shawshank/summarizer

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- training_steps: 500
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -52,6 +52,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.7.1
 - Transformers 4.37.0
-- Pytorch 2.0.0
+- Pytorch 2.1.2+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.15.1

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d34965e44f2aa6c858a5a70692acfded2ff16d1bebfd012bd4fa8fd8c18d011
+oid sha256:b0fdd56eb2d87815b67baab215aa5005777580b986519f2b41d6f31bfc8c537e
 size 27280152

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924e9c6e920621281d40a09975a4b57e8527a4e2db2fafb477fa67ce40e20910
-size 4283
+oid sha256:f0a210e7dd959f06fafa4cd717000f5e098607b00901a78648c79dbf423239a4
+size 4728