AmelieSchreiber
commited on
Commit
·
64bba81
1
Parent(s):
76e17f7
Upload 11 files
Browse files- adapter_config.json +29 -0
- adapter_model.bin +3 -0
- added_tokens.json +7 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +54 -0
- trainer_state.json +579 -0
- training_args.bin +3 -0
- vocab.txt +33 -0
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "facebook/esm2_t12_35M_UR50D",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 1,
|
12 |
+
"lora_dropout": 0.5,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 2,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"query",
|
20 |
+
"key",
|
21 |
+
"value",
|
22 |
+
"EsmSelfOutput.dense",
|
23 |
+
"EsmIntermediate.dense",
|
24 |
+
"EsmOutput.dense",
|
25 |
+
"EsmContactPredictionHead.regression",
|
26 |
+
"classifier"
|
27 |
+
],
|
28 |
+
"task_type": "TOKEN_CLS"
|
29 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a45b650479e9d4da22cc801c31101e1e8508bc9cc781f113bd47aeb213057d1
|
3 |
+
size 316315
|
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<cls>": 0,
|
3 |
+
"<eos>": 2,
|
4 |
+
"<mask>": 32,
|
5 |
+
"<pad>": 1,
|
6 |
+
"<unk>": 3
|
7 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ece97dd78a3f8a055c6517446f92c836c43ed4c033cd2be90739e4f7dca4e8e
|
3 |
+
size 613061
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7620e37bc2e6da54aa1e68fd5cb88e282fc51b57b496e91af2baf81c3d787e0c
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49f8b7ea3e5935adc8bf935be528bc17d37f526d3d3bb3f52f58162c1e6c6bff
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "<cls>",
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<cls>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "<eos>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"32": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "<cls>",
|
47 |
+
"eos_token": "<eos>",
|
48 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 1024,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"tokenizer_class": "EsmTokenizer",
|
52 |
+
"tokenizer_file": null,
|
53 |
+
"unk_token": "<unk>"
|
54 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,579 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.1542571794425746,
|
3 |
+
"best_model_checkpoint": "esm2_t12_35M_qlora_ptm_sites_2023-10-12_18-42-03/checkpoint-18344",
|
4 |
+
"epoch": 0.9999727438741858,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 18344,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 0.00037004824930228345,
|
14 |
+
"loss": 0.3438,
|
15 |
+
"step": 200
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.02,
|
19 |
+
"learning_rate": 0.00036972270781686296,
|
20 |
+
"loss": 0.1099,
|
21 |
+
"step": 400
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.03,
|
25 |
+
"learning_rate": 0.00036918056301062725,
|
26 |
+
"loss": 0.0758,
|
27 |
+
"step": 600
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.04,
|
31 |
+
"learning_rate": 0.0003684224508650944,
|
32 |
+
"loss": 0.0587,
|
33 |
+
"step": 800
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.05,
|
37 |
+
"learning_rate": 0.00036744926070966046,
|
38 |
+
"loss": 0.05,
|
39 |
+
"step": 1000
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.07,
|
43 |
+
"learning_rate": 0.0003662621341783412,
|
44 |
+
"loss": 0.0433,
|
45 |
+
"step": 1200
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.08,
|
49 |
+
"learning_rate": 0.00036486246387053945,
|
50 |
+
"loss": 0.0399,
|
51 |
+
"step": 1400
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.09,
|
55 |
+
"learning_rate": 0.0003632518917174086,
|
56 |
+
"loss": 0.0373,
|
57 |
+
"step": 1600
