End of training

README.md

@@ -34,15 +34,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 3
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 3
-- total_train_batch_size: 9
+- total_train_batch_size: 12
 - 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: 3
+- num_epochs: 150
 
 ### Training results
 

adapter_config.json

@@ -23,14 +23,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
     "down_proj",
-    "k_proj",
     "lora_megnitude_vector",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
     "v_proj",
     "up_proj",
-    "o_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:599f06c2fa8058e1ed38914d7ced7bbc57c88fbc351ba7f3ae1c4a7d70d2e401
+oid sha256:3c6a2efd4cac3b5ceaebbd4ba3907d31a71a352ac80380cb91e09dc5bb2c4bde
 size 48502952

runs/Dec24_02-37-55_ml-ubuntu/events.out.tfevents.1735007876.ml-ubuntu.4180.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5901c59ed3e3188875e9ac93a68c2845ccebe5b36f2ed4a562f8fea36005585
+size 5842

runs/Dec24_02-39-09_ml-ubuntu/events.out.tfevents.1735007950.ml-ubuntu.7797.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649cd7a41c20ceeaa46b228d671aadb09dc92fe4cb9d44d59153a89ab6d70aeb
+size 46879

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d559b667c6e209289535f82e4382127ad95244184b80cefd833153468951a014
+oid sha256:e63eec21761e8ccebac187a7da84b9c87e2496b5551bd2cc2044c81e7ddcd61c
 size 5368