File size: 75,486 Bytes
6eaccad |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 |
========================
START TIME: Thu Jul 4 00:05:41 UTC 2024
python3 version = Python 3.10.14
========================
The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.
Token is valid (permission: write).
Your token has been saved to /admin/home/ferdinand_mom/.cache/huggingface/token
Login successful
fatal: Unable to create '/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/.git/index.lock': File exists.
Another git process seems to be running in this repository, e.g.
an editor opened by 'git commit'. Please make sure all processes
are terminated then try again. If it still fails, a git process
may have crashed in this repository earlier:
remove the file manually to continue.
Job status: RUNNING
W0704 00:05:44.480000 140468343650112 torch/distributed/run.py:757]
W0704 00:05:44.480000 140468343650112 torch/distributed/run.py:757] *****************************************
W0704 00:05:44.480000 140468343650112 torch/distributed/run.py:757] Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
W0704 00:05:44.480000 140468343650112 torch/distributed/run.py:757] *****************************************
[default0]:07/04/2024 00:06:03 [WARNING|DP=0|PP=0|TP=0|ip-26-0-164-187]: [Vocab Size Padding] Padded vocab (size: 50257) with 7 dummy tokens (new size: 50264)
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Config:
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Config(general=GeneralArgs(project='bench_cluster',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: run='%date_%jobid',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: seed=42,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: step=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: consumed_train_samples=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: benchmark_csv_path=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: ignore_sanity_checks=True),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: parallelism=ParallelismArgs(dp=1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: pp=1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: tp=8,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: pp_engine=<nanotron.parallel.pipeline_parallel.engine.OneForwardOneBackwardPipelineEngine object at 0x7f672bd00880>,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: tp_mode=<TensorParallelLinearMode.REDUCE_SCATTER: 2>,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: tp_linear_async_communication=False,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: expert_parallel_size=1),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: model=ModelArgs(model_config=LlamaConfig(bos_token_id=1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: eos_token_id=2,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: hidden_act='silu',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: hidden_size=2048,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: initializer_range=0.02,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: intermediate_size=4096,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: is_llama_config=True,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: max_position_embeddings=4096,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: num_attention_heads=32,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: num_hidden_layers=24,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: num_key_value_heads=32,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: pad_token_id=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: pretraining_tp=1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: rms_norm_eps=1e-05,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: rope_scaling=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: rope_theta=10000.0,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: tie_word_embeddings=True,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: use_cache=True,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: vocab_size=50264),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: init_method=RandomInit(std=0.025),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: dtype=torch.bfloat16,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: make_vocab_size_divisible_by=1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: ddp_bucket_cap_mb=25),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: tokenizer=TokenizerArgs(tokenizer_name_or_path='openai-community/gpt2',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: tokenizer_revision=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: tokenizer_max_length=None),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: checkpoints=CheckpointsArgs(checkpoints_path=Path('/dev/null'),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: checkpoint_interval=100000,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: save_initial_state=False,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: resume_checkpoint_path=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: checkpoints_path_is_shared_file_system=False),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: logging=LoggingArgs(log_level='info',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: log_level_replica='info',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: iteration_step_info_interval=1),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: tokens=TokensArgs(sequence_length=4096,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: train_steps=20,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: micro_batch_size=512,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: batch_accumulation_per_replica=2,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: val_check_interval=-1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: limit_val_batches=0,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: limit_test_batches=0),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: optimizer=OptimizerArgs(optimizer_factory=AdamWOptimizerArgs(adam_eps=1e-08,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: adam_beta1=0.9,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: adam_beta2=0.95,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: torch_adam_is_fused=True,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: name='adamW'),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: zero_stage=1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: weight_decay=0.01,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: clip_grad=1.0,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: accumulate_grad_in_fp32=True,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: learning_rate_scheduler=LRSchedulerArgs(learning_rate=0.0001,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: lr_warmup_steps=1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: lr_warmup_style='linear',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: lr_decay_style='linear',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: lr_decay_steps=19,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: lr_decay_starting_step=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: min_decay_lr=1e-05)),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: data_stages=[DatasetStageArgs(name='Training Stage',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: start_training_step=1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: data=DataArgs(dataset=PretrainDatasetsArgs(hf_dataset_or_datasets='roneneldan/TinyStories',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: hf_dataset_splits='train',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: hf_dataset_config_name=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: dataset_processing_num_proc_per_process=64,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: dataset_overwrite_cache=False,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: text_column_name='text'),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: seed=42,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: num_loading_workers=0))],
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: profiler=ProfilerArgs(profiler_export_path=Path('/fsx/ferdinandmom/ferdinand-hf/bench_cluster/results/llama-1B/8_GPUS/dp-1_tp-8_pp-1_mbz-512')),
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: lighteval=None)
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Model Config:
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: LlamaConfig(bos_token_id=1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: eos_token_id=2,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: hidden_act='silu',
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: hidden_size=2048,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: initializer_range=0.02,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: intermediate_size=4096,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: is_llama_config=True,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: max_position_embeddings=4096,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: num_attention_heads=32,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: num_hidden_layers=24,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: num_key_value_heads=32,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: pad_token_id=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: pretraining_tp=1,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: rms_norm_eps=1e-05,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: rope_scaling=None,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: rope_theta=10000.0,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: tie_word_embeddings=True,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: use_cache=True,
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: vocab_size=50264)
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Building model..
