llme2_sft_model_rlaif

README.md

@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.8.2
-- Transformers 4.37.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.1
+- PEFT 0.9.0
+- Transformers 4.39.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -23,5 +23,6 @@
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c4e15e2aa587157253617d0365ed34f71e62229c68cd5f01344b1eabf456dd
+oid sha256:ee7c36670a521742945938cf82fa8dbbbb8d8c3a6f0a215a3775a923837b80f5
 size 109069176

runs/Mar21_05-38-15_a79452d0b9dd/events.out.tfevents.1710999495.a79452d0b9dd.1533.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139eb469ce06239d856d437a734335aaa66ab4d92d92e4f592d7afc567b9e362
+size 5428

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4839e50db7c680db74fff7ca909f9dd43014b641c023dbbc2ddd67a6a0c0be8
-size 4728
+oid sha256:6285d24d896b9c16bd512f85fa1d1353d0293df20262cce021cbde3aaaedb427
+size 4920