Training in progress, step 600

adapter_config.json

@@ -7,20 +7,20 @@
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 128,
+  "lora_alpha": 256,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 128,
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "o_proj",
     "k_proj",
     "gate_proj",
-    "down_proj",
-    "up_proj",
-    "v_proj",
     "q_proj",
-    "o_proj"
+    "up_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905b3d0774ffd6622f3e4c6632dcb4504ff2f195d75a239f01915d09da533adb
-size 121155320
+oid sha256:984848a50aabaf5208c3fe6da2a5c7d65780348a47e529d7ccb6846eb01e0e9b
+size 242266488

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2fb7352276b090c5ed877de5167c4e9c87b124a8e47ef066c8b96b0f95788b6
+oid sha256:c53ce8e559a65ce29c4be6ac569f936bae5122b3ea1ba2369411242cb556f0b1
 size 6392