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.1,
|
61 |
+
"learning_rate": 0.00036143230705572906,
|
62 |
+
"loss": 0.0345,
|
63 |
+
"step": 1800
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.11,
|
67 |
+
"learning_rate": 0.0003594058444115571,
|
68 |
+
"loss": 0.0361,
|
69 |
+
"step": 2000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.12,
|
73 |
+
"learning_rate": 0.000357174880996246,
|
74 |
+
"loss": 0.0324,
|
75 |
+
"step": 2200
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.13,
|
79 |
+
"learning_rate": 0.000354742033917777,
|
80 |
+
"loss": 0.0294,
|
81 |
+
"step": 2400
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.14,
|
85 |
+
"learning_rate": 0.00035211015711067114,
|
86 |
+
"loss": 0.0307,
|
87 |
+
"step": 2600
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.15,
|
91 |
+
"learning_rate": 0.0003492823379880838,
|
92 |
+
"loss": 0.0286,
|
93 |
+
"step": 2800
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.16,
|
97 |
+
"learning_rate": 0.00034626189382000884,
|
98 |
+
"loss": 0.0258,
|
99 |
+
"step": 3000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.17,
|
103 |
+
"learning_rate": 0.0003430523678418417,
|
104 |
+
"loss": 0.0286,
|
105 |
+
"step": 3200
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.19,
|
109 |
+
"learning_rate": 0.0003396575250978659,
|
110 |
+
"loss": 0.0259,
|
111 |
+
"step": 3400
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.2,
|
115 |
+
"learning_rate": 0.0003360813480245388,
|
116 |
+
"loss": 0.0254,
|
117 |
+
"step": 3600
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.21,
|
121 |
+
"learning_rate": 0.00033232803177875834,
|
122 |
+
"loss": 0.0258,
|
123 |
+
"step": 3800
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.22,
|
127 |
+
"learning_rate": 0.00032840197931659074,
|
128 |
+
"loss": 0.0242,
|
129 |
+
"step": 4000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.23,
|
133 |
+
"learning_rate": 0.00032432867750442764,
|
134 |
+
"loss": 0.0232,
|
135 |
+
"step": 4200
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.24,
|
139 |
+
"learning_rate": 0.0003200936526736335,
|
140 |
+
"loss": 0.0268,
|
141 |
+
"step": 4400
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.25,
|
145 |
+
"learning_rate": 0.0003156793663915513,
|
146 |
+
"loss": 0.0254,
|
147 |
+
"step": 4600
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.26,
|
151 |
+
"learning_rate": 0.0003111118741797566,
|
152 |
+
"loss": 0.0261,
|
153 |
+
"step": 4800
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.27,
|
157 |
+
"learning_rate": 0.0003063965340912947,
|
158 |
+
"loss": 0.0258,
|
159 |
+
"step": 5000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.28,
|
163 |
+
"learning_rate": 0.00030153887761722234,
|
164 |
+
"loss": 0.0266,
|
165 |
+
"step": 5200
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.29,
|
169 |
+
"learning_rate": 0.00029654460319770276,
|
170 |
+
"loss": 0.0228,
|
171 |
+
"step": 5400
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.31,
|
175 |
+
"learning_rate": 0.0002914195695372552,
|
176 |
+
"loss": 0.0222,
|
177 |
+
"step": 5600
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.32,
|
181 |
+
"learning_rate": 0.00028616978873200133,
|
182 |
+
"loss": 0.0217,
|
183 |
+
"step": 5800
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.33,
|
187 |
+
"learning_rate": 0.0002808014192169701,
|
188 |
+
"loss": 0.0218,
|
189 |
+
"step": 6000
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.34,
|
193 |
+
"learning_rate": 0.0002753207585417347,
|
194 |
+
"loss": 0.0218,
|
195 |
+
"step": 6200
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.35,
