language_model.model.layers.31.self_attn.q_proj",
+    "language_model.model.layers.10.mlp.up_proj",
+    "language_model.model.layers.19.mlp.up_proj",
+    "language_model.model.layers.11.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
     "language_model.model.layers.10.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc2",
+    "language_model.model.layers.28.self_attn.q_proj",
+    "language_model.model.layers.1.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc2",
     "vision_tower.vision_model.encoder.layers.21.mlp.fc2",
-    "language_model.model.layers.21.self_attn.o_proj",
-    "language_model.model.layers.31.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
-    "language_model.model.layers.29.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
-    "language_model.model.layers.21.self_attn.v_proj",
-    "language_model.model.layers.0.self_attn.k_proj",
-    "language_model.model.layers.9.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
-    "language_model.model.layers.13.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
-    "language_model.model.layers.14.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
-    "language_model.model.layers.12.self_attn.o_proj",
-    "language_model.model.layers.13.mlp.down_proj",
-    "language_model.model.layers.9.mlp.down_proj",
-    "language_model.model.layers.23.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.23.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
-    "language_model.model.layers.19.self_attn.k_proj",
-    "language_model.model.layers.22.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
-    "language_model.model.layers.4.mlp.down_proj",
-    "language_model.model.layers.11.self_attn.o_proj",
-    "language_model.model.layers.9.self_attn.q_proj",
-    "language_model.model.layers.0.mlp.up_proj",
-    "language_model.model.layers.0.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
     "vision_tower.vision_model.encoder.layers.12.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.20.mlp.fc1",
-    "language_model.model.layers.3.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.1.mlp.fc2",
-    "language_model.model.layers.2.self_attn.v_proj",
-    "language_model.model.layers.3.mlp.up_proj",
-    "language_model.model.layers.30.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
-    "language_model.model.layers.3.self_attn.o_proj",
-    "language_model.model.layers.7.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
-    "language_model.model.layers.21.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.23.mlp.fc1",
-    "language_model.model.layers.2.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.12.mlp.fc2",
-    "language_model.model.layers.20.self_attn.o_proj",
-    "language_model.model.layers.21.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.3.mlp.fc1",
-    "language_model.model.layers.15.self_attn.v_proj",
-    "language_model.model.layers.20.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
-    "language_model.model.layers.25.mlp.down_proj",
-    "language_model.model.layers.17.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
-    "language_model.model.layers.30.self_attn.q_proj",
-    "language_model.model.layers.31.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.10.mlp.fc1",
-    "language_model.model.layers.1.self_attn.k_proj",
-    "language_model.model.layers.27.mlp.gate_proj",
-    "language_model.model.layers.6.self_attn.v_proj",
-    "language_model.model.layers.18.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.0.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
+    "language_model.model.layers.18.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc2",
+    "language_model.model.layers.22.self_attn.o_proj",
+    "language_model.model.layers.6.self_attn.q_proj",
+    "language_model.model.layers.29.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.19.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
     "language_model.model.layers.28.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.6.mlp.fc2",
-    "language_model.model.layers.2.self_attn.q_proj",
-    "language_model.model.layers.1.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.17.mlp.fc2",
-    "language_model.lm_head",
-    "language_model.model.layers.5.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.4.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.9.mlp.fc1",
-    "language_model.model.layers.13.self_attn.k_proj",
-    "language_model.model.layers.12.mlp.gate_proj",
-    "language_model.model.layers.12.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
-    "language_model.model.layers.26.self_attn.k_proj",
-    "language_model.model.layers.31.mlp.up_proj",
-    "language_model.model.layers.26.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.8.mlp.fc2",
