File size: 83,390 Bytes
a1d66ca |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 |
[2024-02-01 14:20:07,768] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-02-01 14:20:09,368] [WARNING] [runner.py:202:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only.
[2024-02-01 14:20:09,369] [INFO] [runner.py:568:main] cmd = /home/lirenhao/anaconda3/envs/llama_factory/bin/python -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbMCwgMSwgMiwgM119 --master_addr=127.0.0.1 --master_port=2345 --enable_each_rank_log=None /home/lirenhao/projects/LLaMA-Factory/src/train_bash.py --deepspeed ds_config.json --stage sft --model_name_or_path /home/lirenhao/pretrained_models/internlm2-chat-7b/ --do_train --dataset cpsycoun --template intern2 --finetuning_type full --lora_target wqkv --output_dir /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9 --overwrite_cache --overwrite_output_dir --per_device_train_batch_size 4 --gradient_accumulation_steps 28 --lr_scheduler_type cosine --logging_steps 10 --save_steps 21 --learning_rate 1e-6 --num_train_epochs 9.0 --plot_loss --fp16
[2024-02-01 14:20:12,819] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-02-01 14:20:14,435] [INFO] [launch.py:145:main] WORLD INFO DICT: {'localhost': [0, 1, 2, 3]}
[2024-02-01 14:20:14,436] [INFO] [launch.py:151:main] nnodes=1, num_local_procs=4, node_rank=0
[2024-02-01 14:20:14,436] [INFO] [launch.py:162:main] global_rank_mapping=defaultdict(<class 'list'>, {'localhost': [0, 1, 2, 3]})
[2024-02-01 14:20:14,436] [INFO] [launch.py:163:main] dist_world_size=4
[2024-02-01 14:20:14,436] [INFO] [launch.py:165:main] Setting CUDA_VISIBLE_DEVICES=0,1,2,3
[2024-02-01 14:20:19,797] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-02-01 14:20:20,069] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-02-01 14:20:20,128] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-02-01 14:20:20,157] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-02-01 14:20:22,839] [INFO] [comm.py:637:init_distributed] cdb=None
[2024-02-01 14:20:23,347] [INFO] [comm.py:637:init_distributed] cdb=None
[2024-02-01 14:20:23,364] [INFO] [comm.py:637:init_distributed] cdb=None
[2024-02-01 14:20:23,375] [INFO] [comm.py:637:init_distributed] cdb=None
[2024-02-01 14:20:23,376] [INFO] [comm.py:668:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
02/01/2024 14:20:24 - INFO - llmtuner.hparams.parser - Process rank: 2, device: cuda:2, n_gpu: 1
distributed training: True, compute dtype: torch.float16
02/01/2024 14:20:24 - INFO - llmtuner.hparams.parser - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_persistent_workers=False,
dataloader_pin_memory=True,
ddp_backend=None,
ddp_broadcast_buffers=None,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=ds_config.json,
disable_tqdm=False,
dispatch_batches=None,
do_eval=False,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=no,
fp16=True,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_config=None,
generation_max_length=None,
generation_num_beams=None,
gradient_accumulation_steps=28,
gradient_checkpointing=False,
gradient_checkpointing_kwargs=None,
greater_is_better=None,
group_by_length=False,
half_precision_backend=auto,
hub_always_push=False,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
include_num_input_tokens_seen=False,
include_tokens_per_second=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=1e-06,
length_column_name=length,
load_best_model_at_end=False,
local_rank=2,
log_level=passive,
log_level_replica=warning,
log_on_each_node=True,
logging_dir=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/runs/Feb01_14-20-22_siat-a100-4-02,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=10,
logging_strategy=steps,
lr_scheduler_kwargs={},
lr_scheduler_type=cosine,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
neftune_noise_alpha=None,
no_cuda=False,
num_train_epochs=9.0,
optim=adamw_torch,
optim_args=None,
output_dir=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=8,
per_device_train_batch_size=4,
predict_with_generate=False,
prediction_loss_only=False,
push_to_hub=False,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=[],
resume_from_checkpoint=None,
run_name=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9,
save_on_each_node=False,
save_only_model=False,
save_safetensors=True,
save_steps=21,
save_strategy=steps,
save_total_limit=None,
seed=42,
skip_memory_metrics=True,
sortish_sampler=False,
split_batches=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_cpu=False,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
)
02/01/2024 14:20:24 - INFO - llmtuner.hparams.parser - Process rank: 0, device: cuda:0, n_gpu: 1
distributed training: True, compute dtype: torch.float16
02/01/2024 14:20:24 - INFO - llmtuner.hparams.parser - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_persistent_workers=False,
dataloader_pin_memory=True,
ddp_backend=None,
ddp_broadcast_buffers=None,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=ds_config.json,
disable_tqdm=False,
dispatch_batches=None,
do_eval=False,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=no,
fp16=True,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_config=None,
generation_max_length=None,
generation_num_beams=None,
gradient_accumulation_steps=28,
gradient_checkpointing=False,
gradient_checkpointing_kwargs=None,
greater_is_better=None,
group_by_length=False,
half_precision_backend=auto,
hub_always_push=False,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
include_num_input_tokens_seen=False,
include_tokens_per_second=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=1e-06,
length_column_name=length,
load_best_model_at_end=False,
local_rank=0,
log_level=passive,
log_level_replica=warning,
log_on_each_node=True,
logging_dir=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/runs/Feb01_14-20-23_siat-a100-4-02,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=10,
logging_strategy=steps,
lr_scheduler_kwargs={},
lr_scheduler_type=cosine,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
neftune_noise_alpha=None,
no_cuda=False,
num_train_epochs=9.0,
optim=adamw_torch,
optim_args=None,
output_dir=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=8,
per_device_train_batch_size=4,
predict_with_generate=False,
prediction_loss_only=False,
push_to_hub=False,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=[],
resume_from_checkpoint=None,
run_name=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9,
save_on_each_node=False,
save_only_model=False,
save_safetensors=True,
save_steps=21,
save_strategy=steps,
save_total_limit=None,
seed=42,
skip_memory_metrics=True,
sortish_sampler=False,
split_batches=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_cpu=False,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
)
[INFO|tokenization_utils_base.py:2025] 2024-02-01 14:20:24,513 >> loading file ./tokenizer.model
[INFO|tokenization_utils_base.py:2025] 2024-02-01 14:20:24,513 >> loading file added_tokens.json
[INFO|tokenization_utils_base.py:2025] 2024-02-01 14:20:24,513 >> loading file special_tokens_map.json
[INFO|tokenization_utils_base.py:2025] 2024-02-01 14:20:24,513 >> loading file tokenizer_config.json
[INFO|tokenization_utils_base.py:2025] 2024-02-01 14:20:24,513 >> loading file tokenizer.json
[INFO|configuration_utils.py:727] 2024-02-01 14:20:24,850 >> loading configuration file /home/lirenhao/pretrained_models/internlm2-chat-7b/config.json
[INFO|configuration_utils.py:727] 2024-02-01 14:20:24,852 >> loading configuration file /home/lirenhao/pretrained_models/internlm2-chat-7b/config.json
[INFO|configuration_utils.py:792] 2024-02-01 14:20:24,854 >> Model config InternLM2Config {
"_name_or_path": "/home/lirenhao/pretrained_models/internlm2-chat-7b/",
"architectures": [
"InternLM2ForCausalLM"
],
"attn_implementation": "eager",
"auto_map": {
"AutoConfig": "configuration_internlm2.InternLM2Config",
"AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
"AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
},
"bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "internlm2",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 2,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 2.0,
"type": "dynamic"
},
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.1",
"use_cache": true,
"vocab_size": 92544
}
[INFO|modeling_utils.py:3475] 2024-02-01 14:20:24,903 >> loading weights file /home/lirenhao/pretrained_models/internlm2-chat-7b/pytorch_model.bin.index.json
[INFO|modeling_utils.py:1428] 2024-02-01 14:20:24,903 >> Instantiating InternLM2ForCausalLM model under default dtype torch.float16.
