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: 5
+- num_epochs: 150
 
 ### Training results
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "gate_proj",
     "up_proj",
-    "down_proj",
-    "v_proj",
     "q_proj",
-    "gate_proj",
-    "o_proj"
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "k_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:de512ce8b87a79dc112f3a9a0ccf651692af7d7a763a599c68abcb054f09ff17
+oid sha256:a6f4318d5eb6cf3436a7a746e93b21bb8c1781bb8ed67c7ffbe6536d08df865c
 size 45258384

runs/Dec20_03-11-30_ml-ubuntu/events.out.tfevents.1734664295.ml-ubuntu.1485956.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35835ebd7e27f85504d35b44a238751c1344b9cfe0fb9a95533e32fc8363848a
+size 4184

runs/Dec20_03-12-03_ml-ubuntu/events.out.tfevents.1734664324.ml-ubuntu.1516322.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29bb66136e6d7925501e5053a68e3ca02042807cdaeee955ed16be9fe819db8f
+size 9156

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435c66c9541cfcb6ba1b946bbb328a03e3c7e8461ff527730ce2076ddff02217
+oid sha256:90d8ad2fdcf2de3697cdd241884918014326bf2dc3f936108a03869e01da1edb
 size 5304