Model save

README.md

@@ -37,7 +37,7 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
+- lr_scheduler_type: constant
 - training_steps: 50
 
 ### Training results

adapter_config.json

@@ -9,13 +9,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "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:d57bf63fdd7419f7fb7b8bc56b36e6fbec99a83a182d4dd6610042c7a5abb3a9
-size 31474080
+oid sha256:a67b84540e36bf5353b03142e2f4da084671ccab521452232b1bde15ccdd26ee
+size 62931408

runs/Jan11_03-12-38_62aac7b96a1a/events.out.tfevents.1704942759.62aac7b96a1a.1849.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d279b80a51fdecec6c8258f6a6ae46b10af575b529d4fdea702dcd1a1a9c673f
+size 5133

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9cfc0abd47e890734294c5ac5f9eaf0d5befc79c93ceec27e77afa8861f9a23
+oid sha256:2dc029ffd6cbd5dd8b2b1baecb5b34965badcb12a74dabb06b57d0c21cf965ca
 size 4600