[INFO|configuration_utils.py:826] 2024-02-01 14:20:24,905 >> Generate config GenerationConfig {
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 2
}
02/01/2024 14:20:24 - INFO - llmtuner.hparams.parser - Process rank: 1, device: cuda:1, n_gpu: 1
distributed training: True, compute dtype: torch.float16
02/01/2024 14:20:24 - INFO - llmtuner.hparams.parser - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_persistent_workers=False,
dataloader_pin_memory=True,
ddp_backend=None,
ddp_broadcast_buffers=None,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=ds_config.json,
disable_tqdm=False,
dispatch_batches=None,
do_eval=False,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=no,
fp16=True,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_config=None,
generation_max_length=None,
generation_num_beams=None,
gradient_accumulation_steps=28,
gradient_checkpointing=False,
gradient_checkpointing_kwargs=None,
greater_is_better=None,
group_by_length=False,
half_precision_backend=auto,
hub_always_push=False,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
include_num_input_tokens_seen=False,
include_tokens_per_second=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=1e-06,
length_column_name=length,
load_best_model_at_end=False,
local_rank=1,
log_level=passive,
log_level_replica=warning,
log_on_each_node=True,
logging_dir=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/runs/Feb01_14-20-23_siat-a100-4-02,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=10,
logging_strategy=steps,
lr_scheduler_kwargs={},
lr_scheduler_type=cosine,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
neftune_noise_alpha=None,
no_cuda=False,
num_train_epochs=9.0,
optim=adamw_torch,
optim_args=None,
output_dir=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=8,
per_device_train_batch_size=4,
predict_with_generate=False,
prediction_loss_only=False,
push_to_hub=False,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=[],
resume_from_checkpoint=None,
run_name=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9,
save_on_each_node=False,
save_only_model=False,
save_safetensors=True,
save_steps=21,
save_strategy=steps,
save_total_limit=None,
seed=42,
skip_memory_metrics=True,
sortish_sampler=False,
split_batches=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_cpu=False,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
)
02/01/2024 14:20:24 - INFO - llmtuner.hparams.parser - Process rank: 3, device: cuda:3, n_gpu: 1
distributed training: True, compute dtype: torch.float16
02/01/2024 14:20:24 - INFO - llmtuner.hparams.parser - Training/evaluation parameters Seq2SeqTrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_persistent_workers=False,
dataloader_pin_memory=True,
ddp_backend=None,
ddp_broadcast_buffers=None,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=ds_config.json,
disable_tqdm=False,
dispatch_batches=None,
do_eval=False,
do_predict=False,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=no,
fp16=True,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
generation_config=None,
generation_max_length=None,
generation_num_beams=None,
gradient_accumulation_steps=28,
gradient_checkpointing=False,
gradient_checkpointing_kwargs=None,
greater_is_better=None,
group_by_length=False,
half_precision_backend=auto,
hub_always_push=False,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
include_num_input_tokens_seen=False,
include_tokens_per_second=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=1e-06,
length_column_name=length,
load_best_model_at_end=False,
local_rank=3,
log_level=passive,
log_level_replica=warning,
log_on_each_node=True,
logging_dir=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/runs/Feb01_14-20-23_siat-a100-4-02,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=10,
logging_strategy=steps,
lr_scheduler_kwargs={},
lr_scheduler_type=cosine,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
neftune_noise_alpha=None,
no_cuda=False,
num_train_epochs=9.0,
optim=adamw_torch,
optim_args=None,
output_dir=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=8,
per_device_train_batch_size=4,
predict_with_generate=False,
prediction_loss_only=False,
push_to_hub=False,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=[],
resume_from_checkpoint=None,
run_name=/home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9,
save_on_each_node=False,
save_only_model=False,
save_safetensors=True,
save_steps=21,
save_strategy=steps,
save_total_limit=None,
seed=42,
skip_memory_metrics=True,
sortish_sampler=False,
split_batches=False,
tf32=None,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_cpu=False,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
)
Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s]/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
return self.fget.__get__(instance, owner)()
Loading checkpoint shards: 12%|█▎ | 1/8 [00:00<00:03, 2.33it/s]
Loading checkpoint shards: 25%|██▌ | 2/8 [00:00<00:02, 2.20it/s]
Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s]/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
return self.fget.__get__(instance, owner)()
Loading checkpoint shards: 38%|███▊ | 3/8 [00:01<00:01, 2.74it/s]
Loading checkpoint shards: 50%|█████ | 4/8 [00:01<00:01, 3.09it/s]
Loading checkpoint shards: 12%|█▎ | 1/8 [00:00<00:02, 2.62it/s]
Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s]/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
return self.fget.__get__(instance, owner)()
Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s]/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
return self.fget.__get__(instance, owner)()
Loading checkpoint shards: 62%|██████▎ | 5/8 [00:01<00:00, 3.30it/s]
Loading checkpoint shards: 25%|██▌ | 2/8 [00:00<00:01, 3.18it/s]
Loading checkpoint shards: 12%|█▎ | 1/8 [00:00<00:01, 3.71it/s]
Loading checkpoint shards: 12%|█▎ | 1/8 [00:00<00:01, 4.09it/s]
Loading checkpoint shards: 75%|███████▌ | 6/8 [00:01<00:00, 3.45it/s]
Loading checkpoint shards: 25%|██▌ | 2/8 [00:00<00:01, 4.62it/s]
Loading checkpoint shards: 38%|███▊ | 3/8 [00:00<00:01, 3.42it/s]
Loading checkpoint shards: 25%|██▌ | 2/8 [00:00<00:01, 3.69it/s]
Loading checkpoint shards: 38%|███▊ | 3/8 [00:00<00:01, 4.86it/s]
Loading checkpoint shards: 88%|████████▊ | 7/8 [00:02<00:00, 3.56it/s]
Loading checkpoint shards: 50%|█████ | 4/8 [00:01<00:01, 3.53it/s]
Loading checkpoint shards: 38%|███▊ | 3/8 [00:00<00:01, 3.68it/s]
Loading checkpoint shards: 50%|█████ | 4/8 [00:00<00:00, 4.94it/s]
Loading checkpoint shards: 100%|██████████| 8/8 [00:02<00:00, 3.63it/s]
Loading checkpoint shards: 100%|██████████| 8/8 [00:02<00:00, 3.23it/s]
02/01/2024 14:20:35 - INFO - llmtuner.model.patcher - Gradient checkpointing enabled.
02/01/2024 14:20:35 - INFO - llmtuner.model.adapter - Fine-tuning method: Full
Loading checkpoint shards: 62%|██████▎ | 5/8 [00:01<00:00, 3.51it/s]
Loading checkpoint shards: 50%|█████ | 4/8 [00:01<00:01, 3.58it/s]
Loading checkpoint shards: 62%|██████▎ | 5/8 [00:01<00:00, 4.71it/s]
Loading checkpoint shards: 75%|███████▌ | 6/8 [00:01<00:00, 4.47it/s]
Loading checkpoint shards: 75%|███████▌ | 6/8 [00:01<00:00, 3.51it/s]
Loading checkpoint shards: 62%|██████▎ | 5/8 [00:01<00:00, 3.53it/s]
Loading checkpoint shards: 88%|████████▊ | 7/8 [00:01<00:00, 4.44it/s]
Loading checkpoint shards: 88%|████████▊ | 7/8 [00:02<00:00, 3.54it/s]
Loading checkpoint shards: 75%|███████▌ | 6/8 [00:01<00:00, 3.52it/s]
Loading checkpoint shards: 100%|██████████| 8/8 [00:01<00:00, 4.37it/s]
Loading checkpoint shards: 100%|██████████| 8/8 [00:01<00:00, 4.51it/s]
02/01/2024 14:20:36 - INFO - llmtuner.model.patcher - Gradient checkpointing enabled.
02/01/2024 14:20:36 - INFO - llmtuner.model.adapter - Fine-tuning method: Full
Loading checkpoint shards: 100%|██████████| 8/8 [00:02<00:00, 3.48it/s]
Loading checkpoint shards: 100%|██████████| 8/8 [00:02<00:00, 3.43it/s]
[INFO|modeling_utils.py:4352] 2024-02-01 14:20:36,242 >> All model checkpoint weights were used when initializing InternLM2ForCausalLM.
