smithblack-0 commited on
Commit
f650e15
·
verified ·
1 Parent(s): 3e25d62

Upload folder using huggingface_hub

Browse files
pilot-replication-v3/conlinear_42/checkpoint_030000/metrics.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v3/conlinear_42/checkpoint_030000/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de83363f7deb8812eb9d9a7820ba9aa0681b98d43eded9865bcc7f5e6bc9a1c
3
+ size 126994575
pilot-replication-v3/conlinear_42/checkpoint_030000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8eb7893878b038dd235c0a7ea8fa1ac2b16a5dafc8b518e5d1cb3c88729cd1de
3
+ size 254071534
pilot-replication-v3/conlinear_42/checkpoint_030000/random_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a0ad322689dfe9c551ffa0c6cb1245ebe451497f962ade1d8acf173c623d913
3
+ size 13655
pilot-replication-v3/conlinear_42/checkpoint_030000/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v3/conlinear_42/checkpoint_030000/tokenizer/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
+ }
pilot-replication-v3/conlinear_42/checkpoint_030000/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v3/conlinear_42/checkpoint_030000/tokenizer/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
+ }
pilot-replication-v3/conlinear_42/checkpoint_030000/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v3/conlinear_42/checkpoint_030000/training_state.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "global_batch": 30000,
3
+ "effective_batch": 30000,
4
+ "miniepoch_num": 30
5
+ }