End of training

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 50
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
     "o",
+    "v",
     "k",
-    "v"
+    "q"
   ],
   "task_type": null,
   "use_dora": false,

runs/Nov23_15-49-30_509db22501e6/events.out.tfevents.1732376972.509db22501e6.377.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:981d9894d5a52aed5ed2625b72ec0daf7cbf068dfba713960c9624ece1f94275
+size 6651

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 128
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c71a8bd68dc8b7808a874fb824404acecb320e8d7c9de0fb194365b6f0888348
+oid sha256:51a14a6e05758db8fa173927995fe6885b58b4f8e971377f422eaa08e2c444ad
 size 5304