aimlresearch2023 commited on
Commit
9ea2036
·
verified ·
1 Parent(s): 32da277

Training in progress, step 100

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<i_am_unknown>": 30523,
3
+ "<i_am_user>": 30522
4
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ElectraForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "embedding_size": 128,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 256,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1024,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "electra",
16
+ "num_attention_heads": 4,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "summary_activation": "gelu",
21
+ "summary_last_dropout": 0.1,
22
+ "summary_type": "first",
23
+ "summary_use_proj": true,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.53.1",
26
+ "type_vocab_size": 2,
27
+ "use_cache": true,
28
+ "vocab_size": 30524
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ea6045534db9bdaabbcbda8241030a5cb83fb69ef9bc233c691f6fc69ad05c3
3
+ size 54222224
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<i_am_user>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<i_am_unknown>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "cls_token": "[CLS]",
19
+ "mask_token": "[MASK]",
20
+ "pad_token": "[PAD]",
21
+ "sep_token": "[SEP]",
22
+ "unk_token": "[UNK]"
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "30522": {
44
+ "content": "<i_am_user>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "30523": {
52
+ "content": "<i_am_unknown>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<i_am_user>",
62
+ "<i_am_unknown>"
63
+ ],
64
+ "clean_up_tokenization_spaces": false,
65
+ "cls_token": "[CLS]",
66
+ "do_lower_case": true,
67
+ "extra_special_tokens": {},
68
+ "mask_token": "[MASK]",
69
+ "model_max_length": 512,
70
+ "pad_token": "[PAD]",
71
+ "sep_token": "[SEP]",
72
+ "strip_accents": null,
73
+ "tokenize_chinese_chars": true,
74
+ "tokenizer_class": "ElectraTokenizer",
75
+ "unk_token": "[UNK]"
76
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec033c894a0ebe47140319dab67b44f93ad64af7fc012af9a150ae3ece586ae
3
+ size 5432
vocab.txt ADDED
The diff for this file is too large to render. See raw diff