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: 5e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42

adapter_config.json

@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "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:e968295972be2151d116df331cc363c70ab340579954ebb49b77da74f06a1dfd
-size 134235048
+oid sha256:25c905192657bea3b27ef561cab3ed65a09e58b82e7f518965e6ba88fdc72f62
+size 268453016

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de08ab6676840575164be5a26e6bae7aab3f393a9518f9110d0639aaa1931a5f
+oid sha256:bccf348eadabee029f31e84fdaf2831d5143de2a66360160edf3f38c47ec0db9
 size 5432