End of training

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 5e-06
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - 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": 64,
+  "lora_alpha": 8,
   "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:f67770225943fdf687ca005134786192688217ce3b045284049cc1cfb2ca5cc8
+oid sha256:b193a6ab0b88ab63a7aaca273b7bd8e9081b996bcb6570b7f5dd63953e247603
 size 268453016

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c710fa95e0bdbfb021c6ded833a8f681ad3373138fa664a7b55a5dd580538ef7
+oid sha256:b3012aec28d05b213631ef45be624e97a4934a40970efa6977e179b7041e4979
 size 5432