Training in progress, step 100

adapter_config.json

@@ -9,23 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "down_proj",
     "q_proj",
+    "gate_proj",
     "k_proj",
     "up_proj",
-    "o_proj",
-    "gate_proj",
-    "v_proj"
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f4a51920f0aaaa7bbf829c83f3786401333ce97045b21375be7de99947e5284
-size 83945744
+oid sha256:1f60b863a8c55044ad3d7a4012dfdcf2469e37949749a91b21014d9a45f871cc
+size 671150064

runs/Feb02_15-24-17_ip-26-0-165-38/events.out.tfevents.1706887790.ip-26-0-165-38.1953627.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b5954d8bef90e6e365b1c7484dc6ec16544c84a3581197c1345cde24dcfbcf
+size 12511

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b735758af514d81f3b69084582bef9048dd946b4f16b534b957ede83d17c5d44
+oid sha256:a1ede90317e859cf087966b9bf69c44fc27d2e9aa2c3cf4b791d80822b1cf383
 size 4856