我正在尝试使用 gpt-2 模型的条件文本生成来调整它以获得一个好的聊天机器人。我正在使用nsheppard 的代码在我的自定义数据集上重新训练它。
我在从 Facebook 数据中提取的自定义对话数据集上训练了我的模型。我将样本长度更改为 20，因为它们是交互式条件生成期间的对话。
数据集如下所示：
How are you
Hi Great and you
Am also good
So you re a graphic designer
Yeah
How can you contribute to making the game In d graphics aspect
Can you show me some of your work if u don t mind
Am planning to learn making it a motion type
U can go through my photos
K
Can you make animations for it
Flash animations to be specific
No please only stable ones
Ok
但是，经过培训后，当我尝试与它聊天时，它却是在完成我的句子而不是回复它们。
User >>> bye
======================================== SAMPLE 1 ========================================
and
hi
are there any positions in khrzh being appointed right now
我知道 interactive_conditional_samples.py 是为了根据提示完成句子而构建的，但我认为更改数据集会起作用，并确保它不起作用。
火车.py
#!/usr/bin/env python3
# Usage:
# PYTHONPATH=src ./train --dataset <file|directory|glob>
import argparse
import json
import os
import numpy as np
import tensorflow as tf
import time
import tqdm
from tensorflow.core.protobuf import rewriter_config_pb2
import model, sample, encoder
from load_dataset import load_dataset, Sampler
from accumulate import AccumulatingOptimizer
import memory_saving_gradients
CHECKPOINT_DIR = 'checkpoint'
SAMPLE_DIR = 'samples'
parser = argparse.ArgumentParser(
description='Fine-tune GPT-2 on your custom dataset.',
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('--dataset', metavar='PATH', type=str, required=True, help='Input file, directory, or glob pattern (utf-8 text, or preencoded .npz files).')
parser.add_argument('--model_name', metavar='MODEL', type=str, default='117M', help='Pretrained model name')
parser.add_argument('--combine', metavar='CHARS', type=int, default=50000, help='Concatenate input files with <|endoftext|> separator into chunks of this minimum size')
parser.add_argument('--batch_size', metavar='SIZE', type=int, default=1, help='Batch size')
parser.add_argument('--learning_rate', metavar='LR', type=float, default=0.00002, help='Learning rate for Adam')
parser.add_argument('--accumulate_gradients', metavar='N', type=int, default=1, help='Accumulate gradients across N minibatches.')
parser.add_argument('--memory_saving_gradients', default=False, action='store_true', help='Use gradient checkpointing to reduce vram usage.')
parser.add_argument('--only_train_transformer_layers', default=False, action='store_true', help='Restrict training to the transformer blocks.')
parser.add_argument('--optimizer', type=str, default='adam', help='Optimizer. <adam|sgd>.')
parser.add_argument('--noise', type=float, default=0.0, help='Add noise to input training data to regularize against typos.')
parser.add_argument('--top_k', type=int, default=40, help='K for top-k sampling.')
parser.add_argument('--top_p', type=float, default=0.0, help='P for top-p sampling. Overrides top_k if set > 0.')
parser.add_argument('--restore_from', type=str, default='latest', help='Either "latest", "fresh", or a path to a checkpoint file')
parser.add_argument('--run_name', type=str, default='run1', help='Run id. Name of subdirectory in checkpoint/ and samples/')
parser.add_argument('--sample_every', metavar='N', type=int, default=100, help='Generate samples every N steps')
parser.add_argument('--sample_length', metavar='TOKENS', type=int, default=1023, help='Sample this many tokens')
parser.add_argument('--sample_num', metavar='N', type=int, default=1, help='Generate this many samples')
parser.add_argument('--save_every', metavar='N', type=int, default=1000, help='Write a checkpoint every N steps')
parser.add_argument('--val_dataset', metavar='PATH', type=str, default=None, help='Dataset for validation loss, defaults to --dataset.')
parser.add_argument('--val_batch_size', metavar='SIZE', type=int, default=2, help='Batch size for validation.')
parser.add_argument('--val_batch_count', metavar='N', type=int, default=40, help='Number of batches for validation.')
parser.add_argument('--val_every', metavar='STEPS', type=int, default=0, help='Calculate validation loss every STEPS steps.')