-    "language_model.model.layers.24.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
-    "language_model.model.layers.23.self_attn.v_proj",
-    "language_model.model.layers.17.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
-    "language_model.model.layers.30.self_attn.k_proj",
-    "language_model.model.layers.21.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
+    "language_model.model.layers.1.mlp.down_proj",
+    "language_model.model.layers.11.self_attn.q_proj",
+    "language_model.model.layers.24.self_attn.o_proj",
     "language_model.model.layers.8.self_attn.q_proj",
-    "language_model.model.layers.19.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
-    "language_model.model.layers.26.self_attn.o_proj",
-    "language_model.model.layers.28.self_attn.o_proj",
-    "language_model.model.layers.4.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
-    "language_model.model.layers.2.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
+    "language_model.model.layers.14.self_attn.q_proj",
     "vision_tower.vision_model.encoder.layers.14.mlp.fc2",
-    "language_model.model.layers.12.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.10.mlp.fc2",
-    "language_model.model.layers.19.self_attn.o_proj",
-    "language_model.model.layers.18.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.7.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.3.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
+    "language_model.lm_head",
+    "vision_tower.vision_model.encoder.layers.1.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.4.mlp.fc1",
+    "language_model.model.layers.3.self_attn.o_proj",
     "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
-    "language_model.model.layers.28.self_attn.q_proj",
-    "language_model.model.layers.6.self_attn.q_proj",
-    "language_model.model.layers.20.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
-    "language_model.model.layers.11.mlp.up_proj",
-    "language_model.model.layers.22.mlp.up_proj",
-    "language_model.model.layers.5.mlp.down_proj",
-    "language_model.model.layers.20.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.20.mlp.fc2",
-    "vision_tower.vision_model.encoder.layers.15.mlp.fc2",
-    "language_model.model.layers.22.self_attn.v_proj",
-    "language_model.model.layers.0.self_attn.q_proj",
-    "language_model.model.layers.5.mlp.up_proj",
+    "language_model.model.layers.8.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
+    "language_model.model.layers.17.mlp.up_proj",
+    "language_model.model.layers.11.self_attn.v_proj",
+    "language_model.model.layers.7.self_attn.q_proj",
+    "language_model.model.layers.16.self_attn.k_proj",
+    "language_model.model.layers.9.self_attn.v_proj",
+    "language_model.model.layers.0.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
+    "language_model.model.layers.18.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
+    "language_model.model.layers.25.self_attn.q_proj",
+    "language_model.model.layers.6.mlp.down_proj",
+    "language_model.model.layers.23.self_attn.q_proj",
+    "language_model.model.layers.15.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc2",
+    "language_model.model.layers.17.self_attn.q_proj",
+    "language_model.model.layers.18.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc2",
+    "language_model.model.layers.2.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.18.mlp.fc1",
+    "language_model.model.layers.9.self_attn.q_proj",
+    "language_model.model.layers.6.mlp.up_proj",
+    "language_model.model.layers.27.mlp.up_proj",
+    "language_model.model.layers.5.mlp.gate_proj",
     "language_model.model.layers.9.mlp.gate_proj",
-    "language_model.model.layers.27.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
+    "language_model.model.layers.21.mlp.up_proj",
+    "multi_modal_projector.linear_1",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
+    "language_model.model.layers.27.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc2",
+    "language_model.model.layers.4.self_attn.q_proj",
+    "language_model.model.layers.3.self_attn.v_proj",
+    "language_model.model.layers.21.self_attn.k_proj",
     "language_model.model.layers.4.mlp.gate_proj",
-    "language_model.model.layers.20.mlp.down_proj",
-    "language_model.model.layers.17.self_attn.q_proj",
-    "language_model.model.layers.14.mlp.down_proj",
-    "language_model.model.layers.1.mlp.gate_proj",
-    "language_model.model.layers.10.self_attn.o_proj",
-    "language_model.model.layers.23.self_attn.o_proj",
-    "language_model.model.layers.18.mlp.gate_proj",
-    "language_model.model.layers.27.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
-    "language_model.model.layers.1.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
