Model save

README.md

@@ -39,7 +39,8 @@ The following hyperparameters were used during training:
 - seed: 42
 - gradient_accumulation_steps: 8
 - total_train_batch_size: 64
-- optimizer: Use adamw_hf with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use adafactor and the args are:
+No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 3
 - num_epochs: 5

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "q_proj",
-    "gate_proj",
-    "v_proj",
     "down_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj",
     "k_proj",
-    "o_proj"
+    "gate_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1d0fb76b2e6856c4622847685edf013db90020624041931b3de9f043374e79
+oid sha256:f7604aa0809418cc069c50fd77a143bbb8c55a624d6216665ae4bad02ab8c9fe
 size 51802928

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3537a01668977a56c41e9d156bd3cc5869bf96cd826c11b6768d9c0ecbb232c
+oid sha256:8203a22f3e66520618cca01e78352bfd205178151b83a29535de51ce851622ed
 size 5240