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": [
-    "up_proj",
+    "k_proj",
     "down_proj",
-    "o_proj",
+    "gate_proj",
     "v_proj",
     "q_proj",
-    "k_proj",
-    "gate_proj"
+    "up_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25b9ed6c47fa94b9cc43d53884d5a76c2bc10ad3341d6c6b37fd1bedf92a05b9
-size 19644912
+oid sha256:ecf440a6744b5f89ac47c511255b27158a4b78c11da949a91c6eb2644bc5e5db
+size 78480320

runs/Jun10_23-03-05_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1718028200.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.11783.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9691c327b08b0f2f92a04b85cdef610f3abacf552951ea77135a569bf1cb4a09
+size 9948

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2d3a33eba36ab36d0a7df6e599152d47fb9110e0f469f1da3ffc573bec11f40
+oid sha256:d67884069e2541369a8e37b9f5b784d6f631ba8b2b92a0b9d58a86ff7e30fe2f
 size 5304