Hugging Face's logo

AmelieSchreiber
/
esm2_t12_35M_ptm_qlora_2100K

PEFT
English
biology
protein language model
ESM-2
post translational modification
Model card Files
xet
 Community
1
AmelieSchreiber commited on
Commit
64bba81
·
1 Parent(s): 76e17f7

Upload 11 files

Browse files
Files changed (11) hide show
  1. adapter_config.json +29 -0
  2. adapter_model.bin +3 -0
  3. added_tokens.json +7 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +7 -0
  8. tokenizer_config.json +54 -0
  9. trainer_state.json +579 -0
  10. training_args.bin +3 -0
  11. 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>