[default0]:07/04/2024 00:06:03 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Setting PP block ranks...
[default6]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=6|ip-26-0-164-187]: Local number of parameters: 139M (264.73MiB)
[default6]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=6|ip-26-0-164-187]: [After model building] Memory usage: 290.76MiB. Peak allocated: 317.33MiB Peak reserved: 324.00MiB
[default6]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=6|ip-26-0-164-187]: No checkpoint path provided.
[default5]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=5|ip-26-0-164-187]: Local number of parameters: 139M (264.73MiB)
[default5]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=5|ip-26-0-164-187]: [After model building] Memory usage: 290.76MiB. Peak allocated: 317.33MiB Peak reserved: 324.00MiB
[default5]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=5|ip-26-0-164-187]: No checkpoint path provided.
[default0]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Total number of parameters: 1.11G (2117.88MiB)
[default0]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Local number of parameters: 139M (264.73MiB)
[default0]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: [After model building] Memory usage: 290.76MiB. Peak allocated: 317.33MiB Peak reserved: 324.00MiB
[default0]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: No checkpoint path provided.
[default0]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Parametrizing model parameters using StandardParametrizator
[default0]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: [Optimizer Building] Using LearningRateForSP as learning rate
[default0]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: [ZeRO sharding] Size of optimizer params per rank:
[default0]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: [ZeRO sharding] DP Rank 0 has 139M out of 139M (100.00%) params' optimizer states
[default1]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=1|ip-26-0-164-187]: Local number of parameters: 139M (264.73MiB)
[default1]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=1|ip-26-0-164-187]: [After model building] Memory usage: 290.76MiB. Peak allocated: 317.33MiB Peak reserved: 324.00MiB
[default1]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=1|ip-26-0-164-187]: No checkpoint path provided.
[default7]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=7|ip-26-0-164-187]: Local number of parameters: 139M (264.73MiB)
[default7]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=7|ip-26-0-164-187]: [After model building] Memory usage: 290.76MiB. Peak allocated: 317.33MiB Peak reserved: 324.00MiB
[default7]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=7|ip-26-0-164-187]: No checkpoint path provided.
[default3]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=3|ip-26-0-164-187]: Local number of parameters: 139M (264.73MiB)
[default3]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=3|ip-26-0-164-187]: [After model building] Memory usage: 290.76MiB. Peak allocated: 317.33MiB Peak reserved: 324.00MiB
[default3]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=3|ip-26-0-164-187]: No checkpoint path provided.
[default2]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=2|ip-26-0-164-187]: Local number of parameters: 139M (264.73MiB)
[default2]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=2|ip-26-0-164-187]: [After model building] Memory usage: 290.76MiB. Peak allocated: 317.33MiB Peak reserved: 324.00MiB
[default2]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=2|ip-26-0-164-187]: No checkpoint path provided.
[default4]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=4|ip-26-0-164-187]: Local number of parameters: 139M (264.73MiB)
[default4]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=4|ip-26-0-164-187]: [After model building] Memory usage: 290.76MiB. Peak allocated: 317.33MiB Peak reserved: 324.00MiB
[default4]:07/04/2024 00:06:18 [INFO|DP=0|PP=0|TP=4|ip-26-0-164-187]: No checkpoint path provided.
