End of training

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - 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
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac5ec1e31d7d4a902254a91e8405094ed6440a43eee53f500749bed5ae476929
-size 21147152
+oid sha256:c980d3e7ef8473e18a8cf5f0b82a1bdf51ba0a234fc71a52f72cf6870f5347d8
+size 42220792

runs/Apr03_13-18-35_e494ea3cf604/events.out.tfevents.1743686320.e494ea3cf604.1185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78f50a1e3ccb19e1129650d36f0b1bc6abca87e0fe924723c2588872b440d638
+size 46179

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a712e1bee443859a5898a10b78e61f3f3b5ccf5d03206d015064c5cb3488f7ff
+oid sha256:bef62eb5768e4e7fa8d6faed7028c4aa7e028086ec088db69448cf4d692a0627
 size 5368