AmelieSchreiber commited on
Commit
26c23d7
1 Parent(s): a5bf52c

Upload 10 files

Browse files
config (3).json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/esm2_t6_8M_UR50D",
3
+ "architectures": [
4
+ "EsmForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "classifier_dropout": null,
8
+ "emb_layer_norm_before": false,
9
+ "esmfold_config": null,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 320,
13
+ "id2label": {
14
+ "0": "No binding site",
15
+ "1": "Binding site"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 1280,
19
+ "is_folding_model": false,
20
+ "label2id": {
21
+ "Binding site": 1,
22
+ "No binding site": 0
23
+ },
24
+ "layer_norm_eps": 1e-05,
25
+ "mask_token_id": 32,
26
+ "max_position_embeddings": 1026,
27
+ "model_type": "esm",
28
+ "num_attention_heads": 20,
29
+ "num_hidden_layers": 6,
30
+ "pad_token_id": 1,
31
+ "position_embedding_type": "rotary",
32
+ "token_dropout": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.32.1",
35
+ "use_cache": true,
36
+ "vocab_list": null,
37
+ "vocab_size": 33
38
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b87c1b79565801752e44cc7aed098e04f1260524419c5b891badba0ddd798c25
3
+ size 59361093
pytorch_model (3).bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:533fc0f41a4509d035112616b31db134f51387ff2b1895fed14ee17058a3305f
3
+ size 30989061
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dd3a816ab8628e6038ecf426e93a907752049203fbc39b63fcde557182a866f
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:068a9051a45626c38f7190ab6a85a94edf90ab8712919a65a71afff348cc9384
3
+ size 627
special_tokens_map (3).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 (3).json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "model_max_length": 1024,
4
+ "tokenizer_class": "EsmTokenizer"
5
+ }
trainer_state.json ADDED
@@ -0,0 +1,217 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6282620163217179,
3
+ "best_model_checkpoint": "esm2_t6_8M-binding-site-classification_2023-09-05_16-25-08/checkpoint-5598",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5598,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.11,
13
+ "learning_rate": 0.0005695234606678405,
14
+ "loss": 0.4679,
15
+ "step": 200
16
+ },
17
+ {
18
+ "epoch": 0.21,
19
+ "learning_rate": 0.0005676006526247637,
20
+ "loss": 0.3559,
21
+ "step": 400
22
+ },
23
+ {
24
+ "epoch": 0.32,
25
+ "learning_rate": 0.0005643970338296423,
26
+ "loss": 0.3089,
27
+ "step": 600
28
+ },
29
+ {
30
+ "epoch": 0.43,
31
+ "learning_rate": 0.0005599271278444283,
32
+ "loss": 0.2692,
33
+ "step": 800
34
+ },
35
+ {
36
+ "epoch": 0.54,
37
+ "learning_rate": 0.0005542111989267148,
38
+ "loss": 0.232,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 0.64,
43
+ "learning_rate": 0.0005472751601620024,
44
+ "loss": 0.2046,
45
+ "step": 1200
46
+ },
47
+ {
48
+ "epoch": 0.75,
49
+ "learning_rate": 0.00053915045598708,
50
+ "loss": 0.2237,
51
+ "step": 1400
52
+ },
53
+ {
54
+ "epoch": 0.86,
55
+ "learning_rate": 0.0005298739196371016,
56
+ "loss": 0.2119,
57
+ "step": 1600
58
+ },
59
+ {
60
+ "epoch": 0.96,
61
+ "learning_rate": 0.0005194876061626189,
62
+ "loss": 0.1905,
63
+ "step": 1800
64
+ },
65
+ {
66
+ "epoch": 1.0,
67
+ "eval_auc": 0.9261141394147127,
68
+ "eval_f1": 0.4530748302654477,
69
+ "eval_loss": 0.2022695094347,
70
+ "eval_precision": 0.30564833493171073,
71
+ "eval_recall": 0.8752367424242424,
72
+ "eval_runtime": 95.9675,
73