[INFO|modeling_utils.py:4360] 2024-02-01 14:20:36,242 >> All the weights of InternLM2ForCausalLM were initialized from the model checkpoint at /home/lirenhao/pretrained_models/internlm2-chat-7b/.
If your task is similar to the task the model of the checkpoint was trained on, you can already use InternLM2ForCausalLM for predictions without further training.
[INFO|configuration_utils.py:779] 2024-02-01 14:20:36,247 >> loading configuration file /home/lirenhao/pretrained_models/internlm2-chat-7b/generation_config.json
[INFO|configuration_utils.py:826] 2024-02-01 14:20:36,248 >> Generate config GenerationConfig {
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 2
}
02/01/2024 14:20:36 - INFO - llmtuner.model.patcher - Gradient checkpointing enabled.
02/01/2024 14:20:36 - INFO - llmtuner.model.adapter - Fine-tuning method: Full
Loading checkpoint shards: 88%|████████▊ | 7/8 [00:01<00:00, 3.43it/s]
Loading checkpoint shards: 100%|██████████| 8/8 [00:02<00:00, 3.42it/s]
Loading checkpoint shards: 100%|██████████| 8/8 [00:02<00:00, 3.50it/s]
02/01/2024 14:20:36 - INFO - llmtuner.model.patcher - Gradient checkpointing enabled.
02/01/2024 14:20:36 - INFO - llmtuner.model.adapter - Fine-tuning method: Full
02/01/2024 14:20:47 - INFO - llmtuner.model.loader - trainable params: 7737708544 || all params: 7737708544 || trainable%: 100.0000
02/01/2024 14:20:48 - INFO - llmtuner.data.template - Add <|im_end|> to stop words.
02/01/2024 14:20:48 - INFO - llmtuner.model.loader - trainable params: 7737708544 || all params: 7737708544 || trainable%: 100.0000
02/01/2024 14:20:48 - INFO - llmtuner.model.loader - trainable params: 7737708544 || all params: 7737708544 || trainable%: 100.0000
02/01/2024 14:20:49 - INFO - llmtuner.data.template - Add <|im_end|> to stop words.
02/01/2024 14:20:49 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
02/01/2024 14:20:49 - INFO - llmtuner.data.template - Add <|im_end|> to stop words.
02/01/2024 14:20:49 - INFO - llmtuner.model.loader - trainable params: 7737708544 || all params: 7737708544 || trainable%: 100.0000
02/01/2024 14:20:49 - INFO - llmtuner.data.template - Add <|im_end|> to stop words.
Using custom data configuration default-7bf826ddf73c2f44
Loading Dataset Infos from /home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/datasets/packaged_modules/json
Overwrite dataset info from restored data version if exists.
Loading Dataset info from /home/lirenhao/.cache/huggingface/datasets/json/default-7bf826ddf73c2f44/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96
Found cached dataset json (/home/lirenhao/.cache/huggingface/datasets/json/default-7bf826ddf73c2f44/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96)
Loading Dataset info from /home/lirenhao/.cache/huggingface/datasets/json/default-7bf826ddf73c2f44/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96
Converting format of dataset: 0%| | 0/3134 [00:00<?, ? examples/s]Caching processed dataset at /home/lirenhao/.cache/huggingface/datasets/json/default-7bf826ddf73c2f44/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96/cache-39a93cb3fc4854d1.arrow
Converting format of dataset: 32%|███▏ | 1000/3134 [00:00<00:00, 7874.85 examples/s]
Converting format of dataset: 64%|██████▍ | 2000/3134 [00:00<00:00, 7860.46 examples/s]
Converting format of dataset: 96%|█████████▌| 3000/3134 [00:00<00:00, 7920.51 examples/s]
Converting format of dataset: 100%|██████████| 3134/3134 [00:00<00:00, 7665.44 examples/s]
02/01/2024 14:20:53 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
02/01/2024 14:20:53 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
02/01/2024 14:20:53 - WARNING - llmtuner.data.utils - Checksum failed: missing SHA-1 hash value in dataset_info.json.
Running tokenizer on dataset: 0%| | 0/3134 [00:00<?, ? examples/s]
Converting format of dataset: 0%| | 0/3134 [00:00<?, ? examples/s]
Converting format of dataset: 0%| | 0/3134 [00:00<?, ? examples/s]
Converting format of dataset: 0%| | 0/3134 [00:00<?, ? examples/s]
Converting format of dataset: 32%|███▏ | 1000/3134 [00:00<00:00, 7894.79 examples/s]
Converting format of dataset: 32%|███▏ | 1000/3134 [00:00<00:00, 7843.15 examples/s]
Converting format of dataset: 32%|███▏ | 1000/3134 [00:00<00:00, 7785.44 examples/s]
Converting format of dataset: 64%|██████▍ | 2000/3134 [00:00<00:00, 7851.76 examples/s]
Converting format of dataset: 64%|██████▍ | 2000/3134 [00:00<00:00, 7817.50 examples/s]
Converting format of dataset: 64%|██████▍ | 2000/3134 [00:00<00:00, 7774.58 examples/s]
Converting format of dataset: 96%|█████████▌| 3000/3134 [00:00<00:00, 7919.08 examples/s]
Converting format of dataset: 100%|██████████| 3134/3134 [00:00<00:00, 7689.85 examples/s]
Converting format of dataset: 96%|█████████▌| 3000/3134 [00:00<00:00, 7876.60 examples/s]
Converting format of dataset: 96%|█████████▌| 3000/3134 [00:00<00:00, 7866.53 examples/s]
Converting format of dataset: 100%|██████████| 3134/3134 [00:00<00:00, 7659.10 examples/s]
Converting format of dataset: 100%|██████████| 3134/3134 [00:00<00:00, 7636.98 examples/s]
Caching processed dataset at /home/lirenhao/.cache/huggingface/datasets/json/default-7bf826ddf73c2f44/0.0.0/8bb11242116d547c741b2e8a1f18598ffdd40a1d4f2a2872c7a28b697434bc96/cache-7cecb244118aac13.arrow
Running tokenizer on dataset: 32%|███▏ | 1000/3134 [00:06<00:13, 161.84 examples/s]
Running tokenizer on dataset: 64%|██████▍ | 2000/3134 [00:10<00:05, 190.86 examples/s]
Running tokenizer on dataset: 96%|█████████▌| 3000/3134 [00:14<00:00, 229.56 examples/s]
Running tokenizer on dataset: 100%|██████████| 3134/3134 [00:14<00:00, 233.78 examples/s]
Running tokenizer on dataset: 100%|██████████| 3134/3134 [00:14<00:00, 215.75 examples/s]
input_ids:
