smithblack-0 commited on
Commit
09f125e
·
verified ·
1 Parent(s): 57c4546

Upload folder using huggingface_hub

Browse files
pilot-replication-v4/conlinear_42/checkpoint_002000/metrics.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v4/conlinear_42/checkpoint_002000/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:592fe3e1c28fee501e7c72024c032eee3428707938ef70d534218f8a1e193605
3
+ size 178457867
pilot-replication-v4/conlinear_42/checkpoint_002000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5806c002ef54a41a3d938ec771ca71df97bee5c2dab32e8ef2f41cedf9401c44
3
+ size 356998705
pilot-replication-v4/conlinear_42/checkpoint_002000/random_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2afc1ba5089ca85e9bdcb606e8c5a9f3c0711a4d6a67368d4e305b4ccb4e7f4
3
+ size 13655
pilot-replication-v4/conlinear_42/checkpoint_002000/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v4/conlinear_42/checkpoint_002000/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-v4/conlinear_42/checkpoint_002000/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v4/conlinear_42/checkpoint_002000/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-v4/conlinear_42/checkpoint_002000/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v4/conlinear_42/checkpoint_002000/training_state.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "global_batch": 2000,
3
+ "effective_batch": 2000,
4
+ "miniepoch_num": 2
5
+ }