Model save

README.md

@@ -38,8 +38,10 @@ The following hyperparameters were used during training:
 - eval_batch_size: 16
 - seed: 42
 - distributed_type: multi-GPU
+- num_devices: 2
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- total_train_batch_size: 8
+- total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 1

adapter_config.json

@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "k_proj",
     "v_proj",
-    "o_proj",
-    "q_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

runs/Feb04_01-20-10_r2d2-devbox-fqvnh/events.out.tfevents.1738632026.r2d2-devbox-fqvnh.23252.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbf9bbcd4df87a9eaa4f03287ea293f6e2c4b44c8b8565d8f317734561d11300
-size 4702
+oid sha256:ba55e79b9ee473fa8ab8598b378c276e2126191501f8d664f99382b2bfc0a228
+size 5318

runs/Feb04_22-38-24_r2d2-devbox-xp7fc/events.out.tfevents.1738708842.r2d2-devbox-xp7fc.888.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6bd34f7bd564b3e89dea287dc1fc02df69c63fbac2734e27387a683ae970fce
+size 4702

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f61e0d477403b0348768c2a5c82297770d6a18e17c7c1da31e26b329c52011d
+oid sha256:912dcdc963386b5c0cad746ef1802ff00a9e0cd07742bddd360e8ea6480356ae
 size 5880