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: 200
+- training_steps: 150
 
 ### Training results
 

adapter_config.json

@@ -10,7 +10,7 @@
   "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",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa8e967cece5697b0f43d52cf8f722ae9b9730a95c2a94060e0729716f548c2c
+oid sha256:0655cde54b9007d2107281da19e94da641af9616282b1def46026228d4d34824
 size 218121344

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:415e289d793336f0cb6265d3ce86045bc2d858b41f65303cbdfdc23f9a5d4063
+oid sha256:31554cf8e10de8e47dced0a6245d019bfddb85e50056aa85b0f46333af5aca1f
 size 5624