End of training

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.0003
 - 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": 16,
+  "lora_alpha": 32,
   "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 sha256:3355ea5a36d0d608a79403a08b96a7b894683dfb7beb5fe1453593d7dce733a1
-size 67126104
+oid sha256:37d2a8f4571e074231579ee351bc1a07cd810af56fec2e66b1ea893fb26d2574
+size 268453016

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49d9f62407b47f26a0c77ac52e8719627cd728cf11062c02bea12ee56e469f90
+oid sha256:5fcee88194851558837ab8d9f019103314244e7de6da7a6842bf6c4e0f321386
 size 5432