2024-12-20-11-24-38

README.md

@@ -37,8 +37,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
 - 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: 50

adapter_config.json

@@ -22,17 +22,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
-    "o_proj",
+    "q_proj",
     "down_proj",
-    "v_proj",
+    "o_proj",
+    "k_proj",
     "up_proj",
-    "q_proj"
+    "gate_proj",
+    "v_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf6df60a4b65e90aa3f6af135dff23eef556304d5fac254bd8ecf3d06c00251a
-size 36981072
+oid sha256:3bbff8b714909d487890895f2c4a3849b97457dbb1fec3fc393337d3a255faa5
+size 147770496

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe7f562ad9fcf58170eb1ffe56497960eab5861febceed52c90fcbce58c1f80
+oid sha256:18f8a4f42a893541463ae552f9b22e83bf6806c3f77f59dee63b8cc76ec9ec46
 size 5368