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: 50
 
 ### Training results
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cdc21ccc1c378f224a305f540676b39b5fc91ba598a0dfadf3c11aa5c7c8479
+oid sha256:f6b9b22decdd1ef0c965a40b883d72a83e0ac61130a12129c7cddf1843c739ff
 size 47584968

runs/Dec14_13-38-35_ml-ubuntu/events.out.tfevents.1734183516.ml-ubuntu.1476380.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed9ba41f7f998e1ed4e851cbb38695b97e520d3619df3b5f05eb630c048638a5
+size 12155

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fcf8e7a1b07d73f07c34ec7439f0a16bc6029c2ca76ceea7907d8b4e8aea0c1
+oid sha256:d32aa38b159632ba657fc6c4f6b5ee58ea518dcb6b76eb5709b82a30be934e14
 size 5304