End of training

README.md

@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 5e-06
 - 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": 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": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:669e9a17346807e75c578f7704ae1234a6c09ce0464aefd9a99df44c7051b425
-size 109069176
+oid sha256:eeaf188e5e77512d90ff49795bffb2127c5b8485dd150ef31ebbfa7782e9af39
+size 54543184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578080474af10395cb0796ef509610b89be7f85af0829107fde6602ade9119d1
+oid sha256:a401ad254ebadf2067654810ed030aceeda90b1d04209f9ff44964f3467447df
 size 5624