NourFakih commited on
Commit
f585049
1 Parent(s): 1142487

Training in progress, step 2000

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:c27ae96eb85bea83f7e574289b45b59edd8ff952bdc085deb9375829f0739ed7
3
  size 956835520
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a5079f16b1d696364f15c7648bfc14368c5633935f14b415ec2fad5b4dbe6e
3
  size 956835520
runs/May26_23-06-35_b8ce27536189/events.out.tfevents.1716764798.b8ce27536189.35.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eab01c015af2f6eaf649a89e5cc697ef6e8190da64d18295037e4bb6ab9fe9a
3
+ size 10069
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "max_length": 32,
17
+ "model_max_length": 1024,
18
+ "pad_to_multiple_of": null,
19
+ "pad_token": "<|endoftext|>",
20
+ "pad_token_type_id": 0,
21
+ "padding_side": "right",
22
+ "stride": 0,
23
+ "tokenizer_class": "GPT2Tokenizer",
24
+ "truncation_side": "right",
25
+ "truncation_strategy": "longest_first",
26
+ "unk_token": "<|endoftext|>"
27
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:960e17cf259f591f551cebe463ec50fbd40a071e870f4b5f4b6fbad1480043db
3
- size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3b5b1b6a869de4a5079c02ab699a7fc3081751cdae6dfadc6d61afbb57f9e82
3
+ size 5176
vocab.json ADDED
The diff for this file is too large to render. See raw diff