Training in progress, epoch 0
Browse files- .gitignore +1 -0
- config.json +32 -0
- last-checkpoint/config.json +32 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scaler.pt +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +1 -0
- last-checkpoint/tokenizer.json +180 -0
- last-checkpoint/tokenizer_config.json +1 -0
- last-checkpoint/trainer_state.json +31 -0
- last-checkpoint/training_args.bin +3 -0
- last-checkpoint/vocab.txt +30 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +180 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +30 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "thundaa/thermo-evotuning-prot_bert",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 4096,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 40000,
|
21 |
+
"model_type": "bert",
|
22 |
+
"num_attention_heads": 16,
|
23 |
+
"num_hidden_layers": 30,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"problem_type": "regression",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.18.0",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 30
|
32 |
+
}
|
last-checkpoint/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "thundaa/thermo-evotuning-prot_bert",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.0,
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 4096,
|
16 |
+
"label2id": {
|
17 |
+
"LABEL_0": 0
|
18 |
+
},
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
+
"max_position_embeddings": 40000,
|
21 |
+
"model_type": "bert",
|
22 |
+
"num_attention_heads": 16,
|
23 |
+
"num_hidden_layers": 30,
|
24 |
+
"pad_token_id": 0,
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
+
"problem_type": "regression",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.18.0",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 30
|
32 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e4c18050de9245ab251500af9a032dd99dffeed30532317e7870e17b112bd3a
|
3 |
+
size 3359741661
|
last-checkpoint/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0915f32c5b132d4ed88bf3849775f777ef26950e5b71615db8a3138ce641661a
|
3 |
+
size 1680212909
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ad6daa8b9e8dabb625aba226dd6a1abad2aa9eb21f2fb53f6b21da32524d629
|
3 |
+
size 15523
|
last-checkpoint/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93170045094c5d8c504218429a224baf8740889f2d5b8cd02987d71733739c99
|
3 |
+
size 559
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acea7af7bea01d618439e5850c88ab96ec1bbdfea3d1d90765014a6087ec7e46
|
3 |
+
size 623
|
last-checkpoint/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
last-checkpoint/tokenizer.json
ADDED
@@ -0,0 +1,180 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "[PAD]",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "[UNK]",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "[CLS]",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "[SEP]",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "[MASK]",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"normalizer": {
|
53 |
+
"type": "BertNormalizer",
|
54 |
+
"clean_text": true,
|
55 |
+
"handle_chinese_chars": true,
|
56 |
+
"strip_accents": null,
|
57 |
+
"lowercase": false
|
58 |
+
},
|
59 |
+
"pre_tokenizer": {
|
60 |
+
"type": "BertPreTokenizer"
|
61 |
+
},
|
62 |
+
"post_processor": {
|
63 |
+
"type": "TemplateProcessing",
|
64 |
+
"single": [
|
65 |
+
{
|
66 |
+
"SpecialToken": {
|
67 |
+
"id": "[CLS]",
|
68 |
+
"type_id": 0
|
69 |
+
}
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"Sequence": {
|
73 |
+
"id": "A",
|
74 |
+
"type_id": 0
|
75 |
+
}
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"SpecialToken": {
|
79 |
+
"id": "[SEP]",
|
80 |
+
"type_id": 0
|
81 |
+
}
|
82 |
+
