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: 1
+- train_batch_size: 10
 - eval_batch_size: 16
 - seed: 42
 - distributed_type: multi-GPU
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 4
+- 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": [
     "o_proj",
+    "q_proj",
     "k_proj",
-    "v_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

runs/Feb04_00-07-58_r2d2-devbox-fqvnh/events.out.tfevents.1738627694.r2d2-devbox-fqvnh.17133.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028feed457d3f46c9b6da2f50baaa4b96de15f0c2fa968a0dbe7c9fd97507598
-size 4702
+oid sha256:46df41f9198b2be14e9eee1038bf7c7a4befd7acc150d169e5962c27bfe87009
+size 4856

runs/Feb04_00-09-28_r2d2-devbox-fqvnh/events.out.tfevents.1738627784.r2d2-devbox-fqvnh.17579.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa23907217066abe27755afee5a0534e3c7d7deb4e93547cae5719d620ccac93
+size 4703

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a69e60d1d32d795983efefed3115d3c99cfa2fc7dd7cbc834eef108f00681762
+oid sha256:a0e54077e4bdcdd3996c6f99df5cf25d02b3a6726850bc66f5302f35ed8bcc44
 size 5816