End of training

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 9
 
 ### Training results
 

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "q_proj",
-    "k_proj",
-    "up_proj",
     "gate_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
     "v_proj",
-    "o_proj"
+    "down_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 sha256:92e73d4da0d2c21dec69bb1f212744ddd671b7871e66badc9232a2666817a1a1
+oid sha256:d2a9861d3807945f4f3529c5160f06eeb8753ab86d557ee01b4b8770867aa737
 size 75012288

runs/Jan30_12-04-39_7385b2eee5f3/events.out.tfevents.1738238683.7385b2eee5f3.244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd69fdc39b88d0011c1183769329335c73b77543efb81bad07519a51479afd54
+size 5513

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7010401aca29a1002512b9a637119571f9fdf936ef2033f41a5f62e062a41ccc
+oid sha256:19899d8f226db522bded7702caf60be70837646ccb1eb9677fdfd37893e4b41e
 size 5368