[default0]:07/04/2024 00:06:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: [Training Plan] Stage Training Stage has 19 remaining training steps and has consumed 0 samples
[default0]:07/04/2024 00:06:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Using `datasets` library
[default0]:07/04/2024 00:06:20 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Loading tokenizer from openai-community/gpt2 and transformers/hf_hub versions ('4.41.2', '0.23.4')
[default0]:07/04/2024 00:06:20 [WARNING|DP=0|PP=0|TP=0|ip-26-0-164-187]: Repo card metadata block was not found. Setting CardData to empty.
[default0]:Repo card metadata block was not found. Setting CardData to empty.
[default0]:07/04/2024 00:06:22 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: [Training Plan] There are 1 training stages
[default0]:07/04/2024 00:06:22 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: [Stage Training Stage] start from step 1
[default0]:07/04/2024 00:06:22 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]:
[default0]:07/04/2024 00:06:22 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: [Start training] datetime: 2024-07-04 00:06:22.734159 | mbs: 512 | grad_accum: 2 | global_batch_size: 1024 | sequence_length: 4096 | train_steps: 20 | start_iteration_step: 0 | consumed_train_samples: 0
[default0]:07/04/2024 00:06:22 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Resuming training from stage Training Stage, it has trained for 0 samples and has 19 remaining train steps
[default0]:07/04/2024 00:06:22 [INFO|DP=0|PP=0|TP=0|ip-26-0-164-187]: Memory usage: 1350.75MiB. Peak allocated 1350.76MiB. Peak reserved: 1384.00MiB
[default4]:Repo card metadata block was not found. Setting CardData to empty.
[default2]:07/04/2024 00:06:22 [WARNING|DP=0|PP=0|TP=2|ip-26-0-164-187]: Repo card metadata block was not found. Setting CardData to empty.
[default4]:07/04/2024 00:06:22 [WARNING|DP=0|PP=0|TP=4|ip-26-0-164-187]: Repo card metadata block was not found. Setting CardData to empty.
[default2]:Repo card metadata block was not found. Setting CardData to empty.
[default7]:07/04/2024 00:06:23 [WARNING|DP=0|PP=0|TP=7|ip-26-0-164-187]: Repo card metadata block was not found. Setting CardData to empty.
[default7]:Repo card metadata block was not found. Setting CardData to empty.
[default6]:07/04/2024 00:06:23 [WARNING|DP=0|PP=0|TP=6|ip-26-0-164-187]: Repo card metadata block was not found. Setting CardData to empty.
[default1]:07/04/2024 00:06:23 [WARNING|DP=0|PP=0|TP=1|ip-26-0-164-187]: Repo card metadata block was not found. Setting CardData to empty.
[default1]:Repo card metadata block was not found. Setting CardData to empty.
[default6]:Repo card metadata block was not found. Setting CardData to empty.
[default5]:07/04/2024 00:06:23 [WARNING|DP=0|PP=0|TP=5|ip-26-0-164-187]: Repo card metadata block was not found. Setting CardData to empty.
[default5]:Repo card metadata block was not found. Setting CardData to empty.
[default3]:Repo card metadata block was not found. Setting CardData to empty.
[default3]:07/04/2024 00:06:23 [WARNING|DP=0|PP=0|TP=3|ip-26-0-164-187]: Repo card metadata block was not found. Setting CardData to empty.
