Training in progress, step 200

adapter_config.json

@@ -11,7 +11,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 128,
-  "lora_dropout": 0.2,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "down_proj",
-    "up_proj",
+    "q_proj",
     "gate_proj",
-    "v_proj",
+    "o_proj",
     "k_proj",
-    "o_proj"
+    "v_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fc896771ac2b0cf800e642cf19a884f4989ffc98ccce5fa3e595f3f159ab3c1
+oid sha256:9a156490d62412884c8b47fa2ff4ff63b215de2767cb5ab808843b67d4312ab7
 size 41581360

runs/Nov07_12-21-54_cd253cb85412/events.out.tfevents.1730982126.cd253cb85412.941.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6c0d9c2230d9c633c1df6bb71201d4a3809855dad8d2b7017c91c96d80fc31
+size 5665

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd2db52635818846bb798a7b5989994c5c589d958bf4e5a93d7c6d42c0e75d35
+oid sha256:6f44ba5ee7ed5f62fcf0771736e5ce9358a241d3f7075b8a47d557f96dcf8987
 size 5176