AmelieSchreiber commited on
Commit
824c532
1 Parent(s): 8fde187

Upload 11 files

Browse files
README (2).md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.5.0
adapter_config (2).json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "facebook/esm2_t12_35M_UR50D",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 1,
11
+ "lora_dropout": 0.2,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 2,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "query",
18
+ "key",
19
+ "value"
20
+ ],
21
+ "task_type": "TOKEN_CLS"
22
+ }
adapter_model (2).bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54f37f13ca6442ec48f43d04f925ff91a92778ad95796881c1fb3486bb17b724
3
+ size 307151
optimizer (5).pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578bdfae167432c9208bd5658db66de8d324fba8853320e43007652d7664e304
3
+ size 622661
rng_state (5).pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fc73934354b49b0958215148a3000afed7c14a59ec6c797b9663bd0ebaed89
3
+ size 14575
scheduler (6).pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cce3f21fc8b26bf2ae65fa03352d5a2dba5b1479fedc1be62d4ae57fb0c5732
3
+ size 627
special_tokens_map (8).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 (8).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 (5).json ADDED
@@ -0,0 +1,896 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3476562916154915,
3
+ "best_model_checkpoint": "esm2_t12_35M-lora-binding-sites_2023-09-11_16-28-57/checkpoint-28970",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 28970,
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": 0.0005701554508678478,
14
+ "loss": 0.4954,
15
+ "step": 200
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.000570151359481901,
20
+ "loss": 0.3627,
21
+ "step": 400
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 0.0005701445314265366,
26
+ "loss": 0.325,
27
+ "step": 600
28
+ },
29
+ {
30
+ "epoch": 0.03,
31
+ "learning_rate": 0.0005701349667673032,
32
+ "loss": 0.2797,
33
+ "step": 800
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 0.0005701226655960202,
38
+ "loss": 0.2708,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 0.0005701076280307777,
44
+ "loss": 0.2547,
45
+ "step": 1200
46
+ },
47
+ {
48
+ "epoch": 0.05,
49
+ "learning_rate": 0.0005700898542159346,
50
+ "loss": 0.2395,
51
+ "step": 1400
52
+ },
53
+ {
54
+ "epoch": 0.06,
55
+ "learning_rate": 0.0005700693443221178,
56
+ "loss": 0.2348,
57
+ "step": 1600
58
+ },
59
+ {
60
+ "epoch": 0.06,
61
+ "learning_rate": 0.0005700460985462198,
62
+ "loss": 0.218,
63
+ "step": 1800
64
+ },
65
+ {
66
+ "epoch": 0.07,
67
+ "learning_rate": 0.0005700202538231217,
68
+ "loss": 0.2284,
69
+ "step": 2000
70
+ },
71
+ {
72
+ "epoch": 0.08,
73
+ "learning_rate": 0.000569991550655178,
74
+ "loss": 0.2307,
75
+ "step": 2200
76
+ },
77
+ {
78
+ "epoch": 0.08,
79
+ "learning_rate": 0.000569960112351964,
80
+ "loss": 0.22,
81