|
199 |
+
"learning_rate": 0.0002697342359828566,
|
200 |
+
"loss": 0.0201,
|
201 |
+
"step": 6400
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.36,
|
205 |
+
"learning_rate": 0.00026404840500180257,
|
206 |
+
"loss": 0.0237,
|
207 |
+
"step": 6600
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.37,
|
211 |
+
"learning_rate": 0.00025826993555718255,
|
212 |
+
"loss": 0.0209,
|
213 |
+
"step": 6800
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.38,
|
217 |
+
"learning_rate": 0.0002524351301631664,
|
218 |
+
"loss": 0.0227,
|
219 |
+
"step": 7000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.39,
|
223 |
+
"learning_rate": 0.0002464921980395868,
|
224 |
+
"loss": 0.0209,
|
225 |
+
"step": 7200
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.4,
|
229 |
+
"learning_rate": 0.00024047722236181782,
|
230 |
+
"loss": 0.0177,
|
231 |
+
"step": 7400
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.41,
|
235 |
+
"learning_rate": 0.0002343972592029196,
|
236 |
+
"loss": 0.0227,
|
237 |
+
"step": 7600
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.43,
|
241 |
+
"learning_rate": 0.00022825944087174108,
|
242 |
+
"loss": 0.019,
|
243 |
+
"step": 7800
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.44,
|
247 |
+
"learning_rate": 0.00022207096754612101,
|
248 |
+
"loss": 0.0186,
|
249 |
+
"step": 8000
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.45,
|
253 |
+
"learning_rate": 0.00021583909882647275,
|
254 |
+
"loss": 0.0202,
|
255 |
+
"step": 8200
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.46,
|
259 |
+
"learning_rate": 0.0002095711452196616,
|
260 |
+
"loss": 0.0205,
|
261 |
+
"step": 8400
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.47,
|
265 |
+
"learning_rate": 0.00020327445956316495,
|
266 |
+
"loss": 0.0193,
|
267 |
+
"step": 8600
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.48,
|
271 |
+
"learning_rate": 0.00019695642839957393,
|
272 |
+
"loss": 0.0199,
|
273 |
+
"step": 8800
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.49,
|
277 |
+
"learning_rate": 0.0001906561455150737,
|
278 |
+
"loss": 0.0224,
|
279 |
+
"step": 9000
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.5,
|
283 |
+
"learning_rate": 0.00018431768846772684,
|
284 |
+
"loss": 0.0199,
|
285 |
+
"step": 9200
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.51,
|
289 |
+
"learning_rate": 0.00017798012380234812,
|
290 |
+
"loss": 0.0196,
|
291 |
+
"step": 9400
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.52,
|
295 |
+
"learning_rate": 0.00017165088601604907,
|
296 |
+
"loss": 0.0219,
|
297 |
+
"step": 9600
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.53,
|
301 |
+
"learning_rate": 0.00016533739983781094,
|
302 |
+
"loss": 0.0211,
|
303 |
+
"step": 9800
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.55,
|
307 |
+
"learning_rate": 0.000159047071518652,
|
308 |
+
"loss": 0.0177,
|
309 |
+
"step": 10000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.56,
|
313 |
+
"learning_rate": 0.00015278728014347137,
|
314 |
+
"loss": 0.0182,
|
315 |
+
"step": 10200
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.57,
|
319 |
+
"learning_rate": 0.00014656536897476115,
|
320 |
+
"loss": 0.021,
|
321 |
+
"step": 10400
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.58,
|
325 |
+
"learning_rate": 0.00014038863683834082,
|
326 |
+
"loss": 0.018,
|
327 |
+
"step": 10600
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.59,
|
331 |
+
"learning_rate": 0.00013426432956121996,
|
332 |
+
"loss": 0.0183,
|
333 |
+
"step": 10800
