End of training

README.md

@@ -35,15 +35,16 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 12
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.3
-- num_epochs: 1
+- num_epochs: 0.5
+- mixed_precision_training: Native AMP
 
 ### Training results
 

adapter_config.json

@@ -19,12 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "q_proj",
     "k_proj",
+    "o_proj",
     "gate_proj",
-    "o_proj"
+    "v_proj",
+    "up_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7b1734a2911736486068fcdd5e37c778ddc8cc2fe7c22c41206e2e0c3b8156
+oid sha256:d9746eed984a839f3ddc00dcd0ee2bfce72abb6a4d0b758836c2173f569d1d21
 size 32294376

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f38b3629f392e31c7e03e3c2ef99e18d01de05a9525e160b1db4a8390c667150
-size 4283
+oid sha256:b8a39c5a3204a96f81eb104a00060bcae8ec777318c46103c7a86ae7111fdbad
+size 4347