smithblack-0 commited on
Commit
6c554fc
·
verified ·
1 Parent(s): d7d8781

Upload folder using huggingface_hub

Browse files
pilot-replication-v10/control_42/checkpoint_002000/metrics.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v10/control_42/checkpoint_002000/model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7841742b9735e137c880a960165f7ba5c26b9f820eb761ec768d99c9555e30ee
3
+ size 127230243
pilot-replication-v10/control_42/checkpoint_002000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c2186a7edcd98bd5c5f17d97a3dce12cbb18a82d7c4a189b79d707210df55a
3
+ size 254511499
pilot-replication-v10/control_42/checkpoint_002000/random_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a2c250698eb78ddfabe105a40faa57d2d1844d434d5f8f0a387119800d8be51
3
+ size 13655
pilot-replication-v10/control_42/checkpoint_002000/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v10/control_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-v10/control_42/checkpoint_002000/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v10/control_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-v10/control_42/checkpoint_002000/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pilot-replication-v10/control_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
+ }