EdBerg/outputs3

README.md

@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- training_steps: 1500
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -21,13 +21,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
+    "v_proj",
     "up_proj",
-    "o_proj",
     "down_proj",
-    "v_proj",
-    "k_proj"
+    "k_proj",
+    "gate_proj",
+    "q_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 sha256:8e71055232ac2b1de9624cd45f7f84c6b03219f2605a93b8516229b9c757fd29
+oid sha256:702cfe5c7c4031b97965efa4afb78f06a5679b64e33c6c0728cc8a75ce7bda94
 size 83945296

runs/Oct26_14-15-08_c9b14f60a56e/events.out.tfevents.1729952112.c9b14f60a56e.1232.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63016246a78e50c815f79374e6b790658e681d92747bdb6ed05fd5bb36487809
+size 427732

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee64836a0a77e296a04a74bf243a17f18ba5f989b815df750ddb483404bdac4
+oid sha256:a144f3f76b56fa074a7b3cbaa95efb7d43089b4ea3b6a4e0715824a5b82b40e1
 size 5496