End of training

README.md

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 150
+- training_steps: 200
 
 ### Training results
 

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 sha256:3ebc7474e4776fd1f97933dac8b6de497e79732b136064ed6495db1cb173d665
-size 67126104
+oid sha256:e968295972be2151d116df331cc363c70ab340579954ebb49b77da74f06a1dfd
+size 134235048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae50825432cee3150128b573251f966e874c56d438195397e926564b04a55835
+oid sha256:de08ab6676840575164be5a26e6bae7aab3f393a9518f9110d0639aaa1931a5f
 size 5432