def maketree(path):
try:
os.makedirs(path)
except:
pass
def randomize(context, hparams, p):
if p > 0:
mask = tf.random.uniform(shape=tf.shape(context)) < p
noise = tf.random.uniform(shape=tf.shape(context), minval=0, maxval=hparams.n_vocab, dtype=tf.int32)
return tf.where(mask, noise, context)
else:
return context
def main():
args = parser.parse_args()
enc = encoder.get_encoder(args.model_name)
hparams = model.default_hparams()
with open(os.path.join('models', args.model_name, 'hparams.json')) as f:
hparams.override_from_dict(json.load(f))
if args.sample_length > hparams.n_ctx:
raise ValueError(
"Can't get samples longer than window size: %s" % hparams.n_ctx)
if args.model_name == '345M':
args.memory_saving_gradients = True
if args.optimizer == 'adam':
args.only_train_transformer_layers = True
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
config.graph_options.rewrite_options.layout_optimizer = rewriter_config_pb2.RewriterConfig.OFF
with tf.Session(config=config) as sess:
context = tf.placeholder(tf.int32, [args.batch_size, None])
context_in = randomize(context, hparams, args.noise)
output = model.model(hparams=hparams, X=context_in)
loss = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=context[:, 1:], logits=output['logits'][:, :-1]))
if args.val_every > 0:
val_context = tf.placeholder(tf.int32, [args.val_batch_size, None])
val_output = model.model(hparams=hparams, X=val_context)
val_loss = tf.reduce_mean(
tf.nn.sparse_softmax_cross_entropy_with_logits(
labels=val_context[:, 1:], logits=val_output['logits'][:, :-1]))
val_loss_summary = tf.summary.scalar('val_loss', val_loss)
tf_sample = sample.sample_sequence(
hparams=hparams,
length=args.sample_length,
context=context,
batch_size=args.batch_size,
temperature=1.0,
top_k=args.top_k,
top_p=args.top_p)
all_vars = [v for v in tf.trainable_variables() if 'model' in v.name]
train_vars = [v for v in all_vars if '/h' in v.name] if args.only_train_transformer_layers else all_vars
if args.optimizer == 'adam':
opt = tf.train.AdamOptimizer(learning_rate=args.learning_rate)
elif args.optimizer == 'sgd':
opt = tf.train.GradientDescentOptimizer(learning_rate=args.learning_rate)
else:
exit('Bad optimizer:', args.optimizer)
if args.accumulate_gradients > 1:
if args.memory_saving_gradients:
exit("Memory saving gradients are not implemented for gradient accumulation yet.")
opt = AccumulatingOptimizer(
opt=opt,
var_list=train_vars)
opt_reset = opt.reset()
opt_compute = opt.compute_gradients(loss)
opt_apply = opt.apply_gradients()
summary_loss = tf.summary.scalar('loss', opt_apply)
else:
if args.memory_saving_gradients:
opt_grads = memory_saving_gradients.gradients(loss, train_vars)
else:
opt_grads = tf.gradients(loss, train_vars)
opt_grads = list(zip(opt_grads, train_vars))
opt_apply = opt.apply_gradients(opt_grads)
summary_loss = tf.summary.scalar('loss', loss)
summary_lr = tf.summary.scalar('learning_rate', args.learning_rate)
summaries = tf.summary.merge([summary_lr, summary_loss])
summary_log = tf.summary.FileWriter(
os.path.join(CHECKPOINT_DIR, args.run_name))
saver = tf.train.Saver(
var_list=all_vars,
max_to_keep=5,
keep_checkpoint_every_n_hours=2)
sess.run(tf.global_variables_initializer())
if args.restore_from == 'latest':
ckpt = tf.train.latest_checkpoint(
os.path.join(CHECKPOINT_DIR, args.run_name))
if ckpt is None:
# Get fresh GPT weights if new run.
ckpt = tf.train.latest_checkpoint(
os.path.join('models', args.model_name))
elif args.restore_from == 'fresh':
ckpt = tf.train.latest_checkpoint(
os.path.join('models', args.model_name))
else:
ckpt = tf.train.latest_checkpoint(args.restore_from)
print('Loading checkpoint', ckpt)
saver.restore(sess, ckpt)
print('Loading dataset...')
chunks = load_dataset(enc, args.dataset, args.combine)
data_sampler = Sampler(chunks)
if args.val_every > 0:
val_chunks = load_dataset(enc, args.val_dataset, args.combine) if args.val_dataset else chunks
print('dataset has', data_sampler.total_size, 'tokens')
print('Training...')
