End of training

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 5e-06
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42

adapter_config.json

@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e731550b52786ff1a74753646a0b6b99c34e39e22e27163e47fe750eef8d954
-size 54543184
+oid sha256:375f9afd19284f5b66f94f42610edce430745a7607ed4bd34d4efa96842c694e
+size 218121344

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f92ce5acb316a2b17603337e16b28082260a7cda9edc75da37a2824c4217f643
+oid sha256:f54c07e08726d164eee90ee2313a4fb7c9b6baf26201ed843f6354b89e22a474
 size 5624