End of training

README.md

@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - 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": 16,
+  "lora_alpha": 64,
   "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:ef36f759c7e8eb043209338e21a6996d6595f56ea86c8dee531245ab8ef1cec5
-size 54543184
+oid sha256:0dfa87e72e0305cf82939a7286a316207bd40974856c48810e7118ebddc845b8
+size 109069176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe897f132f0db00d8449d2d80d97bfcebaa9e2fca72319c89cda40599a20857
+oid sha256:01464678b10fbc91b3d7af334396c4faa13c02a31bfff70f214b40a8ab6e3271
 size 5624