+ "step": 2400
82
+ },
83
+ {
84
+ "epoch": 0.09,
85
+ "learning_rate": 0.000569925939215284,
86
+ "loss": 0.2117,
87
+ "step": 2600
88
+ },
89
+ {
90
+ "epoch": 0.1,
91
+ "learning_rate": 0.0005698890315731962,
92
+ "loss": 0.2246,
93
+ "step": 2800
94
+ },
95
+ {
96
+ "epoch": 0.1,
97
+ "learning_rate": 0.0005698493897800102,
98
+ "loss": 0.2392,
99
+ "step": 3000
100
+ },
101
+ {
102
+ "epoch": 0.11,
103
+ "learning_rate": 0.0005698070142162829,
104
+ "loss": 0.2078,
105
+ "step": 3200
106
+ },
107
+ {
108
+ "epoch": 0.12,
109
+ "learning_rate": 0.0005697619052888148,
110
+ "loss": 0.2098,
111
+ "step": 3400
112
+ },
113
+ {
114
+ "epoch": 0.12,
115
+ "learning_rate": 0.0005697140634306472,
116
+ "loss": 0.1919,
117
+ "step": 3600
118
+ },
119
+ {
120
+ "epoch": 0.13,
121
+ "learning_rate": 0.0005696634891010563,
122
+ "loss": 0.1957,
123
+ "step": 3800
124
+ },
125
+ {
126
+ "epoch": 0.14,
127
+ "learning_rate": 0.0005696101827855504,
128
+ "loss": 0.2156,
129
+ "step": 4000
130
+ },
131
+ {
132
+ "epoch": 0.14,
133
+ "learning_rate": 0.0005695544319784758,
134
+ "loss": 0.1983,
135
+ "step": 4200
136
+ },
137
+ {
138
+ "epoch": 0.15,
139
+ "learning_rate": 0.0005694956769058657,
140
+ "loss": 0.2104,
141
+ "step": 4400
142
+ },
143
+ {
144
+ "epoch": 0.16,
145
+ "learning_rate": 0.0005694341914583195,
146
+ "loss": 0.1789,
147
+ "step": 4600
148
+ },
149
+ {
150
+ "epoch": 0.17,
151
+ "learning_rate": 0.0005693699762260905,
152
+ "loss": 0.1944,
153
+ "step": 4800
154
+ },
155
+ {
156
+ "epoch": 0.17,
157
+ "learning_rate": 0.0005693030318256384,
158
+ "loss": 0.1895,
159
+ "step": 5000
160
+ },
161
+ {
162
+ "epoch": 0.18,
163
+ "learning_rate": 0.0005692333588996219,
164
+ "loss": 0.2007,
165
+ "step": 5200
166
+ },
167
+ {
168
+ "epoch": 0.19,
169
+ "learning_rate": 0.0005691609581168934,
170
+ "loss": 0.1852,
171
+ "step": 5400
172
+ },
173
+ {
174
+ "epoch": 0.19,
175
+ "learning_rate": 0.0005690858301724929,
176
+ "loss": 0.1728,
177
+ "step": 5600
178
+ },
179
+ {
180
+ "epoch": 0.2,
181
+ "learning_rate": 0.0005690079757876402,
182
+ "loss": 0.2076,
183
+ "step": 5800
184
+ },
185
+ {
186
+ "epoch": 0.21,
187
+ "learning_rate": 0.0005689273957097291,
188
+ "loss": 0.1844,
189
+ "step": 6000
190
+ },
191
+ {
192
+ "epoch": 0.21,
193
+ "learning_rate": 0.0005688445140142318,
194
+ "loss": 0.173,
195
+ "step": 6200
196
+ },
197
+ {
198
+ "epoch": 0.22,
199
+ "learning_rate": 0.0005687584985156089,
200
+ "loss": 0.189,
201
+ "step": 6400
202
+ },
203
+ {
204
+ "epoch": 0.23,
205
+ "learning_rate": 0.0005686697597188824,
206
+ "loss": 0.1728,
207
+ "step": 6600
208
+ },
209
+ {
210
+ "epoch": 0.23,
211
+ "learning_rate": 0.0005685782984759349,
212
+ "loss": 0.1764,
213
+ "step": 6800
214
+ },
215
+ {
216
+ "epoch": 0.24,
217
+ "learning_rate": 0.0005684841156647846,
218
+ "loss": 0.1817,
219
+ "step": 7000
220
+ },
221
+ {
222
+ "epoch": 0.25,
