Training in progress, step 500

adapter_config.json

@@ -16,17 +16,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
+    "k_proj",
     "down_proj",
-    "v_proj",
+    "o_proj",
     "gate_proj",
-    "up_proj",
-    "k_proj",
-    "o_proj"
+    "v_proj",
+    "up_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:f0ac22b0ae875fde4c4ef87ee86c6391c36c57d1df30631d854b1396b733b755
-size 83115256
+oid sha256:2937473c457ac1c1b2f3dc3e7df89aed92b52c92d81022ba4ba11f612765c891
+size 664584480

runs/Nov26_16-09-22_04d2f4fdebd9/events.out.tfevents.1732637367.04d2f4fdebd9.16262.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1f1b6e9cf1b7b3f24a0a2bd90a637de9706c26345a0028a9fed3a43b049c87
+size 10474

runs/Nov26_16-15-20_04d2f4fdebd9/events.out.tfevents.1732637729.04d2f4fdebd9.18158.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2da3417bde525cfdda2d4941c2c7f87432975691028daa7429951408874f194
+size 16636

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
-size 34362873
+oid sha256:af22e7336d8422c373462eb93a1ef2c7a4c3da6e1d000dc156a9f062ffb40e6f
+size 34362973

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441367694d46db0f5ea739d307a3ef2d140296cfd88936003b69db6309915826
+oid sha256:95fd331b450619b75ab34a63922310191f3e48cbc05c7b234715aecc728f41fe
 size 5560