[default4]:[rank4]: Traceback (most recent call last):
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py", line 237, in <module>
[default4]:[rank4]: trainer.train(dataloader)
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 429, in train
[default4]:[rank4]: outputs, loss_avg = self.training_step(dataloader=self.current_dataloader)
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 462, in training_step
[default4]:[rank4]: outputs = self.pipeline_engine.train_batch_iter(
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 278, in train_batch_iter
[default4]:[rank4]: output = self.forward(context=context, state=state, micro_batch=micro_batch, model=model)
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 44, in forward
[default4]:[rank4]: output = model(**micro_batch)
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default4]:[rank4]: return self._call_impl(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default4]:[rank4]: return forward_call(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 891, in forward
[default4]:[rank4]: sharded_logits = self.model(
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default4]:[rank4]: return self._call_impl(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default4]:[rank4]: return forward_call(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 764, in forward
[default4]:[rank4]: return self.forward_with_hidden_states(input_ids=input_ids, input_mask=input_mask)[0]
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 780, in forward_with_hidden_states
[default4]:[rank4]: hidden_encoder_states = encoder_block(**hidden_encoder_states)
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default4]:[rank4]: return self._call_impl(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default4]:[rank4]: return forward_call(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/block.py", line 151, in forward
[default4]:[rank4]: output = self.pp_block(**new_kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default4]:[rank4]: return self._call_impl(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default4]:[rank4]: return forward_call(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 637, in forward
[default4]:[rank4]: hidden_states = self.mlp(hidden_states=hidden_states)["hidden_states"]
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default4]:[rank4]: return self._call_impl(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default4]:[rank4]: return forward_call(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 171, in forward
[default4]:[rank4]: merged_states = self.gate_up_proj(hidden_states)
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default4]:[rank4]: return self._call_impl(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default4]:[rank4]: return forward_call(*args, **kwargs)
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/nn.py", line 87, in forward
[default4]:[rank4]: return column_linear(
[default4]:[rank4]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/functional.py", line 359, in column_linear
[default4]:[rank4]: return F.linear(input, weight, bias)
[default4]:[rank4]: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.00 GiB. GPU has a total capacity of 79.33 GiB of which 3.18 GiB is free. Including non-PyTorch memory, this process has 76.13 GiB memory in use. Of the allocated memory 61.47 GiB is allocated by PyTorch, and 2.93 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
[default1]:[rank1]: Traceback (most recent call last):
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py", line 237, in <module>
[default1]:[rank1]: trainer.train(dataloader)
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 429, in train
[default1]:[rank1]: outputs, loss_avg = self.training_step(dataloader=self.current_dataloader)
[default3]:[rank3]: Traceback (most recent call last):
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py", line 237, in <module>
[default3]:[rank3]: trainer.train(dataloader)
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 462, in training_step
[default1]:[rank1]: outputs = self.pipeline_engine.train_batch_iter(
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 429, in train
[default3]:[rank3]: outputs, loss_avg = self.training_step(dataloader=self.current_dataloader)
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 462, in training_step
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 278, in train_batch_iter
[default1]:[rank1]: output = self.forward(context=context, state=state, micro_batch=micro_batch, model=model)
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 44, in forward
[default1]:[rank1]: output = model(**micro_batch)
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default1]:[rank1]: return self._call_impl(*args, **kwargs)
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default1]:[rank1]: return forward_call(*args, **kwargs)
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 891, in forward
[default1]:[rank1]: sharded_logits = self.model(
[default3]:[rank3]: outputs = self.pipeline_engine.train_batch_iter(
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 278, in train_batch_iter
[default3]:[rank3]: output = self.forward(context=context, state=state, micro_batch=micro_batch, model=model)
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 44, in forward
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default1]:[rank1]: return self._call_impl(*args, **kwargs)
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default1]:[rank1]: return forward_call(*args, **kwargs)
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 764, in forward
[default1]:[rank1]: return self.forward_with_hidden_states(input_ids=input_ids, input_mask=input_mask)[0]
[default3]:[rank3]: output = model(**micro_batch)
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default3]:[rank3]: return self._call_impl(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 780, in forward_with_hidden_states
[default1]:[rank1]: hidden_encoder_states = encoder_block(**hidden_encoder_states)
