End of training

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-06
+- learning_rate: 1e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42

adapter_config.json

@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2afd23aeddaccd305939925721448cfa69620160daf4565a2798635e26a8dac3
-size 67126104
+oid sha256:4c0366ffce4210bb44f69a890204e6265e440c06d74c2702c1ad188e35309bae
+size 134235048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e149268c4baf26cc45d746d173ebcdbf4eb7a42d115707feb7be4fd90f2825b9
+oid sha256:776a6654e7117511587825854c1f9102c48f7407b14b96321e85cf546e5c975f
 size 5432