223
+ "learning_rate": 0.0005683872121895759,
224
+ "loss": 0.184,
225
+ "step": 7200
226
+ },
227
+ {
228
+ "epoch": 0.26,
229
+ "learning_rate": 0.000568287588980572,
230
+ "loss": 0.1611,
231
+ "step": 7400
232
+ },
233
+ {
234
+ "epoch": 0.26,
235
+ "learning_rate": 0.0005681852469941448,
236
+ "loss": 0.1782,
237
+ "step": 7600
238
+ },
239
+ {
240
+ "epoch": 0.27,
241
+ "learning_rate": 0.000568080187212766,
242
+ "loss": 0.1674,
243
+ "step": 7800
244
+ },
245
+ {
246
+ "epoch": 0.28,
247
+ "learning_rate": 0.0005679724106449985,
248
+ "loss": 0.1592,
249
+ "step": 8000
250
+ },
251
+ {
252
+ "epoch": 0.28,
253
+ "learning_rate": 0.0005678619183254852,
254
+ "loss": 0.188,
255
+ "step": 8200
256
+ },
257
+ {
258
+ "epoch": 0.29,
259
+ "learning_rate": 0.0005677487113149407,
260
+ "loss": 0.1724,
261
+ "step": 8400
262
+ },
263
+ {
264
+ "epoch": 0.3,
265
+ "learning_rate": 0.00056763279070014,
266
+ "loss": 0.1734,
267
+ "step": 8600
268
+ },
269
+ {
270
+ "epoch": 0.3,
271
+ "learning_rate": 0.0005675141575939082,
272
+ "loss": 0.1802,
273
+ "step": 8800
274
+ },
275
+ {
276
+ "epoch": 0.31,
277
+ "learning_rate": 0.0005673934265999777,
278
+ "loss": 0.1735,
279
+ "step": 9000
280
+ },
281
+ {
282
+ "epoch": 0.32,
283
+ "learning_rate": 0.0005672693855015051,
284
+ "loss": 0.1768,
285
+ "step": 9200
286
+ },
287
+ {
288
+ "epoch": 0.32,
289
+ "learning_rate": 0.0005671426354002519,
290
+ "loss": 0.1759,
291
+ "step": 9400
292
+ },
293
+ {
294
+ "epoch": 0.33,
295
+ "learning_rate": 0.0005670131775130054,
296
+ "loss": 0.1646,
297
+ "step": 9600
298
+ },
299
+ {
300
+ "epoch": 0.34,
301
+ "learning_rate": 0.0005668810130825471,
302
+ "loss": 0.1684,
303
+ "step": 9800
304
+ },
305
+ {
306
+ "epoch": 0.35,
307
+ "learning_rate": 0.0005667461433776413,
308
+ "loss": 0.1636,
309
+ "step": 10000
310
+ },
311
+ {
312
+ "epoch": 0.35,
313
+ "learning_rate": 0.0005666085696930225,
314
+ "loss": 0.1492,
315
+ "step": 10200
316
+ },
317
+ {
318
+ "epoch": 0.36,
319
+ "learning_rate": 0.0005664682933493831,
320
+ "loss": 0.1636,
321
+ "step": 10400
322
+ },
323
+ {
324
+ "epoch": 0.37,
325
+ "learning_rate": 0.0005663253156933608,
326
+ "loss": 0.1647,
327
+ "step": 10600
328
+ },
329
+ {
330
+ "epoch": 0.37,
331
+ "learning_rate": 0.0005661796380975255,
332
+ "loss": 0.181,
333
+ "step": 10800
334
+ },
335
+ {
336
+ "epoch": 0.38,
337
+ "learning_rate": 0.0005660320105513283,
338
+ "loss": 0.1708,
339
+ "step": 11000
340
+ },
341
+ {
342
+ "epoch": 0.39,
343
+ "learning_rate": 0.0005658809507792387,
344
+ "loss": 0.1702,
345
+ "step": 11200
346
+ },
347
+ {
348
+ "epoch": 0.39,
349
+ "learning_rate": 0.0005657271953331912,
350
+ "loss": 0.1617,
351
+ "step": 11400
352
+ },
353
+ {
354
+ "epoch": 0.4,
355
+ "learning_rate": 0.000565570745689221,
356
+ "loss": 0.1722,
357
+ "step": 11600
358
+ },
359
+ {
360
+ "epoch": 0.41,
361