+    "language_model.model.layers.29.mlp.up_proj",
+    "language_model.model.layers.13.mlp.up_proj",
+    "language_model.model.layers.21.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
+    "language_model.model.layers.0.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
     "language_model.model.layers.24.mlp.up_proj",
-    "language_model.model.layers.15.self_attn.k_proj",
-    "language_model.model.layers.2.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
-    "language_model.model.layers.30.self_attn.v_proj",
+    "language_model.model.layers.30.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
+    "language_model.model.layers.1.self_attn.k_proj",
+    "language_model.model.layers.11.mlp.gate_proj",
+    "language_model.model.layers.13.self_attn.o_proj",
+    "language_model.model.layers.24.self_attn.k_proj",
+    "multi_modal_projector.linear_2",
     "language_model.model.layers.25.mlp.up_proj",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
+    "language_model.model.layers.7.mlp.up_proj",
+    "language_model.model.layers.27.self_attn.k_proj",
     "language_model.model.layers.7.self_attn.o_proj",
-    "language_model.model.layers.30.self_attn.o_proj",
-    "language_model.model.layers.13.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.0.mlp.fc1",
-    "language_model.model.layers.0.mlp.gate_proj",
-    "language_model.model.layers.17.mlp.up_proj",
-    "language_model.model.layers.12.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc1",
+    "language_model.model.layers.29.mlp.gate_proj",
+    "language_model.model.layers.19.self_attn.q_proj",
+    "language_model.model.layers.23.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
+    "language_model.model.layers.12.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
+    "language_model.model.layers.13.self_attn.q_proj",
+    "language_model.model.layers.19.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
+    "language_model.model.layers.5.mlp.up_proj",
+    "language_model.model.layers.14.mlp.down_proj",
+    "language_model.model.layers.31.self_attn.v_proj",
+    "language_model.model.layers.18.mlp.up_proj",
+    "language_model.model.layers.12.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
     "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.9.mlp.fc1",
+    "language_model.model.layers.6.self_attn.k_proj",
     "language_model.model.layers.15.self_attn.o_proj",
-    "language_model.model.layers.10.mlp.up_proj",
-    "language_model.model.layers.13.self_attn.o_proj",
-    "language_model.model.layers.5.self_attn.o_proj",
-    "language_model.model.layers.7.self_attn.k_proj",
-    "language_model.model.layers.22.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
-    "language_model.model.layers.29.mlp.down_proj",
-    "language_model.model.layers.31.self_attn.k_proj",
+    "language_model.model.layers.2.mlp.gate_proj",
+    "language_model.model.layers.0.self_attn.o_proj",
+    "language_model.model.layers.5.mlp.down_proj",
+    "language_model.model.layers.2.mlp.up_proj",
     "language_model.model.layers.10.mlp.gate_proj",
-    "language_model.model.layers.26.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
-    "language_model.model.layers.23.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
-    "vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.15.mlp.fc1",
-    "language_model.model.layers.19.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
-    "language_model.model.layers.3.self_attn.v_proj",
-    "language_model.model.layers.1.self_attn.v_proj",
-    "language_model.model.layers.17.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.22.mlp.fc1",
-    "language_model.model.layers.10.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.21.mlp.fc1",
-    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
+    "language_model.model.layers.8.self_attn.o_proj",
+    "language_model.model.layers.31.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
+    "language_model.model.layers.16.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
+    "language_model.model.layers.1.mlp.gate_proj",
     "vision_tower.vision_model.encoder.layers.19.mlp.fc2",
-    "language_model.model.layers.29.self_attn.o_proj",
-    "language_model.model.layers.11.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.20.mlp.fc1",
+    "language_model.model.layers.3.mlp.gate_proj",
+    "language_model.model.layers.20.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
+    "language_model.model.layers.14.self_attn.o_proj",
+    "language_model.model.layers.1.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
+    "language_model.model.layers.16.self_attn.o_proj",
+    "language_model.model.layers.14.self_attn.k_proj",
+    "language_model.model.layers.15.self_attn.k_proj",
+    "language_model.model.layers.30.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
