Training in progress, step 25

adapter_config.json

@@ -16,14 +16,14 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "fc1",
-    "fc2",
     "out_proj",
-    "Wqkv"
+    "Wqkv",
+    "fc2"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e6c2d4eb66fa02af56e5890eb8c6a67a027ed6ac540fc0c2c3ec53af03bae0
-size 167809856
+oid sha256:5be01ab8738239bd21bd2dc789dfbbb4c5b01eeee37b805352029cbcbe03a3a8
+size 335582184

runs/Apr17_00-22-48_58837a1caf67/events.out.tfevents.1713313370.58837a1caf67.465.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cfa9528d89ac6e980c900b99b7afb46d33e862a336b7ab2411b0fd1ee4bbb64
+size 5735

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b714c74ba777eaa5bae00402590b6b7c44ac56a3672b9140b4c678c8840c2a
+oid sha256:6042240f9372fc1a7a500a47bd0e822c40e8a634d9d2230788d359604982d9bb
 size 4920