End of training

README.md

@@ -36,8 +36,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
-- 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
+- optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
 - num_epochs: 10
 
 ### Framework versions

adapter_config.json

@@ -20,18 +20,18 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "o_proj",
+    "down_proj",
+    "in_proj",
+    "dt_proj",
+    "q_proj",
     "k_proj",
-    "embeddings",
+    "v_proj",
     "x_proj",
-    "up_proj",
-    "down_proj",
     "out_proj",
-    "q_proj",
     "gate_proj",
-    "dt_proj",
-    "in_proj",
-    "o_proj"
+    "embeddings",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:272c9e095aec3be5c1667a5c8729d24a0f829ecec92df9ad19753824a4498999
+oid sha256:aa92fe65de35d897d16e776906ac8505135b8fb3d049d8ae0a9bf8171c66e8c3
 size 8835128

runs/Oct31_06-27-30_a05d3760abf4/events.out.tfevents.1730356053.a05d3760abf4.77.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18886255c21f23ee92d59fee1ccc98b3f44fd5578463cf5c472a75fbeea087c9
+size 116675

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edf365b4432be985c5512d030eefe0d5c152e2f1399f5113fa374776075e5ab4
+oid sha256:1ddc3d64c30b7c67119dcd65d7d11d24ecd3dca06bff66f5cf61cac0d4476e3c
 size 5304