[1, 92543, 9081, 364, 2770, 657, 589, 15358, 17993, 6843, 963, 505, 4576, 11146, 451, 60628, 60384, 60721, 62442, 60752, 4452, 285, 4576, 11146, 451, 60628, 60384, 60721, 62442, 60752, 313, 505, 395, 7659, 1813, 4287, 1762, 560, 505, 8020, 684, 36956, 15358, 31288, 451, 68589, 76659, 71581, 699, 1226, 505, 6342, 442, 517, 11100, 328, 10894, 328, 454, 51978, 756, 285, 4576, 11146, 451, 60628, 60384, 60721, 62442, 60752, 313, 777, 3696, 454, 19187, 19829, 4563, 435, 410, 4287, 12032, 684, 410, 1341, 1893, 569, 6519, 454, 262, 69093, 281, 92542, 364, 92543, 1008, 364, 85064, 60703, 60353, 68856, 68306, 61860, 62703, 69516, 68765, 68984, 60362, 60353, 60376, 68678, 60427, 69944, 60355, 92542, 364, 92543, 525, 11353, 364, 73406, 68865, 68364, 69377, 60353, 86839, 70004, 68364, 69516, 69461, 71677, 68287, 60353, 69029, 68831, 68287, 60355, 68931, 69702, 75326, 71838, 60403, 61860, 62703, 77797, 68540, 60355, 364, 92543, 1008, 364, 74820, 68399, 69088, 60677, 68540, 60353, 61032, 71155, 69059, 60355, 92542, 364, 92543, 525, 11353, 364, 91781, 60353, 73161, 80540, 60415, 82098, 60355, 72010, 71404, 60353, 60403, 76153, 68912, 60381, 74112, 61076, 60504, 364, 92543, 1008, 364, 68856, 68306, 68912, 68326, 75848, 68595, 60353, 69972, 71645, 68473, 68585, 60353, 60404, 68965, 61716, 60418, 68273, 60353, 70124, 70698, 60363, 60355, 68389, 60363, 69667, 68306, 68303, 60353, 61214, 68310, 68758, 68261, 70623, 60355, 92542, 364, 92543, 525, 11353, 364, 72010, 69030, 71711, 61076, 60504, 68522, 60353, 86004, 71645, 68629, 68804, 68592, 69095, 60504, 364, 92543, 1008, 364, 84386, 68268, 68315, 75835, 79506, 60353, 60404, 68965, 72245, 68306, 69377, 60355, 60363, 69836, 60427, 70681, 60353, 69281, 91457, 71102, 62600, 62792, 60425, 60355, 92542, 364, 92543, 525, 11353, 364, 82967, 69068, 87160, 68261, 60504, 68319, 60353, 60403, 70868, 69962, 60871, 69893, 60366, 73603, 68261, 60504, 364, 92543, 1008, 364, 68678, 70219, 92396, 84863, 73603, 68252, 71869, 76758, 60353, 68252, 78650, 68306, 71645, 60355, 60363, 70802, 68626, 71010, 73382, 69893, 60353, 60499, 69361, 61032, 68678, 72415, 60355, 92542, 364, 92543, 525, 11353, 364, 72010, 82120, 68381, 72415, 70860, 69209, 61076, 60504, 68522, 60353, 73880, 60359, 75493, 60359, 72415, 60504, 364, 92543, 1008, 364, 74212, 60353, 60363, 73408, 69836, 73880, 60381, 72415, 60355, 69097, 60353, 88720, 60382, 71343, 68254, 70861, 68892, 60459, 71356, 60586, 60355, 92542, 364, 92543, 525, 11353, 364, 68374, 69209, 73175, 68364, 77514, 61076, 60504, 68522, 60353, 68364, 70033, 60359, 69441, 60359, 68273, 60504, 364, 92543, 1008, 364, 88554, 60355, 60363, 68848, 70033, 81269, 60353, 68965, 60520, 80959, 60355, 68389, 60363, 79837, 80665, 60353, 70465, 70802, 70133, 60355, 92542, 364, 92543, 525, 11353, 364, 76273, 68374, 60353, 69060, 71958, 60353, 68364, 69516, 70848, 69715, 60354, 60355, 81425, 68831, 68637, 60353, 80698, 74131, 73382, 79309, 60355, 364, 92543, 1008, 364, 68369, 61076, 60504, 60462, 69735, 91900, 60827, 60504, 92542, 364, 92543, 525, 11353, 364, 68400, 60353, 69897, 68505, 68364, 69209, 60353, 68908, 69116, 60381, 82567, 69290, 60355, 68265, 60353, 73161, 72826, 68288, 69418, 68304, 68747, 60353, 69068, 60381, 71645, 60359, 68303, 82409, 68615, 69715, 60355, 364, 92543, 1008, 364, 82700, 69460, 70417, 60355, 86492, 60577, 69353, 68301, 60827, 60504, 92542, 364, 92543, 525, 11353, 364, 60577, 68505, 68364, 69209, 68301, 60355, 75630, 82261, 68300, 60353, 68848, 68427, 69836, 73880, 68319, 72415, 68269, 60353, 69095, 68540, 74465, 60504, 2]
inputs:
<s> <|im_start|> system
You are an AI assistant whose name is InternLM (书生·浦语).
- InternLM (书生·浦语) is a conversational language model that is developed by Shanghai AI Laboratory (上海人工智能实验室). It is designed to be helpful, honest, and harmless.
- InternLM (书生·浦语) can understand and communicate fluently in the language chosen by the user such as English and 中文.<|im_end|>
<|im_start|> user
心理咨询师，我觉得我的胸闷症状越来越严重了，这让我很害怕。<|im_end|>
<|im_start|> assistant
我能理解你的感受，首先我们要明确你的症状并不是生理问题，而是心理问题。我们可以尝试找出引发你胸闷的心理原因。
<|im_start|> user
可是我一直都在找原因，却找不到答案。<|im_end|>
<|im_start|> assistant
不要着急，我们会一步一步地解决这个问题。你能告诉我，你生活中的压力和困扰吗？
<|im_start|> user
我觉得我的压力主要来自于家庭，我和丈夫关系不好，他总是忙于工作，很少关心我。而且我担心我的孩子，怕他们出了什么意外。<|im_end|>
<|im_start|> assistant
你能详细说说吗？比如，你和丈夫之间的问题具体是什么？
<|im_start|> user
我们经常因为一些小事争吵，他总是忽略我的感受。我感到很孤独，就像被困在一个牢笼里。<|im_end|>
<|im_start|> assistant
这种感觉让你想起了什么？或者，你觉得自己在这段婚姻中失去了什么？
<|im_start|> user
让我想想……我觉得我失去了一个温馨的家，一个关爱我的丈夫。我一直在努力维持这段婚姻，但现实却让我失望。<|im_end|>
<|im_start|> assistant
你能体会到这种失望带来的情绪吗？比如，伤心、愤怒、失望？
<|im_start|> user
是的，我经常会感到伤心和失望。有时候，我甚至会怀疑自己的人生是不是选错了路。<|im_end|>
<|im_start|> assistant
这些情绪会影响你的日常生活吗？比如，你的睡眠、饮食、工作？
<|im_start|> user
肯定的。我最近睡眠很差，总是做噩梦。而且我吃得也不好，体重一直在下降。<|im_end|>
<|im_start|> assistant
了解到这些，我想告诉你，你的症状是可以改善的。我们可以通过心理治疗，帮助你走出这段困境。
<|im_start|> user
真的吗？那我要如何做呢？<|im_end|>
<|im_start|> assistant
首先，我们要了解你的情绪，学会面对和接纳它们。然后，我们会教你怎么表达自己的需求，让你和丈夫、孩子之间的关系得到改善。
<|im_start|> user
听起来很有道理。那我们从哪里开始呢？<|im_end|>
<|im_start|> assistant
从了解你的情绪开始。试着回想一下，最近一次感到伤心或者失望的时候，是什么原因导致的？</s>
label_ids:
[-100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 73406, 68865, 68364, 69377, 60353, 86839, 70004, 68364, 69516, 69461, 71677, 68287, 60353, 69029, 68831, 68287, 60355, 68931, 69702, 75326, 71838, 60403, 61860, 62703, 77797, 68540, 60355, 2, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 91781, 60353, 73161, 80540, 60415, 82098, 60355, 72010, 71404, 60353, 60403, 76153, 68912, 60381, 74112, 61076, 60504, 2, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 72010, 69030, 71711, 61076, 60504, 68522, 60353, 86004, 71645, 68629, 68804, 68592, 69095, 60504, 2, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 82967, 69068, 87160, 68261, 60504, 68319, 60353, 60403, 70868, 69962, 60871, 69893, 60366, 73603, 68261, 60504, 2, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 72010, 82120, 68381, 72415, 70860, 69209, 61076, 60504, 68522, 60353, 73880, 60359, 75493, 60359, 72415, 60504, 2, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 68374, 69209, 73175, 68364, 77514, 61076, 60504, 68522, 60353, 68364, 70033, 60359, 69441, 60359, 68273, 60504, 2, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 76273, 68374, 60353, 69060, 71958, 60353, 68364, 69516, 70848, 69715, 60354, 60355, 81425, 68831, 68637, 60353, 80698, 74131, 73382, 79309, 60355, 2, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 68400, 60353, 69897, 68505, 68364, 69209, 60353, 68908, 69116, 60381, 82567, 69290, 60355, 68265, 60353, 73161, 72826, 68288, 69418, 68304, 68747, 60353, 69068, 60381, 71645, 60359, 68303, 82409, 68615, 69715, 60355, 2, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, 60577, 68505, 68364, 69209, 68301, 60355, 75630, 82261, 68300, 60353, 68848, 68427, 69836, 73880, 68319, 72415, 68269, 60353, 69095, 68540, 74465, 60504, 2]
labels:
我能理解你的感受，首先我们要明确你的症状并不是生理问题，而是心理问题。我们可以尝试找出引发你胸闷的心理原因。</s> 不要着急，我们会一步一步地解决这个问题。你能告诉我，你生活中的压力和困扰吗？</s> 你能详细说说吗？比如，你和丈夫之间的问题具体是什么？</s> 这种感觉让你想起了什么？或者，你觉得自己在这段婚姻中失去了什么？</s> 你能体会到这种失望带来的情绪吗？比如，伤心、愤怒、失望？</s> 这些情绪会影响你的日常生活吗？比如，你的睡眠、饮食、工作？</s> 了解到这些，我想告诉你，你的症状是可以改善的。我们可以通过心理治疗，帮助你走出这段困境。</s> 首先，我们要了解你的情绪，学会面对和接纳它们。然后，我们会教你怎么表达自己的需求，让你和丈夫、孩子之间的关系得到改善。</s> 从了解你的情绪开始。试着回想一下，最近一次感到伤心或者失望的时候，是什么原因导致的？</s>
[INFO|training_args.py:1828] 2024-02-01 14:21:08,098 >> PyTorch: setting up devices
Running tokenizer on dataset: 0%| | 0/3134 [00:00<?, ? examples/s]
Running tokenizer on dataset: 0%| | 0/3134 [00:00<?, ? examples/s]
Running tokenizer on dataset: 0%| | 0/3134 [00:00<?, ? examples/s]/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/transformers/training_args.py:1741: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_token` instead.
