End of training

README.md

@@ -35,12 +35,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 1
+- 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: cosine
-- training_steps: 5
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "lm_head",
+    "down_proj",
+    "k_proj",
+    "q_proj",
     "v_proj",
     "gate_proj",
-    "down_proj",
     "o_proj",
-    "q_proj",
-    "k_proj"
+    "lm_head",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f33298be34ff9200ae69e79c567efa4b6f1bbedd734256815a26e5bf276297c
+oid sha256:e28c6d372cc3a758ea7de337ebb289c750e9d4f34eae885155a7309fd0f65c32
 size 694431312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f79c3b584885a55c425fe5f49484b58bff6d2d478fd4e9a7325f302260f25a5
+oid sha256:802c31e0c110bc47c788532bbe8bfd380ab207357add85eab48468806ea2e138
 size 4728