Training in progress, epoch 1

adapter_config.json

@@ -13,9 +13,9 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 4,
+  "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc31ea64e2075b58c29d465f6d0c3da9e0d3f2127463c2a2be01a92d73815f87
+oid sha256:204c3906d4fbf980ac526eaba15c4a1a07e61c8d584355db71ffd5312264154c
 size 13093200

runs/May20_10-40-55_a7435d519f39/events.out.tfevents.1747737675.a7435d519f39.2140.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20aef8a43e3e9221bff0dfcf24981e1e09a9f6c3f2ac269a47fbfce9196cb0fa
+size 7021

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e406b62586ff95318c44eb371fd51d52863e1133e7d6a6b7e173507f5402f23e
+oid sha256:0c1c9daeb57dfecbf9275b8fa9ba4f8d6ee989edf4a37e567c752dd01032f566
 size 5688