warnings.warn(
Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.
[INFO|trainer.py:571] 2024-02-01 14:21:08,153 >> Using auto half precision backend
[2024-02-01 14:21:08,351] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed info: version=0.13.1, git-hash=unknown, git-branch=unknown
Running tokenizer on dataset: 32%|███▏ | 1000/3134 [00:06<00:13, 162.30 examples/s]
Running tokenizer on dataset: 32%|███▏ | 1000/3134 [00:06<00:13, 161.85 examples/s]
Running tokenizer on dataset: 32%|███▏ | 1000/3134 [00:06<00:13, 161.58 examples/s]
Running tokenizer on dataset: 64%|██████▍ | 2000/3134 [00:11<00:06, 172.50 examples/s]
Running tokenizer on dataset: 64%|██████▍ | 2000/3134 [00:12<00:07, 160.87 examples/s]
Running tokenizer on dataset: 64%|██████▍ | 2000/3134 [00:12<00:07, 160.52 examples/s]
Running tokenizer on dataset: 96%|█████████▌| 3000/3134 [00:15<00:00, 213.06 examples/s]
Running tokenizer on dataset: 100%|██████████| 3134/3134 [00:15<00:00, 217.65 examples/s]
Running tokenizer on dataset: 100%|██████████| 3134/3134 [00:15<00:00, 201.27 examples/s]
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/transformers/training_args.py:1741: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_token` instead.
warnings.warn(
Running tokenizer on dataset: 96%|█████████▌| 3000/3134 [00:18<00:00, 159.71 examples/s]
Running tokenizer on dataset: 96%|█████████▌| 3000/3134 [00:18<00:00, 159.56 examples/s]
Running tokenizer on dataset: 100%|██████████| 3134/3134 [00:19<00:00, 159.07 examples/s]
Running tokenizer on dataset: 100%|██████████| 3134/3134 [00:19<00:00, 159.20 examples/s]
Running tokenizer on dataset: 100%|██████████| 3134/3134 [00:19<00:00, 159.55 examples/s]
Running tokenizer on dataset: 100%|██████████| 3134/3134 [00:19<00:00, 159.49 examples/s]
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/transformers/training_args.py:1741: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_token` instead.
warnings.warn(
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/transformers/training_args.py:1741: FutureWarning: `--push_to_hub_token` is deprecated and will be removed in version 5 of 🤗 Transformers. Use `--hub_token` instead.
warnings.warn(
[2024-02-01 14:21:41,776] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False
[2024-02-01 14:21:41,778] [INFO] [logging.py:96:log_dist] [Rank 0] Using client Optimizer as basic optimizer
[2024-02-01 14:21:41,778] [INFO] [logging.py:96:log_dist] [Rank 0] Removing param_group that has no 'params' in the basic Optimizer
[2024-02-01 14:21:41,794] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Basic Optimizer = AdamW
[2024-02-01 14:21:41,794] [INFO] [utils.py:56:is_zero_supported_optimizer] Checking ZeRO support for optimizer=AdamW type=<class 'torch.optim.adamw.AdamW'>
[2024-02-01 14:21:41,794] [INFO] [logging.py:96:log_dist] [Rank 0] Creating torch.float16 ZeRO stage 2 optimizer
[2024-02-01 14:21:41,795] [INFO] [stage_1_and_2.py:143:__init__] Reduce bucket size 500000000
[2024-02-01 14:21:41,795] [INFO] [stage_1_and_2.py:144:__init__] Allgather bucket size 500000000
[2024-02-01 14:21:41,795] [INFO] [stage_1_and_2.py:145:__init__] CPU Offload: False
[2024-02-01 14:21:41,795] [INFO] [stage_1_and_2.py:146:__init__] Round robin gradient partitioning: False
[2024-02-01 14:22:01,253] [INFO] [utils.py:791:see_memory_usage] Before initializing optimizer states
[2024-02-01 14:22:01,254] [INFO] [utils.py:792:see_memory_usage] MA 22.12 GB Max_MA 25.72 GB CA 25.85 GB Max_CA 26 GB
[2024-02-01 14:22:01,254] [INFO] [utils.py:799:see_memory_usage] CPU Virtual Memory: used = 119.45 GB, percent = 12.4%
[2024-02-01 14:22:01,614] [INFO] [utils.py:791:see_memory_usage] After initializing optimizer states
[2024-02-01 14:22:01,615] [INFO] [utils.py:792:see_memory_usage] MA 36.53 GB Max_MA 50.95 GB CA 54.68 GB Max_CA 55 GB
[2024-02-01 14:22:01,615] [INFO] [utils.py:799:see_memory_usage] CPU Virtual Memory: used = 109.91 GB, percent = 11.4%
[2024-02-01 14:22:01,615] [INFO] [stage_1_and_2.py:533:__init__] optimizer state initialized
[2024-02-01 14:22:01,876] [INFO] [utils.py:791:see_memory_usage] After initializing ZeRO optimizer
[2024-02-01 14:22:01,877] [INFO] [utils.py:792:see_memory_usage] MA 36.53 GB Max_MA 36.53 GB CA 54.68 GB Max_CA 55 GB
[2024-02-01 14:22:01,878] [INFO] [utils.py:799:see_memory_usage] CPU Virtual Memory: used = 101.72 GB, percent = 10.5%
[2024-02-01 14:22:01,881] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Final Optimizer = AdamW
[2024-02-01 14:22:01,881] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed using client LR scheduler
[2024-02-01 14:22:01,881] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed LR Scheduler = None
[2024-02-01 14:22:01,881] [INFO] [logging.py:96:log_dist] [Rank 0] step=0, skipped=0, lr=[1e-06], mom=[(0.9, 0.999)]
[2024-02-01 14:22:01,883] [INFO] [config.py:984:print] DeepSpeedEngine configuration:
[2024-02-01 14:22:01,883] [INFO] [config.py:988:print] activation_checkpointing_config {
"partition_activations": false,
"contiguous_memory_optimization": false,
"cpu_checkpointing": false,
"number_checkpoints": null,
"synchronize_checkpoint_boundary": false,
"profile": false
}
[2024-02-01 14:22:01,883] [INFO] [config.py:988:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True}
[2024-02-01 14:22:01,883] [INFO] [config.py:988:print] amp_enabled .................. False
[2024-02-01 14:22:01,883] [INFO] [config.py:988:print] amp_params ................... False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] autotuning_config ............ {
"enabled": false,
"start_step": null,
"end_step": null,
"metric_path": null,
"arg_mappings": null,
"metric": "throughput",
"model_info": null,
"results_dir": "autotuning_results",
"exps_dir": "autotuning_exps",
"overwrite": true,
"fast": true,
"start_profile_step": 3,
"end_profile_step": 5,
"tuner_type": "gridsearch",
"tuner_early_stopping": 5,
"tuner_num_trials": 50,
"model_info_path": null,
"mp_size": 1,
"max_train_batch_size": null,
"min_train_batch_size": 1,
"max_train_micro_batch_size_per_gpu": 1.024000e+03,
"min_train_micro_batch_size_per_gpu": 1,
"num_tuning_micro_batch_sizes": 3
}
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] bfloat16_enabled ............. False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] checkpoint_parallel_write_pipeline False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] checkpoint_tag_validation_enabled True
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] checkpoint_tag_validation_fail False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] comms_config ................. <deepspeed.comm.config.DeepSpeedCommsConfig object at 0x7f7f6152d840>
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] communication_data_type ...... None
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}}
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] curriculum_enabled_legacy .... False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] curriculum_params_legacy ..... False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] data_efficiency_config ....... {'enabled': False, 'seed': 1234, 'data_sampling': {'enabled': False, 'num_epochs': 1000, 'num_workers': 0, 'curriculum_learning': {'enabled': False}}, 'data_routing': {'enabled': False, 'random_ltd': {'enabled': False, 'layer_token_lr_schedule': {'enabled': False}}}}
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] data_efficiency_enabled ...... False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] dataloader_drop_last ......... False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] disable_allgather ............ False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] dump_state ................... False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] dynamic_loss_scale_args ...... {'init_scale': 65536, 'scale_window': 1000, 'delayed_shift': 2, 'consecutive_hysteresis': False, 'min_scale': 1}
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] eigenvalue_enabled ........... False
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] eigenvalue_gas_boundary_resolution 1
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] eigenvalue_layer_name ........ bert.encoder.layer
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] eigenvalue_layer_num ......... 0
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] eigenvalue_max_iter .......... 100
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] eigenvalue_stability ......... 1e-06
