Training in progress, step 100

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
     "k_proj",
     "up_proj",
     "gate_proj",
+    "o_proj",
     "down_proj",
-    "v_proj"
+    "v_proj",
+    "q_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:d4711620e971ab843c174762480b72259ca41cd9ba5e1123d1b7c569ba006191
-size 39256960
+oid sha256:13b6e8814a401b823f101bb64f9003b311654c09fe91dcbe63ed5bb0e417fbcc
+size 78480320

runs/Jun10_06-37-27_48ddfe8e991f/events.out.tfevents.1718001468.48ddfe8e991f.199825.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc9c6c5c1b07a5be4ae590d14f039873e5702136eb83118e7c90bab034463177
+size 10217

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640fa1fe4d89d99997cead971aff6c7d3558f0517f57ac44d497ee2dee47b977
+oid sha256:fdcb93ad745e951a41fd2655fa57cd48763f40a50d83ca9fd79f9ec9bb50b9cb
 size 5304