Hugging Face's logo

Christian2903
/
gpt-neo

Text Classification
Transformers
TensorBoard
gpt_neo
Model card Files
xet
 Metrics Community
Christian2903 commited on
Commit
db85157
·
1 Parent(s): 54d2c19

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +84 -0
  2. merges.txt +0 -0
  3. runs/Nov15_14-52-14_0b9dac1fca90/events.out.tfevents.1700059935.0b9dac1fca90.6447.0 +3 -0
  4. special_tokens_map.json +6 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +20 -0
  7. training_args.bin +3 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "KennethTM/gpt-neo-1.3B-danish",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
+ ],
43
+ "bos_token_id": 50256,
44
+ "classifier_dropout": 0.1,
45
+ "embed_dropout": 0,
46
+ "eos_token_id": 50256,
47
+ "gradient_checkpointing": false,
48
+ "hidden_size": 2048,
49
+ "id2label": {
50
+ "0": "NEGATIVE",
51
+ "1": "POSITIVE"
52
+ },
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": null,
55
+ "label2id": {
56
+ "NEGATIVE": 0,
57
+ "POSITIVE": 1
58
+ },
59
+ "layer_norm_epsilon": 1e-05,
60
+ "max_position_embeddings": 2048,
61
+ "model_type": "gpt_neo",
62
+ "num_heads": 16,
63
+ "num_layers": 24,
64
+ "problem_type": "single_label_classification",
65
+ "resid_dropout": 0,
66
+ "summary_activation": null,
67
+ "summary_first_dropout": 0.1,
68
+ "summary_proj_to_labels": true,
69
+ "summary_type": "cls_index",
70
+ "summary_use_proj": true,
71
+ "task_specific_params": {
72
+ "text-generation": {
73
+ "do_sample": true,
74
+ "max_length": 50,
75
+ "temperature": 0.9
76
+ }
77
+ },
78
+ "tokenizer_class": "GPT2Tokenizer",
79
+ "torch_dtype": "float32",
80
+ "transformers_version": "4.35.1",
81
+ "use_cache": true,
82
+ "vocab_size": 50257,
83
+ "window_size": 256
84
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Nov15_14-52-14_0b9dac1fca90/events.out.tfevents.1700059935.0b9dac1fca90.6447.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd64d61230c1b2f2a793195472bd7015543caf273eab922a3084e387220f0701
3
+ size 5436
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b91e78ff7a63733254a4ae8a8b962561e0ae734f90ace402b9618c0be31b521
3
+ size 4536
vocab.json ADDED
The diff for this file is too large to render. See raw diff