}
|
83 |
+
],
|
84 |
+
"pair": [
|
85 |
+
{
|
86 |
+
"SpecialToken": {
|
87 |
+
"id": "[CLS]",
|
88 |
+
"type_id": 0
|
89 |
+
}
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"Sequence": {
|
93 |
+
"id": "A",
|
94 |
+
"type_id": 0
|
95 |
+
}
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"SpecialToken": {
|
99 |
+
"id": "[SEP]",
|
100 |
+
"type_id": 0
|
101 |
+
}
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"Sequence": {
|
105 |
+
"id": "B",
|
106 |
+
"type_id": 1
|
107 |
+
}
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"SpecialToken": {
|
111 |
+
"id": "[SEP]",
|
112 |
+
"type_id": 1
|
113 |
+
}
|
114 |
+
}
|
115 |
+
],
|
116 |
+
"special_tokens": {
|
117 |
+
"[CLS]": {
|
118 |
+
"id": "[CLS]",
|
119 |
+
"ids": [
|
120 |
+
2
|
121 |
+
],
|
122 |
+
"tokens": [
|
123 |
+
"[CLS]"
|
124 |
+
]
|
125 |
+
},
|
126 |
+
"[SEP]": {
|
127 |
+
"id": "[SEP]",
|
128 |
+
"ids": [
|
129 |
+
3
|
130 |
+
],
|
131 |
+
"tokens": [
|
132 |
+
"[SEP]"
|
133 |
+
]
|
134 |
+
}
|
135 |
+
}
|
136 |
+
},
|
137 |
+
"decoder": {
|
138 |
+
"type": "WordPiece",
|
139 |
+
"prefix": "##",
|
140 |
+
"cleanup": true
|
141 |
+
},
|
142 |
+
"model": {
|
143 |
+
"type": "WordPiece",
|
144 |
+
"unk_token": "[UNK]",
|
145 |
+
"continuing_subword_prefix": "##",
|
146 |
+
"max_input_chars_per_word": 100,
|
147 |
+
"vocab": {
|
148 |
+
"[PAD]": 0,
|
149 |
+
"[UNK]": 1,
|
150 |
+
"[CLS]": 2,
|
151 |
+
"[SEP]": 3,
|
152 |
+
"[MASK]": 4,
|
153 |
+
"L": 5,
|
154 |
+
"A": 6,
|
155 |
+
"G": 7,
|
156 |
+
"V": 8,
|
157 |
+
"E": 9,
|
158 |
+
"S": 10,
|
159 |
+
"I": 11,
|
160 |
+
"K": 12,
|
161 |
+
"R": 13,
|
162 |
+
"D": 14,
|
163 |
+
"T": 15,
|
164 |
+
"P": 16,
|
165 |
+
"N": 17,
|
166 |
+
"Q": 18,
|
167 |
+
"F": 19,
|
168 |
+
"Y": 20,
|
169 |
+
"M": 21,
|
170 |
+
"H": 22,
|
171 |
+
"C": 23,
|
172 |
+
"W": 24,
|
173 |
+
"X": 25,
|
174 |
+
"U": 26,
|
175 |
+
"B": 27,
|
176 |
+
"Z": 28,
|
177 |
+
"O": 29
|
178 |
+
}
|
179 |
+
}
|
180 |
+
}
|
last-checkpoint/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "thundaa/thermo-evotuning-prot_bert", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3051428198814392,
|
3 |
+
"best_model_checkpoint": "thermo-predictor-thermo-evotuning-prot_bert/checkpoint-2",
|
4 |
+
"epoch": 0.6772486772486772,
|
5 |
+
"global_step": 2,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.68,
|
12 |
+
"learning_rate": 1.9600000000000002e-05,
|
13 |
+
"loss": 0.4721,
|
14 |
+
"step": 2
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.68,
|
18 |
+
"eval_loss": 0.3051428198814392,
|
19 |
+
"eval_runtime": 2.9691,
|
20 |
+
"eval_samples_per_second": 1805.937,
|
21 |
+
"eval_spearmanr": 0.3140976759909239,
|
22 |
+
"eval_steps_per_second": 7.073,
|
23 |
+
"step": 2
|
24 |
+
}
|
25 |
+
],
|
26 |
+
"max_steps": 100,
|
27 |
+
"num_train_epochs": 50,
|
28 |
+
"total_flos": 5704790080403232.0,
|
29 |
+
"trial_name": null,
|
30 |
+
"trial_params": null
|
31 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:722c7efe43432dfdfccca10d400f5a7d8162919aa208468573386cce2f9e0496
|
3 |
+
size 3247
|
last-checkpoint/vocab.txt
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[PAD]
|
2 |
+
[UNK]
|
3 |
+
[CLS]
|
4 |
+
[SEP]
|
5 |
+
[MASK]
|
6 |
+
L
|
7 |
+
A
|
8 |
+
G
|
9 |
+
V
|
10 |
+
E
|
11 |
+
S
|
12 |
+
I
|
13 |
+
K
|
14 |
+
R
|
15 |
+
D
|
16 |
+
T
|
17 |
+
P
|
18 |
+
N
|
19 |
+
Q
|
20 |
+
F
|
21 |
+
Y
|
22 |
+
M
|
23 |
+
H
|
24 |
+
C
|
25 |
+
W
|
26 |
+
X
|
27 |
+
U
|
28 |
+
B
|
29 |
+
Z
|
30 |
+
O
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0915f32c5b132d4ed88bf3849775f777ef26950e5b71615db8a3138ce641661a
|
3 |
+
size 1680212909
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