+ "learning_rate": 0.000565411603349228,
362
+ "loss": 0.1702,
363
+ "step": 11800
364
+ },
365
+ {
366
+ "epoch": 0.41,
367
+ "learning_rate": 0.0005652497698409615,
368
+ "loss": 0.1543,
369
+ "step": 12000
370
+ },
371
+ {
372
+ "epoch": 0.42,
373
+ "learning_rate": 0.0005650852467180052,
374
+ "loss": 0.1654,
375
+ "step": 12200
376
+ },
377
+ {
378
+ "epoch": 0.43,
379
+ "learning_rate": 0.0005649180355597633,
380
+ "loss": 0.1676,
381
+ "step": 12400
382
+ },
383
+ {
384
+ "epoch": 0.43,
385
+ "learning_rate": 0.000564748137971445,
386
+ "loss": 0.16,
387
+ "step": 12600
388
+ },
389
+ {
390
+ "epoch": 0.44,
391
+ "learning_rate": 0.0005645755555840486,
392
+ "loss": 0.1627,
393
+ "step": 12800
394
+ },
395
+ {
396
+ "epoch": 0.45,
397
+ "learning_rate": 0.0005644002900543462,
398
+ "loss": 0.1712,
399
+ "step": 13000
400
+ },
401
+ {
402
+ "epoch": 0.46,
403
+ "learning_rate": 0.0005642232394671313,
404
+ "loss": 0.1603,
405
+ "step": 13200
406
+ },
407
+ {
408
+ "epoch": 0.46,
409
+ "learning_rate": 0.0005640426261206144,
410
+ "loss": 0.1648,
411
+ "step": 13400
412
+ },
413
+ {
414
+ "epoch": 0.47,
415
+ "learning_rate": 0.0005638593347478565,
416
+ "loss": 0.1608,
417
+ "step": 13600
418
+ },
419
+ {
420
+ "epoch": 0.48,
421
+ "learning_rate": 0.0005636733671084348,
422
+ "loss": 0.162,
423
+ "step": 13800
424
+ },
425
+ {
426
+ "epoch": 0.48,
427
+ "learning_rate": 0.0005634847249876185,
428
+ "loss": 0.1516,
429
+ "step": 14000
430
+ },
431
+ {
432
+ "epoch": 0.49,
433
+ "learning_rate": 0.0005632934101963515,
434
+ "loss": 0.1638,
435
+ "step": 14200
436
+ },
437
+ {
438
+ "epoch": 0.5,
439
+ "learning_rate": 0.000563099424571235,
440
+ "loss": 0.1691,
441
+ "step": 14400
442
+ },
443
+ {
444
+ "epoch": 0.5,
445
+ "learning_rate": 0.0005629027699745098,
446
+ "loss": 0.149,
447
+ "step": 14600
448
+ },
449
+ {
450
+ "epoch": 0.51,
451
+ "learning_rate": 0.0005627034482940388,
452
+ "loss": 0.1713,
453
+ "step": 14800
454
+ },
455
+ {
456
+ "epoch": 0.52,
457
+ "learning_rate": 0.0005625014614432885,
458
+ "loss": 0.1615,
459
+ "step": 15000
460
+ },
461
+ {
462
+ "epoch": 0.52,
463
+ "learning_rate": 0.0005622978412332689,
464
+ "loss": 0.1618,
465
+ "step": 15200
466
+ },
467
+ {
468
+ "epoch": 0.53,
469
+ "learning_rate": 0.0005620905431860859,
470
+ "loss": 0.1695,
471
+ "step": 15400
472
+ },
473
+ {
474
+ "epoch": 0.54,
475
+ "learning_rate": 0.0005618805858524459,
476
+ "loss": 0.1575,
477
+ "step": 15600
478
+ },
479
+ {
480
+ "epoch": 0.55,
481
+ "learning_rate": 0.0005616679712479168,
482
+ "loss": 0.1494,
483
+ "step": 15800
484
+ },
485
+ {
486
+ "epoch": 0.55,
487
+ "learning_rate": 0.0005614527014135753,
488
+ "loss": 0.1441,
489
+ "step": 16000
490
+ },
491
+ {
492
+ "epoch": 0.56,
493
+ "learning_rate": 0.0005612347784159886,
494
+ "loss": 0.1554,
495
+ "step": 16200
496
+ },
497
+ {
498
+ "epoch": 0.57,
499
+ "learning_rate": 0.000561014204347194,
