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": [
-    "k_proj",
-    "q_proj",
-    "down_proj",
     "o_proj",
-    "up_proj",
+    "gate_proj",
+    "down_proj",
     "v_proj",
-    "gate_proj"
+    "q_proj",
+    "k_proj",
+    "up_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:ccdb982320a0542c5a2a9955f444d77be1609421b536bda3fd94e51e213d8441
-size 39256960
+oid sha256:86dc18b8b7c9ed1f2f53a59aa116252f725f6b6cbf1e0fa0de1c65e70bd9ea53
+size 78480320

runs/Jun10_15-40-50_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718001669.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.6920.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879c74188102c1c1cdcdf45c5e705554c85e5d933742c6f2432f43696557fd91
+size 9944

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe7d8f07e9ae0577ea726d7f308ae61d4f258ff82fa8b9c5dcc586ea4a3c210
+oid sha256:aae3e2f6210d4166ef09db52ce85d70cb78702bbce822456496e5dc8c63bc034
 size 5304