End of training

README.md

@@ -37,13 +37,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 20
+- num_epochs: 40
 
 ### Training results
 

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "o_proj",
     "k_proj",
-    "v_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857adf7f69f8d34f07585321aa0ecf298659c2d3e47929f770f29c0b1d848a21
-size 6200
+oid sha256:a8d48a5194204384fdedf4c20625a51ce73c14424f353b51057386bee169d7e1
+size 5560