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] eigenvalue_tol ............... 0.01
[2024-02-01 14:22:01,884] [INFO] [config.py:988:print] eigenvalue_verbose ........... False
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] elasticity_enabled ........... False
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] flops_profiler_config ........ {
"enabled": false,
"recompute_fwd_factor": 0.0,
"profile_step": 1,
"module_depth": -1,
"top_modules": 1,
"detailed": true,
"output_file": null
}
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] fp16_auto_cast ............... False
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] fp16_enabled ................. True
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] fp16_master_weights_and_gradients False
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] global_rank .................. 0
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] grad_accum_dtype ............. None
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] gradient_accumulation_steps .. 28
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] gradient_clipping ............ 1.0
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] gradient_predivide_factor .... 1.0
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] graph_harvesting ............. False
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] hybrid_engine ................ enabled=False max_out_tokens=512 inference_tp_size=1 release_inference_cache=False pin_parameters=True tp_gather_partition_size=8
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] initial_dynamic_scale ........ 65536
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] load_universal_checkpoint .... False
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] loss_scale ................... 0
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] memory_breakdown ............. False
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] mics_hierarchial_params_gather False
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] mics_shard_size .............. -1
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] monitor_config ............... tensorboard=TensorBoardConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') wandb=WandbConfig(enabled=False, group=None, team=None, project='deepspeed') csv_monitor=CSVConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') enabled=False
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] nebula_config ................ {
"enabled": false,
"persistent_storage_path": null,
"persistent_time_interval": 100,
"num_of_version_in_retention": 2,
"enable_nebula_load": true,
"load_path": null
}
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] optimizer_legacy_fusion ...... False
[2024-02-01 14:22:01,885] [INFO] [config.py:988:print] optimizer_name ............... None
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] optimizer_params ............. None
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0, 'pipe_partitioned': True, 'grad_partitioned': True}
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] pld_enabled .................. False
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] pld_params ................... False
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] prescale_gradients ........... False
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] scheduler_name ............... None
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] scheduler_params ............. None
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] seq_parallel_communication_data_type torch.float32
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] sparse_attention ............. None
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] sparse_gradients_enabled ..... False
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] steps_per_print .............. inf
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] train_batch_size ............. 448
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] train_micro_batch_size_per_gpu 4
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] use_data_before_expert_parallel_ False
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] use_node_local_storage ....... False
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] wall_clock_breakdown ......... False
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] weight_quantization_config ... None
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] world_size ................... 4
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] zero_allow_untested_optimizer True
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] zero_config .................. stage=2 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 use_multi_rank_bucket_allreduce=True allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1,000,000,000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50,000,000 param_persistence_threshold=100,000 model_persistence_threshold=sys.maxsize max_live_parameters=1,000,000,000 max_reuse_distance=1,000,000,000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False zero_hpz_partition_size=1 zero_quantized_weights=False zero_quantized_nontrainable_weights=False zero_quantized_gradients=False mics_shard_size=-1 mics_hierarchical_params_gather=False memory_efficient_linear=True pipeline_loading_checkpoint=False override_module_apply=True
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] zero_enabled ................. True
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] zero_force_ds_cpu_optimizer .. True
[2024-02-01 14:22:01,886] [INFO] [config.py:988:print] zero_optimization_stage ...... 2
[2024-02-01 14:22:01,887] [INFO] [config.py:974:print_user_config] json = {
"train_batch_size": 448,
"train_micro_batch_size_per_gpu": 4,
"gradient_accumulation_steps": 28,
"gradient_clipping": 1.0,
"zero_allow_untested_optimizer": true,
"fp16": {
"enabled": true,
"loss_scale": 0,
"initial_scale_power": 16,
"loss_scale_window": 1000,
"hysteresis": 2,
"min_loss_scale": 1
},
"zero_optimization": {
"stage": 2,
"allgather_partitions": true,
"allgather_bucket_size": 5.000000e+08,
"reduce_scatter": true,
"reduce_bucket_size": 5.000000e+08,
"overlap_comm": false,
"contiguous_gradients": true
},
"steps_per_print": inf,
"bf16": {
"enabled": false
}
}
[INFO|trainer.py:1721] 2024-02-01 14:22:01,887 >> ***** Running training *****
[INFO|trainer.py:1722] 2024-02-01 14:22:01,887 >> Num examples = 3,134
[INFO|trainer.py:1723] 2024-02-01 14:22:01,887 >> Num Epochs = 9
[INFO|trainer.py:1724] 2024-02-01 14:22:01,887 >> Instantaneous batch size per device = 4
[INFO|trainer.py:1727] 2024-02-01 14:22:01,887 >> Total train batch size (w. parallel, distributed & accumulation) = 448
[INFO|trainer.py:1728] 2024-02-01 14:22:01,887 >> Gradient Accumulation steps = 28
[INFO|trainer.py:1729] 2024-02-01 14:22:01,887 >> Total optimization steps = 63
[INFO|trainer.py:1730] 2024-02-01 14:22:01,889 >> Number of trainable parameters = 7,737,708,544
0%| | 0/63 [00:00<?, ?it/s]/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
warnings.warn(
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
warnings.warn(
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
warnings.warn(
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
warnings.warn(
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/deepspeed/runtime/zero/stage_1_and_2.py:1968: UserWarning: The torch.cuda.*DtypeTensor constructors are no longer recommended. It's best to use methods such as torch.tensor(data, dtype=*, device='cuda') to create tensors. (Triggered internally at ../torch/csrc/tensor/python_tensor.cpp:83.)
overflow_gpu = get_accelerator().ByteTensor([overflow])
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/deepspeed/runtime/zero/stage_1_and_2.py:1968: UserWarning: The torch.cuda.*DtypeTensor constructors are no longer recommended. It's best to use methods such as torch.tensor(data, dtype=*, device='cuda') to create tensors. (Triggered internally at ../torch/csrc/tensor/python_tensor.cpp:83.)
overflow_gpu = get_accelerator().ByteTensor([overflow])
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/deepspeed/runtime/zero/stage_1_and_2.py:1968: UserWarning: The torch.cuda.*DtypeTensor constructors are no longer recommended. It's best to use methods such as torch.tensor(data, dtype=*, device='cuda') to create tensors. (Triggered internally at ../torch/csrc/tensor/python_tensor.cpp:83.)