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default1]:[rank1]: return self._call_impl(*args, **kwargs)
[default3]:[rank3]: return forward_call(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 891, in forward
[default3]:[rank3]: sharded_logits = self.model(
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default3]:[rank3]: return self._call_impl(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default3]:[rank3]: return forward_call(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 764, in forward
[default3]:[rank3]: return self.forward_with_hidden_states(input_ids=input_ids, input_mask=input_mask)[0]
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 780, in forward_with_hidden_states
[default3]:[rank3]: hidden_encoder_states = encoder_block(**hidden_encoder_states)
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default3]:[rank3]: return self._call_impl(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default3]:[rank3]: return forward_call(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/block.py", line 151, in forward
[default3]:[rank3]: output = self.pp_block(**new_kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default3]:[rank3]: return self._call_impl(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default3]:[rank3]: return forward_call(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 637, in forward
[default3]:[rank3]: hidden_states = self.mlp(hidden_states=hidden_states)["hidden_states"]
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default3]:[rank3]: return self._call_impl(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default0]:[rank0]: Traceback (most recent call last):
[default3]:[rank3]: return forward_call(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 171, in forward
[default3]:[rank3]: merged_states = self.gate_up_proj(hidden_states)
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default7]:[rank7]: Traceback (most recent call last):
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py", line 237, in <module>
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default1]:[rank1]: return forward_call(*args, **kwargs)
[default3]:[rank3]: return self._call_impl(*args, **kwargs)
[default7]:[rank7]: trainer.train(dataloader)
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/block.py", line 151, in forward
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 429, in train
[default7]:[rank7]: outputs, loss_avg = self.training_step(dataloader=self.current_dataloader)
[default1]:[rank1]: output = self.pp_block(**new_kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 462, in training_step
[default3]:[rank3]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py", line 237, in <module>
[default0]:[rank0]: trainer.train(dataloader)
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 429, in train
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default7]:[rank7]: outputs = self.pipeline_engine.train_batch_iter(
[default0]:[rank0]: outputs, loss_avg = self.training_step(dataloader=self.current_dataloader)
[default3]:[rank3]: return forward_call(*args, **kwargs)
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/nn.py", line 87, in forward
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 278, in train_batch_iter
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 462, in training_step
[default0]:[rank0]: outputs = self.pipeline_engine.train_batch_iter(
[default1]:[rank1]: return self._call_impl(*args, **kwargs)
[default3]:[rank3]: return column_linear(
[default3]:[rank3]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/functional.py", line 359, in column_linear
[default7]:[rank7]: output = self.forward(context=context, state=state, micro_batch=micro_batch, model=model)
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 278, in train_batch_iter
[default0]:[rank0]: output = self.forward(context=context, state=state, micro_batch=micro_batch, model=model)
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 44, in forward
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 44, in forward
[default0]:[rank0]: output = model(**micro_batch)
[default1]:[rank1]: return forward_call(*args, **kwargs)
[default7]:[rank7]: output = model(**micro_batch)
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default3]:[rank3]: return F.linear(input, weight, bias)
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 637, in forward
[default7]:[rank7]: return self._call_impl(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default7]:[rank7]: return forward_call(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 891, in forward
[default1]:[rank1]: hidden_states = self.mlp(hidden_states=hidden_states)["hidden_states"]
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default0]:[rank0]: return self._call_impl(*args, **kwargs)
[default7]:[rank7]: sharded_logits = self.model(
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default3]:[rank3]: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.00 GiB. GPU has a total capacity of 79.33 GiB of which 3.18 GiB is free. Including non-PyTorch memory, this process has 76.13 GiB memory in use. Of the allocated memory 61.47 GiB is allocated by PyTorch, and 2.93 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
[default1]:[rank1]: return self._call_impl(*args, **kwargs)
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default0]:[rank0]: return forward_call(*args, **kwargs)
[default7]:[rank7]: return self._call_impl(*args, **kwargs)
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 891, in forward
[default0]:[rank0]: sharded_logits = self.model(
[default1]:[rank1]: return forward_call(*args, **kwargs)
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 171, in forward
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default0]:[rank0]: return self._call_impl(*args, **kwargs)
[default1]:[rank1]: merged_states = self.gate_up_proj(hidden_states)
[default7]:[rank7]: return forward_call(*args, **kwargs)