@@ -0,0 +1,180 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "[PAD]",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 1,
|
17 |
+
"content": "[UNK]",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "[CLS]",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 3,
|
35 |
+
"content": "[SEP]",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 4,
|
44 |
+
"content": "[MASK]",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
}
|
51 |
+
],
|
52 |
+
"normalizer": {
|
53 |
+
"type": "BertNormalizer",
|
54 |
+
"clean_text": true,
|
55 |
+
"handle_chinese_chars": true,
|
56 |
+
"strip_accents": null,
|
57 |
+
"lowercase": false
|
58 |
+
},
|
59 |
+
"pre_tokenizer": {
|
60 |
+
"type": "BertPreTokenizer"
|
61 |
+
},
|
62 |
+
"post_processor": {
|
63 |
+
"type": "TemplateProcessing",
|
64 |
+
"single": [
|
65 |
+
{
|
66 |
+
"SpecialToken": {
|
67 |
+
"id": "[CLS]",
|
68 |
+
"type_id": 0
|
69 |
+
}
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"Sequence": {
|
73 |
+
"id": "A",
|
74 |
+
"type_id": 0
|
75 |
+
}
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"SpecialToken": {
|
79 |
+
"id": "[SEP]",
|
80 |
+
"type_id": 0
|
81 |
+
}
|
82 |
+
}
|
83 |
+
],
|
84 |
+
"pair": [
|
85 |
+
{
|
86 |
+
"SpecialToken": {
|
87 |
+
"id": "[CLS]",
|
88 |
+
"type_id": 0
|
89 |
+
}
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"Sequence": {
|
93 |
+
"id": "A",
|
94 |
+
"type_id": 0
|
95 |
+
}
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"SpecialToken": {
|
99 |
+
"id": "[SEP]",
|
100 |
+
"type_id": 0
|
101 |
+
}
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"Sequence": {
|
105 |
+
"id": "B",
|
106 |
+
"type_id": 1
|
107 |
+
}
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"SpecialToken": {
|
111 |
+
"id": "[SEP]",
|
112 |
+
"type_id": 1
|
113 |
+
}
|
114 |
+
}
|
115 |
+
],
|
116 |
+
"special_tokens": {
|
117 |
+
"[CLS]": {
|
118 |
+
"id": "[CLS]",
|
119 |
+
"ids": [
|
120 |
+
2
|
121 |
+
],
|
122 |
+
"tokens": [
|
123 |
+
"[CLS]"
|
124 |
+
]
|
125 |
+
},
|
126 |
+
"[SEP]": {
|
127 |
+
"id": "[SEP]",
|
128 |
+
"ids": [
|
129 |
+
3
|
130 |
+
],
|
131 |
+
"tokens": [
|
132 |
+
"[SEP]"
|
133 |
+
]
|
134 |
+
}
|
135 |
+
}
|
136 |
+
},
|
137 |
+
"decoder": {
|
138 |
+
"type": "WordPiece",
|
139 |
+
"prefix": "##",
|
140 |
+
"cleanup": true
|
141 |
+
},
|
142 |
+
"model": {
|
143 |
+
"type": "WordPiece",
|
144 |
+
"unk_token": "[UNK]",
|
145 |
+
"continuing_subword_prefix": "##",
|
146 |
+
"max_input_chars_per_word": 100,
|
147 |
+
"vocab": {
|
148 |
+
"[PAD]": 0,
|
149 |
+
"[UNK]": 1,
|
150 |
+
"[CLS]": 2,
|
151 |
+
"[SEP]": 3,
|
152 |
+
"[MASK]": 4,
|
153 |
+
"L": 5,
|
154 |
+
"A": 6,
|
155 |
+
"G": 7,
|
156 |
+
"V": 8,
|
157 |
+
"E": 9,
|
158 |
+
"S": 10,
|
159 |
+
"I": 11,
|
160 |
+
"K": 12,
|
161 |
+
"R": 13,
|
162 |
+
"D": 14,
|
163 |
+
"T": 15,
|
164 |
+
"P": 16,
|
165 |
+
"N": 17,
|
166 |
+
"Q": 18,
|
167 |
+
"F": 19,
|
168 |
+
"Y": 20,
|
169 |
+
"M": 21,
|
170 |
+
"H": 22,
|
171 |
+
"C": 23,
|
172 |
+
"W": 24,
|
173 |
+
"X": 25,
|
174 |
+
"U": 26,
|
175 |
+
"B": 27,
|
176 |
+
"Z": 28,
|
177 |
+
"O": 29
|
178 |
+
}
|
179 |
+
}
|
180 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "thundaa/thermo-evotuning-prot_bert", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:722c7efe43432dfdfccca10d400f5a7d8162919aa208468573386cce2f9e0496
|
3 |
+
size 3247
|
vocab.txt
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[PAD]
|
2 |
+
[UNK]
|
3 |
+
[CLS]
|
4 |
+
[SEP]
|
5 |
+
[MASK]
|
6 |
+
L
|
7 |
+
A
|
8 |
+
G
|
9 |
+
V
|
10 |
+
E
|
11 |
+
S
|
12 |
+
I
|
13 |
+
K
|
14 |
+
R
|
15 |
+
D
|
16 |
+
T
|
17 |
+
P
|
18 |
+
N
|
19 |
+
Q
|
20 |
+
F
|
21 |
+
Y
|
22 |
+
M
|
23 |
+
H
|
24 |
+
C
|
25 |
+
W
|
26 |
+
X
|
27 |
+
U
|
28 |
+
B
|
29 |
+
Z
|
30 |
+
O
|