Training in progress, step 500

adapter_config.json

@@ -19,23 +19,23 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
+    "linear_1",
+    "down_proj",
     "linear_2",
-    "up_proj",
     "k_proj",
     "fc1",
-    "out_proj",
-    "lm_head",
-    "down_proj",
-    "fc2",
-    "q_proj",
     "v_proj",
-    "linear_1"
+    "q_proj",
+    "gate_proj",
+    "fc2",
+    "up_proj",
+    "lm_head",
+    "out_proj",
+    "o_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74b3c83ab4bf88899822113eb418d7c92fbea46563d52a192bf87068682a8f05
-size 908222720
+oid sha256:fb85de9462fb13588ad65634270fe2b6b4c30f40360cedbe5aa4b769a261ae96
+size 1290994752

runs/May01_11-30-49_8f29578212c0/events.out.tfevents.1714563156.8f29578212c0.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1aa851d3c828d8246dcbeb34051bf29d0e1a7ecf01b16affa576aa419e84de
+size 32274

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1608be2131fc4e0b93bf01a65f7dd7ea5a0f6c6f29f5e2675d73f6cab29da32a
+oid sha256:4cdc42e6ac90ea2e6b035ca91f0ec92529220ebdf3a1a3bcd86249d130d3c2de
 size 4984