Model save

README.md

@@ -35,15 +35,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 1e-05
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 256
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 1024
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5.0
+- num_epochs: 4.0
 
 ### Training results
 

adapter_config.json

@@ -10,18 +10,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_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 sha256:436a8e49ed479b3771044c0d35c85b216bedf0ae72ba42937cde7bcc457209f5
-size 27280152
+oid sha256:ff04d359bd3f3884f76a699008110bfb5dba0f39495d199c3a1a8c675a76f436
+size 109069176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d36706fc0e414b2efc9b699216597cbba4c420758aea9451622ab794f17a43
+oid sha256:2cd0176290873c5f31a9f07c67d182e12ee94c5ead73e09323e5bbc58f07094f
 size 5432