Sara Price commited on
Commit
1c8d3d6
1 Parent(s): faab996

Training in progress, step 400

Browse files
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</headline>": 32008,
3
+ "</scratchpad>": 32006,
4
+ "<</SYS>>": 32004,
5
+ "<<SYS>>": 32003,
6
+ "<headline>": 32007,
7
+ "<pad>": 32000,
8
+ "<scratchpad>": 32005,
9
+ "[/INST]": 32002,
10
+ "[INST]": 32001
11
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Llama-2-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.40.2",
26
+ "use_cache": true,
27
+ "vocab_size": 32016
28
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[INST]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": true
9
+ },
10
+ {
11
+ "content": "[/INST]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": true
16
+ },
17
+ {
18
+ "content": "<<SYS>>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": true
23
+ },
24
+ {
25
+ "content": "<</SYS>>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": true
30
+ },
31
+ {
32
+ "content": "<scratchpad>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": true
37
+ },
38
+ {
39
+ "content": "</scratchpad>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": true
44
+ },
45
+ {
46
+ "content": "<headline>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": true
51
+ },
52
+ {
53
+ "content": "</headline>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": true
58
+ }
59
+ ],
60
+ "bos_token": {
61
+ "content": "<s>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "eos_token": {
68
+ "content": "</s>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ },
74
+ "pad_token": "<pad>",
75
+ "unk_token": {
76
+ "content": "<unk>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false
81
+ }
82
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<pad>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "[INST]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": true,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "[/INST]",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": true,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<<SYS>>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": true,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<</SYS>>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": true,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<scratchpad>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": true,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "</scratchpad>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": true,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<headline>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": true,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "</headline>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": true,
99
+ "special": true
100
+ }
101
+ },
102
+ "additional_special_tokens": [
103
+ "[INST]",
104
+ "[/INST]",
105
+ "<<SYS>>",
106
+ "<</SYS>>",
107
+ "<scratchpad>",
108
+ "</scratchpad>",
109
+ "<headline>",
110
+ "</headline>"
111
+ ],
112
+ "bos_token": "<s>",
113
+ "clean_up_tokenization_spaces": false,
114
+ "eos_token": "</s>",
115
+ "legacy": false,
116
+ "model_max_length": 1000000000000000019884624838656,
117
+ "pad_to_multiple_of": 8,
118
+ "pad_token": "<pad>",
119
+ "padding_side": "left",
120
+ "sp_model_kwargs": {},
121
+ "tokenizer_class": "LlamaTokenizer",
122
+ "unk_token": "<unk>",
123
+ "use_default_system_prompt": false
124
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a880f8f765143af5aeb78bcf094bd2577da8042cf5c2af6e0602e5da9e4faa
3
+ size 5176