Training in progress, epoch 8
Browse files- egy_training_log.txt +288 -0
- model.safetensors +1 -1
- tokenizer.json +2 -16
- training_args.bin +1 -1
egy_training_log.txt
CHANGED
@@ -570,3 +570,291 @@ INFO:root:Epoch 7.0: Train Loss = 0.0164, Eval Loss = 0.05724157765507698
|
|
570 |
INFO:absl:Using default tokenizer.
|
571 |
INFO:__main__:*** Evaluate ***
|
572 |
INFO:absl:Using default tokenizer.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
570 |
INFO:absl:Using default tokenizer.
|
571 |
INFO:__main__:*** Evaluate ***
|
572 |
INFO:absl:Using default tokenizer.
|
573 |
+
WARNING:__main__:Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False
|
574 |
+
INFO:__main__:Training/evaluation parameters TrainingArguments(
|
575 |
+
_n_gpu=1,
|
576 |
+
accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
|
577 |
+
adafactor=False,
|
578 |
+
adam_beta1=0.9,
|
579 |
+
adam_beta2=0.999,
|
580 |
+
adam_epsilon=1e-08,
|
581 |
+
auto_find_batch_size=False,
|
582 |
+
batch_eval_metrics=False,
|
583 |
+
bf16=False,
|
584 |
+
bf16_full_eval=False,
|
585 |
+
data_seed=None,
|
586 |
+
dataloader_drop_last=False,
|
587 |
+
dataloader_num_workers=0,
|
588 |
+
dataloader_persistent_workers=False,
|
589 |
+
dataloader_pin_memory=True,
|
590 |
+
dataloader_prefetch_factor=None,
|
591 |
+
ddp_backend=None,
|
592 |
+
ddp_broadcast_buffers=None,
|
593 |
+
ddp_bucket_cap_mb=None,
|
594 |
+
ddp_find_unused_parameters=None,
|
595 |
+
ddp_timeout=1800,
|
596 |
+
debug=[],
|
597 |
+
deepspeed=None,
|
598 |
+
disable_tqdm=False,
|
599 |
+
dispatch_batches=None,
|
600 |
+
do_eval=True,
|
601 |
+
do_predict=False,
|
602 |
+
do_train=True,
|
603 |
+
eval_accumulation_steps=None,
|
604 |
+
eval_delay=0,
|
605 |
+
eval_do_concat_batches=True,
|
606 |
+
eval_on_start=False,
|
607 |
+
eval_steps=None,
|
608 |
+
eval_strategy=IntervalStrategy.EPOCH,
|
609 |
+
eval_use_gather_object=False,
|
610 |
+
evaluation_strategy=epoch,
|
611 |
+
fp16=False,
|
612 |
+
fp16_backend=auto,
|
613 |
+
fp16_full_eval=False,
|
614 |
+
fp16_opt_level=O1,
|
615 |
+
fsdp=[],
|
616 |
+
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
|
617 |
+
fsdp_min_num_params=0,
|
618 |
+
fsdp_transformer_layer_cls_to_wrap=None,
|
619 |
+
full_determinism=False,
|
620 |
+
gradient_accumulation_steps=1,
|
621 |
+
gradient_checkpointing=False,
|
622 |
+
gradient_checkpointing_kwargs=None,
|
623 |
+
greater_is_better=False,
|
624 |
+
group_by_length=False,
|
625 |
+
half_precision_backend=auto,
|
626 |
+
hub_always_push=False,
|
627 |
+
hub_model_id=None,
|
628 |
+
hub_private_repo=False,
|
629 |
+
hub_strategy=HubStrategy.EVERY_SAVE,
|
630 |
+
hub_token=<HUB_TOKEN>,
|
631 |
+
ignore_data_skip=False,
|
632 |
+
include_inputs_for_metrics=False,
|
633 |
+
include_num_input_tokens_seen=False,
|
634 |
+
include_tokens_per_second=False,
|
635 |
+
jit_mode_eval=False,
|
636 |
+
label_names=None,
|
637 |
+
label_smoothing_factor=0.0,
|
638 |
+
learning_rate=5e-05,
|
639 |
+
length_column_name=length,
|
640 |
+
load_best_model_at_end=True,
|
641 |
+
local_rank=0,
|
642 |
+
log_level=passive,
|
643 |
+
log_level_replica=warning,
|
644 |
+
log_on_each_node=True,
|
645 |
+
logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_gulf_aragpt2-large/runs/Sep08_18-44-04_lmgpu-node-07,
|
646 |
+
logging_first_step=False,
|
647 |
+
logging_nan_inf_filter=True,
|
648 |
+
logging_steps=500,
