End of training

README.md

@@ -33,13 +33,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0001
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 10
 
 ### Training results
 

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "up_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
     "gate_proj",
-    "v_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060539aee4dcced1343578a8ee48d583b5217793135fa61923b4ffb446b8d0c1
+oid sha256:c682d6aa0827e42eb266099f9bc36931660a40855d92c823fdc5dedfa0af465b
 size 22573704

runs/Dec26_15-14-23_072ec0e7eab9/events.out.tfevents.1735226075.072ec0e7eab9.40.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a4ed66840cc0b7df34bbbb026d6ca038eca1cbbba3f930773a4a8a2e12c581
+size 990853

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b34f4b4e0caa7619c5f1bc7909d610e832a33448d9183d390411ba3548ca5e33
+oid sha256:df3605f584af95f7d37e84a2d4ef763494b89e27d7176581b0feeec4849bbab1
 size 5176