AmelieSchreiber commited on
Commit
ccad8a7
·
1 Parent(s): 9c0ac17

Upload 11 files

Browse files
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "facebook/esm2_t30_150M_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:a736f147969b9f8db1faf8f1b8c2ebca0e99000fd58e7686337eb8b879d449c8
3
+ size 1005173
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 sha256:3de72a937f0ccc95780f8d284deca1db8530886bfc0522f9699d5bce0fa5d044
3
+ size 1972101
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bccfd6199f27e82b1e80be70b3d54ecbcf92e0aeadb5032e076fbabb66dc8d9
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881dea0b454e7a7b8cc9c38662ff6d4066c973f0e9755287df59379519a8196a
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": 1000000000000000019884624838656,
50
+ "pad_token": "<pad>",
51
+ "tokenizer_class": "EsmTokenizer",
52
+ "tokenizer_file": null,
53
+ "unk_token": "<unk>"
54
+ }
trainer_state.json ADDED
@@ -0,0 +1,681 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.10229773443883387,
3
+ "best_model_checkpoint": "esm2_t30_150M_qlora_ptm_sites_2023-10-17_05-49-32/checkpoint-21690",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 21690,
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": 0.0003700791565537852,
14
+ "loss": 0.2788,
15
+ "step": 200
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 0.0003698462746319928,
20
+ "loss": 0.0908,
21
+ "step": 400
22
+ },
23
+ {
24
+ "epoch": 0.03,
25
+ "learning_rate": 0.00036945835522359584,
26
+ "loss": 0.061,
27
+ "step": 600
28
+ },
29
+ {
30
+ "epoch": 0.04,
31
+ "learning_rate": 0.00036891572382917795,
32
+ "loss": 0.0467,
33
+ "step": 800
34
+ },
35
+ {
36
+ "epoch": 0.05,
37
+ "learning_rate": 0.0003682188357671161,
38
+ "loss": 0.0447,
39
+ "step": 1000
40
+ },
41
+ {
42
+ "epoch": 0.06,
43
+ "learning_rate": 0.00036736827579152647,
44
+ "loss": 0.0411,
45
+ "step": 1200
46
+ },
47
+ {
48
+ "epoch": 0.06,
49
+ "learning_rate": 0.00036637015433638333,
50
+ "loss": 0.039,
51
+ "step": 1400
52
+ },
53
+ {
54
+ "epoch": 0.07,
55
+ "learning_rate": 0.0003652152782523256,
56
+ "loss": 0.0389,
57
+ "step": 1600
58
+ },
59
+ {
60
+ "epoch": 0.08,
61
+ "learning_rate": 0.0003639092505197804,
62
+ "loss": 0.0307,
63
+ "step": 1800
64
+ },
65
+ {
66
+ "epoch": 0.09,
67
+ "learning_rate": 0.0003624531670178909,
68
+ "loss": 0.0333,
69
+ "step": 2000
70
+ },
71
+ {
72
+ "epoch": 0.1,
73
+ "learning_rate": 0.0003608482495365936,
74
+ "loss": 0.0289,
75
+ "step": 2200
76
+ },
77
+ {
78
+ "epoch": 0.11,
79
+ "learning_rate": 0.00035909584475142265,
80
+ "loss": 0.0312,
81
+ "step": 2400
82
+ },
83
+ {
84
+ "epoch": 0.12,
85
+ "learning_rate": 0.0003571974230935234,
86
+ "loss": 0.029,
87
+ "step": 2600
88
+ },
89
+ {
90
+ "epoch": 0.13,
91
+ "learning_rate": 0.00035515457751582335,
92
+ "loss": 0.0278,
93
+ "step": 2800
94
+ },
95
+ {
96
+ "epoch": 0.14,
97
+ "learning_rate": 0.000352969022156396,
98
+ "loss": 0.0276,
99
+ "step": 3000
100
+ },
101
+ {
102
+ "epoch": 0.15,
103
+ "learning_rate": 0.000350642590900139,
104
+ "loss": 0.0284,
105
+ "step": 3200
106
+ },
107
+ {
108
