lmaop

README.md

@@ -36,12 +36,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.002
-- train_batch_size: 4
+- 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: 1
+- num_epochs: 2
 
 ### Training results
 
@@ -51,6 +51,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.12.0
 - Transformers 4.43.2
-- Pytorch 2.0.0
+- Pytorch 2.3.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "fc1",
-    "v_proj",
-    "q_proj",
     "dense",
-    "fc2"
+    "q_proj",
+    "fc1",
+    "k_proj",
+    "fc2",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1c74b96eb55fd47ccec08fb40fc7555eaaabab346bb30fcc2346002afe5f5f
+oid sha256:174b333c70752a69dcff1403b686d5cf27a7d22f1d0605c019cbcf8c801b8136
 size 94422368

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92902489244edff7984e4c62d5fcb802bb29b6a5f82c2096f4a7a19d4f4539c1
-size 4987
+oid sha256:2268492489fd679e900981c68d0831be9fd40a800daf21ccaa903235f93407d9
+size 5432