Training in progress, epoch 0

adapter_config.json

@@ -12,7 +12,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
@@ -25,8 +25,8 @@
   "target_modules": [
     "v_proj",
     "q_proj",
-    "k_proj",
-    "o_proj"
+    "o_proj",
+    "k_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:a088081016f48a0811ac5bc87abbb215792b8a2490da8da934b8e47194e37847
-size 13665592
+oid sha256:fdc223d0db70b78465fe3cfa81ee3803315a4ff8cf92fb914dc48ab4c9dc493d
+size 27297032

runs/Feb02_02-57-34_runsensible-dell/events.out.tfevents.1738483056.runsensible-dell.751102.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9f8e42e59f21474b1ab942edf4e3667950494c844d894088367c9fd3d6df324
+size 13148

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38925732c97f86d1b642ae3ef558e51ec50fd0d7f1cc4091b4a92e10eaaaf999
+oid sha256:ea531fdd8e833583b03d9d8e3b4b1a47ab8419ed1d4a9cb7ff4c732fee3650c1
 size 5688