+ "epoch": 0.16,
109
+ "learning_rate": 0.00034817723583997393,
110
+ "loss": 0.0265,
111
+ "step": 3400
112
+ },
113
+ {
114
+ "epoch": 0.17,
115
+ "learning_rate": 0.0003455750256388576,
116
+ "loss": 0.0263,
117
+ "step": 3600
118
+ },
119
+ {
120
+ "epoch": 0.18,
121
+ "learning_rate": 0.0003428381437939813,
122
+ "loss": 0.0266,
123
+ "step": 3800
124
+ },
125
+ {
126
+ "epoch": 0.18,
127
+ "learning_rate": 0.00033996888680461266,
128
+ "loss": 0.0295,
129
+ "step": 4000
130
+ },
131
+ {
132
+ "epoch": 0.19,
133
+ "learning_rate": 0.0003369696622451184,
134
+ "loss": 0.0259,
135
+ "step": 4200
136
+ },
137
+ {
138
+ "epoch": 0.2,
139
+ "learning_rate": 0.00033384298674478505,
140
+ "loss": 0.0229,
141
+ "step": 4400
142
+ },
143
+ {
144
+ "epoch": 0.21,
145
+ "learning_rate": 0.0003305914838761317,
146
+ "loss": 0.0228,
147
+ "step": 4600
148
+ },
149
+ {
150
+ "epoch": 0.22,
151
+ "learning_rate": 0.00032721788195348825,
152
+ "loss": 0.0236,
153
+ "step": 4800
154
+ },
155
+ {
156
+ "epoch": 0.23,
157
+ "learning_rate": 0.0003237427679674208,
158
+ "loss": 0.0241,
159
+ "step": 5000
160
+ },
161
+ {
162
+ "epoch": 0.24,
163
+ "learning_rate": 0.00032013413454873025,
164
+ "loss": 0.0278,
165
+ "step": 5200
166
+ },
167
+ {
168
+ "epoch": 0.25,
169
+ "learning_rate": 0.000316412176767992,
170
+ "loss": 0.0231,
171
+ "step": 5400
172
+ },
173
+ {
174
+ "epoch": 0.26,
175
+ "learning_rate": 0.00031258001769510885,
176
+ "loss": 0.0247,
177
+ "step": 5600
178
+ },
179
+ {
180
+ "epoch": 0.27,
181
+ "learning_rate": 0.0003086408728691517,
182
+ "loss": 0.0243,
183
+ "step": 5800
184
+ },
185
+ {
186
+ "epoch": 0.28,
187
+ "learning_rate": 0.0003045980476002217,
188
+ "loss": 0.0236,
189
+ "step": 6000
190
+ },
191
+ {
192
+ "epoch": 0.29,
193
+ "learning_rate": 0.00030045493419598703,
194
+ "loss": 0.0213,
195
+ "step": 6200
196
+ },
197
+ {
198
+ "epoch": 0.3,
199
+ "learning_rate": 0.00029621500911522,
200
+ "loss": 0.0244,
201
+ "step": 6400
202
+ },
203
+ {
204
+ "epoch": 0.3,
205
+ "learning_rate": 0.00029188183005072376,
206
+ "loss": 0.019,
207
+ "step": 6600
208
+ },
209
+ {
210
+ "epoch": 0.31,
211
+ "learning_rate": 0.0002874590329440961,
212
+ "loss": 0.0223,
213
+ "step": 6800
214
+ },
215
+ {
216
+ "epoch": 0.32,
217
+ "learning_rate": 0.0002829503289348351,
218
+ "loss": 0.0221,
219
+ "step": 7000
220
+ },
221
+ {
222
+ "epoch": 0.33,
223
+ "learning_rate": 0.00027835950124634694,
224
+ "loss": 0.0215,
225
+ "step": 7200
226
+ },
227
+ {
228
+ "epoch": 0.34,
229
+ "learning_rate": 0.000273690402011468,
230
+ "loss": 0.0235,
231
+ "step": 7400
232
+ },
233
+ {
234
+ "epoch": 0.35,
235
+ "learning_rate": 0.0002689469490401664,
236
+ "loss": 0.021,
237
+ "step": 7600
238
+ },
239
+ {
240
+ "epoch": 0.36,
241
+ "learning_rate": 0.0002641331225321336,
242
+ "loss": 0.0198,
243
+ "step": 7800
244
+ },
245
+ {
246
+ "epoch": 0.37,
247
+ "learning_rate": 0.0002592529617370253,
248
+ "loss": 0.0184,
249
+ "step": 8000
250
+ },
251
+ {
252
+ "epoch": 0.38,
253
+ "learning_rate": 0.0002543105615651547,
254
+ "loss": 0.0208,
255
+ "step": 8200
