Training in progress, step 500

adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj",
-    "down_proj",
-    "gate_proj",
     "o_proj",
+    "gate_proj",
+    "q_proj",
     "k_proj",
-    "up_proj"
+    "up_proj",
+    "down_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:a46347461bae1c3fbf43643670e8c95fe56bbfb17586a9cc2f3acaa76b05e0f4
-size 1279323952
+oid sha256:f90f1a20c9d18147c667c1524e0bec66cc4be4478dcb5eef30bdf755510f977e
+size 639691872

runs/Mar31_23-09-24_30b4cad7fc5e/events.out.tfevents.1711926565.30b4cad7fc5e.1568.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:771d6850df1c54a98076bcc504c41ba8d25629f38460438849bc641e263161ab
+size 5060

runs/Mar31_23-10-44_30b4cad7fc5e/events.out.tfevents.1711926644.30b4cad7fc5e.1568.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2071792dc28ddf2c36f9058be6bdb89f25e9127e344b25d6c735145a3c89ad9f
+size 6111

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eedc7a704f25868b49e1e9fecb18824968eef7c34af0ab11e756658cd9c76e67
+oid sha256:854e743f8430c460031ae8ac94e03e2388c65175dad6d89bf4f6c4034b8ff677
 size 4920