Training in progress, step 150

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 1024,
+  "lora_alpha": 2048,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
+    "v_proj",
+    "down_proj",
     "up_proj",
     "k_proj",
-    "gate_proj",
-    "v_proj",
-    "down_proj"
+    "o_proj",
+    "q_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2cb9ba98a989f2d605ee29458160c5e8861a58e1fa8299b7474cfa34d1e67b0
+oid sha256:6abc906c39d67627240d3a237e0efa14287e263aad18422239a3b08e1e55763a
 size 5368770952

runs/Sep06_23-38-08_29814392f55c/events.out.tfevents.1725665904.29814392f55c.2845.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f4383a057f4fee777430fdb1da97aab1dadca998bd552a022e6dc21816295cc
+size 11468

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfa1762e8a05d995aae704eb13233285dec21f9baf60d078c2f7d2e2d7c8de4
+oid sha256:96ac11d0d2b491c0474c3fa4a6f303e018d228d70be0e5d7df1c27b27ca2429d
 size 5496