256
+ },
257
+ {
258
+ "epoch": 0.39,
259
+ "learning_rate": 0.00024931006915147966,
260
+ "loss": 0.02,
261
+ "step": 8400
262
+ },
263
+ {
264
+ "epoch": 0.4,
265
+ "learning_rate": 0.0002442556803757701,
266
+ "loss": 0.0201,
267
+ "step": 8600
268
+ },
269
+ {
270
+ "epoch": 0.41,
271
+ "learning_rate": 0.00023915163634187332,
272
+ "loss": 0.0216,
273
+ "step": 8800
274
+ },
275
+ {
276
+ "epoch": 0.41,
277
+ "learning_rate": 0.00023400221981903174,
278
+ "loss": 0.0216,
279
+ "step": 9000
280
+ },
281
+ {
282
+ "epoch": 0.42,
283
+ "learning_rate": 0.00022881175164824033,
284
+ "loss": 0.0196,
285
+ "step": 9200
286
+ },
287
+ {
288
+ "epoch": 0.43,
289
+ "learning_rate": 0.00022358458711665722,
290
+ "loss": 0.0192,
291
+ "step": 9400
292
+ },
293
+ {
294
+ "epoch": 0.44,
295
+ "learning_rate": 0.00021832511230311189,
296
+ "loss": 0.0203,
297
+ "step": 9600
298
+ },
299
+ {
300
+ "epoch": 0.45,
301
+ "learning_rate": 0.00021303774039777544,
302
+ "loss": 0.0204,
303
+ "step": 9800
304
+ },
305
+ {
306
+ "epoch": 0.46,
307
+ "learning_rate": 0.0002077269079990823,
308
+ "loss": 0.0204,
309
+ "step": 10000
310
+ },
311
+ {
312
+ "epoch": 0.47,
313
+ "learning_rate": 0.0002023970713910101,
314
+ "loss": 0.0212,
315
+ "step": 10200
316
+ },
317
+ {
318
+ "epoch": 0.48,
319
+ "learning_rate": 0.00019705270280384151,
320
+ "loss": 0.0204,
321
+ "step": 10400
322
+ },
323
+ {
324
+ "epoch": 0.49,
325
+ "learning_rate": 0.00019169828666154592,
326
+ "loss": 0.0184,
327
+ "step": 10600
328
+ },
329
+ {
330
+ "epoch": 0.5,
331
+ "learning_rate": 0.00018633831581892887,
332
+ "loss": 0.0202,
333
+ "step": 10800
334
+ },
335
+ {
336
+ "epoch": 0.51,
337
+ "learning_rate": 0.00018097728779170797,
338
+ "loss": 0.0198,
339
+ "step": 11000
340
+ },
341
+ {
342
+ "epoch": 0.52,
343
+ "learning_rate": 0.0001756464729181275,
344
+ "loss": 0.0189,
345
+ "step": 11200
346
+ },
347
+ {
348
+ "epoch": 0.53,
349
+ "learning_rate": 0.00017029677198576599,
350
+ "loss": 0.0164,
351
+ "step": 11400
352
+ },
353
+ {
354
+ "epoch": 0.53,
355
+ "learning_rate": 0.00016495947422103804,
356
+ "loss": 0.0191,
357
+ "step": 11600
358
+ },
359
+ {
360
+ "epoch": 0.54,
361
+ "learning_rate": 0.00015963905811483306,
362
+ "loss": 0.0195,
363
+ "step": 11800
364
+ },
365
+ {
366
+ "epoch": 0.55,
367
+ "learning_rate": 0.0001543399879927535,
368
+ "loss": 0.0188,
369
+ "step": 12000
370
+ },
371
+ {
372
+ "epoch": 0.56,
373
+ "learning_rate": 0.00014906671026912937,
374
+ "loss": 0.0185,
375
+ "step": 12200
376
+ },
377
+ {
378
+ "epoch": 0.57,
379
+ "learning_rate": 0.0001438236497160614,
380
+ "loss": 0.0189,
381
+ "step": 12400
382
+ },
383
+ {
384
+ "epoch": 0.58,
385
+ "learning_rate": 0.0001386152057506243,
386
+ "loss": 0.0194,
387
+ "step": 12600
388
+ },
389
+ {
390
+ "epoch": 0.59,
391
+ "learning_rate": 0.00013344574874334572,
392
+ "loss": 0.0191,
393
+ "step": 12800
394
+ },
395
+ {
396
+ "epoch": 0.6,
397
+ "learning_rate": 0.00012831961635105695,
398
+ "loss": 0.0172,
399
+ "step": 13000
400
+ },
401
+ {
402
+ "epoch": 0.61,
403
+ "learning_rate": 0.00012326637687353276,
