End of training

README.md

@@ -34,11 +34,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 8
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 16
 - optimizer: Use OptimizerNames.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: 50

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "q_proj",
-    "v_proj",
     "down_proj",
-    "up_proj",
-    "k_proj",
+    "o_proj",
     "gate_proj",
-    "o_proj"
+    "v_proj",
+    "k_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c43737795cff77cb582873e88358e82b94c2f483345405cdee11c64b266a701b
+oid sha256:732422f9c642947ca65ea333ea08d047fcee9abad18fc61928342c1e15ddb372
 size 42220792

runs/Nov29_10-27-45_ip-26-0-161-138/events.out.tfevents.1732876679.ip-26-0-161-138.1610271.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4875ca09af1fc0ebfd6ff7f2153be4fffecc71e72aa40a08a66ee22b757ee8
+size 18114

runs/Nov29_10-27-45_ip-26-0-161-138/events.out.tfevents.1732883572.ip-26-0-161-138.1610271.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2e7d2513fb1ba8259bad8fc724afead39fac466ded3a151fd64629005eea0b
+size 377

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6720d8ef001ee02d7f240f84dc44b0707be621d9a1facb2356d314b3ee6ee9f
+oid sha256:228b94b7543ad41c26e90578dd79645014e344f1a6e840ab3f3fbac63a4c98f2
 size 5304