juanquivilla commited on
Commit
413cdbf
1 Parent(s): 0604d84

Training in progress, step 1000

Browse files
config.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
3
+ "architectures": [
4
+ "Phi3ForTokenClassification"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
9
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
10
+ },
11
+ "bos_token_id": 1,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 32000,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3072,
16
+ "id2label": {
17
+ "0": "O",
18
+ "1": "B-BOD",
19
+ "2": "I-BOD",
20
+ "3": "B-BUILDING",
21
+ "4": "I-BUILDING",
22
+ "5": "B-CARDISSUER",
23
+ "6": "I-CARDISSUER",
24
+ "7": "B-CITY",
25
+ "8": "I-CITY",
26
+ "9": "B-COUNTRY",
27
+ "10": "I-COUNTRY",
28
+ "11": "B-DATE",
29
+ "12": "I-DATE",
30
+ "13": "B-DRIVERLICENSE",
31
+ "14": "I-DRIVERLICENSE",
32
+ "15": "B-EMAIL",
33
+ "16": "I-EMAIL",
34
+ "17": "B-GEOCOORD",
35
+ "18": "I-GEOCOORD",
36
+ "19": "B-GIVENNAME1",
37
+ "20": "I-GIVENNAME1",
38
+ "21": "B-GIVENNAME2",
39
+ "22": "I-GIVENNAME2",
40
+ "23": "B-IDCARD",
41
+ "24": "I-IDCARD",
42
+ "25": "B-IP",
43
+ "26": "I-IP",
44
+ "27": "B-LASTNAME1",
45
+ "28": "I-LASTNAME1",
46
+ "29": "B-LASTNAME2",
47
+ "30": "I-LASTNAME2",
48
+ "31": "B-LASTNAME3",
49
+ "32": "I-LASTNAME3",
50
+ "33": "B-PASS",
51
+ "34": "I-PASS",
52
+ "35": "B-PASSPORT",
53
+ "36": "I-PASSPORT",
54
+ "37": "B-POSTCODE",
55
+ "38": "I-POSTCODE",
56
+ "39": "B-SECADDRESS",
57
+ "40": "I-SECADDRESS",
58
+ "41": "B-SEX",
59
+ "42": "I-SEX",
60
+ "43": "B-SOCIALNUMBER",
61
+ "44": "I-SOCIALNUMBER",
62
+ "45": "B-STATE",
63
+ "46": "I-STATE",
64
+ "47": "B-STREET",
65
+ "48": "I-STREET",
66
+ "49": "B-TEL",
67
+ "50": "I-TEL",
68
+ "51": "B-TIME",
69
+ "52": "I-TIME",
70
+ "53": "B-TITLE",
71
+ "54": "I-TITLE",
72
+ "55": "B-USERNAME",
73
+ "56": "I-USERNAME"
74
+ },
75
+ "initializer_range": 0.02,
76
+ "intermediate_size": 8192,
77
+ "label2id": {
78
+ "B-BOD": 1,
79
+ "B-BUILDING": 3,
80
+ "B-CARDISSUER": 5,
81
+ "B-CITY": 7,
82
+ "B-COUNTRY": 9,
83
+ "B-DATE": 11,
84
+ "B-DRIVERLICENSE": 13,
85
+ "B-EMAIL": 15,
86
+ "B-GEOCOORD": 17,
87
+ "B-GIVENNAME1": 19,
88
+ "B-GIVENNAME2": 21,
89
+ "B-IDCARD": 23,
90
+ "B-IP": 25,
91
+ "B-LASTNAME1": 27,
92
+ "B-LASTNAME2": 29,
93
+ "B-LASTNAME3": 31,
94
+ "B-PASS": 33,
95
+ "B-PASSPORT": 35,
96
+ "B-POSTCODE": 37,
97
+ "B-SECADDRESS": 39,
98
+ "B-SEX": 41,
99
+ "B-SOCIALNUMBER": 43,
100
+ "B-STATE": 45,
101
+ "B-STREET": 47,
102
+ "B-TEL": 49,
103
+ "B-TIME": 51,
104
+ "B-TITLE": 53,
105
+ "B-USERNAME": 55,
106
+ "I-BOD": 2,
107
+ "I-BUILDING": 4,
108
+ "I-CARDISSUER": 6,
109
+ "I-CITY": 8,
110
+ "I-COUNTRY": 10,
111
+ "I-DATE": 12,
112
+ "I-DRIVERLICENSE": 14,
113
+ "I-EMAIL": 16,
114
+ "I-GEOCOORD": 18,
115
+ "I-GIVENNAME1": 20,
116
+ "I-GIVENNAME2": 22,
117
+ "I-IDCARD": 24,
118
+ "I-IP": 26,
119
+ "I-LASTNAME1": 28,
120
+ "I-LASTNAME2": 30,
121
+ "I-LASTNAME3": 32,
122
+ "I-PASS": 34,
123
+ "I-PASSPORT": 36,
124
+ "I-POSTCODE": 38,
125
+ "I-SECADDRESS": 40,
126
+ "I-SEX": 42,
127
+ "I-SOCIALNUMBER": 44,
128
+ "I-STATE": 46,
129
+ "I-STREET": 48,
130
+ "I-TEL": 50,
131
+ "I-TIME": 52,
132
+ "I-TITLE": 54,
133
+ "I-USERNAME": 56,
134
+ "O": 0
135
+ },
136
+ "max_position_embeddings": 4096,
137
+ "model_type": "phi3",
138
+ "num_attention_heads": 32,
139
+ "num_hidden_layers": 32,
140
+ "num_key_value_heads": 32,
141
+ "original_max_position_embeddings": 4096,
142
+ "pad_token_id": 32000,
143
+ "resid_pdrop": 0.0,
144
+ "rms_norm_eps": 1e-05,
145
+ "rope_scaling": null,
146
+ "rope_theta": 10000.0,
147
+ "sliding_window": 2047,
148
+ "tie_word_embeddings": false,
149
+ "torch_dtype": "bfloat16",
150
+ "transformers_version": "4.41.1",
151
+ "use_cache": false,
152
+ "vocab_size": 32064
153
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ }
117
+ },
118
+ "bos_token": "<s>",
119
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "legacy": false,
123
+ "model_max_length": 4096,
124
+ "pad_token": "<|endoftext|>",
125
+ "padding_side": "left",
126
+ "sp_model_kwargs": {},
127
+ "tokenizer_class": "LlamaTokenizer",
128
+ "unk_token": "<unk>",
129
+ "use_default_system_prompt": false
130
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0271e90fe712d108391e9604da84d9ead429b9bc63b42a1744e2f9cb076ba173
3
+ size 5176