Daisuke675 commited on
Commit
c169f7f
·
verified ·
1 Parent(s): c70d4b6

final SFT PRO MIX from best pretrain checkpoint

Browse files
training-runs/sft-python-math-1b-v2/checkpoint_last.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0a61f63243f201dc0e3f606f17af34524f98af0f612b08b45d0a7cbb0aef5eb
3
  size 15758460499
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5daa0eb6ad611bb39b36606900e54d909bb2edb4a074530754a52bed21cefba
3
  size 15758460499
training-runs/sft-python-math-1b-v2/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
training-runs/sft-python-math-1b-v2/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "local_files_only": false,
9
+ "model_max_length": 1024,
10
+ "pad_token": "<|endoftext|>",
11
+ "tokenizer_class": "GPT2Tokenizer",
12
+ "unk_token": "<|endoftext|>"
13
+ }