Training in progress, epoch 0

adapter_config.json

@@ -9,24 +9,24 @@
   "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": [
     "q_proj",
-    "gate_proj",
-    "o_proj",
-    "lm_head",
+    "up_proj",
     "v_proj",
-    "k_proj",
     "down_proj",
-    "up_proj"
+    "lm_head",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11b319716601e9dc025e1959b455121ddb6cbcacf9ace204b623bfa250e30818
-size 694431312
+oid sha256:df0f9410220b2c60caf57d459887dc8b6137a8b28774c6ce47f84b41345f15de
+size 864513616

runs/Feb15_04-12-37_1ad2abcb34be/events.out.tfevents.1707970367.1ad2abcb34be.861.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9143c82ac685154a8c01b5b7cf51ca8095b16c5feb891f3d2ddaae07cc837cab
+size 9027

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0946f1dd9e946ba7b80d35bdbdc0c640bf71b6f123c518ee00b781cbee8fb11f
+oid sha256:88dab8211dd818c87b38b2af2f9a0f9c2ffc07a09f50fc176e913de7e6ee8154
 size 4600