404
+ "loss": 0.0179,
405
+ "step": 13200
406
+ },
407
+ {
408
+ "epoch": 0.62,
409
+ "learning_rate": 0.00011826448612580445,
410
+ "loss": 0.0196,
411
+ "step": 13400
412
+ },
413
+ {
414
+ "epoch": 0.63,
415
+ "learning_rate": 0.00011329339019600353,
416
+ "loss": 0.0182,
417
+ "step": 13600
418
+ },
419
+ {
420
+ "epoch": 0.64,
421
+ "learning_rate": 0.00010838252859058713,
422
+ "loss": 0.0191,
423
+ "step": 13800
424
+ },
425
+ {
426
+ "epoch": 0.65,
427
+ "learning_rate": 0.00010353602198071279,
428
+ "loss": 0.0209,
429
+ "step": 14000
430
+ },
431
+ {
432
+ "epoch": 0.65,
433
+ "learning_rate": 9.875793703769172e-05,
434
+ "loss": 0.0196,
435
+ "step": 14200
436
+ },
437
+ {
438
+ "epoch": 0.66,
439
+ "learning_rate": 9.405228302067126e-05,
440
+ "loss": 0.0186,
441
+ "step": 14400
442
+ },
443
+ {
444
+ "epoch": 0.67,
445
+ "learning_rate": 8.942300841249284e-05,
446
+ "loss": 0.0186,
447
+ "step": 14600
448
+ },
449
+ {
450
+ "epoch": 0.68,
451
+ "learning_rate": 8.48739976065466e-05,
452
+ "loss": 0.0206,
453
+ "step": 14800
454
+ },
455
+ {
456
+ "epoch": 0.69,
457
+ "learning_rate": 8.040906764740216e-05,
458
+ "loss": 0.0191,
459
+ "step": 15000
460
+ },
461
+ {
462
+ "epoch": 0.7,
463
+ "learning_rate": 7.603196502795268e-05,
464
+ "loss": 0.0177,
465
+ "step": 15200
466
+ },
467
+ {
468
+ "epoch": 0.71,
469
+ "learning_rate": 7.17463625457574e-05,
470
+ "loss": 0.0167,
471
+ "step": 15400
472
+ },
473
+ {
474
+ "epoch": 0.72,
475
+ "learning_rate": 6.757656635075146e-05,
476
+ "loss": 0.0169,
477
+ "step": 15600
478
+ },
479
+ {
480
+ "epoch": 0.73,
481
+ "learning_rate": 6.348417073686787e-05,
482
+ "loss": 0.0187,
483
+ "step": 15800
484
+ },
485
+ {
486
+ "epoch": 0.74,
487
+ "learning_rate": 5.949380403058096e-05,
488
+ "loss": 0.0188,
489
+ "step": 16000
490
+ },
491
+ {
492
+ "epoch": 0.75,
493
+ "learning_rate": 5.560881452192967e-05,
494
+ "loss": 0.0185,
495
+ "step": 16200
496
+ },
497
+ {
498
+ "epoch": 0.76,
499
+ "learning_rate": 5.18324620796504e-05,
500
+ "loss": 0.0156,
501
+ "step": 16400
502
+ },
503
+ {
504
+ "epoch": 0.77,
505
+ "learning_rate": 4.816791541584292e-05,
506
+ "loss": 0.0157,
507
+ "step": 16600
508
+ },
509
+ {
510
+ "epoch": 0.77,
511
+ "learning_rate": 4.4618249427125566e-05,
512
+ "loss": 0.0159,
513
+ "step": 16800
514
+ },
515
+ {
516
+ "epoch": 0.78,
517
+ "learning_rate": 4.1186442614509987e-05,
518
+ "loss": 0.0163,
519
+ "step": 17000
520
+ },
521
+ {
522
+ "epoch": 0.79,
523
+ "learning_rate": 3.787537458416044e-05,
524
+ "loss": 0.0155,
525
+ "step": 17200
526
+ },
527
+ {
528
+ "epoch": 0.8,
529
+ "learning_rate": 3.468782363113597e-05,
530
+ "loss": 0.0175,
531
+ "step": 17400
532
+ },
533
+ {
534
+ "epoch": 0.81,
535
+ "learning_rate": 3.164145300855508e-05,
536
+ "loss": 0.0159,
537
+ "step": 17600
538
+ },
539
+ {
540
+ "epoch": 0.82,
541
+ "learning_rate": 2.8708204267220065e-05,
542
+ "loss": 0.0171,
543
+ "step": 17800
544
+ },
545
+ {
546
+ "epoch": 0.83,
547
+ "learning_rate": 2.590616471456609e-05,
548
+ "loss": 0.0203,
549
+ "step": 18000
550
+ },
551
+ {
552
