End of training

README.md

@@ -33,13 +33,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
+- learning_rate: 1e-05
 - train_batch_size: 1024
 - eval_batch_size: 1024
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 10
 
 ### Training results
 

adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
     "k",
+    "v",
     "o",
-    "v"
+    "q"
   ],
   "task_type": "SEQ_2_SEQ_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a32c60d50a738a6a3cd20b2a8a6a759afc801793512779a20f375fb3c78cdb23
+oid sha256:b363d16c4098943fc007cc1b99cbdb1a333779321276ed72c7ecef508d07d710
 size 1199384

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb63849f5849f4e46f5b44a7e49b69cbea7dc39a282f0c6092889bfdb11c5f0c
+oid sha256:06fdec916fdf25d4f1b4897338682dba2f4232c26ec64c3054667b4c1f36b316
 size 5304