Training in progress, step 100

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "up_proj",
     "o_proj",
+    "down_proj",
     "v_proj",
+    "gate_proj",
     "q_proj",
-    "k_proj",
-    "down_proj",
-    "up_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 sha256:39cf74574cfe6f13b5d50debb286925f697d14805dcd43a13f9f8d145bbef3ec
-size 19644912
+oid sha256:92ebd4b074bfad19b0b7076e75f543e065902aa22496be97519e4ca77ed7a4bf
+size 78480320

runs/Jun10_18-07-27_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718010465.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.8637.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f7e20ccfd00032539a48e660ce52951a9c94d7608cabfc4c5d600e0a8754b2
+size 9948

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2fd9dc1b21de06e034923e5381116a27aa520aaecbea9531cbaadf31b5396e
+oid sha256:79403370bd0f434808148b492792063f20e5cb55a839de3e56f8ea44a6289725
 size 5304