End of training

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.PAGED_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.05
-- training_steps: 100
+- training_steps: 500
 
 ### Training results
 

adapter_config.json

@@ -26,12 +26,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
+    "o_proj",
     "up_proj",
     "k_proj",
-    "o_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef11d96bdff5e4087096bb77a64550becce58d96d3a284a8fdd55bd5db3f11ae
+oid sha256:ea928363d7e581124e3576a85c7717a5b7302a61b9f5a7fd38b5b47d4c116166
 size 327208280

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c2db11f29c8c063ea9726100cd651a31379213f88e877aa2390f132d375434
+oid sha256:cbe5673256a2d5b79ddbf20ecb9823db5ae90402ef1b454451e75aaa7bb3d91f
 size 4453437644

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45b6e0cd9a15580cf37d3bfa5fd0ef557593f1eeca984b4a1041b538d99824b6
+oid sha256:30d23b424b142342170684b778958211400bb09eb979481ff6e6a47622fd9d89
 size 5304