500
+ "loss": 0.1597,
501
+ "step": 16400
502
+ },
503
+ {
504
+ "epoch": 0.57,
505
+ "learning_rate": 0.0005607909813246783,
506
+ "loss": 0.1603,
507
+ "step": 16600
508
+ },
509
+ {
510
+ "epoch": 0.58,
511
+ "learning_rate": 0.0005605651114913586,
512
+ "loss": 0.1566,
513
+ "step": 16800
514
+ },
515
+ {
516
+ "epoch": 0.59,
517
+ "learning_rate": 0.0005603365970155604,
518
+ "loss": 0.148,
519
+ "step": 17000
520
+ },
521
+ {
522
+ "epoch": 0.59,
523
+ "learning_rate": 0.0005601054400909981,
524
+ "loss": 0.153,
525
+ "step": 17200
526
+ },
527
+ {
528
+ "epoch": 0.6,
529
+ "learning_rate": 0.0005598728184863933,
530
+ "loss": 0.1551,
531
+ "step": 17400
532
+ },
533
+ {
534
+ "epoch": 0.61,
535
+ "learning_rate": 0.000559636396531194,
536
+ "loss": 0.1808,
537
+ "step": 17600
538
+ },
539
+ {
540
+ "epoch": 0.61,
541
+ "learning_rate": 0.0005593973388490791,
542
+ "loss": 0.1537,
543
+ "step": 17800
544
+ },
545
+ {
546
+ "epoch": 0.62,
547
+ "learning_rate": 0.0005591556477349764,
548
+ "loss": 0.1488,
549
+ "step": 18000
550
+ },
551
+ {
552
+ "epoch": 0.63,
553
+ "learning_rate": 0.0005589113255090943,
554
+ "loss": 0.1632,
555
+ "step": 18200
556
+ },
557
+ {
558
+ "epoch": 0.64,
559
+ "learning_rate": 0.0005586643745168998,
560
+ "loss": 0.1595,
561
+ "step": 18400
562
+ },
563
+ {
564
+ "epoch": 0.64,
565
+ "learning_rate": 0.0005584147971290952,
566
+ "loss": 0.1692,
567
+ "step": 18600
568
+ },
569
+ {
570
+ "epoch": 0.65,
571
+ "learning_rate": 0.0005581625957415966,
572
+ "loss": 0.1454,
573
+ "step": 18800
574
+ },
575
+ {
576
+ "epoch": 0.66,
577
+ "learning_rate": 0.0005579077727755101,
578
+ "loss": 0.1608,
579
+ "step": 19000
580
+ },
581
+ {
582
+ "epoch": 0.66,
583
+ "learning_rate": 0.0005576503306771081,
584
+ "loss": 0.1506,
585
+ "step": 19200
586
+ },
587
+ {
588
+ "epoch": 0.67,
589
+ "learning_rate": 0.0005573915787164281,
590
+ "loss": 0.1639,
591
+ "step": 19400
592
+ },
593
+ {
594
+ "epoch": 0.68,
595
+ "learning_rate": 0.000557128918857334,
596
+ "loss": 0.1463,
597
+ "step": 19600
598
+ },
599
+ {
600
+ "epoch": 0.68,
601
+ "learning_rate": 0.0005568636473428375,
602
+ "loss": 0.159,
603
+ "step": 19800
604
+ },
605
+ {
606
+ "epoch": 0.69,
607
+ "learning_rate": 0.0005565957667195164,
608
+ "loss": 0.1792,
609
+ "step": 20000
610
+ },
611
+ {
612
+ "epoch": 0.7,
613
+ "learning_rate": 0.0005563252795589956,
614
+ "loss": 0.1512,
615
+ "step": 20200
616
+ },
617
+ {
618
+ "epoch": 0.7,
619
+ "learning_rate": 0.0005560521884579225,
620
+ "loss": 0.1604,
621
+ "step": 20400
622
+ },
623
+ {
624
+ "epoch": 0.71,
625
+ "learning_rate": 0.000555776496037942,
626
+ "loss": 0.1563,
627
+ "step": 20600
628
+ },
629
+ {
630
+ "epoch": 0.72,
631
+ "learning_rate": 0.0005554982049456713,
632
+ "loss": 0.1598,
633
+ "step": 20800
634
+ },
635
+ {
636
+ "epoch": 0.72,
637
+ "learning_rate": 0.0005552173178526746,
