End of training

README.md

@@ -35,12 +35,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 0.0003
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 64
+- 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: 3

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "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 sha256:88f824bb50ae76b5e62762de05c697528bf77956b9950bb98275e669f60bf49b
+oid sha256:e685876d0d49b65176aaa0c6bf6fe39de81494937cd7981c02f3d2fab952a637
 size 67126104

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ac6a7bdcb1bb4d8973f6c89812c517c458594ac813a9bf04d95f10f3f9549bf
+oid sha256:fed91af97d6c8a31075cca4d1d0ac896fc360f68c6780d35b4ceab234079a1fd
 size 5624