+    "language_model.model.layers.26.self_attn.v_proj",
+    "language_model.model.layers.29.self_attn.k_proj",
+    "language_model.model.layers.27.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
+    "language_model.model.layers.20.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
+    "language_model.model.layers.23.mlp.down_proj",
+    "language_model.model.layers.9.mlp.up_proj",
+    "language_model.model.layers.13.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.23.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
+    "language_model.model.layers.26.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.13.mlp.fc2",
+    "language_model.model.layers.2.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
+    "language_model.model.layers.21.self_attn.o_proj",
+    "language_model.model.layers.31.self_attn.o_proj",
     "language_model.model.layers.4.mlp.up_proj",
+    "language_model.model.layers.4.self_attn.o_proj",
     "language_model.model.layers.19.mlp.gate_proj",
-    "language_model.model.layers.14.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.2.mlp.fc2",
-    "language_model.model.layers.4.self_attn.k_proj",
-    "language_model.model.layers.8.mlp.up_proj",
-    "language_model.model.layers.18.mlp.up_proj",
+    "language_model.model.layers.24.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
+    "language_model.model.layers.15.mlp.gate_proj",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
+    "language_model.model.layers.26.mlp.down_proj",
+    "language_model.model.layers.2.mlp.down_proj",
+    "language_model.model.layers.25.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.5.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
     "vision_tower.vision_model.encoder.layers.18.mlp.fc2",
-    "language_model.model.layers.8.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
-    "language_model.model.layers.6.mlp.down_proj",
-    "language_model.model.layers.27.self_attn.k_proj",
-    "language_model.model.layers.25.self_attn.q_proj",
-    "language_model.model.layers.25.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.11.mlp.fc1",
-    "language_model.model.layers.6.mlp.up_proj",
+    "language_model.model.layers.25.self_attn.k_proj",
+    "language_model.model.layers.2.self_attn.q_proj",
+    "language_model.model.layers.19.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.12.mlp.fc2",
+    "language_model.model.layers.22.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
+    "language_model.model.layers.10.self_attn.v_proj",
+    "language_model.model.layers.5.self_attn.k_proj",
     "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
-    "language_model.model.layers.19.self_attn.q_proj",
-    "language_model.model.layers.7.self_attn.q_proj",
-    "language_model.model.layers.14.self_attn.v_proj",
-    "language_model.model.layers.24.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
-    "vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
-    "language_model.model.layers.8.self_attn.v_proj",
-    "language_model.model.layers.23.mlp.gate_proj",
-    "language_model.model.layers.21.mlp.up_proj",
-    "language_model.model.layers.15.self_attn.q_proj",
+    "language_model.model.layers.3.self_attn.q_proj",
+    "language_model.model.layers.1.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.16.mlp.fc1",
     "vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
-    "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
+    "language_model.model.layers.30.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
+    "language_model.model.layers.29.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
+    "language_model.model.layers.21.mlp.gate_proj",
+    "language_model.model.layers.24.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.10.mlp.fc1",
+    "language_model.model.layers.18.mlp.gate_proj",
+    "language_model.model.layers.26.self_attn.o_proj",
+    "language_model.model.layers.9.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
+    "language_model.model.layers.22.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
+    "language_model.model.layers.6.self_attn.o_proj",
+    "language_model.model.layers.22.mlp.down_proj",
     "language_model.model.layers.16.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.18.mlp.fc1",
-    "language_model.model.layers.23.mlp.up_proj",
-    "language_model.model.layers.25.self_attn.k_proj",
-    "language_model.model.layers.22.mlp.gate_proj",
-    "vision_tower.vision_model.encoder.layers.13.mlp.fc1",
+    "language_model.model.layers.28.self_attn.k_proj",
+    "language_model.model.layers.23.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.6.mlp.fc1",
+    "language_model.model.layers.21.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
