End of training

README.md

@@ -40,7 +40,8 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 5
+- num_epochs: 8
+- mixed_precision_training: Native AMP
 
 ### Training results
 

adapter_config.json

@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "gate_proj",
     "down_proj",
+    "q_proj",
     "v_proj",
-    "up_proj",
-    "lm_head",
     "o_proj",
-    "q_proj",
-    "gate_proj"
+    "k_proj",
+    "up_proj",
+    "lm_head"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a25085dd0bd4db688606c304c39c4a713863ff86fc0fd8ed011e0d9bfb0c6c6
+oid sha256:744d8c0d91a593b105ee52c3f5453c887b91cdb869414dcb79df299ae8139345
 size 694431312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba642184d95b3ee2638c78b1a1cfbcd13b7136c53ee88f3eae2cda5de08f87f
+oid sha256:0fca3c7cae03502c7e2fd66bd8662325107c83fe508b11a1bda904de7ff9e1cb
 size 4728