Training in progress, step 24000

adapter_config.json

@@ -10,18 +10,17 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
-    "k_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a773cd2f742371c8b04678b34785bb22529420fece4a1f83216918bb31893a33
-size 7108136
+oid sha256:be2696e8f11b2d6251f18539d68751a13e8632cca21d53e2c3d970636823ac43
+size 9457520

runs/Sep05_14-16-25_9a76d9e283dc/events.out.tfevents.1725545787.9a76d9e283dc.372160.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b612ba34d64c3e11e5b3d060226645e4f4d4c75eb00502f7d946cf58185a2f
-size 7641
+oid sha256:cdb57a02fedbb6f7f4a69641eecda21ac93c27c7e8729dd48faf3193244da5e1
+size 7856

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1ce35009f186db29559ca704e389cacd95dcb79fde29440a0b027134128d37b
+oid sha256:5b25f2878401c234c9383813c9a0aae1f4b93a35eb3da32b2a9bdf17fb62b895
 size 5304