638
+ "loss": 0.1429,
639
+ "step": 21000
640
+ },
641
+ {
642
+ "epoch": 0.73,
643
+ "learning_rate": 0.0005549338374554378,
644
+ "loss": 0.1544,
645
+ "step": 21200
646
+ },
647
+ {
648
+ "epoch": 0.74,
649
+ "learning_rate": 0.0005546477664753415,
650
+ "loss": 0.1435,
651
+ "step": 21400
652
+ },
653
+ {
654
+ "epoch": 0.75,
655
+ "learning_rate": 0.00055436055738539,
656
+ "loss": 0.1562,
657
+ "step": 21600
658
+ },
659
+ {
660
+ "epoch": 0.75,
661
+ "learning_rate": 0.0005540693264215625,
662
+ "loss": 0.1501,
663
+ "step": 21800
664
+ },
665
+ {
666
+ "epoch": 0.76,
667
+ "learning_rate": 0.0005537755131740878,
668
+ "loss": 0.1511,
669
+ "step": 22000
670
+ },
671
+ {
672
+ "epoch": 0.77,
673
+ "learning_rate": 0.0005534791204635411,
674
+ "loss": 0.1456,
675
+ "step": 22200
676
+ },
677
+ {
678
+ "epoch": 0.77,
679
+ "learning_rate": 0.0005531801511352604,
680
+ "loss": 0.1507,
681
+ "step": 22400
682
+ },
683
+ {
684
+ "epoch": 0.78,
685
+ "learning_rate": 0.0005528786080593183,
686
+ "loss": 0.1477,
687
+ "step": 22600
688
+ },
689
+ {
690
+ "epoch": 0.79,
691
+ "learning_rate": 0.000552574494130496,
692
+ "loss": 0.1507,
693
+ "step": 22800
694
+ },
695
+ {
696
+ "epoch": 0.79,
697
+ "learning_rate": 0.000552267812268254,
698
+ "loss": 0.1494,
699
+ "step": 23000
700
+ },
701
+ {
702
+ "epoch": 0.8,
703
+ "learning_rate": 0.0005519585654167048,
704
+ "loss": 0.1489,
705
+ "step": 23200
706
+ },
707
+ {
708
+ "epoch": 0.81,
709
+ "learning_rate": 0.0005516467565445848,
710
+ "loss": 0.1495,
711
+ "step": 23400
712
+ },
713
+ {
714
+ "epoch": 0.81,
715
+ "learning_rate": 0.0005513323886452253,
716
+ "loss": 0.1467,
717
+ "step": 23600
718
+ },
719
+ {
720
+ "epoch": 0.82,
721
+ "learning_rate": 0.0005510154647365238,
722
+ "loss": 0.1465,
723
+ "step": 23800
724
+ },
725
+ {
726
+ "epoch": 0.83,
727
+ "learning_rate": 0.0005506975915907354,
728
+ "loss": 0.1725,
729
+ "step": 24000
730
+ },
731
+ {
732
+ "epoch": 0.84,
733
+ "learning_rate": 0.0005503755775569938,
734
+ "loss": 0.1604,
735
+ "step": 24200
736
+ },
737
+ {
738
+ "epoch": 0.84,
739
+ "learning_rate": 0.0005500510166991929,
740
+ "loss": 0.1492,
741
+ "step": 24400
742
+ },
743
+ {
744
+ "epoch": 0.85,
745
+ "learning_rate": 0.0005497239121330815,
746
+ "loss": 0.1446,
747
+ "step": 24600
748
+ },
749
+ {
750
+ "epoch": 0.86,
751
+ "learning_rate": 0.0005493942669988278,
752
+ "loss": 0.1492,
753
+ "step": 24800
754
+ },
755
+ {
756
+ "epoch": 0.86,
757
+ "learning_rate": 0.0005490620844609896,
758
+ "loss": 0.152,
759
+ "step": 25000
760
+ },
761
+ {
762
+ "epoch": 0.87,
763
+ "learning_rate": 0.0005487273677084831,
764
+ "loss": 0.1601,
765
+ "step": 25200
766
+ },
767
+ {
768
+ "epoch": 0.88,
769
+ "learning_rate": 0.0005483901199545525,
770
+ "loss": 0.1432,
771
+ "step": 25400
772
+ },
773
+ {
774
+ "epoch": 0.88,
775
+ "learning_rate": 0.0005480503444367399,
776