|
649 |
+
logging_strategy=IntervalStrategy.EPOCH,
|
650 |
+
lr_scheduler_kwargs={},
|
651 |
+
lr_scheduler_type=SchedulerType.LINEAR,
|
652 |
+
max_grad_norm=1.0,
|
653 |
+
max_steps=-1,
|
654 |
+
metric_for_best_model=loss,
|
655 |
+
mp_parameters=,
|
656 |
+
neftune_noise_alpha=None,
|
657 |
+
no_cuda=False,
|
658 |
+
num_train_epochs=20.0,
|
659 |
+
optim=OptimizerNames.ADAMW_TORCH,
|
660 |
+
optim_args=None,
|
661 |
+
optim_target_modules=None,
|
662 |
+
output_dir=/home/iais_marenpielka/Bouthaina/res_nw_gulf_aragpt2-large,
|
663 |
+
overwrite_output_dir=False,
|
664 |
+
past_index=-1,
|
665 |
+
per_device_eval_batch_size=4,
|
666 |
+
per_device_train_batch_size=4,
|
667 |
+
prediction_loss_only=False,
|
668 |
+
push_to_hub=True,
|
669 |
+
push_to_hub_model_id=None,
|
670 |
+
push_to_hub_organization=None,
|
671 |
+
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
|
672 |
+
ray_scope=last,
|
673 |
+
remove_unused_columns=True,
|
674 |
+
report_to=[],
|
675 |
+
restore_callback_states_from_checkpoint=False,
|
676 |
+
resume_from_checkpoint=None,
|
677 |
+
run_name=/home/iais_marenpielka/Bouthaina/res_nw_gulf_aragpt2-large,
|
678 |
+
save_on_each_node=False,
|
679 |
+
save_only_model=False,
|
680 |
+
save_safetensors=True,
|
681 |
+
save_steps=500,
|
682 |
+
save_strategy=IntervalStrategy.EPOCH,
|
683 |
+
save_total_limit=None,
|
684 |
+
seed=42,
|
685 |
+
skip_memory_metrics=True,
|
686 |
+
split_batches=None,
|
687 |
+
tf32=None,
|
688 |
+
torch_compile=False,
|
689 |
+
torch_compile_backend=None,
|
690 |
+
torch_compile_mode=None,
|
691 |
+
torch_empty_cache_steps=None,
|
692 |
+
torchdynamo=None,
|
693 |
+
tpu_metrics_debug=False,
|
694 |
+
tpu_num_cores=None,
|
695 |
+
use_cpu=False,
|
696 |
+
use_ipex=False,
|
697 |
+
use_legacy_prediction_loop=False,
|
698 |
+
use_mps_device=False,
|
699 |
+
warmup_ratio=0.0,
|
700 |
+
warmup_steps=500,
|
701 |
+
weight_decay=0.0,
|
702 |
+
)
|
703 |
+
INFO:__main__:Checkpoint detected, resuming training at /home/iais_marenpielka/Bouthaina/res_nw_gulf_aragpt2-large/checkpoint-11704. To avoid this behavior, change the `--output_dir` or add `--overwrite_output_dir` to train from scratch.
|
704 |
+
INFO:datasets.builder:Using custom data configuration default-481a1a6a0ca4575e
|
705 |
+
INFO:datasets.info:Loading Dataset Infos from /home/iais_marenpielka/Bouthaina/miniconda3/lib/python3.12/site-packages/datasets/packaged_modules/text
|
706 |
+
INFO:datasets.builder:Overwrite dataset info from restored data version if exists.
|
707 |
+
INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
|
708 |
+
INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
|
709 |
+
INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
|
710 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-798e68ee1238406a.arrow
|
711 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-08141c170f1669b9.arrow
|
712 |
+
WARNING:__main__:The tokenizer picked seems to have a very large `model_max_length` (1000000000000000019884624838656). Using block_size=1024 instead. You can change that default value by passing --block_size xxx.
|
713 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-2ba0b834485aeaf5.arrow
|
714 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-7a0a05502f2d2ac6.arrow
|
715 |
+
WARNING:accelerate.utils.other: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.