overflow_gpu = get_accelerator().ByteTensor([overflow])
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/deepspeed/runtime/zero/stage_1_and_2.py:1968: UserWarning: The torch.cuda.*DtypeTensor constructors are no longer recommended. It's best to use methods such as torch.tensor(data, dtype=*, device='cuda') to create tensors. (Triggered internally at ../torch/csrc/tensor/python_tensor.cpp:83.)
overflow_gpu = get_accelerator().ByteTensor([overflow])
2%|▏ | 1/63 [00:44<45:32, 44.06s/it]
3%|▎ | 2/63 [01:23<42:01, 41.33s/it]
5%|▍ | 3/63 [02:04<41:04, 41.08s/it]
6%|▋ | 4/63 [02:43<39:37, 40.30s/it]
8%|▊ | 5/63 [03:22<38:23, 39.72s/it][2024-02-01 14:26:04,941] [INFO] [loss_scaler.py:190:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 65536, but hysteresis is 2. Reducing hysteresis to 1
10%|▉ | 6/63 [04:03<38:08, 40.15s/it][2024-02-01 14:26:44,502] [INFO] [loss_scaler.py:183:update_scale] [deepspeed] OVERFLOW! Rank 0 Skipping step. Attempted loss scale: 65536, reducing to 32768
11%|█ | 7/63 [04:42<37:17, 39.96s/it]
13%|█▎ | 8/63 [05:21<36:23, 39.71s/it]
14%|█▍ | 9/63 [06:01<35:39, 39.62s/it]
16%|█▌ | 10/63 [06:41<35:16, 39.93s/it]
{'loss': 2.1176, 'learning_rate': 9.607381059352038e-07, 'epoch': 1.43}
16%|█▌ | 10/63 [06:41<35:16, 39.93s/it]
17%|█▋ | 11/63 [07:20<34:22, 39.65s/it]
19%|█▉ | 12/63 [08:00<33:47, 39.76s/it]
21%|██ | 13/63 [08:39<32:56, 39.53s/it]
22%|██▏ | 14/63 [09:20<32:32, 39.85s/it]
24%|██▍ | 15/63 [09:59<31:45, 39.69s/it]
25%|██▌ | 16/63 [10:38<30:47, 39.31s/it]
27%|██▋ | 17/63 [11:19<30:31, 39.82s/it]
29%|██▊ | 18/63 [11:58<29:51, 39.81s/it]
30%|███ | 19/63 [12:39<29:15, 39.89s/it]
32%|███▏ | 20/63 [13:19<28:42, 40.06s/it]
{'loss': 1.5678, 'learning_rate': 8.117449009293668e-07, 'epoch': 2.86}
32%|███▏ | 20/63 [13:19<28:42, 40.06s/it]
33%|███▎ | 21/63 [13:59<27:59, 39.99s/it][INFO|trainer.py:2926] 2024-02-01 14:36:12,897 >> Saving model checkpoint to /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21
[INFO|configuration_utils.py:473] 2024-02-01 14:36:12,902 >> Configuration saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/config.json
[INFO|configuration_utils.py:594] 2024-02-01 14:36:12,903 >> Configuration saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/generation_config.json
[INFO|modeling_utils.py:2503] 2024-02-01 14:36:40,422 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2433] 2024-02-01 14:36:40,424 >> tokenizer config file saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/tokenizer_config.json
[INFO|tokenization_utils_base.py:2442] 2024-02-01 14:36:40,424 >> Special tokens file saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/special_tokens_map.json
[2024-02-01 14:36:41,670] [INFO] [logging.py:96:log_dist] [Rank 0] [Torch] Checkpoint global_step21 is about to be saved!
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/nn/modules/module.py:1879: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
warnings.warn(
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/nn/modules/module.py:1879: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
warnings.warn(
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/nn/modules/module.py:1879: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
warnings.warn(
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/nn/modules/module.py:1879: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
warnings.warn(
[2024-02-01 14:36:41,683] [INFO] [logging.py:96:log_dist] [Rank 0] Saving model checkpoint: /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/global_step21/mp_rank_00_model_states.pt
[2024-02-01 14:36:41,684] [INFO] [torch_checkpoint_engine.py:21:save] [Torch] Saving /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/global_step21/mp_rank_00_model_states.pt...
[2024-02-01 14:37:17,058] [INFO] [torch_checkpoint_engine.py:23:save] [Torch] Saved /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/global_step21/mp_rank_00_model_states.pt.
[2024-02-01 14:37:17,061] [INFO] [torch_checkpoint_engine.py:21:save] [Torch] Saving /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/global_step21/zero_pp_rank_0_mp_rank_00_optim_states.pt...
[2024-02-01 14:38:15,362] [INFO] [torch_checkpoint_engine.py:23:save] [Torch] Saved /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/global_step21/zero_pp_rank_0_mp_rank_00_optim_states.pt.
[2024-02-01 14:38:15,363] [INFO] [engine.py:3477:_save_zero_checkpoint] zero checkpoint saved /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-21/global_step21/zero_pp_rank_0_mp_rank_00_optim_states.pt
[2024-02-01 14:38:15,363] [INFO] [torch_checkpoint_engine.py:33:commit] [Torch] Checkpoint global_step21 is ready now!
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
warnings.warn(
35%|███▍ | 22/63 [16:52<54:35, 79.88s/it]
37%|███▋ | 23/63 [17:32<45:23, 68.08s/it]
38%|███▊ | 24/63 [18:15<39:17, 60.44s/it]
40%|███▉ | 25/63 [18:54<34:12, 54.02s/it]
41%|████▏ | 26/63 [19:33<30:33, 49.54s/it]
43%|████▎ | 27/63 [20:12<27:49, 46.38s/it]
44%|████▍ | 28/63 [20:51<25:45, 44.17s/it]
46%|████▌ | 29/63 [21:31<24:19, 42.92s/it]
48%|████▊ | 30/63 [22:11<23:07, 42.06s/it]
{'loss': 1.4173, 'learning_rate': 5.868240888334652e-07, 'epoch': 4.29}
48%|████▊ | 30/63 [22:11<23:07, 42.06s/it]
49%|████▉ | 31/63 [22:52<22:17, 41.80s/it]
51%|█████ | 32/63 [23:32<21:11, 41.02s/it]
52%|█████▏ | 33/63 [24:10<20:06, 40.20s/it]
54%|█████▍ | 34/63 [24:49<19:18, 39.96s/it]
56%|█████▌ | 35/63 [25:30<18:43, 40.11s/it]
57%|█████▋ | 36/63 [26:10<18:03, 40.13s/it]
59%|█████▊ | 37/63 [26:49<17:12, 39.70s/it]
60%|██████ | 38/63 [27:29<16:36, 39.88s/it]
62%|██████▏ | 39/63 [28:08<15:48, 39.51s/it]
63%|██████▎ | 40/63 [28:46<15:04, 39.34s/it]
{'loss': 1.342, 'learning_rate': 3.4075667487415785e-07, 'epoch': 5.71}
63%|██████▎ | 40/63 [28:46<15:04, 39.34s/it]
65%|██████▌ | 41/63 [29:27<14:36, 39.84s/it]
67%|██████▋ | 42/63 [30:07<13:57, 39.87s/it][INFO|trainer.py:2926] 2024-02-01 14:52:21,426 >> Saving model checkpoint to /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42
[INFO|configuration_utils.py:473] 2024-02-01 14:52:21,431 >> Configuration saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/config.json
[INFO|configuration_utils.py:594] 2024-02-01 14:52:21,432 >> Configuration saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/generation_config.json
[INFO|modeling_utils.py:2503] 2024-02-01 14:52:48,702 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2433] 2024-02-01 14:52:48,704 >> tokenizer config file saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/tokenizer_config.json
[INFO|tokenization_utils_base.py:2442] 2024-02-01 14:52:48,704 >> Special tokens file saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/special_tokens_map.json
[2024-02-01 14:52:49,843] [INFO] [logging.py:96:log_dist] [Rank 0] [Torch] Checkpoint global_step42 is about to be saved!