+ "loss": 0.153,
777
+ "step": 25600
778
+ },
779
+ {
780
+ "epoch": 0.89,
781
+ "learning_rate": 0.0005477080444168533,
782
+ "loss": 0.1446,
783
+ "step": 25800
784
+ },
785
+ {
786
+ "epoch": 0.9,
787
+ "learning_rate": 0.0005473649535531743,
788
+ "loss": 0.1543,
789
+ "step": 26000
790
+ },
791
+ {
792
+ "epoch": 0.9,
793
+ "learning_rate": 0.0005470176269927267,
794
+ "loss": 0.1652,
795
+ "step": 26200
796
+ },
797
+ {
798
+ "epoch": 0.91,
799
+ "learning_rate": 0.0005466677858441803,
800
+ "loss": 0.1463,
801
+ "step": 26400
802
+ },
803
+ {
804
+ "epoch": 0.92,
805
+ "learning_rate": 0.0005463154334659722,
806
+ "loss": 0.152,
807
+ "step": 26600
808
+ },
809
+ {
810
+ "epoch": 0.93,
811
+ "learning_rate": 0.0005459605732406469,
812
+ "loss": 0.1572,
813
+ "step": 26800
814
+ },
815
+ {
816
+ "epoch": 0.93,
817
+ "learning_rate": 0.0005456032085748239,
818
+ "loss": 0.1439,
819
+ "step": 27000
820
+ },
821
+ {
822
+ "epoch": 0.94,
823
+ "learning_rate": 0.0005452433428991655,
824
+ "loss": 0.1483,
825
+ "step": 27200
826
+ },
827
+ {
828
+ "epoch": 0.95,
829
+ "learning_rate": 0.000544880979668343,
830
+ "loss": 0.1633,
831
+ "step": 27400
832
+ },
833
+ {
834
+ "epoch": 0.95,
835
+ "learning_rate": 0.0005445161223610037,
836
+ "loss": 0.1559,
837
+ "step": 27600
838
+ },
839
+ {
840
+ "epoch": 0.96,
841
+ "learning_rate": 0.0005441487744797385,
842
+ "loss": 0.1582,
843
+ "step": 27800
844
+ },
845
+ {
846
+ "epoch": 0.97,
847
+ "learning_rate": 0.000543778939551047,
848
+ "loss": 0.1607,
849
+ "step": 28000
850
+ },
851
+ {
852
+ "epoch": 0.97,
853
+ "learning_rate": 0.0005434084888892294,
854
+ "loss": 0.1444,
855
+ "step": 28200
856
+ },
857
+ {
858
+ "epoch": 0.98,
859
+ "learning_rate": 0.0005430337029313361,
860
+ "loss": 0.1411,
861
+ "step": 28400
862
+ },
863
+ {
864
+ "epoch": 0.99,
865
+ "learning_rate": 0.0005426564406305822,
866
+ "loss": 0.145,
867
+ "step": 28600
868
+ },
869
+ {
870
+ "epoch": 0.99,
871
+ "learning_rate": 0.0005422767056086448,
872
+ "loss": 0.1543,
873
+ "step": 28800
874
+ },
875
+ {
876
+ "epoch": 1.0,
877
+ "eval_accuracy": 0.9266715807717144,
878
+ "eval_auc": 0.8547374969101048,
879
+ "eval_f1": 0.3476562916154915,
880
+ "eval_loss": 0.36462366580963135,
881
+ "eval_precision": 0.22375778821030992,
882
+ "eval_recall": 0.7790042059793111,
883
+ "eval_runtime": 1778.9025,
884
+ "eval_samples_per_second": 24.978,
885
+ "eval_steps_per_second": 4.163,
886
+ "step": 28970
887
+ }
888
+ ],
889
+ "logging_steps": 200,
890
+ "max_steps": 202790,
891
+ "num_train_epochs": 7,
892
+ "save_steps": 500,
893
+ "total_flos": 3.4755022197e+16,
894
+ "trial_name": null,
895
+ "trial_params": null
896
+ }
training_args (5).bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aabfc585a5b018aaa712111ce2f054ea567fe971ffe6acd839649a028f2c23bf
3
+ size 4091
vocab (8).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>