Model save

README.md

@@ -36,11 +36,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 16
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 20

model_fold_0_batch0/adapter_config.json

@@ -40,9 +40,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "v_proj",
     "q_proj",
-    "v_proj"
+    "k_proj"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

model_fold_0_batch0/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:835c437387d81519e42e460a80666370769d2657c67434b42e0ba960ffa64056
+oid sha256:d2e88a260e9d2641c42dfd7058e465462713bcdae4023b5d890356f1e64a778f
 size 4780504

model_fold_0_batch0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e45a8de8819d4c04f3cdeed9685c2d41fe73a64e3b265506968b9f80ebf26556
+oid sha256:b093f9a99f5bcfbe28a31dcc057e5e9dff06005a60705aed8ee673e56a7ec907
 size 5496