smithblack-0 commited on
Commit
5fbc2eb
·
verified ·
1 Parent(s): 294bee9

Upload folder using huggingface_hub

Browse files
pilot-replication-v3/conlinear_42/checkpoint_024000/metrics.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v3/conlinear_42/checkpoint_024000/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ca5bd608d7b4ad1eb92cdf99d3d320e0c54ab94c9e6382ee8b297d5f88cd9a
3
+ size 126994575
pilot-replication-v3/conlinear_42/checkpoint_024000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3575e840069bd8eb0e66328a485724404160f35bca2d69a189b1189637e9c850
3
+ size 254071534
pilot-replication-v3/conlinear_42/checkpoint_024000/random_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c92ee2341488ddf14e5ff3d0cb91cffc4c9d906317017b46fcce0f31980c88d
3
+ size 13655
pilot-replication-v3/conlinear_42/checkpoint_024000/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v3/conlinear_42/checkpoint_024000/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_024000/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v3/conlinear_42/checkpoint_024000/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_024000/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v3/conlinear_42/checkpoint_024000/training_state.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "global_batch": 24000,
3
+ "effective_batch": 24000,
4
+ "miniepoch_num": 24
5
+ }