File size: 14,270 Bytes
1f3c3f5
 
3c71c8d
52dd92a
3c71c8d
52dd92a
 
 
8cec513
52dd92a
 
 
 
1f3c3f5
 
 
 
3c71c8d
 
 
 
 
 
52dd92a
 
 
 
 
 
 
 
 
 
3c71c8d
 
 
 
 
 
 
 
 
 
 
52dd92a
 
 
 
 
 
 
0dd35c7
52dd92a
 
 
 
 
 
 
 
0dd35c7
52dd92a
 
 
 
 
 
 
 
0dd35c7
52dd92a
 
 
 
 
 
 
 
0dd35c7
52dd92a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0dd35c7
52dd92a
 
 
 
 
 
 
 
0dd35c7
52dd92a
 
 
 
 
 
 
 
0dd35c7
52dd92a
 
 
 
 
 
 
1c33eb8
 
fd5f965
1c33eb8
 
 
 
 
 
 
 
fd5f965
1c33eb8
 
 
 
 
 
3aad5f3
 
 
 
 
 
 
 
 
6fa40bf
 
 
3aad5f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
babf0fd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eea2731
14668fa
 
 
 
 
 
 
 
 
 
 
 
 
fd2c981
eea2731
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cb9d3af
 
 
 
 
19cf0bd
cb9d3af
 
 
 
 
 
 
 
 
 
 
 
 
 
19cf0bd
cb9d3af
 
 
 
 
 
 
 
 
 
 
 
 
 
19cf0bd
 
 
cb9d3af
 
 
 
ad5ca4f
 
 
 
 
 
 
 
2bb0b78
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3437149
 
 
 
 
 
 
 
 
 
 
 
 
 
2bb0b78
 
 
 
 
 
 
 
 
cfbce02
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e7d3e2d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
383f88d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
"""Module for testing the validation module"""

import logging
import unittest
from typing import Optional

import pytest

from axolotl.utils.config import validate_config
from axolotl.utils.dict import DictDefault


class ValidationTest(unittest.TestCase):
    """
    Test the validation module
    """

    _caplog: Optional[pytest.LogCaptureFixture] = None

    @pytest.fixture(autouse=True)
    def inject_fixtures(self, caplog):
        self._caplog = caplog

    def test_load_4bit_deprecate(self):
        cfg = DictDefault(
            {
                "load_4bit": True,
            }
        )

        with pytest.raises(ValueError):
            validate_config(cfg)

    def test_batch_size_unused_warning(self):
        cfg = DictDefault(
            {
                "batch_size": 32,
            }
        )

        with self._caplog.at_level(logging.WARNING):
            validate_config(cfg)
            assert "batch_size is not recommended" in self._caplog.records[0].message

    def test_qlora(self):
        base_cfg = DictDefault(
            {
                "adapter": "qlora",
            }
        )

        cfg = base_cfg | DictDefault(  # pylint: disable=unsupported-binary-operation
            {
                "load_in_8bit": True,
            }
        )

        with pytest.raises(ValueError, match=r".*8bit.*"):
            validate_config(cfg)

        cfg = base_cfg | DictDefault(  # pylint: disable=unsupported-binary-operation
            {
                "gptq": True,
            }
        )

        with pytest.raises(ValueError, match=r".*gptq.*"):
            validate_config(cfg)

        cfg = base_cfg | DictDefault(  # pylint: disable=unsupported-binary-operation
            {
                "load_in_4bit": False,
            }
        )

        with pytest.raises(ValueError, match=r".*4bit.*"):
            validate_config(cfg)

        cfg = base_cfg | DictDefault(  # pylint: disable=unsupported-binary-operation
            {
                "load_in_4bit": True,
            }
        )

        validate_config(cfg)

    def test_qlora_merge(self):
        base_cfg = DictDefault(
            {
                "adapter": "qlora",
                "merge_lora": True,
            }
        )

        cfg = base_cfg | DictDefault(  # pylint: disable=unsupported-binary-operation
            {
                "load_in_8bit": True,
            }
        )

        with pytest.raises(ValueError, match=r".*8bit.*"):
            validate_config(cfg)

        cfg = base_cfg | DictDefault(  # pylint: disable=unsupported-binary-operation
            {
                "gptq": True,
            }
        )

