Training in progress, epoch 1

adapter_config.json

@@ -13,9 +13,9 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.01,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
@@ -24,7 +24,7 @@
   ],
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e0c85a813484d98643510570d16a42d349bc8d2ec3670cfe27c959f2af85b1a
-size 2736625528
+oid sha256:57bdfcb9efe57540bd12105437725b4951dd7dce10e156e772041673995fa549
+size 2710837024

runs/Jul16_17-44-52_a79bdaa254ce/events.out.tfevents.1752687894.a79bdaa254ce.50153.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2241ce67225ea71d076082104a00a6088a65731c2607f4fad5a7fdacc55887
-size 401102
+oid sha256:3ab62c558bb6a5cf1bb873fcab71fc4d21a51d3cb26dd150f0c1b3961c2dcbdf
+size 410750

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2919a8628ed7ac043a11bcb88ccf2e54394268634af96ffe404d3bfcb6380d81
+oid sha256:2ca12bfa6caf078d31b97f6b6eca96e35f69142ac89d337937ba255663196bfa
 size 6225