+ "eval_samples_per_second": 27.447,
74
+ "eval_steps_per_second": 3.439,
75
+ "step": 1866
76
+ },
77
+ {
78
+ "epoch": 1.07,
79
+ "learning_rate": 0.0005080386017735853,
80
+ "loss": 0.173,
81
+ "step": 2000
82
+ },
83
+ {
84
+ "epoch": 1.18,
85
+ "learning_rate": 0.0004955788103746674,
86
+ "loss": 0.1316,
87
+ "step": 2200
88
+ },
89
+ {
90
+ "epoch": 1.29,
91
+ "learning_rate": 0.00048223406367877986,
92
+ "loss": 0.1423,
93
+ "step": 2400
94
+ },
95
+ {
96
+ "epoch": 1.39,
97
+ "learning_rate": 0.00046793079280001864,
98
+ "loss": 0.1411,
99
+ "step": 2600
100
+ },
101
+ {
102
+ "epoch": 1.5,
103
+ "learning_rate": 0.00045279856311429995,
104
+ "loss": 0.1111,
105
+ "step": 2800
106
+ },
107
+ {
108
+ "epoch": 1.61,
109
+ "learning_rate": 0.00043690597637775135,
110
+ "loss": 0.1513,
111
+ "step": 3000
112
+ },
113
+ {
114
+ "epoch": 1.71,
115
+ "learning_rate": 0.00042032508141478175,
116
+ "loss": 0.1106,
117
+ "step": 3200
118
+ },
119
+ {
120
+ "epoch": 1.82,
121
+ "learning_rate": 0.0004031310474857221,
122
+ "loss": 0.1073,
123
+ "step": 3400
124
+ },
125
+ {
126
+ "epoch": 1.93,
127
+ "learning_rate": 0.0003854018235080123,
128
+ "loss": 0.1079,
129
+ "step": 3600
130
+ },
131
+ {
132
+ "epoch": 2.0,
133
+ "eval_auc": 0.9625828119645666,
134
+ "eval_f1": 0.39631155965817316,
135
+ "eval_loss": 0.10649576038122177,
136
+ "eval_precision": 0.24979947431420216,
137
+ "eval_recall": 0.9584753787878788,
138
+ "eval_runtime": 96.1903,
139
+ "eval_samples_per_second": 27.383,
140
+ "eval_steps_per_second": 3.431,
141
+ "step": 3732
142
+ },
143
+ {
144
+ "epoch": 2.04,
145
+ "learning_rate": 0.0003672177846758513,
146
+ "loss": 0.1161,
147
+ "step": 3800
148
+ },
149
+ {
150
+ "epoch": 2.14,
151
+ "learning_rate": 0.00034866136808035477,
152
+ "loss": 0.0703,
153
+ "step": 4000
154
+ },
155
+ {
156
+ "epoch": 2.25,
157
+ "learning_rate": 0.00032981669898213067,
158
+ "loss": 0.087,
159
+ "step": 4200
160
+ },
161
+ {
162
+ "epoch": 2.36,
163
+ "learning_rate": 0.000310769209430562,
164
+ "loss": 0.0662,
165
+ "step": 4400
166
+ },
167
+ {
168
+ "epoch": 2.47,
169
+ "learning_rate": 0.0002916052509587806,
170
+ "loss": 0.0602,
171
+ "step": 4600
172
+ },
173
+ {
174
+ "epoch": 2.57,
175
+ "learning_rate": 0.0002725076004735508,
176
+ "loss": 0.0788,
177
+ "step": 4800
178
+ },
179
+ {
180
+ "epoch": 2.68,
181
+ "learning_rate": 0.00025337097363328114,
182
+ "loss": 0.0511,
183
+ "step": 5000
184
+ },
185
+ {
186
+ "epoch": 2.79,
187
+ "learning_rate": 0.00023437809198903362,
188
+ "loss": 0.0506,
189
+ "step": 5200
190
+ },
191
+ {
192
+ "epoch": 2.89,
193
+ "learning_rate": 0.00021561505950973994,
194
+ "loss": 0.0554,
195
+ "step": 5400
196
+ },
197
+ {
198
+ "epoch": 3.0,
199
+ "eval_auc": 0.9730075655719146,
200
+ "eval_f1": 0.6282620163217179,
201
+ "eval_loss": 0.08585791289806366,
202
+ "eval_precision": 0.4672312733650252,
203
+ "eval_recall": 0.9586647727272727,
204
+ "eval_runtime": 96.1068,
205
+ "eval_samples_per_second": 27.407,
206
+ "eval_steps_per_second": 3.434,
207
+ "step": 5598
208
+ }
209
+ ],
210
+ "logging_steps": 200,
211
+ "max_steps": 9330,
212
+ "num_train_epochs": 5,
213
+ "save_steps": 500,
214
+ "total_flos": 1987518770082000.0,
215
+ "trial_name": null,
216
+ "trial_params": null
217
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00e62d9bc654e9fc3dddd9e18034c546c97f9692dc1da6a2867d54883b2c5c7c
3
+ size 4091
vocab (3).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>