End of training

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 6e-05
+- learning_rate: 0.0003
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -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": 8,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7f41654d28013bb7871fb879c74510a731624c853bc6c6b22d8ccda1c4bd8c
-size 109069176
+oid sha256:a6874a6f2fe18b782116a28f9239ddfe36501113dcf01a9f4984a5f4356991a6
+size 54543184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d07f3ae26ef6e4f7b79d1bc4a9e5e967cdb1bc39bfc5b8651181d59dcc21bd90
+oid sha256:3759cb6f48dff080222ac221462c25b3fb6ff9705f1af07c2e8a54b5457088c9
 size 5624