End of training

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 

adapter_config.json

@@ -24,12 +24,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc2",
-    "k_proj",
-    "v_proj",
     "fc1",
     "o_proj",
-    "q_proj"
+    "fc2",
+    "v_proj",
+    "q_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da440f3a5efadf285fe17702e8f7d24082b332fe18fbf12be5d7ea1dbcc7962d
+oid sha256:aa05f3c56f5b029bce856f7de5fdca48953b1d8b03d5919d16d34a369c2df305
 size 10839776

runs/May22_12-02-10_216350d5a5f9/events.out.tfevents.1747915334.216350d5a5f9.1300.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0f852f363d044d5b39459dc817c1135b7b52ffb86f98564ab9be8b6cbbd099
+size 8153

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e80dd5dac1a600027bf4f4c9743710dc0b4b06225afc12425157ee6a61ca9902
+oid sha256:8b7829e7ec2a860f3a1db9fb67aed686068284e7a79d2a88f356f1f8b65d3c6f
 size 5304