|
716 |
+
WARNING:__main__:Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, 16-bits training: False
|
717 |
+
INFO:__main__:Training/evaluation parameters TrainingArguments(
|
718 |
+
_n_gpu=1,
|
719 |
+
accelerator_config={'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None, 'use_configured_state': False},
|
720 |
+
adafactor=False,
|
721 |
+
adam_beta1=0.9,
|
722 |
+
adam_beta2=0.999,
|
723 |
+
adam_epsilon=1e-08,
|
724 |
+
auto_find_batch_size=False,
|
725 |
+
batch_eval_metrics=False,
|
726 |
+
bf16=False,
|
727 |
+
bf16_full_eval=False,
|
728 |
+
data_seed=None,
|
729 |
+
dataloader_drop_last=False,
|
730 |
+
dataloader_num_workers=0,
|
731 |
+
dataloader_persistent_workers=False,
|
732 |
+
dataloader_pin_memory=True,
|
733 |
+
dataloader_prefetch_factor=None,
|
734 |
+
ddp_backend=None,
|
735 |
+
ddp_broadcast_buffers=None,
|
736 |
+
ddp_bucket_cap_mb=None,
|
737 |
+
ddp_find_unused_parameters=None,
|
738 |
+
ddp_timeout=1800,
|
739 |
+
debug=[],
|
740 |
+
deepspeed=None,
|
741 |
+
disable_tqdm=False,
|
742 |
+
dispatch_batches=None,
|
743 |
+
do_eval=True,
|
744 |
+
do_predict=False,
|
745 |
+
do_train=True,
|
746 |
+
eval_accumulation_steps=None,
|
747 |
+
eval_delay=0,
|
748 |
+
eval_do_concat_batches=True,
|
749 |
+
eval_on_start=False,
|
750 |
+
eval_steps=None,
|
751 |
+
eval_strategy=IntervalStrategy.EPOCH,
|
752 |
+
eval_use_gather_object=False,
|
753 |
+
evaluation_strategy=epoch,
|
754 |
+
fp16=False,
|
755 |
+
fp16_backend=auto,
|
756 |
+
fp16_full_eval=False,
|
757 |
+
fp16_opt_level=O1,
|
758 |
+
fsdp=[],
|
759 |
+
fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False},
|
760 |
+
fsdp_min_num_params=0,
|
761 |
+
fsdp_transformer_layer_cls_to_wrap=None,
|
762 |
+
full_determinism=False,
|
763 |
+
gradient_accumulation_steps=1,
|
764 |
+
gradient_checkpointing=False,
|
765 |
+
gradient_checkpointing_kwargs=None,
|
766 |
+
greater_is_better=False,
|
767 |
+
group_by_length=False,
|
768 |
+
half_precision_backend=auto,
|
769 |
+
hub_always_push=False,
|
770 |
+
hub_model_id=None,
|
771 |
+
hub_private_repo=False,
|
772 |
+
hub_strategy=HubStrategy.EVERY_SAVE,
|
773 |
+
hub_token=<HUB_TOKEN>,
|
774 |
+
ignore_data_skip=False,
|
775 |
+
include_inputs_for_metrics=False,
|
776 |
+
include_num_input_tokens_seen=False,
|
777 |
+
include_tokens_per_second=False,
|
778 |
+
jit_mode_eval=False,
|
779 |
+
label_names=None,
|
780 |
+
label_smoothing_factor=0.0,
|
781 |
+
learning_rate=5e-05,
|
782 |
+
length_column_name=length,
|
783 |
+
load_best_model_at_end=True,
|
784 |
+
local_rank=0,
|
785 |
+
log_level=passive,
|
786 |
+
log_level_replica=warning,
|
787 |
+
log_on_each_node=True,
|
788 |
+
logging_dir=/home/iais_marenpielka/Bouthaina/res_nw_gulf_aragpt2-large/runs/Sep08_18-48-04_lmgpu-node-07,
|
789 |
+
logging_first_step=False,
|
790 |
+
logging_nan_inf_filter=True,
|
791 |
+
logging_steps=500,
|
792 |
+
logging_strategy=IntervalStrategy.EPOCH,
|
793 |
+
lr_scheduler_kwargs={},
|
794 |
+
lr_scheduler_type=SchedulerType.LINEAR,
|
795 |
+
max_grad_norm=1.0,
|
796 |
+
max_steps=-1,
|
797 |
+
metric_for_best_model=loss,
|
798 |
+
mp_parameters=,
|
799 |
+
neftune_noise_alpha=None,
|
800 |
+
no_cuda=False,
|
801 |
+
num_train_epochs=20.0,
|
802 |
+
optim=OptimizerNames.ADAMW_TORCH,
|
803 |
+
optim_args=None,
|
804 |
+
optim_target_modules=None,
|
805 |
+
output_dir=/home/iais_marenpielka/Bouthaina/res_nw_gulf_aragpt2-large,
|
806 |
+
overwrite_output_dir=False,
|
807 |
+
past_index=-1,
|
808 |
+
per_device_eval_batch_size=4,
|
809 |
+
per_device_train_batch_size=4,
|
810 |
+
prediction_loss_only=False,
|
811 |
+
