Training in progress, epoch 1

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 128,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
-    "k_proj",
     "q_proj",
+    "gate_proj",
+    "down_proj",
     "v_proj",
     "o_proj",
-    "down_proj"
+    "k_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b2887453663f5bd531ee2c3da41fd216b5d9e6cd30ff11034393f8c8217b07
+oid sha256:7d520e5440076db9be57dd06c445dd131439dccc540fd164270e98431b2c98fe
 size 2537622976

runs/May29_13-20-28_031dd5e789c8/events.out.tfevents.1716981637.031dd5e789c8.170097.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e65e362dcec605c867a96de1addeaa00b882b7b0cb2ed12901d58b2cb3fe72c
+size 5345

runs/May29_13-28-42_031dd5e789c8/events.out.tfevents.1716982130.031dd5e789c8.175177.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4deb00ccb76027ef13fa519b8be690db2dfadb8dd8cd4821fa55f78c7d77bb03
+size 17444

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c870dcffa5be6f48c8647ffce2efc31bc764ca8738f30886d58faf941db2bd
+oid sha256:e285a1e26411e0ea716bb07d11dedef08fa2e4ddee5910bf220e5f6d76e1b39e
 size 4728