Training in progress, epoch 1

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "k_proj",
     "v_proj",
-    "up_proj",
     "gate_proj",
+    "q_proj",
     "o_proj",
-    "down_proj",
-    "q_proj"
+    "up_proj",
+    "down_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:e5f9b73001d612fe9b75fbab72aff8dd02e66692f9cf8507b3289dba272438ce
-size 664584480
+oid sha256:a1255d3b3fb053719a5e2ffb25a9d7d65935358dc207eda6eef0b9c693c35a8d
+size 83115256

runs/Oct08_06-09-39_f299bf4d1004/events.out.tfevents.1728367971.f299bf4d1004.1255628.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6eaa3b2430559bf815ecd894a25e927020d78ec759fe5c2f40c983ffe932638
+size 134629

runs/Oct08_15-06-58_f299bf4d1004/events.out.tfevents.1728400025.f299bf4d1004.1334979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc7ba8f05b78b1daf6dc08c36a2fd2fdabb6d4b8ceb597cbac4a6335eeced9a
+size 134275

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0e62ee48e616f5361c92d0518617e50f16edb597db2b7102273bc46a9b00548
+oid sha256:8daa8e5782a671d5a7d637a25d4e90ea0b4b38c381f84fb1d53fe389c5a4a123
 size 5304