Model save

README.md

@@ -31,16 +31,17 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 2e-05
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.05
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 2.0
+- num_epochs: 1.0
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -8,10 +8,10 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "lora_alpha": 64,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0.1,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "revision": null,
   "target_modules": [
     "q_proj",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa244c15fdbc06be69ec86acc857554edf4c913e1948c03ad503bbd6abe7774f
-size 340225224
+oid sha256:2cc9601565cd49aa464d0ba01062fdf0b1adbe2f5cf4a62b83fac6f1d305c9cc
+size 170142632

runs/Nov03_06-34-13_2d39af33b868/events.out.tfevents.1698993254.2d39af33b868.5736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6804d15c977a93c72ef8df44e653159f3d7284fbfdae812ff7428fc11748cde6
+size 10481

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72764532fdef946e72fb40cb5e97243f0d5b9a61b3ab3c3a3f1fd3b24f57746d
-size 4664
+oid sha256:9b57aae45f5e1e2612cf1fa86adad1048b50e88c0c3ea4a027518901f5615e8c
+size 4728