Farhana812 commited on
Commit
f98a237
·
verified ·
1 Parent(s): 6e3d280

Training in progress, epoch 1

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:329d5c19219e89410afb91b2b4d634cd638605518ebca84c74a69f22c0ff1c98
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7cefd8e5b27384eff8a6bd3747dc1dc7d4ce0939acc3d1bbb389458d10e7c4b
3
  size 497774208
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 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "pad_token": "<|endoftext|>",
19
+ "tokenizer_class": "GPT2Tokenizer",
20
+ "unk_token": "<|endoftext|>"
21
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bfa0d791639f98ef55580b09282348edc86ab6306ab4b2723d7a21c6fb53443
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57622ffb95e46c32d0d41fd64a38d61f2c5cee63e8aa24e5d58a79e16ec02761
3
  size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff