Model save

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_HF 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
-- num_epochs: 200
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -26,13 +26,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
-    "q_proj",
     "v_proj",
+    "q_proj",
     "up_proj",
+    "down_proj",
+    "k_proj",
     "o_proj",
-    "k_proj"
+    "gate_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2683308a30558ca889407a1ffeb0cd1fe45632a17e28fc7083426396fd5b3846
+oid sha256:9df8be3d456dcc78d7ad14050738589f046087b89f227f8e1da5ec26e032ee4b
 size 125866776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:696556ef4dee1a9991278385df2ab089a6b669e63fcab51ea38414b5a147ca93
+oid sha256:1d23a1f32ab6bce0f981768bbac4bf8756b5e2cc4c71db976163be7a16401af7
 size 5304