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default1]:[rank1]: return self._call_impl(*args, **kwargs)
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default0]:[rank0]: return forward_call(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 764, in forward
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 764, in forward
[default1]:[rank1]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default1]:[rank1]: return forward_call(*args, **kwargs)
[default0]:[rank0]: return self.forward_with_hidden_states(input_ids=input_ids, input_mask=input_mask)[0]
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 780, in forward_with_hidden_states
[default7]:[rank7]: return self.forward_with_hidden_states(input_ids=input_ids, input_mask=input_mask)[0]
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/nn.py", line 87, in forward
[default0]:[rank0]: hidden_encoder_states = encoder_block(**hidden_encoder_states)
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 780, in forward_with_hidden_states
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default1]:[rank1]: return column_linear(
[default1]:[rank1]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/functional.py", line 359, in column_linear
[default0]:[rank0]: return self._call_impl(*args, **kwargs)
[default7]:[rank7]: hidden_encoder_states = encoder_block(**hidden_encoder_states)
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default1]:[rank1]: return F.linear(input, weight, bias)
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default0]:[rank0]: return forward_call(*args, **kwargs)
[default7]:[rank7]: return self._call_impl(*args, **kwargs)
[default1]:[rank1]: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.00 GiB. GPU has a total capacity of 79.33 GiB of which 3.18 GiB is free. Including non-PyTorch memory, this process has 76.13 GiB memory in use. Of the allocated memory 61.47 GiB is allocated by PyTorch, and 2.93 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default7]:[rank7]: return forward_call(*args, **kwargs)
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/block.py", line 151, in forward
[default0]:[rank0]: output = self.pp_block(**new_kwargs)
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default0]:[rank0]: return self._call_impl(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/block.py", line 151, in forward
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default7]:[rank7]: output = self.pp_block(**new_kwargs)
[default0]:[rank0]: return forward_call(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default7]:[rank7]: return self._call_impl(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 637, in forward
[default7]:[rank7]: return forward_call(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 637, in forward
[default7]:[rank7]: hidden_states = self.mlp(hidden_states=hidden_states)["hidden_states"]
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default7]:[rank7]: return self._call_impl(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default0]:[rank0]: hidden_states = self.mlp(hidden_states=hidden_states)["hidden_states"]
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default7]:[rank7]: return forward_call(*args, **kwargs)
[default0]:[rank0]: return self._call_impl(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 171, in forward
[default7]:[rank7]: merged_states = self.gate_up_proj(hidden_states)
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default7]:[rank7]: return self._call_impl(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default7]:[rank7]: return forward_call(*args, **kwargs)
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/nn.py", line 87, in forward
[default0]:[rank0]: return forward_call(*args, **kwargs)
[default7]:[rank7]: return column_linear(
[default7]:[rank7]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/functional.py", line 359, in column_linear
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 171, in forward
[default0]:[rank0]: merged_states = self.gate_up_proj(hidden_states)
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default0]:[rank0]: return self._call_impl(*args, **kwargs)
[default0]:[rank0]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default7]:[rank7]: return F.linear(input, weight, bias)
[default7]:[rank7]: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.00 GiB. GPU has a total capacity of 79.33 GiB of which 3.89 GiB is free. Including non-PyTorch memory, this process has 75.43 GiB memory in use. Of the allocated memory 61.47 GiB is allocated by PyTorch, and 2.93 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
[default0]:[rank0]: return forward_call(*args, **kwargs)
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/nn.py", line 87, in forward
[default0]:[rank0]: return column_linear(
[default0]:[rank0]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/functional.py", line 359, in column_linear
[default0]:[rank0]: return F.linear(input, weight, bias)
[default0]:[rank0]: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.00 GiB. GPU
[default6]:[rank6]: Traceback (most recent call last):
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py", line 237, in <module>
[default5]:[rank5]: Traceback (most recent call last):
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py", line 237, in <module>
[default6]:[rank6]: trainer.train(dataloader)
[default2]:[rank2]: Traceback (most recent call last):
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py", line 237, in <module>
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 429, in train
[default5]:[rank5]: trainer.train(dataloader)
[default6]:[rank6]: outputs, loss_avg = self.training_step(dataloader=self.current_dataloader)
[default2]:[rank2]: trainer.train(dataloader)
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 429, in train
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 462, in training_step
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 429, in train
[default5]:[rank5]: outputs, loss_avg = self.training_step(dataloader=self.current_dataloader)