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.6,
|
337 |
+
"learning_rate": 0.00012819963147163302,
|
338 |
+
"loss": 0.0196,
|
339 |
+
"step": 11000
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.61,
|
343 |
+
"learning_rate": 0.00012220165697121683,
|
344 |
+
"loss": 0.0167,
|
345 |
+
"step": 11200
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.62,
|
349 |
+
"learning_rate": 0.00011627744218921885,
|
350 |
+
"loss": 0.0169,
|
351 |
+
"step": 11400
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.63,
|
355 |
+
"learning_rate": 0.00011043393672852448,
|
356 |
+
"loss": 0.0178,
|
357 |
+
"step": 11600
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.64,
|
361 |
+
"learning_rate": 0.00010467799551318781,
|
362 |
+
"loss": 0.0188,
|
363 |
+
"step": 11800
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.65,
|
367 |
+
"learning_rate": 9.901637074702851e-05,
|
368 |
+
"loss": 0.0195,
|
369 |
+
"step": 12000
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.67,
|
373 |
+
"learning_rate": 9.345570399272756e-05,
|
374 |
+
"loss": 0.0214,
|
375 |
+
"step": 12200
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.68,
|
379 |
+
"learning_rate": 8.80025183807155e-05,
|
380 |
+
"loss": 0.0177,
|
381 |
+
"step": 12400
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.69,
|
385 |
+
"learning_rate": 8.26632109569906e-05,
|
386 |
+
"loss": 0.0189,
|
387 |
+
"step": 12600
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.7,
|
391 |
+
"learning_rate": 7.744404517884536e-05,
|
392 |
+
"loss": 0.0197,
|
393 |
+
"step": 12800
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.71,
|
397 |
+
"learning_rate": 7.235114356730338e-05,
|
398 |
+
"loss": 0.016,
|
399 |
+
"step": 13000
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.72,
|
403 |
+
"learning_rate": 6.739048052488678e-05,
|
404 |
+
"loss": 0.0186,
|
405 |
+
"step": 13200
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.73,
|
409 |
+
"learning_rate": 6.256787532713881e-05,
|
410 |
+
"loss": 0.0183,
|
411 |
+
"step": 13400
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.74,
|
415 |
+
"learning_rate": 5.7888985296123274e-05,
|
416 |
+
"loss": 0.0171,
|
417 |
+
"step": 13600
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.75,
|
421 |
+
"learning_rate": 5.3359299163909725e-05,
|
422 |
+
"loss": 0.0174,
|
423 |
+
"step": 13800
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.76,
|
427 |
+
"learning_rate": 4.898413063382821e-05,
|
428 |
+
"loss": 0.0172,
|
429 |
+
"step": 14000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.77,
|
433 |
+
"learning_rate": 4.476861214704764e-05,
|
434 |
+
"loss": 0.0181,
|
435 |
+
"step": 14200
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.78,
|
439 |
+
"learning_rate": 4.071768886179024e-05,
|
440 |
+
"loss": 0.0162,
|
441 |
+
"step": 14400
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.8,
|
445 |
+
"learning_rate": 3.683611285224441e-05,
|
446 |
+
"loss": 0.0173,
|
447 |
+
"step": 14600
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.81,
|
451 |
+
"learning_rate": 3.312843753398155e-05,
|
452 |
+
"loss": 0.0182,
|
453 |
+
"step": 14800
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.82,
|
457 |
+
"learning_rate": 2.9616209114343275e-05,
|
458 |
+
"loss": 0.0184,
|
459 |
+
"step": 15000
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.83,
|
463 |
+
"learning_rate": 2.6268252423346314e-05,
|
464 |
+
"loss": 0.0173,
|
465 |
+
"step": 15200
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.84,
|
469 |
+
"learning_rate": 2.310659341395623e-05,
|
470 |
+
"loss": 0.0193,
