End of training

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - 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: 2
-- num_epochs: 10
+- num_epochs: 50
 
 ### Training results
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "k_proj",
-    "gate_proj",
+    "q_proj",
     "v_proj",
+    "down_proj",
     "o_proj",
-    "q_proj",
-    "down_proj"
+    "k_proj",
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06b86d077097b044f809857aa0d5cf5b1db951af2e21ac18019414804ac731f
+oid sha256:f45fe0e6cc100cd116347e50201c73272237592df51e27293f20faf9c8429ae8
 size 47584968

runs/Dec20_02-17-01_ml-ubuntu/events.out.tfevents.1734661027.ml-ubuntu.1364545.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62b1c684c6e07c23f42d923275807f95849c34eee45d9505f81c4719495376ce
+size 7242

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a2e495542170e3efe41ae13f5115f669b4cd5abe8a882896f82fd879c61b5e2
+oid sha256:d878227c718c962ef31e935fcb3981ae10b6b0681b50a47b71e4a7f42aa0d48d
 size 5304