Training in progress, step 100

adapter_config.json

@@ -16,17 +16,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "down_proj",
-    "k_proj",
-    "gate_proj",
     "v_proj",
+    "o_proj",
+    "gate_proj",
     "up_proj",
-    "o_proj"
+    "q_proj",
+    "down_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e2f47b19e1ef80b3747ac0993c511d8979d287874d9303607c583432eba0bf
-size 3345822528
+oid sha256:28b9594b932ff4c5d737ccfb26dfccb99c61ca7aea28e0031c859c777987c9e7
+size 4745934024

runs/Sep12_04-10-39_m3u008/events.out.tfevents.1757614268.m3u008.172707.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8875f755c1a9e161146731121e9de0cdb876714eaf410f2ca1641917821a0870
+size 8000

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fede37b18a4affac3f10a6ed911ac16ae0890e2a2f3157dca187d2bb15345160
+oid sha256:6f6f8ed8da34724508cd461d6d62979a58769bc4195a0b5f0a6434e050b38e38
 size 6520