Training in progress, step 75

adapter_config.json

@@ -16,17 +16,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "down_proj",
-    "o_proj",
-    "q_proj",
-    "up_proj",
     "k_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
     "v_proj",
-    "gate_proj"
+    "o_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:e83eef1b5672651bf92ab668302669dd56ea95820b7010fafd7a02dea51100bf
-size 45258384
+oid sha256:adccfc0db6a9311b9f76815f974e217aad36598071503d5df140019e78a3cad1
+size 90454136

runs/May26_22-15-55_bebcc02e1da5/events.out.tfevents.1716761764.bebcc02e1da5.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c57277eb6844ded296c60b2da014476e1753f6164cf99ac37aca9a20219f89ea
+size 21527

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f6a101a1abf0080f8e5ac055ea48d3c008f6ad1d52a1f8c0b344b2e50d50f94
+oid sha256:809e74a2853d14b98078c1fa7077ffd9863dc198180fdaf6d0836dbc86e2a44f
 size 5112