SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'huggingface/master'

Browse Source 
# Conflicts:
#	pytorch_transformers/__init__.py
This commit is contained in:
erenup
2019-09-16 19:06:12 +08:00
parent 6e1ac34e2b 32e1332acf
commit 84b9d1c423
88 changed files with 4517 additions and 3909 deletions
Download Patch File Download Diff File Expand all files Collapse all files

357
examples/README.md Normal file
View File

@@ -0,0 +1,357 @@
# Examples
In this section a few examples are put together. All of these examples work for several models, making use of the very
similar API between the different models.
| Section | Description |
|----------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [Language Model fine-tuning](#language-model-fine-tuning) | Fine-tuning the library models for language modeling on a text dataset. Causal language modeling for GPT/GPT-2, masked language modeling for BERT/RoBERTa. |
| [Language Generation](#language-generation) | Conditional text generation using the auto-regressive models of the library: GPT, GPT-2, Transformer-XL and XLNet. |
| [GLUE](#glue) | Examples running BERT/XLM/XLNet/RoBERTa on the 9 GLUE tasks. Examples feature distributed training as well as half-precision. |
| [SQuAD](#squad) | Using BERT for question answering, examples with distributed training. |
## Language model fine-tuning
Based on the script [`run_lm_finetuning.py`](https://github.com/huggingface/pytorch-transformers/blob/master/examples/run_lm_finetuning.py).
Fine-tuning the library models for language modeling on a text dataset for GPT, GPT-2, BERT and RoBERTa (DistilBERT
to be added soon). GPT and GPT-2 are fine-tuned using a causal language modeling (CLM) loss while BERT and RoBERTa
are fine-tuned using a masked language modeling (MLM) loss.
Before running the following example, you should get a file that contains text on which the language model will be
fine-tuned. A good example of such text is the [WikiText-2 dataset](https://blog.einstein.ai/the-wikitext-long-term-dependency-language-modeling-dataset/).
We will refer to two different files: `$TRAIN_FILE`, which contains text for training, and `$TEST_FILE`, which contains
text that will be used for evaluation.
### GPT-2/GPT and causal language modeling
The following example fine-tunes GPT-2 on WikiText-2. We're using the raw WikiText-2 (no tokens were replaced before
the tokenization). The loss here is that of causal language modeling.
```bash
export TRAIN_FILE=/path/to/dataset/wiki.train.raw
export TEST_FILE=/path/to/dataset/wiki.test.raw
python run_lm_finetuning.py \
--output_dir=output \
--model_type=gpt2 \
--model_name_or_path=gpt2 \
--do_train \
--train_data_file=$TRAIN_FILE \
--do_eval \
--eval_data_file=$TEST_FILE
```
This takes about half an hour to train on a single K80 GPU and about one minute for the evaluation to run. It reaches
a score of ~20 perplexity once fine-tuned on the dataset.
### RoBERTa/BERT and masked language modeling
The following example fine-tunes RoBERTa on WikiText-2. Here too, we're using the raw WikiText-2. The loss is different
as BERT/RoBERTa have a bidirectional mechanism; we're therefore using the same loss that was used during their
pre-training: masked language modeling.
In accordance to the RoBERTa paper, we use dynamic masking rather than static masking. The model may, therefore, converge
slightly slower (over-fitting takes more epochs).
We use the `--mlm` flag so that the script may change its loss function.
```bash
export TRAIN_FILE=/path/to/dataset/wiki.train.raw
export TEST_FILE=/path/to/dataset/wiki.test.raw
python run_lm_finetuning.py \
--output_dir=output \
--model_type=roberta \
--model_name_or_path=roberta-base \
--do_train \
--train_data_file=$TRAIN_FILE \
--do_eval \
--eval_data_file=$TEST_FILE \
--mlm
```
## Language generation
Based on the script [`run_generation.py`](https://github.com/huggingface/pytorch-transformers/blob/master/examples/run_generation.py).
Conditional text generation using the auto-regressive models of the library: GPT, GPT-2, Transformer-XL and XLNet.
A similar script is used for our official demo [Write With Transfomer](https://transformer.huggingface.co), where you
