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: 1000
+- training_steps: 1500
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -21,13 +21,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "v_proj",
-    "down_proj",
-    "k_proj",
     "q_proj",
     "gate_proj",
-    "up_proj"
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "k_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:b2da7bf419a887982144253368f0c4a3114c3ccbe37d4f0594ab7fe3c9d657e9
+oid sha256:8e71055232ac2b1de9624cd45f7f84c6b03219f2605a93b8516229b9c757fd29
 size 83945296

runs/Oct25_23-45-49_4b884d802a1f/events.out.tfevents.1729899950.4b884d802a1f.367.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d26c32617a4a3322f92a06999d288ea733043912d44762c32640144a108a2f7d
+size 6093

runs/Oct25_23-46-27_4b884d802a1f/events.out.tfevents.1729899989.4b884d802a1f.367.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e38c4782514b044e615420711275d92dcb68e257e8e976b7328c472987b61b5
+size 6093

runs/Oct25_23-49-17_4b884d802a1f/events.out.tfevents.1729900159.4b884d802a1f.21731.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6873fdf8989b3ab74b4be2827fa44e6ca96c7653bef58a8236c989568fbb01
+size 322232

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f799f978f20620cd5057ee82ebda9e2b32ca2054f1a96cc1b833e6ba30cf505
+oid sha256:eee64836a0a77e296a04a74bf243a17f18ba5f989b815df750ddb483404bdac4
 size 5496