[default2]:[rank2]: outputs, loss_avg = self.training_step(dataloader=self.current_dataloader)
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 462, in training_step
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/trainer.py", line 462, in training_step
[default2]:[rank2]: outputs = self.pipeline_engine.train_batch_iter(
[default6]:[rank6]: outputs = self.pipeline_engine.train_batch_iter(
[default5]:[rank5]: outputs = self.pipeline_engine.train_batch_iter(
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 278, in train_batch_iter
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 278, in train_batch_iter
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 278, in train_batch_iter
[default5]:[rank5]: output = self.forward(context=context, state=state, micro_batch=micro_batch, model=model)
[default6]:[rank6]: output = self.forward(context=context, state=state, micro_batch=micro_batch, model=model)
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 44, in forward
[default2]:[rank2]: output = self.forward(context=context, state=state, micro_batch=micro_batch, model=model)
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 44, in forward
[default5]:[rank5]: output = model(**micro_batch)
[default6]:[rank6]: output = model(**micro_batch)
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/engine.py", line 44, in forward
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default2]:[rank2]: output = model(**micro_batch)
[default6]:[rank6]: return self._call_impl(*args, **kwargs)
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default5]:[rank5]: return self._call_impl(*args, **kwargs)
[default2]:[rank2]: return self._call_impl(*args, **kwargs)
[default6]:[rank6]: return forward_call(*args, **kwargs)
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 891, in forward
[default5]:[rank5]: return forward_call(*args, **kwargs)
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 891, in forward
[default6]:[rank6]: sharded_logits = self.model(
[default2]:[rank2]: return forward_call(*args, **kwargs)
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 891, in forward
[default5]:[rank5]: sharded_logits = self.model(
[default2]:[rank2]: sharded_logits = self.model(
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default5]:[rank5]: return self._call_impl(*args, **kwargs)
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default6]:[rank6]: return self._call_impl(*args, **kwargs)
[default5]:[rank5]: return forward_call(*args, **kwargs)
[default2]:[rank2]: return self._call_impl(*args, **kwargs)
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 764, in forward
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default6]:[rank6]: return forward_call(*args, **kwargs)
[default2]:[rank2]: return forward_call(*args, **kwargs)
[default5]:[rank5]: return self.forward_with_hidden_states(input_ids=input_ids, input_mask=input_mask)[0]
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 764, in forward
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 780, in forward_with_hidden_states
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 764, in forward
[default2]:[rank2]: return self.forward_with_hidden_states(input_ids=input_ids, input_mask=input_mask)[0]
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 780, in forward_with_hidden_states
[default5]:[rank5]: hidden_encoder_states = encoder_block(**hidden_encoder_states)
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default6]:[rank6]: return self.forward_with_hidden_states(input_ids=input_ids, input_mask=input_mask)[0]
[default2]:[rank2]: hidden_encoder_states = encoder_block(**hidden_encoder_states)
[default5]:[rank5]: return self._call_impl(*args, **kwargs)
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 780, in forward_with_hidden_states
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default2]:[rank2]: return self._call_impl(*args, **kwargs)
[default5]:[rank5]: return forward_call(*args, **kwargs)
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/block.py", line 151, in forward
[default2]:[rank2]: return forward_call(*args, **kwargs)
[default5]:[rank5]: output = self.pp_block(**new_kwargs)
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/block.py", line 151, in forward
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default6]:[rank6]: hidden_encoder_states = encoder_block(**hidden_encoder_states)
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default6]:[rank6]: return self._call_impl(*args, **kwargs)
[default5]:[rank5]: return self._call_impl(*args, **kwargs)
[default2]:[rank2]: output = self.pp_block(**new_kwargs)
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default6]:[rank6]: return forward_call(*args, **kwargs)
[default2]:[rank2]: return self._call_impl(*args, **kwargs)
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/pipeline_parallel/block.py", line 151, in forward
[default6]:[rank6]: output = self.pp_block(**new_kwargs)
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default5]:[rank5]: return forward_call(*args, **kwargs)
[default2]:[rank2]: return forward_call(*args, **kwargs)
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 637, in forward
[default6]:[rank6]: return self._call_impl(*args, **kwargs)
[default2]:[rank2]: hidden_states = self.mlp(hidden_states=hidden_states)["hidden_states"]
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 637, in forward
[default5]:[rank5]: hidden_states = self.mlp(hidden_states=hidden_states)["hidden_states"]
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default5]:[rank5]: return self._call_impl(*args, **kwargs)
[default6]:[rank6]: return forward_call(*args, **kwargs)
[default2]:[rank2]: return self._call_impl(*args, **kwargs)
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 637, in forward
[default2]:[rank2]: return forward_call(*args, **kwargs)
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 171, in forward
[default5]:[rank5]: return forward_call(*args, **kwargs)