push_to_hub=True,
|
812 |
+
push_to_hub_model_id=None,
|
813 |
+
push_to_hub_organization=None,
|
814 |
+
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
|
815 |
+
ray_scope=last,
|
816 |
+
remove_unused_columns=True,
|
817 |
+
report_to=[],
|
818 |
+
restore_callback_states_from_checkpoint=False,
|
819 |
+
resume_from_checkpoint=None,
|
820 |
+
run_name=/home/iais_marenpielka/Bouthaina/res_nw_gulf_aragpt2-large,
|
821 |
+
save_on_each_node=False,
|
822 |
+
save_only_model=False,
|
823 |
+
save_safetensors=True,
|
824 |
+
save_steps=500,
|
825 |
+
save_strategy=IntervalStrategy.EPOCH,
|
826 |
+
save_total_limit=None,
|
827 |
+
seed=42,
|
828 |
+
skip_memory_metrics=True,
|
829 |
+
split_batches=None,
|
830 |
+
tf32=None,
|
831 |
+
torch_compile=False,
|
832 |
+
torch_compile_backend=None,
|
833 |
+
torch_compile_mode=None,
|
834 |
+
torch_empty_cache_steps=None,
|
835 |
+
torchdynamo=None,
|
836 |
+
tpu_metrics_debug=False,
|
837 |
+
tpu_num_cores=None,
|
838 |
+
use_cpu=False,
|
839 |
+
use_ipex=False,
|
840 |
+
use_legacy_prediction_loop=False,
|
841 |
+
use_mps_device=False,
|
842 |
+
warmup_ratio=0.0,
|
843 |
+
warmup_steps=500,
|
844 |
+
weight_decay=0.0,
|
845 |
+
)
|
846 |
+
INFO:__main__:Checkpoint detected, resuming training at /home/iais_marenpielka/Bouthaina/res_nw_gulf_aragpt2-large/checkpoint-11704. To avoid this behavior, change the `--output_dir` or add `--overwrite_output_dir` to train from scratch.
|
847 |
+
INFO:datasets.builder:Using custom data configuration default-481a1a6a0ca4575e
|
848 |
+
INFO:datasets.info:Loading Dataset Infos from /home/iais_marenpielka/Bouthaina/miniconda3/lib/python3.12/site-packages/datasets/packaged_modules/text
|
849 |
+
INFO:datasets.builder:Overwrite dataset info from restored data version if exists.
|
850 |
+
INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
|
851 |
+
INFO:datasets.builder:Found cached dataset text (/home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101)
|
852 |
+
INFO:datasets.info:Loading Dataset info from /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101
|
853 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-798e68ee1238406a.arrow
|
854 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-08141c170f1669b9.arrow
|
855 |
+
WARNING:__main__:The tokenizer picked seems to have a very large `model_max_length` (1000000000000000019884624838656). Using block_size=1024 instead. You can change that default value by passing --block_size xxx.
|
856 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-2ba0b834485aeaf5.arrow
|
857 |
+
INFO:datasets.arrow_dataset:Loading cached processed dataset at /home/iais_marenpielka/.cache/huggingface/datasets/text/default-481a1a6a0ca4575e/0.0.0/96636a050ef51804b84abbfd4f4ad440e01153c24b86293eb5c3b300a41f9101/cache-7a0a05502f2d2ac6.arrow
|
858 |
+
WARNING:accelerate.utils.other: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.
|
859 |
+
INFO:root:Epoch 8.0: Train Loss = 0.0148, Eval Loss = 0.05825383961200714
|
860 |
+
INFO:absl:Using default tokenizer.
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3166550552
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72428eb693eb4400f6f9ebc2b541739b8e512b7964d04dea4072bfce7197fd14
|
3 |
size 3166550552
|
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 1024,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 1024
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 64002,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "[PAD]"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e35118fac8928c2503b72682aeecba0516bf0a7b8ce487ee06590491631f00dc
|
3 |
size 5240
|