End of training

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.0003
 - 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

@@ -10,13 +10,13 @@
  "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",
  "modules_to_save": null,
  "peft_type": "LORA",
- "r": 64,
+ "r": 128,
  "rank_pattern": {},
  "revision": null,
  "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d66ff7032ad0a8b057407389c0054cf63cd4bb135a976812b7db7b17b1d486d
-size 134235048
+oid sha256:5b7170023e8f0929a86df6a1e36f291c0adf97b99c9c866350e3edb0e4d74788
+size 268453016

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6679ccab2258735fa3bf9b367688c88938e19686e456f5322da4a5c99505b51f
+oid sha256:62c565fbabddec5cd09235e24b6f89314f5a830e05864462a367ba2ee53ba1d9
 size 5432