chunwoolee0 commited on
Commit
97a85e8
1 Parent(s): 29f0b0a

Training in progress, epoch 1

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:515bea455a86011f769cef08ffa2158db998857ea8f571a0c2a9ed257a04beee
3
  size 327674773
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:174693a38aacff0fc1faee969a777588dd0e6d0a8ec502ea3d2caa6e5e2f21b4
3
  size 327674773
runs/Jul09_14-52-12_e53c214375dd/events.out.tfevents.1688914335.e53c214375dd.4194.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b48ed3c2109718236d3506ee093cfa8583dcc7346db7155b81e901d47a4e6f38
3
+ size 4991
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8169d42217fb7d938fd05813c35664a9f02a941d8d8830a175c2026a3ae0a85c
3
  size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5d14a62cb974bf3f8534e0d4c7e0bb7794021f03765e4c840d64ca5ec7b1a3c
3
  size 3963
vocab.json ADDED
The diff for this file is too large to render. See raw diff