End of training

README.md

@@ -35,14 +35,12 @@ More information needed
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
 - train_batch_size: 1
-- eval_batch_size: 8
+- eval_batch_size: 1
 - seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 8
 - optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 50
-- num_epochs: 3
+- num_epochs: 0.5
 
 ### Training results
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2179834d8320c628e0ae4b2c4512210978c74c09297a77a34c10f3c143714b10
+oid sha256:d566a619bb3017d6c473652e3cc5362a5c056fdbe2f49814214a413829cbb85a
 size 21146656

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1a05de5cfdaf4d9888b30ba7a833c3852b88b37ba81bd059b899b6b8cfc2d0
+oid sha256:2f433d3bdfcaf6ad259ce3eb6621f59717ec01f88d7f474d7856f999020fc459
 size 5304