model_2024-07-27_02-39

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 2
 
 ### Training results
 

adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
     "qkv_proj",
     "fc_in",
     "lm_head",
-    "fc_out"
+    "fc_out",
+    "out_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ac780f189dac7db30ff059ca8572eb2dd4decfceb4708c052ded852842c07d
+oid sha256:d1e8e59b115d1291175991eafbe2c5228057102c763d5cee150d70cc57e9c773
 size 222098488

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12cdd3c33f2a644763426340deb64edb0d5181e80301040cb9d9160e275cdc59
+oid sha256:a3d6c90366eb01820b9dc6433e141563b723377c39dacf342b9ac1fbef8bb9e5
 size 5048