yyding1 / gner Goto Github PK

$ bash scripts/eval_t5_task_adaptation.sh
++ shuf -i25000-30000 -n1
+ port=27486
+ BEAM_SIZE=1
+ MODEL_NAME_OR_PATH=./../../LLM_checkpoint/GNER-T5-base
+ DATA_DIR=data
+ DATA_CONFIG_DIR=configs/dataset_configs/task_adaptation_configs
+ INSTRUCTION_FILE=configs/instruction_configs/instruction.json
+ OUTPUT_DIR=output/flan-t5-base-task-adaptation-beam1
+ RUN_NAME=flan-t5-base-experiment
+ deepspeed --include=localhost:6,7 --master_port 27486 src/run.py --bf16 True --tf32 True --generation_num_beams 1 --do_predict --predict_with_generate --model_name_or_path ./../../LLM_checkpoint/GNER-T5-base --data_dir data --preprocessing_num_workers 4 --data_config_dir configs/dataset_configs/task_adaptation_configs --instruction_file configs/instruction_configs/instruction.json --output_dir output/flan-t5-base-task-adaptation-beam1 --per_device_eval_batch_size 4 --run_name flan-t5-base-experiment --max_source_length 640 --max_target_length 640 --generation_max_length 640 --overwrite_output_dir --overwrite_cache --seed 1234
[2024-03-18 10:27:51,415] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-03-18 10:28:06,363] [WARNING] [runner.py:202:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only.
[2024-03-18 10:28:06,409] [INFO] [runner.py:568:main] cmd = /data2/derongxu/anaconda3/envs/py/bin/python -u -m deepspeed.launcher.launch --world_info=eyJsb2NhbGhvc3QiOiBbNiwgN119 --master_addr=127.0.0.1 --master_port=27486 --enable_each_rank_log=None src/run.py --bf16 True --tf32 True --generation_num_beams 1 --do_predict --predict_with_generate --model_name_or_path ./../../LLM_checkpoint/GNER-T5-base --data_dir data --preprocessing_num_workers 4 --data_config_dir configs/dataset_configs/task_adaptation_configs --instruction_file configs/instruction_configs/instruction.json --output_dir output/flan-t5-base-task-adaptation-beam1 --per_device_eval_batch_size 4 --run_name flan-t5-base-experiment --max_source_length 640 --max_target_length 640 --generation_max_length 640 --overwrite_output_dir --overwrite_cache --seed 1234
[2024-03-18 10:28:10,530] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2024-03-18 10:28:16,303] [INFO] [launch.py:145:main] WORLD INFO DICT: {'localhost': [6, 7]}
[2024-03-18 10:28:16,303] [INFO] [launch.py:151:main] nnodes=1, num_local_procs=2, node_rank=0
[2024-03-18 10:28:16,303] [INFO] [launch.py:162:main] global_rank_mapping=defaultdict(<class 'list'>, {'localhost': [0, 1]})
[2024-03-18 10:28:16,303] [INFO] [launch.py:163:main] dist_world_size=2
[2024-03-18 10:28:16,303] [INFO] [launch.py:165:main] Setting CUDA_VISIBLE_DEVICES=6,7
[2024-03-18 10:28:16,318] [INFO] [launch.py:253:main] process 417252 spawned with command: ['/data2/derongxu/anaconda3/envs/py/bin/python', '-u', 'src/run.py', '--local_rank=0', '--bf16', 'True', '--tf32', 'True', '--generation_num_beams', '1', '--do_predict', '--predict_with_generate', '--model_name_or_path', './../../LLM_checkpoint/GNER-T5-base', '--data_dir', 'data', '--preprocessing_num_workers', '4', '--data_config_dir', 'configs/dataset_configs/task_adaptation_configs', '--instruction_file', 'configs/instruction_configs/instruction.json', '--output_dir', 'output/flan-t5-base-task-adaptation-beam1', '--per_device_eval_batch_size', '4', '--run_name', 'flan-t5-base-experiment', '--max_source_length', '640', '--max_target_length', '640', '--generation_max_length', '640', '--overwrite_output_dir', '--overwrite_cache', '--seed', '1234']
[2024-03-18 10:28:16,327] [INFO] [launch.py:253:main] process 417253 spawned with command: ['/data2/derongxu/anaconda3/envs/py/bin/python', '-u', 'src/run.py', '--local_rank=1', '--bf16', 'True', '--tf32', 'True', '--generation_num_beams', '1', '--do_predict', '--predict_with_generate', '--model_name_or_path', './../../LLM_checkpoint/GNER-T5-base', '--data_dir', 'data', '--preprocessing_num_workers', '4', '--data_config_dir', 'configs/dataset_configs/task_adaptation_configs', '--instruction_file', 'configs/instruction_configs/instruction.json', '--output_dir', 'output/flan-t5-base-task-adaptation-beam1', '--per_device_eval_batch_size', '4', '--run_name', 'flan-t5-base-experiment', '--max_source_length', '640', '--max_target_length', '640', '--generation_max_length', '640', '--overwrite_output_dir', '--overwrite_cache', '--seed', '1234']
Using the `WANDB_DISABLED` environment variable is deprecated and will be removed in v5. Use the --report_to flag to control the integrations used for logging result (for instance --report_to none).
03/18/2024 10:28:35 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: True
Using the `WANDB_DISABLED` environment variable is deprecated and will be removed in v5. Use the --report_to flag to control the integrations used for logging result (for instance --report_to none).
03/18/2024 10:28:35 - INFO - __main__ - 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=True,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_pin_memory=True,
ddp_backend=None,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
do_eval=False,
do_predict=True,
do_train=False,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=no,
fp16=False,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_config={'fsdp_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=640,
generation_num_beams=1,
gradient_accumulation_steps=1,
gradient_checkpointing=False,
greater_is_better=None,
group_by_length=False,
half_precision_backend=auto,
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,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=5e-05,
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=output/flan-t5-base-task-adaptation-beam1/runs/Mar18_10-28-35_sota,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=500,
logging_strategy=steps,
lr_scheduler_type=linear,
max_grad_norm=1.0,
max_steps=-1,
metric_for_best_model=None,
mp_parameters=,
no_cuda=False,
num_train_epochs=3.0,
optim=adamw_hf,
optim_args=None,
output_dir=output/flan-t5-base-task-adaptation-beam1,
overwrite_output_dir=True,
past_index=-1,
per_device_eval_batch_size=4,
per_device_train_batch_size=8,
predict_with_generate=True,
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=flan-t5-base-experiment,
save_on_each_node=False,
save_safetensors=False,
save_steps=500,
save_strategy=steps,
save_total_limit=None,
seed=1234,
sharded_ddp=[],
skip_memory_metrics=True,
sortish_sampler=False,
tf32=True,
torch_compile=False,
torch_compile_backend=None,
torch_compile_mode=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.0,
warmup_steps=0,
weight_decay=0.0,
xpu_backend=None,
)
03/18/2024 10:28:35 - WARNING - __main__ - Process rank: 1, device: cuda:1, n_gpu: 1distributed training: True, 16-bits training: True