if args.val_every > 0:
# Sample from validation set once with fixed seed to make
# it deterministic during training as well as across runs.
val_data_sampler = Sampler(val_chunks, seed=1)
val_batches = [[val_data_sampler.sample(1024) for _ in range(args.val_batch_size)]
for _ in range(args.val_batch_count)]
counter = 1
counter_path = os.path.join(CHECKPOINT_DIR, args.run_name, 'counter')
if os.path.exists(counter_path):
# Load the step number if we're resuming a run
# Add 1 so we don't immediately try to save again
with open(counter_path, 'r') as fp:
counter = int(fp.read()) + 1
def save():
maketree(os.path.join(CHECKPOINT_DIR, args.run_name))
print(
'Saving',
os.path.join(CHECKPOINT_DIR, args.run_name,
'model-{}').format(counter))
saver.save(
sess,
os.path.join(CHECKPOINT_DIR, args.run_name, 'model'),
global_step=counter)
with open(counter_path, 'w') as fp:
fp.write(str(counter) + '\n')
def generate_samples():
print('Generating samples...')
context_tokens = data_sampler.sample(1)
all_text = []
index = 0
while index < args.sample_num:
out = sess.run(
tf_sample,
feed_dict={context: args.batch_size * [context_tokens]})
for i in range(min(args.sample_num - index, args.batch_size)):
text = enc.decode(out[i])
text = '======== SAMPLE {} ========\n{}\n'.format(
index + 1, text)
all_text.append(text)
index += 1
print(text)
maketree(os.path.join(SAMPLE_DIR, args.run_name))
with open(
os.path.join(SAMPLE_DIR, args.run_name,
'samples-{}').format(counter), 'w') as fp:
fp.write('\n'.join(all_text))
def validation():
print('Calculating validation loss...')
losses = []
for batch in tqdm.tqdm(val_batches):
losses.append(sess.run(val_loss, feed_dict={val_context: batch}))
v_val_loss = np.mean(losses)
v_summary = sess.run(val_loss_summary, feed_dict={val_loss: v_val_loss})
summary_log.add_summary(v_summary, counter)
summary_log.flush()
print(
'[{counter} | {time:2.2f}] validation loss = {loss:2.2f}'
.format(
counter=counter,
time=time.time() - start_time,
loss=v_val_loss))
def sample_batch():
return [data_sampler.sample(1024) for _ in range(args.batch_size)]
avg_loss = (0.0, 0.0)
start_time = time.time()
try:
while True:
if counter % args.save_every == 0:
save()
if counter % args.sample_every == 0:
generate_samples()
if args.val_every > 0 and (counter % args.val_every == 0 or counter == 1):
validation()
if args.accumulate_gradients > 1:
sess.run(opt_reset)
for _ in range(args.accumulate_gradients):
sess.run(
opt_compute, feed_dict={context: sample_batch()})
(v_loss, v_summary) = sess.run((opt_apply, summaries))
else:
(_, v_loss, v_summary) = sess.run(
(opt_apply, loss, summaries),
feed_dict={context: sample_batch()})
summary_log.add_summary(v_summary, counter)
avg_loss = (avg_loss[0] * 0.99 + v_loss,
avg_loss[1] * 0.99 + 1.0)
print(
'[{counter} | {time:2.2f}] loss={loss:2.2f} avg={avg:2.2f}'
.format(
counter=counter,
time=time.time() - start_time,
loss=v_loss,
avg=avg_loss[0] / avg_loss[1]))
counter += 1
except KeyboardInterrupt:
print('interrupted')
save()
if __name__ == '__main__':
main()
示例.py
import tensorflow as tf
import model
def top_k_logits(logits, k):
if k == 0:
# no truncation
return logits
def _top_k():
values, _ = tf.nn.top_k(logits, k=k)
min_values = values[:, -1, tf.newaxis]
return tf.where(
logits < min_values,
tf.ones_like(logits, dtype=logits.dtype) * -1e10,
logits,
)
return tf.cond(
tf.equal(k, 0),
lambda: logits,
lambda: _top_k(),
)
def top_p_logits(logits, p):
with tf.variable_scope('top_p_logits'):
logits_sort = tf.sort(logits, direction='DESCENDING')
probs_sort = tf.nn.softmax(logits_sort)
probs_sums = tf.cumsum(probs_sort, axis=1, exclusive=True)
logits_masked = tf.where(probs_sums < p, logits_sort, tf.ones_like(logits_sort)*1000) # [batchsize, vocab]
min_logits = tf.reduce_min(logits_masked, axis=1, keepdims=True) # [batchsize, 1]
return tf.where(
logits < min_logits,
tf.ones_like(logits, dtype=logits.dtype) * -1e10,
logits,
)
def sample_sequence(*, hparams, length, start_token=None, batch_size=None, context=None, temperature=1, top_k=0, top_p=0.0):
if start_token is None:
assert context is not None, 'Specify exactly one of start_token and context!'
else:
assert context is None, 'Specify exactly one of start_token and context!'