|
471 |
+
"step": 15400
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.85,
|
475 |
+
"learning_rate": 2.0134940978470748e-05,
|
476 |
+
"loss": 0.0156,
|
477 |
+
"step": 15600
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.86,
|
481 |
+
"learning_rate": 1.737018511568027e-05,
|
482 |
+
"loss": 0.0193,
|
483 |
+
"step": 15800
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.87,
|
487 |
+
"learning_rate": 1.4787785356205422e-05,
|
488 |
+
"loss": 0.0171,
|
489 |
+
"step": 16000
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.88,
|
493 |
+
"learning_rate": 1.2405150833109309e-05,
|
494 |
+
"loss": 0.0184,
|
495 |
+
"step": 16200
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.89,
|
499 |
+
"learning_rate": 1.0225076577356552e-05,
|
500 |
+
"loss": 0.0171,
|
501 |
+
"step": 16400
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.9,
|
505 |
+
"learning_rate": 8.25011999965819e-06,
|
506 |
+
"loss": 0.0181,
|
507 |
+
"step": 16600
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.92,
|
511 |
+
"learning_rate": 6.482597890413681e-06,
|
512 |
+
"loss": 0.0162,
|
513 |
+
"step": 16800
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.93,
|
517 |
+
"learning_rate": 4.924583701920537e-06,
|
518 |
+
"loss": 0.0175,
|
519 |
+
"step": 17000
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.94,
|
523 |
+
"learning_rate": 3.5779051160400913e-06,
|
524 |
+
"loss": 0.017,
|
525 |
+
"step": 17200
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.95,
|
529 |
+
"learning_rate": 2.4441419001728858e-06,
|
530 |
+
"loss": 0.0196,
|
531 |
+
"step": 17400
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.96,
|
535 |
+
"learning_rate": 1.524624054058352e-06,
|
536 |
+
"loss": 0.0184,
|
537 |
+
"step": 17600
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.97,
|
541 |
+
"learning_rate": 8.204302495731164e-07,
|
542 |
+
"loss": 0.0176,
|
543 |
+
"step": 17800
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.98,
|
547 |
+
"learning_rate": 3.3238656535812453e-07,
|
548 |
+
"loss": 0.018,
|
549 |
+
"step": 18000
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.99,
|
553 |
+
"learning_rate": 6.106551775873308e-08,
|
554 |
+
"loss": 0.0154,
|
555 |
+
"step": 18200
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 1.0,
|
559 |
+
"eval_accuracy": 0.9762591331328516,
|
560 |
+
"eval_auc": 0.8833701456278934,
|
561 |
+
"eval_f1": 0.1542571794425746,
|
562 |
+
"eval_loss": 0.28556737303733826,
|
563 |
+
"eval_mcc": 0.25511446421928063,
|
564 |
+
"eval_precision": 0.08547382057474782,
|
565 |
+
"eval_recall": 0.7899691877651231,
|
566 |
+
"eval_runtime": 10582.0535,
|
567 |
+
"eval_samples_per_second": 42.891,
|
568 |
+
"eval_steps_per_second": 0.894,
|
569 |
+
"step": 18344
|
570 |
+
}
|
571 |
+
],
|
572 |
+
"logging_steps": 200,
|
573 |
+
"max_steps": 18344,
|
574 |
+
"num_train_epochs": 1,
|
575 |
+
"save_steps": 500,
|
576 |
+
"total_flos": 3.5283848306530406e+17,
|
577 |
+
"trial_name": null,
|
578 |
+
"trial_params": null
|
579 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93307a60032c8f7e795cecb4fb452cb73258770b6df20af8bae5ea2e6ecd2adb
|
3 |
+
size 4155
|
vocab.txt
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
<cls>
|
2 |
+
<pad>
|
3 |
+
<eos>
|
4 |
+
<unk>
|
5 |
+
L
|
6 |
+
A
|
7 |
+
G
|
8 |
+
V
|
9 |
+
S
|
10 |
+
E
|
11 |
+
R
|
12 |
+
T
|
13 |
+
I
|
14 |
+
D
|
15 |
+
P
|
16 |
+
K
|
17 |
+
Q
|
18 |
+
N
|
19 |
+
F
|
20 |
+
Y
|
21 |
+
M
|
22 |
+
H
|
23 |
+
W
|
24 |
+
C
|
25 |
+
X
|
26 |
+
B
|
27 |
+
U
|
28 |
+
Z
|
29 |
+
O
|
30 |
+
.
|
31 |
+
-
|
32 |
+
<null_1>
|
33 |
+
<mask>
|