can try out the different models available in the library.
Example usage:
```bash
python run_generation.py \
--model_type=gpt2 \
--model_name_or_path=gpt2
```
## GLUE
Based on the script [`run_glue.py`](https://github.com/huggingface/pytorch-transformers/blob/master/examples/run_glue.py).
Fine-tuning the library models for sequence classification on the GLUE benchmark: [General Language Understanding
Evaluation](https://gluebenchmark.com/). This script can fine-tune the following models: BERT, XLM, XLNet and RoBERTa.
GLUE is made up of a total of 9 different tasks. We get the following results on the dev set of the benchmark with an
uncased BERT base model (the checkpoint `bert-base-uncased`). All experiments ran on 8 V100 GPUs with a total train
batch size of 24. Some of these tasks have a small dataset and training can lead to high variance in the results
between different runs. We report the median on 5 runs (with different seeds) for each of the metrics.
| Task | Metric | Result |
|-------|------------------------------|-------------|
| CoLA | Matthew's corr | 55.75 |
| SST-2 | Accuracy | 92.09 |
| MRPC | F1/Accuracy | 90.48/86.27 |
| STS-B | Person/Spearman corr. | 89.03/88.64 |
| QQP | Accuracy/F1 | 90.92/87.72 |
| MNLI | Matched acc./Mismatched acc. | 83.74/84.06 |
| QNLI | Accuracy | 91.07 |
| RTE | Accuracy | 68.59 |
| WNLI | Accuracy | 43.66 |
Some of these results are significantly different from the ones reported on the test set
of GLUE benchmark on the website. For QQP and WNLI, please refer to [FAQ #12](https://gluebenchmark.com/faq) on the webite.
Before running anyone of these GLUE tasks you should download the
[GLUE data](https://gluebenchmark.com/tasks) by running
[this script](https://gist.github.com/W4ngatang/60c2bdb54d156a41194446737ce03e2e)
and unpack it to some directory `$GLUE_DIR`.
```bash
export GLUE_DIR=/path/to/glue
export TASK_NAME=MRPC
python run_glue.py \
--model_type bert \
--model_name_or_path bert-base-cased \
--task_name $TASK_NAME \
--do_train \
--do_eval \
--do_lower_case \
--data_dir $GLUE_DIR/$TASK_NAME \
--max_seq_length 128 \
--per_gpu_train_batch_size 32 \
--learning_rate 2e-5 \
--num_train_epochs 3.0 \
--output_dir /tmp/$TASK_NAME/
```
where task name can be one of CoLA, SST-2, MRPC, STS-B, QQP, MNLI, QNLI, RTE, WNLI.
The dev set results will be present within the text file `eval_results.txt` in the specified output_dir.
In case of MNLI, since there are two separate dev sets (matched and mismatched), there will be a separate
output folder called `/tmp/MNLI-MM/` in addition to `/tmp/MNLI/`.
The code has not been tested with half-precision training with apex on any GLUE task apart from MRPC, MNLI,
CoLA, SST-2. The following section provides details on how to run half-precision training with MRPC. With that being
said, there shouldn’t be any issues in running half-precision training with the remaining GLUE tasks as well,
since the data processor for each task inherits from the base class DataProcessor.
### MRPC
#### Fine-tuning example
The following examples fine-tune BERT on the Microsoft Research Paraphrase Corpus (MRPC) corpus and runs in less
than 10 minutes on a single K-80 and in 27 seconds (!) on single tesla V100 16GB with apex installed.
Before running anyone of these GLUE tasks you should download the
[GLUE data](https://gluebenchmark.com/tasks) by running
[this script](https://gist.github.com/W4ngatang/60c2bdb54d156a41194446737ce03e2e)
and unpack it to some directory `$GLUE_DIR`.
```bash
export GLUE_DIR=/path/to/glue
python run_glue.py \
--model_type bert \
--model_name_or_path bert-base-cased \
--task_name MRPC \
--do_train \
--do_eval \
--do_lower_case \
--data_dir $GLUE_DIR/MRPC/ \
--max_seq_length 128 \
--per_gpu_train_batch_size 32 \
--learning_rate 2e-5 \
--num_train_epochs 3.0 \
--output_dir /tmp/mrpc_output/
```
Our test ran on a few seeds with [the original implementation hyper-
parameters](https://github.com/google-research/bert#sentence-and-sentence-pair-classification-tasks) gave evaluation
results between 84% and 88%.
#### Using Apex and mixed-precision
Using Apex and 16 bit precision, the fine-tuning on MRPC only takes 27 seconds. First install