context = tf.fill([batch_size, 1], start_token)
def step(hparams, tokens, past=None):
lm_output = model.model(hparams=hparams, X=tokens, past=past, reuse=tf.AUTO_REUSE)
logits = lm_output['logits'][:, :, :hparams.n_vocab]
presents = lm_output['present']
presents.set_shape(model.past_shape(hparams=hparams, batch_size=batch_size))
return {
'logits': logits,
'presents': presents,
}
with tf.name_scope('sample_sequence'):
# Don't feed the last context token -- leave that to the loop below
# TODO: Would be slightly faster if we called step on the entire context,
# rather than leaving the last token transformer calculation to the while loop.
context_output = step(hparams, context[:, :-1])
def body(past, prev, output):
next_outputs = step(hparams, prev[:, tf.newaxis], past=past)
logits = next_outputs['logits'][:, -1, :] / tf.to_float(temperature)
if top_p > 0.0:
logits = top_p_logits(logits, p=top_p)
else:
logits = top_k_logits(logits, k=top_k)
samples = tf.multinomial(logits, num_samples=1, output_dtype=tf.int32)
return [
tf.concat([past, next_outputs['presents']], axis=-2),
tf.squeeze(samples, axis=[1]),
tf.concat([output, samples], axis=1),
]
def cond(*args):
return True
_, _, tokens = tf.while_loop(
cond=cond, body=body,
maximum_iterations=length,
loop_vars=[
context_output['presents'],
context[:, -1],
context,
],
shape_invariants=[
tf.TensorShape(model.past_shape(hparams=hparams, batch_size=batch_size)),
tf.TensorShape([batch_size]),
tf.TensorShape([batch_size, None]),
],
back_prop=False,
)
return tokens
interactive_conditional_samples.py
#!/usr/bin/env python3
import fire
import json
import os
import numpy as np
import tensorflow as tf
import model, sample, encoder
def interact_model(
model_name='chatbot',
seed=None,
nsamples=1,
batch_size=1,
length=20,
temperature=1,
top_k=0,
top_p=0.0
):
"""
Interactively run the model
:model_name=chatbot : String, which model to use
:seed=None : Integer seed for random number generators, fix seed to reproduce
results
:nsamples=1 : Number of samples to return total
:batch_size=1 : Number of batches (only affects speed/memory). Must divide nsamples.
:length=None : Number of tokens in generated text, if None (default), is
determined by model hyperparameters
:temperature=1 : Float value controlling randomness in boltzmann
distribution. Lower temperature results in less random completions. As the
temperature approaches zero, the model will become deterministic and
repetitive. Higher temperature results in more random completions.
:top_k=0 : Integer value controlling diversity. 1 means only 1 word is
considered for each step (token), resulting in deterministic completions,
while 40 means 40 words are considered at each step. 0 (default) is a
special setting meaning no restrictions. 40 generally is a good value.
:top_p=0.0 : Float value controlling diversity. Implements nucleus sampling,
overriding top_k if set to a value > 0. A good setting is 0.9.
"""
if batch_size is None:
batch_size = 1
assert nsamples % batch_size == 0
enc = encoder.get_encoder(model_name)
hparams = model.default_hparams()
with open(os.path.join('models', model_name, 'hparams.json')) as f:
hparams.override_from_dict(json.load(f))
if length is None:
length = hparams.n_ctx // 2
elif length > hparams.n_ctx:
raise ValueError("Can't get samples longer than window size: %s" % hparams.n_ctx)
with tf.Session(graph=tf.Graph()) as sess:
context = tf.placeholder(tf.int32, [batch_size, None])
np.random.seed(seed)
tf.set_random_seed(seed)
output = sample.sample_sequence(
hparams=hparams, length=length,
context=context,
batch_size=batch_size,
temperature=temperature, top_k=top_k, top_p=top_p
)
saver = tf.train.Saver()
ckpt = tf.train.latest_checkpoint(os.path.join('models', model_name))
saver.restore(sess, ckpt)
while True:
raw_text = input("User >>> ")
while not raw_text:
print('Prompt should not be empty!')
raw_text = input("User >>> ")
context_tokens = enc.encode(raw_text)
generated = 0
for _ in range(nsamples // batch_size):
out = sess.run(output, feed_dict={
context: [context_tokens for _ in range(batch_size)]
})[:, len(context_tokens):]
for i in range(batch_size):
generated += 1
text = enc.decode(out[i])
print("=" * 40 + " SAMPLE " + str(generated) + " " + "=" * 40)
print(text)
print("=" * 80)
if __name__ == '__main__':
fire.Fire(interact_model)
如何调整代码以使其像聊天机器人一样工作？我猜它与 sample.py 中的上下文部分有关，但我不确定这将如何工作。