End of training

README.md

@@ -33,13 +33,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 1
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
 - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1
-- num_epochs: 1
+- num_epochs: 5
 
 ### Training results
 

adapter_config.json

@@ -26,13 +26,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
+    "gate_proj",
     "k_proj",
-    "up_proj",
+    "down_proj",
+    "o_proj",
     "q_proj",
-    "gate_proj",
-    "down_proj"
+    "v_proj",
+    "up_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9ccf974fd81e21f8f2bb5198e1eedb43590c71ed0a11e9cc6ed4c0344f97da
+oid sha256:49db08f5163ea18ba60f8eb0f24f271f420a0d2051fac600e78ebeb02a722040
 size 11608320

runs/Feb19_15-45-36_CGLAPTOP-BIGASUS/events.out.tfevents.1739976337.CGLAPTOP-BIGASUS.14316.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8470eb240c3b33ac3e87be8281a536db26b7e0817986ddbaa2925e93ef64bb2
+size 14271

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b843d756875c92af8cca72f6a80a23ece0f6d8eeba9b74947cbf07ae879c5f7
+oid sha256:99d711fbb3ab3e6cdcf7e629f52aaca96cd9f6ce367c826e17c93c704480c6be
 size 5368