[apex](https://github.com/NVIDIA/apex), then run the following example:
```bash
export GLUE_DIR=/path/to/glue
python run_glue.py \
--model_type bert \
--model_name_or_path bert-base-cased \
--task_name MRPC \
--do_train \
--do_eval \
--do_lower_case \
--data_dir $GLUE_DIR/MRPC/ \
--max_seq_length 128 \
--per_gpu_train_batch_size 32 \
--learning_rate 2e-5 \
--num_train_epochs 3.0 \
--output_dir /tmp/mrpc_output/ \
--fp16
```
#### Distributed training
Here is an example using distributed training on 8 V100 GPUs. The model used is the BERT whole-word-masking and it
reaches F1 > 92 on MRPC.
```bash
export GLUE_DIR=/path/to/glue
python -m torch.distributed.launch \
--nproc_per_node 8 run_glue.py \
--model_type bert \
--model_name_or_path bert-base-cased \
--task_name MRPC \
--do_train \
--do_eval \
--do_lower_case \
--data_dir $GLUE_DIR/MRPC/ \
--max_seq_length 128 \
--per_gpu_train_batch_size 8 \
--learning_rate 2e-5 \
--num_train_epochs 3.0 \
--output_dir /tmp/mrpc_output/
```
Training with these hyper-parameters gave us the following results:
```bash
acc = 0.8823529411764706
acc_and_f1 = 0.901702786377709
eval_loss = 0.3418912578906332
f1 = 0.9210526315789473
global_step = 174
loss = 0.07231863956341798
```
### MNLI
The following example uses the BERT-large, uncased, whole-word-masking model and fine-tunes it on the MNLI task.
```bash
export GLUE_DIR=/path/to/glue
python -m torch.distributed.launch \
--nproc_per_node 8 run_glue.py \
--model_type bert \
--model_name_or_path bert-base-cased \
--task_name mnli \
--do_train \
--do_eval \
--do_lower_case \
--data_dir $GLUE_DIR/MNLI/ \
--max_seq_length 128 \
--per_gpu_train_batch_size 8 \
--learning_rate 2e-5 \
--num_train_epochs 3.0 \
--output_dir output_dir \
```
The results are the following:
```bash
***** Eval results *****
acc = 0.8679706601466992
eval_loss = 0.4911287787382479
global_step = 18408
loss = 0.04755385363816904
***** Eval results *****
acc = 0.8747965825874695
eval_loss = 0.45516540421714036
global_step = 18408
loss = 0.04755385363816904
```
## SQuAD
Based on the script [`run_squad.py`](https://github.com/huggingface/pytorch-transformers/blob/master/examples/run_squad.py).
#### Fine-tuning on SQuAD
This example code fine-tunes BERT on the SQuAD dataset. It runs in 24 min (with BERT-base) or 68 min (with BERT-large)
on a single tesla V100 16GB. The data for SQuAD can be downloaded with the following links and should be saved in a
$SQUAD_DIR directory.
* [train-v1.1.json](https://rajpurkar.github.io/SQuAD-explorer/dataset/train-v1.1.json)
* [dev-v1.1.json](https://rajpurkar.github.io/SQuAD-explorer/dataset/dev-v1.1.json)
* [evaluate-v1.1.py](https://github.com/allenai/bi-att-flow/blob/master/squad/evaluate-v1.1.py)
```bash
export SQUAD_DIR=/path/to/SQUAD
python run_squad.py \
--model_type bert \
--model_name_or_path bert-base-cased \
--do_train \
--do_eval \
--do_lower_case \
--train_file $SQUAD_DIR/train-v1.1.json \
--predict_file $SQUAD_DIR/dev-v1.1.json \
--per_gpu_train_batch_size 12 \
--learning_rate 3e-5 \
--num_train_epochs 2.0 \
--max_seq_length 384 \
--doc_stride 128 \
--output_dir /tmp/debug_squad/
```
Training with the previously defined hyper-parameters yields the following results:
```bash
f1 = 88.52
exact_match = 81.22
```
#### Distributed training
Here is an example using distributed training on 8 V100 GPUs and Bert Whole Word Masking uncased model to reach a F1 > 93 on SQuAD:
```bash
python -m torch.distributed.launch --nproc_per_node=8 run_squad.py \
--model_type bert \
--model_name_or_path bert-base-cased \
--do_train \
--do_eval \
--do_lower_case \
--train_file $SQUAD_DIR/train-v1.1.json \
--predict_file $SQUAD_DIR/dev-v1.1.json \
--learning_rate 3e-5 \
--num_train_epochs 2 \
--max_seq_length 384 \
--doc_stride 128 \
--output_dir ../models/wwm_uncased_finetuned_squad/ \
--per_gpu_train_batch_size 24 \
--gradient_accumulation_steps 12
```
Training with the previously defined hyper-parameters yields the following results:
```bash
f1 = 93.15
exact_match = 86.91
```
This fine-tuneds model is available as a checkpoint under the reference
`bert-large-uncased-whole-word-masking-finetuned-squad`.

