2024-12-18-15-38-01

README.md

@@ -34,16 +34,20 @@ 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: 2
-- total_train_batch_size: 16
+- total_train_batch_size: 8
 - 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: 50
 - num_epochs: 2
 
+### Training results
+
+
+
 ### Framework versions
 
 - PEFT 0.14.0

adapter_config.json

@@ -27,12 +27,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "up_proj",
-    "o_proj",
+    "v_proj",
     "down_proj",
-    "q_proj",
+    "up_proj",
     "k_proj",
-    "v_proj"
+    "q_proj",
+    "o_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0de7981adf78b5cd6fec87b9b8f63414eaa767187d209eb18994a368160042f
+oid sha256:e78360308a1be6d34038ca06da6156096c5095c08ce35657a6066df431458a00
 size 36981072

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9128f85f4032d1e8e8949c41b05e5aa0303cf4010c2ed2dd7ab32649ac7e4c0c
+oid sha256:d680724ae53cf05e4f8c3d0264c79a9fe57361214e446256c8d3759b9286cb09
 size 5368