End of training

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-06
+- learning_rate: 0.0003
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42

adapter_config.json

@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 16,
   "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 sha256:87ce0f983d2a7f8a3c2aba77d00fa276325c429c4c299d32555d4c82ae61cfda
-size 109069176
+oid sha256:8c35befae33d7b24f5b8ae859d66cbb123162b011f72c1847f566784e9424e6d
+size 54543184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4884afb0b9a903c10e57eceeba12a51f072b101908785632e12c815d8adfdea9
+oid sha256:dc3d7d5567729bd476fc6d6bcf2669d37ffc32b644c6f2bf86268ee15ee5f675
 size 5624