jackoyoungblood commited on
Commit
fa90e6d
1 Parent(s): 2b5421b

Training in progress, step 500

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. model.safetensors +3 -0
  3. tokenizer_config.json +13 -24
  4. training_args.bin +2 -2
config.json CHANGED
@@ -33,7 +33,7 @@
33
  }
34
  },
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.30.2",
37
  "use_cache": true,
38
  "vocab_size": 50257
39
  }
 
33
  }
34
  },
35
  "torch_dtype": "float32",
36
+ "transformers_version": "4.35.2",
37
  "use_cache": true,
38
  "vocab_size": 50257
39
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f427c733642877744ca410880f7f4944857d3e335221b44450c6f53b8fa5e905
3
+ size 497774208
tokenizer_config.json CHANGED
@@ -1,33 +1,22 @@
1
  {
2
  "add_bos_token": false,
3
  "add_prefix_space": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
 
 
11
  },
 
12
  "clean_up_tokenization_spaces": true,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "<|endoftext|>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
  "errors": "replace",
22
  "model_max_length": 1024,
23
- "pad_token": null,
24
  "tokenizer_class": "GPT2Tokenizer",
25
- "unk_token": {
26
- "__type": "AddedToken",
27
- "content": "<|endoftext|>",
28
- "lstrip": false,
29
- "normalized": true,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
  }
 
1
  {
2
  "add_bos_token": false,
3
  "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
  },
14
+ "bos_token": "<|endoftext|>",
15
  "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
17
  "errors": "replace",
18
  "model_max_length": 1024,
19
+ "pad_token": "<|endoftext|>",
20
  "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
22
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30afe0cd5ab954f471d552a1a331ed9e1675aa97216fade5237508827717630e
3
- size 3899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d98f7bafc778a5d1be4cf9242fa3ca812fe48a5083c69255608eb322bb643c56
3
+ size 4536