+    "language_model.model.layers.12.self_attn.v_proj",
+    "language_model.model.layers.17.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
+    "language_model.model.layers.14.mlp.gate_proj",
+    "language_model.model.layers.4.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
+    "language_model.model.layers.26.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
+    "language_model.model.layers.6.self_attn.v_proj",
+    "language_model.model.layers.16.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.2.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
+    "language_model.model.layers.0.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
+    "language_model.model.layers.31.mlp.gate_proj",
+    "language_model.model.layers.16.self_attn.v_proj",
+    "language_model.model.layers.9.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
     "language_model.model.layers.8.mlp.gate_proj",
+    "language_model.model.layers.15.mlp.up_proj",
+    "language_model.model.layers.7.mlp.down_proj",
+    "language_model.model.layers.24.self_attn.q_proj",
+    "language_model.model.layers.13.self_attn.v_proj",
+    "language_model.model.layers.13.mlp.down_proj",
+    "language_model.model.layers.0.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
     "language_model.model.layers.28.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.1.mlp.fc1",
-    "language_model.model.layers.10.self_attn.v_proj",
-    "language_model.model.layers.11.self_attn.q_proj",
-    "language_model.model.layers.0.self_attn.o_proj",
-    "language_model.model.layers.16.self_attn.v_proj",
-    "language_model.model.layers.5.self_attn.q_proj",
-    "language_model.model.layers.5.self_attn.v_proj",
-    "vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
-    "language_model.model.layers.22.self_attn.k_proj",
+    "language_model.model.layers.18.self_attn.q_proj",
+    "language_model.model.layers.22.mlp.gate_proj",
+    "language_model.model.layers.25.self_attn.v_proj",
+    "language_model.model.layers.31.mlp.down_proj",
+    "language_model.model.layers.9.mlp.down_proj",
+    "language_model.model.layers.11.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.8.mlp.fc2",
+    "language_model.model.layers.20.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
+    "language_model.model.layers.17.mlp.gate_proj",
+    "language_model.model.layers.7.mlp.gate_proj",
+    "language_model.model.layers.2.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
+    "language_model.model.layers.0.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.15.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.11.mlp.fc2",
+    "language_model.model.layers.19.self_attn.k_proj",
+    "language_model.model.layers.27.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
     "language_model.model.layers.10.mlp.down_proj",
-    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
-    "language_model.model.layers.18.self_attn.o_proj",
-    "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj"
+    "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc2",
+    "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
+    "language_model.model.layers.23.self_attn.v_proj",
+    "language_model.model.layers.20.self_attn.v_proj",
+    "language_model.model.layers.7.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.7.mlp.fc2",
+    "language_model.model.layers.5.self_attn.v_proj",
+    "language_model.model.layers.27.self_attn.o_proj",
+    "vision_tower.vision_model.encoder.layers.0.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
+    "language_model.model.layers.29.mlp.down_proj",
+    "language_model.model.layers.12.mlp.up_proj",
+    "language_model.model.layers.15.mlp.down_proj",
+    "vision_tower.vision_model.encoder.layers.21.mlp.fc1",
+    "vision_tower.vision_model.encoder.layers.17.mlp.fc1",
+    "language_model.model.layers.12.self_attn.k_proj",
+    "vision_tower.vision_model.encoder.layers.22.mlp.fc1",
+    "language_model.model.layers.11.mlp.up_proj",
+    "vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
+    "language_model.model.layers.8.mlp.down_proj",
+    "language_model.model.layers.5.self_attn.q_proj",
+    "vision_tower.vision_model.encoder.layers.14.mlp.fc1",
+    "language_model.model.layers.26.mlp.gate_proj",
+    "language_model.model.layers.14.self_attn.v_proj",
+    "vision_tower.vision_model.encoder.layers.23.self_attn.q_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a95d9fe3f227393cbd1d69bb25184c7987bb99c7509a9397149910c4e49de51
-size 398614376
+oid sha256:7b31c8978d8904d33c0f88993bb53cbbc4daeab9da3cdbdf89f7e04eb0dd465d
+size 1594115680

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7204647bdfaec599e84fb1a563cf2ff27187148713bbdd82e35528202840193d
+oid sha256:b257ac31e3690035c99048e792dac12813f37ca6c8eb305df5056b588120c3de
 size 5496