16
examples/distillation/README.md
View File

@@ -9,6 +9,12 @@ DistilBERT stands for Distillated-BERT. DistilBERT is a small, fast, cheap and l
For more information on DistilBERT, please refer to our [detailed blog post](https://medium.com/huggingface/smaller-faster-cheaper-lighter-introducing-distilbert-a-distilled-version-of-bert-8cf3380435b5
).
## Setup
This part of the library has only be tested with Python3.6+. There are few specific dependencies to install before launching a distillation, you can install them with the command `pip install -r requirements.txt`.
**Important note:** The training scripts have been updated to support PyTorch v1.2.0 (there are breakings changes compared to v1.1.0). It is important to note that there is a small internal bug in the current version of PyTorch available on pip that causes a memory leak in our training/distillation. It has been recently fixed and will likely be integrated into the next release. For the moment, we recommend to [compile PyTorch from source](https://github.com/pytorch/pytorch#from-source). Please refer to [issue 1179](https://github.com/huggingface/pytorch-transformers/issues/1179) for more details.
## How to use DistilBERT
PyTorch-Transformers includes two pre-trained DistilBERT models, currently only provided for English (we are investigating the possibility to train and release a multilingual version of DistilBERT):
@@ -68,7 +74,7 @@ python train.py \
By default, this will launch a training on a single GPU (even if more are available on the cluster). Other parameters are available in the command line, please look in `train.py` or run `python train.py --help` to list them.
We highly encourage you to distributed training for training DistilBert as the training corpus is quite large. Here's an example that runs a distributed training on a single node having 4 GPUs:
We highly encourage you to use distributed training for training DistilBert as the training corpus is quite large. Here's an example that runs a distributed training on a single node having 4 GPUs:
```bash
export NODE_RANK=0
@@ -90,11 +96,11 @@ python -m torch.distributed.launch \
train.py \
--force \
--n_gpu $WORLD_SIZE \
--data_file data/dump_concat_wiki_toronto_bk.bert-base-uncased.pickle \
--token_counts data/token_counts_concat_wiki_toronto_bk.bert-base-uncased.pickle \
--dump_path serialization_dir/with_transform/last_word
--data_file data/binarized_text.bert-base-uncased.pickle \
--token_counts data/token_counts.bert-base-uncased.pickle \
--dump_path serialization_dir/my_first_distillation
```
**Tips** Starting distillated training with good initialization of the model weights is crucial to reach decent performance. In our experiments, we initialized our model from a few layers of the teacher (Bert) itself! Please refer to `scripts/extract_for_distil.py` to create a valid initialization checkpoint and use `--from_pretrained_weights` and `--from_pretrained_config` arguments to use this initialization for the distilled training!
**Tips:** Starting distillated training with good initialization of the model weights is crucial to reach decent performance. In our experiments, we initialized our model from a few layers of the teacher (Bert) itself! Please refer to `scripts/extract_for_distil.py` to create a valid initialization checkpoint and use `--from_pretrained_weights` and `--from_pretrained_config` arguments to use this initialization for the distilled training!
Happy distillation!

2
examples/distillation/dataset.py
View File

@@ -77,7 +77,7 @@ class Dataset:
if sub_s[0] != cls_id:
sub_s = np.insert(sub_s, 0, cls_id)
if sub_s[-1] != sep_id:
sub_s = np.insert(sub_s, len(sub_s), cls_id)
sub_s = np.insert(sub_s, len(sub_s), sep_id)
assert len(sub_s) <= max_len
sub_seqs.append(sub_s)

