End of training

README.md

@@ -37,8 +37,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 3
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 3
-- total_train_batch_size: 9
+- gradient_accumulation_steps: 5
+- total_train_batch_size: 15
 - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2

adapter_config.json

@@ -23,14 +23,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
-    "up_proj",
-    "o_proj",
-    "lora_megnitude_vector",
     "q_proj",
+    "lora_megnitude_vector",
+    "v_proj",
     "gate_proj",
-    "v_proj"
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d48a2037234151d7fb8624bcab892f3640c9774e64801c04d20720246066f1a
+oid sha256:518203a53c55c3877c59cd3d01c791f1144f1ca96c4c450a93bc8b54f2f4cf55
 size 50821720

runs/Dec25_03-15-34_ml-ubuntu/events.out.tfevents.1735096535.ml-ubuntu.4126827.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e336a59e7a4f3aced4c450bfedc89301469ef9aaeb7cf21d8d6850fd0a176b
+size 17120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32dcbd27207a6381f2b0b7e32a8bd61c8b548565c1c92430f8af26a179938415
+oid sha256:6c5134e231f50dc18ccae6c079db42be8252c3d6dde06c0674f98c2d904f20bf
 size 5368