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: 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": 32,
+  "lora_alpha": 16,
   "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 sha256:23daff0420084344f78db2199539ed9e2446cc942c58f4a3f1a863b8d27e8e01
-size 109069176
+oid sha256:dff707982c56aee503b5b9fc858c963124a9c5f002fe6cce35b112b0cc305072
+size 218121344

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9918114e463697b0a0c3429cd9de8983b0cb76174fcbff3dea5387d7d9d958e3
+oid sha256:b77265255758707ffba6196c81dfa9efc2271c3470f43858a8781d763f4ec74a
 size 5624