14
examples/distillation/distiller.py
View File

@@ -17,6 +17,7 @@
"""
import os
import math
import psutil
from tensorboardX import SummaryWriter
from tqdm import trange, tqdm
import numpy as np
@@ -192,7 +193,7 @@ class Distiller:
x_prob = self.token_probs[token_ids.flatten()]
n_tgt = math.ceil(self.mlm_mask_prop * lengths.sum().item())
tgt_ids = torch.multinomial(x_prob / x_prob.sum(), n_tgt, replacement=False)
pred_mask = torch.zeros(bs * max_seq_len, dtype=torch.uint8, device=token_ids.device)
pred_mask = torch.zeros(bs * max_seq_len, dtype=torch.bool, device=token_ids.device) # previously `dtype=torch.uint8`, cf pytorch 1.2.0 compatibility
pred_mask[tgt_ids] = 1
pred_mask = pred_mask.view(bs, max_seq_len)
@@ -216,7 +217,7 @@ class Distiller:
_token_ids = _token_ids_mask * (probs == 0).long() + _token_ids_real * (probs == 1).long() + _token_ids_rand * (probs == 2).long()
token_ids = token_ids.masked_scatter(pred_mask, _token_ids)
mlm_labels[1-pred_mask] = -1
mlm_labels[~pred_mask] = -1 # previously `mlm_labels[1-pred_mask] = -1`, cf pytorch 1.2.0 compatibility
return token_ids, attn_mask, mlm_labels
@@ -294,7 +295,10 @@ class Distiller:
if self.is_master: logger.info(f'--- Ending epoch {self.epoch}/{self.params.n_epoch-1}')
self.end_epoch()
if self.is_master: logger.info('Training is finished')
if self.is_master:
logger.info(f'Save very last checkpoint as `pytorch_model.bin`.')
self.save_checkpoint(checkpoint_name=f'pytorch_model.bin')
logger.info('Training is finished')
def step(self,
input_ids: torch.tensor,
@@ -379,9 +383,9 @@ class Distiller:
torch.nn.utils.clip_grad_norm_(amp.master_params(self.optimizer), self.params.max_grad_norm)
else:
torch.nn.utils.clip_grad_norm_(self.student.parameters(), self.params.max_grad_norm)
self.scheduler.step()
self.optimizer.step()
self.optimizer.zero_grad()
self.scheduler.step()
def iter(self):
"""
@@ -418,6 +422,8 @@ class Distiller:
if self.alpha_mse > 0.:
self.tensorboard.add_scalar(tag="losses/loss_mse", scalar_value=self.last_loss_mse, global_step=self.n_total_iter)
self.tensorboard.add_scalar(tag="learning_rate/lr", scalar_value=self.scheduler.get_lr()[0], global_step=self.n_total_iter)
self.tensorboard.add_scalar(tag="global/memory_usage", scalar_value=psutil.virtual_memory()._asdict()['used']/1_000_000, global_step=self.n_total_iter)
def end_epoch(self):
"""

3
examples/distillation/requirements.txt
View File

@@ -1 +1,4 @@
gitpython==3.0.2
tensorboard>=1.14.0
tensorboardX==1.8
psutil==5.6.3

8
examples/distillation/scripts/binarized_data.py
View File

@@ -21,8 +21,12 @@ import random
import time
import numpy as np
from pytorch_transformers import BertTokenizer
import logging
from ..utils import logger
logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s - %(message)s',
datefmt = '%m/%d/%Y %H:%M:%S',
level = logging.INFO)
logger = logging.getLogger(__name__)
def main():
parser = argparse.ArgumentParser(description="Preprocess the data to avoid re-doing it several times by (tokenization + token_to_ids).")
@@ -74,4 +78,4 @@ def main():
if __name__ == "__main__":
main()
main()

6
examples/distillation/scripts/token_counts.py
View File

@@ -18,8 +18,12 @@ Preprocessing script before training DistilBERT.
from collections import Counter
import argparse
import pickle
import logging
from utils import logger
logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s - %(message)s',
datefmt = '%m/%d/%Y %H:%M:%S',
level = logging.INFO)
logger = logging.getLogger(__name__)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description="Token Counts for smoothing the masking probabilities in MLM (cf XLM/word2vec)")

