Re-trained QLora Adapter with 260 data (5 epoch)

README.md

@@ -53,8 +53,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.0
-- Transformers 4.45.1
+- PEFT 0.13.2
+- Transformers 4.45.2
 - Pytorch 2.4.1+cu121
 - Datasets 3.0.1
-- Tokenizers 0.20.0
+- Tokenizers 0.20.1

adapter_config.json

@@ -16,7 +16,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a970cc1fd0b2a707748f41aed2540f761b682b52eda5a4237ce4e58bccefb1b
-size 33571624
+oid sha256:661f55bd9eb4481c5f7a7184c7eeade2c372c6aabc24f5c9d34b4a2392d4d104
+size 134235048

runs/Oct20_11-03-28_c06fa3a5df24/events.out.tfevents.1729422227.c06fa3a5df24.5296.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd143292d17a0c96ae378531c7a4ab6ce7a2166acae4b3b51f9f1bf9a9d7e20e
+size 8752

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d8b2d24b4bcdd742706fced1648a7ff5a29daef93bca22b7c4feecf2ac49f9
+oid sha256:979ac9c98655e77d2a9a425d077f28e51b2e3ab00acb9c79bb029c2575e87ea9
 size 5496