Model save

README.md

@@ -34,12 +34,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 11
+- train_batch_size: 10
 - eval_batch_size: 16
 - seed: 42
 - distributed_type: multi-GPU
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 44
+- total_train_batch_size: 40
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - num_epochs: 1

adapter_config.json

@@ -17,9 +17,9 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "o_proj",
+    "v_proj",
     "q_proj",
-    "v_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

runs/Feb04_00-13-38_r2d2-devbox-fqvnh/events.out.tfevents.1738628034.r2d2-devbox-fqvnh.19365.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335e33f0549a29dabed4dedfd6e88cb98d0c447de1ebf99d69c818eeee11d5b6
+size 4703

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b027ae1527c5de80c84f0d58eb362f13779af620421bc086e44c3e04992c32d
+oid sha256:396c8c4306e10ad91ae799765368d2426aeedea19ac53f195842b542b396e6fb
 size 5816