Model save

README.md

@@ -38,10 +38,8 @@ 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: 8
-- total_eval_batch_size: 32
+- total_train_batch_size: 4
 - 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": [
+    "v_proj",
     "q_proj",
     "k_proj",
-    "o_proj",
-    "v_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

runs/Feb04_23-51-53_r2d2-devbox-xp7fc/events.out.tfevents.1738713131.r2d2-devbox-xp7fc.4176.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1debc124e4c65243d43a5d5b49193761a063325930bedc5f0dd78163d5d02bb8
+size 4702

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91be86cea99cc3d59ca477bddd0a852d375f8d139353f40e67a89340fa7f8e0b
+oid sha256:45499b87505940de721ec42e507068d8d46364562141a4905c8d11d5b8f3ea49
 size 5880