+ "epoch": 0.84,
553
+ "learning_rate": 2.3237685523257935e-05,
554
+ "loss": 0.0177,
555
+ "step": 18200
556
+ },
557
+ {
558
+ "epoch": 0.85,
559
+ "learning_rate": 2.0705005796353695e-05,
560
+ "loss": 0.0189,
561
+ "step": 18400
562
+ },
563
+ {
564
+ "epoch": 0.86,
565
+ "learning_rate": 1.832187800404772e-05,
566
+ "loss": 0.018,
567
+ "step": 18600
568
+ },
569
+ {
570
+ "epoch": 0.87,
571
+ "learning_rate": 1.6066352463134496e-05,
572
+ "loss": 0.0173,
573
+ "step": 18800
574
+ },
575
+ {
576
+ "epoch": 0.88,
577
+ "learning_rate": 1.3952643804275625e-05,
578
+ "loss": 0.0173,
579
+ "step": 19000
580
+ },
581
+ {
582
+ "epoch": 0.89,
583
+ "learning_rate": 1.1982525626282391e-05,
584
+ "loss": 0.0168,
585
+ "step": 19200
586
+ },
587
+ {
588
+ "epoch": 0.89,
589
+ "learning_rate": 1.0157651042153225e-05,
590
+ "loss": 0.0168,
591
+ "step": 19400
592
+ },
593
+ {
594
+ "epoch": 0.9,
595
+ "learning_rate": 8.479551291957473e-06,
596
+ "loss": 0.0162,
597
+ "step": 19600
598
+ },
599
+ {
600
+ "epoch": 0.91,
601
+ "learning_rate": 6.949634457982115e-06,
602
+ "loss": 0.017,
603
+ "step": 19800
604
+ },
605
+ {
606
+ "epoch": 0.92,
607
+ "learning_rate": 5.569184283219286e-06,
608
+ "loss": 0.0169,
609
+ "step": 20000
610
+ },
611
+ {
612
+ "epoch": 0.93,
613
+ "learning_rate": 4.339359094186193e-06,
614
+ "loss": 0.0162,
615
+ "step": 20200
616
+ },
617
+ {
618
+ "epoch": 0.94,
619
+ "learning_rate": 3.2611908289809675e-06,
620
+ "loss": 0.0166,
621
+ "step": 20400
622
+ },
623
+ {
624
+ "epoch": 0.95,
625
+ "learning_rate": 2.3355841713904373e-06,
626
+ "loss": 0.0163,
627
+ "step": 20600
628
+ },
629
+ {
630
+ "epoch": 0.96,
631
+ "learning_rate": 1.5633157917758234e-06,
632
+ "loss": 0.0168,
633
+ "step": 20800
634
+ },
635
+ {
636
+ "epoch": 0.97,
637
+ "learning_rate": 9.450336953740333e-07,
638
+ "loss": 0.0168,
639
+ "step": 21000
640
+ },
641
+ {
642
+ "epoch": 0.98,
643
+ "learning_rate": 4.812566785606635e-07,
644
+ "loss": 0.0178,
645
+ "step": 21200
646
+ },
647
+ {
648
+ "epoch": 0.99,
649
+ "learning_rate": 1.7237389353147272e-07,
650
+ "loss": 0.0196,
651
+ "step": 21400
652
+ },
653
+ {
654
+ "epoch": 1.0,
655
+ "learning_rate": 1.864452176733613e-08,
656
+ "loss": 0.0154,
657
+ "step": 21600
658
+ },
659
+ {
660
+ "epoch": 1.0,
661
+ "eval_accuracy": 0.9653004077243341,
662
+ "eval_auc": 0.8861627985063656,
663
+ "eval_f1": 0.10229773443883387,
664
+ "eval_loss": 0.36874082684516907,
665
+ "eval_mcc": 0.20444634920778376,
666
+ "eval_precision": 0.05461181025780778,
667
+ "eval_recall": 0.8066353389360433,
668
+ "eval_runtime": 12018.8462,
669
+ "eval_samples_per_second": 43.311,
670
+ "eval_steps_per_second": 0.451,
671
+ "step": 21690
672
+ }
673
+ ],
674
+ "logging_steps": 200,
675
+ "max_steps": 21690,
676
+ "num_train_epochs": 1,
677
+ "save_steps": 500,
678
+ "total_flos": 9.463065703778611e+17,
679
+ "trial_name": null,
680
+ "trial_params": null
681
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a7863a49c575499f29d569e18d8a200bcbf050c5c13871157c94c46c8f2d6de
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>