Training in progress, step 100

adapter_config.json

@@ -16,17 +16,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "down_proj",
     "k_proj",
     "up_proj",
-    "q_proj",
     "gate_proj",
     "o_proj",
-    "v_proj",
-    "down_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566f0ec3bc73d340a12f4623c413c2efea15aab74d83290f4d774c48a1d4f0ab
-size 90454136
+oid sha256:6295b6fc80305438533aacad51111c1e49ddd675d8c6f6046d131b36348ff397
+size 45258384

runs/Jul27_16-29-02_8253f41ceeb1/events.out.tfevents.1722097749.8253f41ceeb1.35.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda15f7a81b95e22fa042c036a8d4a90fd8e24e9d60d136c19cfcfced919e77f
-size 7519
+oid sha256:fd23a17cdfd285880fa067c801771de4b4671b13e096c6745b76a77962808deb
+size 7726

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25beb9ed16a5d29f2e40ce8adb0c8006f56163c6340b8865161706c725d45d2c
-size 5112
+oid sha256:2d4f9dfca8fa6cbfa4ad4f70b4f4a959bad66d6b0e12aab197fa6b1c46edc1d1
+size 5048