        with pytest.raises(ValueError, match=r".*gptq.*"):
            validate_config(cfg)

        cfg = base_cfg | DictDefault(  # pylint: disable=unsupported-binary-operation
            {
                "load_in_4bit": True,
            }
        )

        with pytest.raises(ValueError, match=r".*4bit.*"):
            validate_config(cfg)

    def test_hf_use_auth_token(self):
        cfg = DictDefault(
            {
                "push_dataset_to_hub": "namespace/repo",
            }
        )

        with pytest.raises(ValueError, match=r".*hf_use_auth_token.*"):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "push_dataset_to_hub": "namespace/repo",
                "hf_use_auth_token": True,
            }
        )
        validate_config(cfg)

    def test_gradient_accumulations_or_batch_size(self):
        cfg = DictDefault(
            {
                "gradient_accumulation_steps": 1,
                "batch_size": 1,
            }
        )

        with pytest.raises(
            ValueError, match=r".*gradient_accumulation_steps or batch_size.*"
        ):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "batch_size": 1,
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "gradient_accumulation_steps": 1,
            }
        )

        validate_config(cfg)

    def test_falcon_fsdp(self):
        regex_exp = r".*FSDP is not supported for falcon models.*"

        # Check for lower-case
        cfg = DictDefault(
            {
                "base_model": "tiiuae/falcon-7b",
                "fsdp": ["full_shard", "auto_wrap"],
            }
        )

        with pytest.raises(ValueError, match=regex_exp):
            validate_config(cfg)

        # Check for upper-case
        cfg = DictDefault(
            {
                "base_model": "Falcon-7b",
                "fsdp": ["full_shard", "auto_wrap"],
            }
        )

        with pytest.raises(ValueError, match=regex_exp):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "base_model": "tiiuae/falcon-7b",
            }
        )

        validate_config(cfg)

    def test_mpt_gradient_checkpointing(self):
        regex_exp = r".*gradient_checkpointing is not supported for MPT models*"

        # Check for lower-case
        cfg = DictDefault(
            {
                "base_model": "mosaicml/mpt-7b",
                "gradient_checkpointing": True,
            }
        )

        with pytest.raises(ValueError, match=regex_exp):
            validate_config(cfg)

    def test_flash_optimum(self):
        cfg = DictDefault(
            {
                "flash_optimum": True,
                "adapter": "lora",
            }
        )

        with self._caplog.at_level(logging.WARNING):
            validate_config(cfg)
            assert any(
                "BetterTransformers probably doesn't work with PEFT adapters"
                in record.message
                for record in self._caplog.records
            )

        cfg = DictDefault(
            {
                "flash_optimum": True,
            }
        )

        with self._caplog.at_level(logging.WARNING):
            validate_config(cfg)
            assert any(
                "probably set bfloat16 or float16" in record.message
                for record in self._caplog.records
            )

        cfg = DictDefault(
            {
                "flash_optimum": True,
                "fp16": True,
            }
        )
        regex_exp = r".*AMP is not supported.*"

        with pytest.raises(ValueError, match=regex_exp):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "flash_optimum": True,
                "bf16": True,
            }
        )
        regex_exp = r".*AMP is not supported.*"

        with pytest.raises(ValueError, match=regex_exp):
            validate_config(cfg)

    def test_adamw_hyperparams(self):
        cfg = DictDefault(
            {
                "optimizer": None,
                "adam_epsilon": 0.0001,
            }
        )

        with self._caplog.at_level(logging.WARNING):
            validate_config(cfg)
            assert any(
                "adamw hyperparameters found, but no adamw optimizer set"
                in record.message
                for record in self._caplog.records
            )

        cfg = DictDefault(
            {
                "optimizer": "adafactor",
                "adam_beta1": 0.0001,
            }
        )

        with self._caplog.at_level(logging.WARNING):
            validate_config(cfg)
            assert any(
                "adamw hyperparameters found, but no adamw optimizer set"
                in record.message
                for record in self._caplog.records
            )

        cfg = DictDefault(
            {
                "optimizer": "adamw_bnb_8bit",
                "adam_beta1": 0.9,
                "adam_beta2": 0.99,
                "adam_epsilon": 0.0001,
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "optimizer": "adafactor",
            }
        )

        validate_config(cfg)

