Model save

README.md

@@ -35,15 +35,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 2
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 16
-- total_train_batch_size: 32
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 150
+- training_steps: 300
 - mixed_precision_training: Native AMP
 
 ### Framework versions

adapter_config.json

@@ -10,19 +10,19 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.3,
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 62,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "output_proj",
     "v_proj",
-    "q_proj",
-    "output_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd05f214dc622562ed168c3655734276c2266553db79edc68825ad1448fdaaca
-size 105661296
+oid sha256:de5af9275dcffaae041fb85356b6395ad80d14002885a5c9d4ca1e38c47769f7
+size 109069176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea75da07f1ba70e77c160385fa626b641050435114d80aa7f5462afa04741a30
+oid sha256:38b362958e6fbf011cda70c85197f1ce1023f1f9f87f87f5c5293fc0dae56d64
 size 5368