[default6]:[rank6]: hidden_states = self.mlp(hidden_states=hidden_states)["hidden_states"]
[default2]:[rank2]: merged_states = self.gate_up_proj(hidden_states)
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 171, in forward
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default5]:[rank5]: merged_states = self.gate_up_proj(hidden_states)
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default2]:[rank2]: return self._call_impl(*args, **kwargs)
[default5]:[rank5]: return self._call_impl(*args, **kwargs)
[default5]:[rank5]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default6]:[rank6]: return self._call_impl(*args, **kwargs)
[default2]:[rank2]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default5]:[rank5]: return forward_call(*args, **kwargs)
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/nn.py", line 87, in forward
[default5]:[rank5]: return column_linear(
[default2]:[rank2]: return forward_call(*args, **kwargs)
[default5]:[rank5]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/functional.py", line 359, in column_linear
[default6]:[rank6]: return forward_call(*args, **kwargs)
[default5]:[rank5]: return F.linear(input, weight, bias)
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/nn.py", line 87, in forward
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/models/llama.py", line 171, in forward
[default5]:[rank5]: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.00 GiB. GPU has a total capacity of 79.33 GiB of which 3.18 GiB is free. Including non-PyTorch memory, this process has 76.13 GiB memory in use. Of the allocated memory 61.47 GiB is allocated by PyTorch, and 2.93 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
[default6]:[rank6]: merged_states = self.gate_up_proj(hidden_states)
[default2]:[rank2]: return column_linear(
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
[default2]:[rank2]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/functional.py", line 359, in column_linear
[default2]:[rank2]: return F.linear(input, weight, bias)
[default6]:[rank6]: return self._call_impl(*args, **kwargs)
[default6]:[rank6]: File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
[default2]:[rank2]: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.00 GiB. GPU has a total capacity of 79.33 GiB of which 3.18 GiB is free. Including non-PyTorch memory, this process has 76.13 GiB memory in use. Of the allocated memory 61.47 GiB is allocated by PyTorch, and 2.93 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
[default6]:[rank6]: return forward_call(*args, **kwargs)
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/nn.py", line 87, in forward
[default6]:[rank6]: return column_linear(
[default6]:[rank6]: File "/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/src/nanotron/parallel/tensor_parallel/functional.py", line 359, in column_linear
[default6]:[rank6]: return F.linear(input, weight, bias)
[default6]:[rank6]: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.00 GiB. GPU has a total capacity of 79.33 GiB of which 3.18 GiB is free. Including non-PyTorch memory, this process has 76.13 GiB memory in use. Of the allocated memory 61.47 GiB is allocated by PyTorch, and 2.93 GiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
W0704 00:06:34.768000 140468343650112 torch/distributed/elastic/multiprocessing/api.py:851] Sending process 38624 closing signal SIGTERM
E0704 00:06:35.390000 140468343650112 torch/distributed/elastic/multiprocessing/api.py:826] failed (exitcode: 1) local_rank: 0 (pid: 38618) of binary: /fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/bin/python3.10
Traceback (most recent call last):
File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/bin/torchrun", line 8, in <module>
sys.exit(main())
File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 347, in wrapper
return f(*args, **kwargs)
File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/run.py", line 879, in main
run(args)
File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/run.py", line 870, in run
elastic_launch(
File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 132, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
File "/fsx/ferdinandmom/miniforge3/envs/env-bench-cluster/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 263, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
============================================================
/fsx/ferdinandmom/ferdinand-hf/bench_cluster/nanotron/run_train.py FAILED
------------------------------------------------------------
Failures:
[1]:
time : 2024-07-04_00:06:34
host : ip-26-0-164-187.ec2.internal
rank : 1 (local_rank: 1)
exitcode : 1 (pid: 38619)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[2]:
time : 2024-07-04_00:06:34
host : ip-26-0-164-187.ec2.internal
rank : 2 (local_rank: 2)
exitcode : 1 (pid: 38620)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[3]:
time : 2024-07-04_00:06:34
host : ip-26-0-164-187.ec2.internal
rank : 3 (local_rank: 3)
exitcode : 1 (pid: 38621)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[4]:
time : 2024-07-04_00:06:34
host : ip-26-0-164-187.ec2.internal
rank : 4 (local_rank: 4)
exitcode : 1 (pid: 38622)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[5]:
time : 2024-07-04_00:06:34
host : ip-26-0-164-187.ec2.internal
rank : 5 (local_rank: 5)
exitcode : 1 (pid: 38623)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
[6]:
time : 2024-07-04_00:06:34
host : ip-26-0-164-187.ec2.internal
rank : 7 (local_rank: 7)
exitcode : 1 (pid: 38625)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
time : 2024-07-04_00:06:34
host : ip-26-0-164-187.ec2.internal
rank : 0 (local_rank: 0)
exitcode : 1 (pid: 38618)
error_file: <N/A>
traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
============================================================
srun: error: ip-26-0-164-187: task 0: Exited with exit code 1
Consider using `hf_transfer` for faster uploads. This solution comes with some limitations. See https://huggingface.co/docs/huggingface_hub/hf_transfer for more details.
|