End of training

README.md

@@ -34,14 +34,14 @@ 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 OptimizerNames.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: 9
+- num_epochs: 3
 
 ### Training results
 

adapter_config.json

@@ -23,12 +23,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "gate_proj",
     "up_proj",
-    "q_proj",
     "o_proj",
-    "v_proj",
     "down_proj",
+    "q_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2a9861d3807945f4f3529c5160f06eeb8753ab86d557ee01b4b8770867aa737
+oid sha256:47168045040d2a120df63929508f1dbf6c3d0e9de944eb6326c801be5ae2a362
 size 75012288

runs/Jan30_14-12-50_d50c14c094bd/events.out.tfevents.1738246372.d50c14c094bd.1338.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb45bcc72c297a6464318022c4d9a98ce4a15bf962ebc306037e74564c5da8a
+size 5513

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19899d8f226db522bded7702caf60be70837646ccb1eb9677fdfd37893e4b41e
+oid sha256:7e1ec4beda6ecb750d42179d227ff85667cd3193fd5cb834a761f9cff7ea7b45
 size 5368