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/nn/modules/module.py:1879: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
warnings.warn(
[2024-02-01 14:52:49,856] [INFO] [logging.py:96:log_dist] [Rank 0] Saving model checkpoint: /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/global_step42/mp_rank_00_model_states.pt
[2024-02-01 14:52:49,856] [INFO] [torch_checkpoint_engine.py:21:save] [Torch] Saving /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/global_step42/mp_rank_00_model_states.pt...
[2024-02-01 14:53:25,041] [INFO] [torch_checkpoint_engine.py:23:save] [Torch] Saved /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/global_step42/mp_rank_00_model_states.pt.
[2024-02-01 14:53:25,044] [INFO] [torch_checkpoint_engine.py:21:save] [Torch] Saving /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/global_step42/zero_pp_rank_0_mp_rank_00_optim_states.pt...
[2024-02-01 14:54:24,364] [INFO] [torch_checkpoint_engine.py:23:save] [Torch] Saved /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/global_step42/zero_pp_rank_0_mp_rank_00_optim_states.pt.
[2024-02-01 14:54:24,364] [INFO] [engine.py:3477:_save_zero_checkpoint] zero checkpoint saved /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-42/global_step42/zero_pp_rank_0_mp_rank_00_optim_states.pt
[2024-02-01 14:54:24,364] [INFO] [torch_checkpoint_engine.py:33:commit] [Torch] Checkpoint global_step42 is ready now!
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
warnings.warn(
68%|██████▊ | 43/63 [33:01<26:37, 79.86s/it]
70%|██████▉ | 44/63 [33:41<21:31, 67.96s/it]
71%|███████▏ | 45/63 [34:20<17:47, 59.29s/it]
73%|███████▎ | 46/63 [35:01<15:13, 53.75s/it]
75%|███████▍ | 47/63 [35:41<13:13, 49.58s/it]
76%|███████▌ | 48/63 [36:21<11:40, 46.71s/it]
78%|███████▊ | 49/63 [37:00<10:25, 44.69s/it]
79%|███████▉ | 50/63 [37:42<09:26, 43.60s/it]
{'loss': 1.3108, 'learning_rate': 1.3347406408508694e-07, 'epoch': 7.14}
79%|███████▉ | 50/63 [37:42<09:26, 43.60s/it]
81%|████████ | 51/63 [38:20<08:24, 42.07s/it]
83%|████████▎ | 52/63 [39:00<07:34, 41.29s/it]
84%|████████▍ | 53/63 [39:41<06:52, 41.22s/it]
86%|████████▌ | 54/63 [40:21<06:07, 40.87s/it]
87%|████████▋ | 55/63 [41:00<05:22, 40.28s/it]
89%|████████▉ | 56/63 [41:38<04:39, 39.88s/it]
90%|█████████ | 57/63 [42:18<03:58, 39.78s/it]
92%|█████████▏| 58/63 [42:59<03:20, 40.10s/it]
94%|█████████▎| 59/63 [43:39<02:40, 40.24s/it]
95%|█████████▌| 60/63 [44:19<02:00, 40.04s/it]
{'loss': 1.2987, 'learning_rate': 1.5461356885461075e-08, 'epoch': 8.57}
95%|█████████▌| 60/63 [44:19<02:00, 40.04s/it]
97%|█████████▋| 61/63 [44:58<01:19, 39.67s/it]
98%|█████████▊| 62/63 [45:38<00:39, 39.80s/it]
100%|██████████| 63/63 [46:16<00:00, 39.26s/it][INFO|trainer.py:2926] 2024-02-01 15:08:30,323 >> Saving model checkpoint to /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63
[INFO|configuration_utils.py:473] 2024-02-01 15:08:30,328 >> Configuration saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/config.json
[INFO|configuration_utils.py:594] 2024-02-01 15:08:30,329 >> Configuration saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/generation_config.json
[INFO|modeling_utils.py:2503] 2024-02-01 15:08:57,391 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2433] 2024-02-01 15:08:57,393 >> tokenizer config file saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/tokenizer_config.json
[INFO|tokenization_utils_base.py:2442] 2024-02-01 15:08:57,393 >> Special tokens file saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/special_tokens_map.json
[2024-02-01 15:08:58,595] [INFO] [logging.py:96:log_dist] [Rank 0] [Torch] Checkpoint global_step63 is about to be saved!
/home/lirenhao/anaconda3/envs/llama_factory/lib/python3.10/site-packages/torch/nn/modules/module.py:1879: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
warnings.warn(
[2024-02-01 15:08:58,608] [INFO] [logging.py:96:log_dist] [Rank 0] Saving model checkpoint: /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/global_step63/mp_rank_00_model_states.pt
[2024-02-01 15:08:58,608] [INFO] [torch_checkpoint_engine.py:21:save] [Torch] Saving /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/global_step63/mp_rank_00_model_states.pt...
[2024-02-01 15:09:33,948] [INFO] [torch_checkpoint_engine.py:23:save] [Torch] Saved /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/global_step63/mp_rank_00_model_states.pt.
[2024-02-01 15:09:33,951] [INFO] [torch_checkpoint_engine.py:21:save] [Torch] Saving /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/global_step63/zero_pp_rank_0_mp_rank_00_optim_states.pt...
[2024-02-01 15:10:31,865] [INFO] [torch_checkpoint_engine.py:23:save] [Torch] Saved /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/global_step63/zero_pp_rank_0_mp_rank_00_optim_states.pt.
[2024-02-01 15:10:31,866] [INFO] [engine.py:3477:_save_zero_checkpoint] zero checkpoint saved /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tmp-checkpoint-63/global_step63/zero_pp_rank_0_mp_rank_00_optim_states.pt
[2024-02-01 15:10:31,866] [INFO] [torch_checkpoint_engine.py:33:commit] [Torch] Checkpoint global_step63 is ready now!
[INFO|trainer.py:1962] 2024-02-01 15:10:32,863 >>
Training completed. Do not forget to share your model on huggingface.co/models =)
{'train_runtime': 2910.9748, 'train_samples_per_second': 9.69, 'train_steps_per_second': 0.022, 'train_loss': 1.4981852107577853, 'epoch': 9.0}
100%|██████████| 63/63 [48:30<00:00, 39.26s/it]
100%|██████████| 63/63 [48:30<00:00, 46.21s/it]
[INFO|trainer.py:2926] 2024-02-01 15:10:44,639 >> Saving model checkpoint to /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9
[INFO|configuration_utils.py:473] 2024-02-01 15:10:44,787 >> Configuration saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/config.json
[INFO|configuration_utils.py:594] 2024-02-01 15:10:44,788 >> Configuration saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/generation_config.json
[2024-02-01 15:10:49,742] [INFO] [launch.py:347:main] Process 3771596 exits successfully.
[2024-02-01 15:10:49,742] [INFO] [launch.py:347:main] Process 3771597 exits successfully.
[2024-02-01 15:10:49,742] [INFO] [launch.py:347:main] Process 3771598 exits successfully.
[INFO|modeling_utils.py:2503] 2024-02-01 15:11:12,707 >> The model is bigger than the maximum size per checkpoint (5GB) and is going to be split in 4 checkpoint shards. You can find where each parameters has been saved in the index located at /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/model.safetensors.index.json.
[INFO|tokenization_utils_base.py:2433] 2024-02-01 15:11:12,709 >> tokenizer config file saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/tokenizer_config.json
[INFO|tokenization_utils_base.py:2442] 2024-02-01 15:11:12,709 >> Special tokens file saved in /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/special_tokens_map.json
***** train metrics *****
epoch = 9.0
train_loss = 1.4982
train_runtime = 0:48:30.97
train_samples_per_second = 9.69
train_steps_per_second = 0.022
Figure saved: /home/lirenhao/projects/LLaMA-Factory/output/9f100e26-d997-46e8-afee-721977a16ca9/training_loss.png
02/01/2024 15:11:14 - WARNING - llmtuner.extras.ploting - No metric eval_loss to plot.
[INFO|modelcard.py:452] 2024-02-01 15:11:14,095 >> Dropping the following result as it does not have all the necessary fields:
{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
[2024-02-01 15:11:17,773] [INFO] [launch.py:347:main] Process 3771595 exits successfully.
|