47
examples/lm_finetuning/finetune_on_pregenerated.py
View File

@@ -235,8 +235,9 @@ def main():
# Prepare model
model = BertForPreTraining.from_pretrained(args.bert_model)
if args.fp16:
model.half()
# We don't need to manually call model.half() following Apex's recommend
# if args.fp16:
# model.half()
model.to(device)
if args.local_rank != -1:
try:
@@ -257,25 +258,36 @@ def main():
{'params': [p for n, p in param_optimizer if any(nd in n for nd in no_decay)], 'weight_decay': 0.0}
]
optimizer = AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon)
scheduler = WarmupLinearSchedule(optimizer, warmup_steps=args.warmup_steps,
t_total=num_train_optimization_steps)
if args.fp16:
try:
from apex.optimizers import FP16_Optimizer
from apex.optimizers import FusedAdam
# from apex.optimizers import FP16_Optimizer
# from apex.optimizers import FusedAdam
from apex import amp
except ImportError:
raise ImportError(
"Please install apex from https://www.github.com/nvidia/apex to use distributed and fp16 training.")
optimizer = FusedAdam(optimizer_grouped_parameters,
lr=args.learning_rate,
bias_correction=False,
max_grad_norm=1.0)
if args.loss_scale == 0:
optimizer = FP16_Optimizer(optimizer, dynamic_loss_scale=True)
else:
optimizer = FP16_Optimizer(optimizer, static_loss_scale=args.loss_scale)
else:
optimizer = AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon)
scheduler = WarmupLinearSchedule(optimizer, warmup_steps=args.warmup_steps, t_total=num_train_optimization_steps)
# This below line of code is the main upgrade of Apex Fp16 implementation. I chose opt_leve="01"
# because it's recommended for typical use by Apex. We can make it configured
model, optimizer = amp.initialize(model, optimizer, opt_level="O1")
# We don't need to use FP16_Optimizer wrapping over FusedAdam as well. Now Apex supports all Pytorch Optimizer
# optimizer = FusedAdam(optimizer_grouped_parameters,
# lr=args.learning_rate,
# bias_correction=False,
# max_grad_norm=1.0)
# if args.loss_scale == 0:
# optimizer = FP16_Optimizer(optimizer, dynamic_loss_scale=True)
# else:
# optimizer = FP16_Optimizer(optimizer, static_loss_scale=args.loss_scale)
# else:
# optimizer = AdamW(optimizer_grouped_parameters, lr=args.learning_rate, eps=args.adam_epsilon)
# scheduler = WarmupLinearSchedule(optimizer, warmup_steps=args.warmup_steps, t_total=num_train_optimization_steps)
global_step = 0
logging.info("***** Running training *****")
@@ -304,7 +316,10 @@ def main():
if args.gradient_accumulation_steps > 1:
loss = loss / args.gradient_accumulation_steps
if args.fp16:
optimizer.backward(loss)
# I depricate FP16_Optimizer's backward func and replace as Apex document
# optimizer.backward(loss)
with amp.scale_loss(loss, optimizer) as scaled_loss:
scaled_loss.backward()
else:
loss.backward()
tr_loss += loss.item()

3
examples/lm_finetuning/pregenerate_training_data.py
View File

@@ -329,7 +329,8 @@ def main():
doc = []
else:
tokens = tokenizer.tokenize(line)
doc.append(tokens)
if tokens:
doc.append(tokens)
if doc:
docs.add_document(doc) # If the last doc didn't end on a newline, make sure it still gets added
if len(docs) <= 1:

1
examples/run_glue.py
View File

@@ -474,6 +474,7 @@ def main():
# 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)))

5
examples/run_lm_finetuning.py
View File

@@ -14,7 +14,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
"""
Fine-tuning the library models for language modeling on WikiText-2 (GPT, GPT-2, BERT, RoBERTa).
Fine-tuning the library models for language modeling on a text file (GPT, GPT-2, BERT, RoBERTa).
GPT and GPT-2 are fine-tuned using a causal language modeling (CLM) loss while BERT and RoBERTa are fine-tuned
using a masked language modeling (MLM) loss.
"""
@@ -247,7 +247,6 @@ def evaluate(args, model, tokenizer, prefix=""):
# Loop to handle MNLI double evaluation (matched, mis-matched)
eval_output_dir = args.output_dir
results = {}
eval_dataset = load_and_cache_examples(args, tokenizer, evaluate=True)
if not os.path.exists(eval_output_dir) and args.local_rank in [-1, 0]:
@@ -289,7 +288,7 @@ def evaluate(args, model, tokenizer, prefix=""):
logger.info(" %s = %s", key, str(result[key]))
writer.write("%s = %s\n" % (key, str(result[key])))
return results
return result
def main():