    def test_packing(self):
        cfg = DictDefault(
            {
                "max_packed_sequence_len": 2048,
            }
        )
        with self._caplog.at_level(logging.WARNING):
            validate_config(cfg)
            assert any(
                "max_packed_sequence_len will be deprecated in favor of sample_packing"
                in record.message
                for record in self._caplog.records
            )

        cfg = DictDefault(
            {
                "sample_packing": True,
                "pad_to_sequence_len": None,
            }
        )
        with self._caplog.at_level(logging.WARNING):
            validate_config(cfg)
            assert any(
                "`pad_to_sequence_len: true` is recommended when using sample_packing"
                in record.message
                for record in self._caplog.records
            )

        cfg = DictDefault(
            {
                "max_packed_sequence_len": 2048,
                "sample_packing": True,
            }
        )
        regex_exp = r".*set only one of max_packed_sequence_len \(deprecated soon\) or sample_packing.*"
        with pytest.raises(ValueError, match=regex_exp):
            validate_config(cfg)

    def test_merge_lora_no_bf16_fail(self):
        """
        This is assumed to be run on a CPU machine, so bf16 is not supported.
        """

        cfg = DictDefault(
            {
                "bf16": True,
            }
        )

        with pytest.raises(ValueError, match=r".*AMP is not supported on this GPU*"):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "bf16": True,
                "merge_lora": True,
            }
        )

        validate_config(cfg)

    def test_sharegpt_deprecation(self):
        cfg = DictDefault(
            {"datasets": [{"path": "lorem/ipsum", "type": "sharegpt:chat"}]}
        )
        with self._caplog.at_level(logging.WARNING):
            validate_config(cfg)
            assert any(
                "`type: sharegpt:chat` will soon be deprecated." in record.message
                for record in self._caplog.records
            )
        assert cfg.datasets[0].type == "sharegpt"

        cfg = DictDefault(
            {"datasets": [{"path": "lorem/ipsum", "type": "sharegpt_simple:load_role"}]}
        )
        with self._caplog.at_level(logging.WARNING):
            validate_config(cfg)
            assert any(
                "`type: sharegpt_simple` will soon be deprecated." in record.message
                for record in self._caplog.records
            )
        assert cfg.datasets[0].type == "sharegpt:load_role"

    def test_no_conflict_save_strategy(self):
        cfg = DictDefault(
            {
                "save_strategy": "epoch",
                "save_steps": 10,
            }
        )

        with pytest.raises(
            ValueError, match=r".*save_strategy and save_steps mismatch.*"
        ):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "save_strategy": "no",
                "save_steps": 10,
            }
        )

        with pytest.raises(
            ValueError, match=r".*save_strategy and save_steps mismatch.*"
        ):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "save_strategy": "steps",
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "save_strategy": "steps",
                "save_steps": 10,
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "save_steps": 10,
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "save_strategy": "no",
            }
        )

        validate_config(cfg)

    def test_no_conflict_eval_strategy(self):
        cfg = DictDefault(
            {
                "evaluation_strategy": "epoch",
                "eval_steps": 10,
            }
        )

        with pytest.raises(
            ValueError, match=r".*evaluation_strategy and eval_steps mismatch.*"
        ):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "evaluation_strategy": "no",
                "eval_steps": 10,
            }
        )

        with pytest.raises(
            ValueError, match=r".*evaluation_strategy and eval_steps mismatch.*"
        ):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "evaluation_strategy": "steps",
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "evaluation_strategy": "steps",
                "eval_steps": 10,
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "eval_steps": 10,
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "evaluation_strategy": "no",
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "evaluation_strategy": "epoch",
                "val_set_size": 0,
            }
        )

        with pytest.raises(
            ValueError,
            match=r".*eval_steps and evaluation_strategy are not supported with val_set_size == 0.*",
        ):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "eval_steps": 10,
                "val_set_size": 0,
            }
        )

        with pytest.raises(
            ValueError,
            match=r".*eval_steps and evaluation_strategy are not supported with val_set_size == 0.*",
        ):
            validate_config(cfg)

        cfg = DictDefault(
            {
                "val_set_size": 0,
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "eval_steps": 10,
                "val_set_size": 0.01,
            }
        )

        validate_config(cfg)

        cfg = DictDefault(
            {
                "evaluation_strategy": "epoch",
                "val_set_size": 0.01,
            }
        )

        validate_config(cfg)