finnstrom3693 commited on
Commit
b90c018
1 Parent(s): 89e40a4

Upload Minisun Trained using model.fit on lss dataset[400],lr 2e-4, 2 epoch,batch size 2,cosine with restart

Browse files
Files changed (7) hide show
  1. config.json +14 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +30 -0
  4. tf_model.h5 +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +30 -0
  7. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 50272,
3
+ "max_position_embeddings": 2048,
4
+ "hidden_size": 768,
5
+ "num_attention_heads": 12,
6
+ "intermediate_size": 3072,
7
+ "num_hidden_layers": 12,
8
+ "dropout_rate": 0.1,
9
+ "weight_decay": 0.01,
10
+ "learning_rate": 0.0002,
11
+ "restart_period": 66,
12
+ "total_steps": 200,
13
+ "warmup_ratio": 0.2
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:924db56aa3ee83d96c9e6ffd38a6c9f615b45c59f16da5741c3c86ff10d08284
3
+ size 1902620720
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "1": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "2": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "</s>",
23
+ "clean_up_tokenization_spaces": true,
24
+ "eos_token": "</s>",
25
+ "errors": "replace",
26
+ "model_max_length": 1000000000000000019884624838656,
27
+ "pad_token": "</s>",
28
+ "tokenizer_class": "GPT2Tokenizer",
29
+ "unk_token": "</s>"
30
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff