from utils import DataFiles
dataFiles = DataFiles(__file__)
inputRaw = dataFiles.input
inputRawEX = dataFiles.inputEX
def calc_score(q1, q2):
ans = 0
if (len(q1) > 0):
for i in range(1, len(q1) + 1):
ans += i * q1[-i]
else:
for i in range(1, len(q2) + 1):
ans += i * q2[-i]
return ans
def part1(q1, q2):
while (len(q1) > 0 and len(q2) > 0):
c1 = q1[0]
c2 = q2[0]
if c1 > c2:
q1 = q1[1:] + [c1, c2]
q2 = q2[1:]
else:
q1 = q1[1:]
from utils import DataFiles
dataFiles = DataFiles(__file__)
input = dataFiles.get_input() # inputRaw = dataFiles.input
inputEX = dataFiles.get_inputEX() # inputRawEX = dataFiles.inputEX
numbers = [int(line) for line in input]
numbers.sort()
diff_1 = 0
diff_3 = 1
prev = 0
for curr in numbers:
diff = curr - prev
if diff == 1:
diff_1 += 1
if diff == 3:
diff_3 += 1
prev = curr
print('Part 1:', diff_1 * diff_3)
numbers.insert(0, 0)
dp = [1] + [0] * len(numbers)
for i in range(len(numbers)):
for j in range(i):
def main():
parser = argparse.ArgumentParser()
# Required parameters
parser.add_argument(
"--data_dir",
default=None,
type=str,
required=True,
help=
"The input data dir. Should contain the .tsv files (or other data files) for the task.",
)
parser.add_argument(
"--model_type",
default=None,
type=str,
required=True,
help="Model type selected in the list: " +
", ".join(MODEL_CLASSES.keys()),
)
parser.add_argument(
"--model_name_or_path",
default=None,
type=str,
required=True,
help="Path to pre-trained model or shortcut name selected in the list: "
+ ", ".join(ALL_MODELS),
)
parser.add_argument(
"--task_name",
default=None,
type=str,
required=True,
help="The name of the task to train selected in the list: " +
", ".join(processors.keys()),
)
parser.add_argument(
"--output_dir",
default=None,
type=str,
required=True,
help=
"The output directory where the model predictions and checkpoints will be written.",
)
parser.add_argument(
"--bert_representation",
default="pool",
choices=["avg", "pool"],
type=str,
help="The BERT representation type",
)
parser.add_argument(
"--similarity_function",
default="pool",
choices=["dot"],
type=str,
help="The similarity scoring function",
)
# Other parameters
parser.add_argument(
"--config_name",
default="",
type=str,
help="Pretrained config name or path if not the same as model_name",
)
parser.add_argument(
"--tokenizer_name",
default="",
type=str,
help="Pretrained tokenizer name or path if not the same as model_name",
)
parser.add_argument(
"--cache_dir",
default="",
type=str,
help=
"Where do you want to store the pre-trained models downloaded from s3",
)
parser.add_argument(
"--max_seq_length",
default=128,
type=int,
help=
"The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded.",
)
parser.add_argument("--do_train",
action="store_true",
help="Whether to run training.")
parser.add_argument("--do_eval",
action="store_true",
help="Whether to run eval on the dev set.")
parser.add_argument(
"--evaluate_during_training",
action="store_true",
help="Run evaluation during training at each logging step.",
)
parser.add_argument(
"--do_lower_case",
action="store_true",
help="Set this flag if you are using an uncased model.",
)
parser.add_argument(
"--per_gpu_train_batch_size",
default=8,
type=int,
help="Batch size per GPU/CPU for training.",
)
parser.add_argument(
"--per_gpu_eval_batch_size",
default=8,
type=int,
help="Batch size per GPU/CPU for evaluation.",
)
parser.add_argument(
"--gradient_accumulation_steps",
type=int,
default=1,
help=
"Number of updates steps to accumulate before performing a backward/update pass.",
)
parser.add_argument("--learning_rate",
default=5e-5,
type=float,
help="The initial learning rate for Adam.")
parser.add_argument("--weight_decay",
default=0.0,
type=float,
help="Weight decay if we apply some.")
parser.add_argument("--adam_epsilon",
default=1e-8,
type=float,
help="Epsilon for Adam optimizer.")
parser.add_argument("--max_grad_norm",
default=1.0,
type=float,
help="Max gradient norm.")
parser.add_argument(
"--num_train_epochs",
default=3.0,
type=float,
help="Total number of training epochs to perform.",
)
parser.add_argument(
"--max_steps",
default=-1,
type=int,
help=
"If > 0: set total number of training steps to perform. Override num_train_epochs.",
)
parser.add_argument("--warmup_steps",
default=0,
type=int,
help="Linear warmup over warmup_steps.")
parser.add_argument("--logging_steps",
type=int,
default=500,
help="Log every X updates steps.")
parser.add_argument("--save_steps",
type=int,
default=500,
help="Save checkpoint every X updates steps.")
parser.add_argument(
"--eval_all_checkpoints",
action="store_true",
help=
"Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number",
)
parser.add_argument("--no_cuda",
action="store_true",
help="Avoid using CUDA when available")
parser.add_argument(
"--overwrite_output_dir",
action="store_true",
help="Overwrite the content of the output directory",
)
parser.add_argument(
"--overwrite_cache",
action="store_true",
help="Overwrite the cached training and evaluation sets",
)
parser.add_argument("--seed",
type=int,
default=42,
help="random seed for initialization")
parser.add_argument(
"--fp16",
action="store_true",
help=
"Whether to use 16-bit (mixed) precision (through NVIDIA apex) instead of 32-bit",
)
parser.add_argument(
"--fp16_opt_level",
type=str,
default="O1",
help=
"For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']."
"See details at https://nvidia.github.io/apex/amp.html",
)
parser.add_argument(
"--save_total_limit",
type=int,
default=None,
help=
"Limit the total amount of checkpoints, delete the older checkpoints in the output_dir, does not delete by default",
)
parser.add_argument("--local_rank",
type=int,
default=-1,
help="For distributed training: local_rank")
parser.add_argument("--server_ip",
type=str,
default="",
help="For distant debugging.")
parser.add_argument("--server_port",
type=str,
default="",
help="For distant debugging.")
args = parser.parse_args()
logging.basicConfig(
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
datefmt="%m/%d/%Y %H:%M:%S",
level=logging.INFO if args.local_rank in [-1, 0] else logging.WARN,
)
if (os.path.exists(args.output_dir) and os.listdir(args.output_dir)
and args.do_train and not args.overwrite_output_dir):
# set to load the latest checkpoint for training
args.model_name_or_path = args.output_dir
all_model_checkpoints = [
ckpt for ckpt in os.listdir(args.model_name_or_path)
if os.path.isdir(os.path.join(args.model_name_or_path, ckpt))
]
all_model_checkpoints = [(ckpt.split("-")[-1] if "-" in ckpt else -1,
ckpt) for ckpt in all_model_checkpoints]
all_model_checkpoints.sort(reverse=True)
args.model_name_or_path = os.path.join(args.model_name_or_path,
all_model_checkpoints[0][1])
logger.info("setting to load the model from %s",
args.model_name_or_path)
# Setup distant debugging if needed
if args.server_ip and args.server_port:
# Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script
import ptvsd
print("Waiting for debugger attach")
ptvsd.enable_attach(address=(args.server_ip, args.server_port),
redirect_output=True)
ptvsd.wait_for_attach()
# Setup CUDA, GPU & distributed training
if args.local_rank == -1 or args.no_cuda:
device = torch.device("cuda" if torch.cuda.is_available()
and not args.no_cuda else "cpu")
args.n_gpu = 0 if args.no_cuda else torch.cuda.device_count()
else: # Initializes the distributed backend which will take care of sychronizing nodes/GPUs
torch.cuda.set_device(args.local_rank)
device = torch.device("cuda", args.local_rank)
torch.distributed.init_process_group(backend="nccl")
args.n_gpu = 1
args.device = device
# Setup logging
logger.warning(
"Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s",
args.local_rank,
device,
args.n_gpu,
bool(args.local_rank != -1),
args.fp16,
)
# Set seed
set_seed(args)
# Prepare GLUE task
args.task_name = args.task_name.lower()
if args.task_name not in processors:
raise ValueError("Task not found: %s" % (args.task_name))
processor = processors[args.task_name]()
args.output_mode = output_modes[args.task_name]
num_labels = 2
# Load pretrained model and tokenizer
if args.local_rank not in [-1, 0]:
torch.distributed.barrier(
) # Make sure only the first process in distributed training will download model & vocab
args.model_type = args.model_type.lower()
config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type]
config = config_class.from_pretrained(
args.config_name if args.config_name else args.model_name_or_path,
num_labels=num_labels,
finetuning_task=args.task_name,
cache_dir=args.cache_dir if args.cache_dir else None,
)
tokenizer = tokenizer_class.from_pretrained(
args.tokenizer_name
if args.tokenizer_name else args.model_name_or_path,
do_lower_case=args.do_lower_case,
cache_dir=args.cache_dir if args.cache_dir else None,
)
model = model_class.from_pretrained(
args.model_name_or_path,
from_tf=bool(".ckpt" in args.model_name_or_path),
config=config,
cache_dir=args.cache_dir if args.cache_dir else None,
)
if args.local_rank == 0:
torch.distributed.barrier(
) # Make sure only the first process in distributed training will download model & vocab
model.to(args.device)
logger.info("Training/evaluation parameters %s", args)
# Training
if args.do_train:
datafiles = DataFiles(args.data_dir)
if os.path.isfile(
os.path.join(args.model_name_or_path, "datafiles.txt")):
datafiles.load(
os.path.join(args.model_name_or_path, "datafiles.txt"))
global_step = 0
shard_count = 0
if args.local_rank in [-1, 0]:
tb_writer = SummaryWriter()
while True:
todo_file = datafiles.next()
if not todo_file:
break
if args.local_rank == 0:
torch.distributed.barrier()
train_dataset = load_and_cache_examples(args, args.task_name,
tokenizer, todo_file)
args.train_batch_size = args.per_gpu_train_batch_size * max(
1, args.n_gpu)
train_sampler = RandomSampler(
train_dataset
) if args.local_rank == -1 else DistributedSampler(train_dataset)
train_dataloader = DataLoader(train_dataset,
sampler=train_sampler,
batch_size=args.train_batch_size)
if shard_count == 0: # if this is the first shard, create the optimizer or load from the previous checkpoint
# Prepare optimizer and schedule (linear warmup and decay)
no_decay = ["bias", "LayerNorm.weight"]
optimizer_grouped_parameters = [
{
"params": [
p for n, p in model.named_parameters()
if not any(nd in n for nd in no_decay)
],
"weight_decay":
args.weight_decay,
},
{
"params": [
p for n, p in model.named_parameters()
if any(nd in n for nd in no_decay)
],
"weight_decay":
0.0
},
]
t_total = len(
train_dataloader
) // args.gradient_accumulation_steps * args.num_train_epochs * len(
datafiles.all_files) # 280 shards of data files in total
optimizer = AdamW(optimizer_grouped_parameters,
lr=args.learning_rate,
eps=args.adam_epsilon)
scheduler = get_linear_schedule_with_warmup(
optimizer,
num_warmup_steps=args.warmup_steps,
num_training_steps=t_total)
# Check if saved optimizer or scheduler states exist
if os.path.isfile(
os.path.join(args.model_name_or_path,
"optimizer.pt")) and os.path.isfile(
os.path.join(args.model_name_or_path,
"scheduler.pt")):
logger.info("loading optimizer and scheduler from %s",
args.model_name_or_path)
# Load in optimizer and scheduler states
optimizer.load_state_dict(
torch.load(
os.path.join(args.model_name_or_path,
"optimizer.pt")))
scheduler.load_state_dict(
torch.load(
os.path.join(args.model_name_or_path,
"scheduler.pt")))
if args.fp16:
try:
from apex import amp
except ImportError:
raise ImportError(
"Please install apex from https://www.github.com/nvidia/apex to use fp16 training."
)
model, optimizer = amp.initialize(
model, optimizer, opt_level=args.fp16_opt_level)
# multi-gpu training (should be after apex fp16 initialization)
if args.n_gpu > 1:
model = torch.nn.DataParallel(model)
# Distributed training (should be after apex fp16 initialization)
if args.local_rank != -1:
model = torch.nn.parallel.DistributedDataParallel(
model,
device_ids=[args.local_rank],
output_device=args.local_rank,
find_unused_parameters=True,
)
# Train!
logger.info("***** Running training *****")
logger.info(" Num examples = %d", len(train_dataset))
logger.info(" Num Epochs = %d", args.num_train_epochs)
logger.info(" Instantaneous batch size per GPU = %d",
args.per_gpu_train_batch_size)
logger.info(
" Total train batch size (w. parallel, distributed & accumulation) = %d",
args.train_batch_size * args.gradient_accumulation_steps *
(torch.distributed.get_world_size()
if args.local_rank != -1 else 1),
)
logger.info(" Gradient Accumulation steps = %d",
args.gradient_accumulation_steps)
logger.info(" Total optimization steps = %d", t_total)
if shard_count == 0:
# Check if continuing training from a checkpoint
if os.path.exists(args.model_name_or_path):
# set global_step to global_step of last saved checkpoint from model path
try:
global_step = int(
args.model_name_or_path.split("-")[-1].split("/")
[0])
except ValueError:
global_step = 0
epochs_trained = global_step // (
len(train_dataloader) //
args.gradient_accumulation_steps)
logger.info(" Continuing training from checkpoint %s",
args.model_name_or_path)
logger.info(" Continuing training from global step %d",
global_step)
global_step, tr_loss, optimizer, scheduler = train(
args,
train_dataset,
train_dataloader,
model,
tokenizer,
optimizer,
scheduler,
tb_writer,
global_step=global_step)
logger.info(" global_step = %s, average loss = %s", global_step,
tr_loss)
# Save model checkpoint
output_dir = os.path.join(args.output_dir,
"checkpoint-{}".format(global_step))
if not os.path.exists(output_dir):
os.makedirs(output_dir)
model_to_save = (
model.module if hasattr(model, "module") else model
) # Take care of distributed/parallel training
model_to_save.save_pretrained(output_dir)
tokenizer.save_pretrained(output_dir)
torch.save(args, os.path.join(output_dir, "training_args.bin"))
logger.info("Saving model checkpoint to %s", output_dir)
torch.save(optimizer.state_dict(),
os.path.join(output_dir, "optimizer.pt"))
torch.save(scheduler.state_dict(),
os.path.join(output_dir, "scheduler.pt"))
datafiles.save(os.path.join(output_dir, "datafiles.txt"))
logger.info("Saving optimizer and scheduler states to %s",
output_dir)
_rotate_checkpoints(args, "checkpoint")
shard_count += 1
if args.local_rank in [-1, 0]:
tb_writer.close()
# Saving best-practices: if you use defaults names for the model, you can reload it using from_pretrained()
if args.do_train and (args.local_rank == -1
or torch.distributed.get_rank() == 0):
# Create output directory if needed
if not os.path.exists(args.output_dir) and args.local_rank in [-1, 0]:
os.makedirs(args.output_dir)
logger.info("Saving model checkpoint to %s", args.output_dir)
# Save a trained model, configuration and tokenizer using `save_pretrained()`.
# They can then be reloaded using `from_pretrained()`
model_to_save = (model.module if hasattr(model, "module") else model
) # Take care of distributed/parallel training
model_to_save.save_pretrained(args.output_dir)
tokenizer.save_pretrained(args.output_dir)
# Good practice: save your training arguments together with the trained model
torch.save(args, os.path.join(args.output_dir, "training_args.bin"))
# Load a trained model and vocabulary that you have fine-tuned
model = model_class.from_pretrained(args.output_dir)
tokenizer = tokenizer_class.from_pretrained(args.output_dir)
model.to(args.device)
# Evaluation
results = {}
if args.do_eval and args.local_rank in [-1, 0]:
tokenizer = tokenizer_class.from_pretrained(
args.output_dir, do_lower_case=args.do_lower_case)
checkpoints = [args.output_dir]
if args.eval_all_checkpoints:
checkpoints = list(
os.path.dirname(c) for c in sorted(
glob.glob(args.output_dir + "/**/" + WEIGHTS_NAME,
recursive=True)))
logging.getLogger("transformers.modeling_utils").setLevel(
logging.WARN) # Reduce logging
logger.info("Evaluate the following checkpoints: %s", checkpoints)
for checkpoint in checkpoints:
global_step = checkpoint.split(
"-")[-1] if len(checkpoints) > 1 else ""
prefix = checkpoint.split(
"/")[-1] if checkpoint.find("checkpoint") != -1 else ""
model = model_class.from_pretrained(checkpoint)
model.to(args.device)
result = evaluate(args, model, tokenizer, prefix=prefix)
result = dict(
(k + "_{}".format(global_step), v) for k, v in result.items())
results.update(result)
return results
import itertools
import numpy as np
from utils import DataFiles
dataFiles = DataFiles(__file__)
input = dataFiles.get_input()
def part1_iterative(numbers):
for i in range(preamble, len(numbers)):
sums = set()
for nr_j in numbers[i - preamble: i]:
for nr_k in numbers[i - preamble: i]:
sums.add(nr_j + nr_k)
if numbers[i] not in sums:
return numbers[i]
def part1_numpy(numbers):
for i in range(preamble, len(numbers)):
partial_sum = np.array(numbers[i - preamble: i], dtype=np.int64)
sums = partial_sum.reshape(1, -1) + partial_sum.reshape(-1, 1)
for aux in range(0, preamble):
sums[aux][aux] = -1
if numbers[i] not in sums:
return numbers[i]
