update the examples, docs and template

README.md

@@ -521,12 +521,12 @@ Here is a conversion examples from `BertAdam` with a linear warmup and decay sch
 # Parameters:
 lr = 1e-3
 max_grad_norm = 1.0
-num_total_steps = 1000
+num_training_steps = 1000
 num_warmup_steps = 100
-warmup_proportion = float(num_warmup_steps) / float(num_total_steps)  # 0.1
+warmup_proportion = float(num_warmup_steps) / float(num_training_steps)  # 0.1
 
 ### Previously BertAdam optimizer was instantiated like this:
-optimizer = BertAdam(model.parameters(), lr=lr, schedule='warmup_linear', warmup=warmup_proportion, t_total=num_total_steps)
+optimizer = BertAdam(model.parameters(), lr=lr, schedule='warmup_linear', warmup=warmup_proportion, t_total=num_training_steps)
 ### and used like this:
 for batch in train_data:
     loss = model(batch)
@@ -535,7 +535,7 @@ for batch in train_data:
 
 ### In Transformers, optimizer and schedules are splitted and instantiated like this:
 optimizer = AdamW(model.parameters(), lr=lr, correct_bias=False)  # To reproduce BertAdam specific behavior set correct_bias=False
-scheduler = WarmupLinearSchedule(optimizer, warmup_steps=num_warmup_steps, t_total=num_total_steps)  # PyTorch scheduler
+scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=num_warmup_steps, num_training_steps=num_training_steps)  # PyTorch scheduler
 ### and used like this:
 for batch in train_data:
     model.train()

docs/source/main_classes/optimizer_schedules.rst

@@ -18,19 +18,17 @@ Schedules
 Learning Rate Schedules
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-.. autoclass:: transformers.ConstantLRSchedule
-    :members:
+.. autofunction:: transformers.get_constant_schedule
 
 
-.. autoclass:: transformers.WarmupConstantSchedule
-    :members:
+.. autofunction:: transformers.get_constant_schedule_with_warmup
 
 .. image:: /imgs/warmup_constant_schedule.png
     :target: /imgs/warmup_constant_schedule.png
     :alt:
 
 
-.. autoclass:: transformers.WarmupCosineSchedule
+.. autofunction:: transformers.get_cosine_schedule_with_warmup
     :members:
 
 .. image:: /imgs/warmup_cosine_schedule.png
@@ -38,8 +36,7 @@ Learning Rate Schedules
     :alt:
 
 
-.. autoclass:: transformers.WarmupCosineWithHardRestartsSchedule
-    :members:
+.. autofunction:: transformers.get_cosine_with_hard_restarts_schedule_with_warmup
 
 .. image:: /imgs/warmup_cosine_hard_restarts_schedule.png
     :target: /imgs/warmup_cosine_hard_restarts_schedule.png
@@ -47,8 +44,7 @@ Learning Rate Schedules
 
 
 
-.. autoclass:: transformers.WarmupLinearSchedule
-    :members:
+.. autofunction:: transformers.get_linear_schedule_with_warmup
 
 .. image:: /imgs/warmup_linear_schedule.png
     :target: /imgs/warmup_linear_schedule.png

docs/source/migration.md

@@ -84,12 +84,12 @@ Here is a conversion examples from `BertAdam` with a linear warmup and decay sch
 # Parameters:
 lr = 1e-3
 max_grad_norm = 1.0
-num_total_steps = 1000
+num_training_steps = 1000
 num_warmup_steps = 100
-warmup_proportion = float(num_warmup_steps) / float(num_total_steps)  # 0.1
+warmup_proportion = float(num_warmup_steps) / float(num_training_steps)  # 0.1
 
 ### Previously BertAdam optimizer was instantiated like this:
-optimizer = BertAdam(model.parameters(), lr=lr, schedule='warmup_linear', warmup=warmup_proportion, t_total=num_total_steps)
+optimizer = BertAdam(model.parameters(), lr=lr, schedule='warmup_linear', warmup=warmup_proportion, num_training_steps=num_training_steps)
 ### and used like this:
 for batch in train_data:
     loss = model(batch)
@@ -98,7 +98,7 @@ for batch in train_data:
 
 ### In Transformers, optimizer and schedules are splitted and instantiated like this:
 optimizer = AdamW(model.parameters(), lr=lr, correct_bias=False)  # To reproduce BertAdam specific behavior set correct_bias=False
-scheduler = WarmupLinearSchedule(optimizer, warmup_steps=num_warmup_steps, t_total=num_total_steps)  # PyTorch scheduler
+scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=num_warmup_steps, num_training_steps=num_training_steps)  # PyTorch scheduler
 ### and used like this:
 for batch in train_data:
     loss = model(batch)

examples/contrib/run_openai_gpt.py

@@ -41,7 +41,7 @@ from torch.utils.data import (DataLoader, RandomSampler, SequentialSampler,
 
 from transformers import (OpenAIGPTDoubleHeadsModel, OpenAIGPTTokenizer,
                                      AdamW, cached_path, WEIGHTS_NAME, CONFIG_NAME,
-                                     WarmupLinearSchedule)
+                                     get_linear_schedule_with_warmup)
 
 ROCSTORIES_URL = "https://s3.amazonaws.com/datasets.huggingface.co/ROCStories.tar.gz"
 
@@ -211,7 +211,7 @@ 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=t_total)
+        scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total)
 
     if args.do_train:
         nb_tr_steps, tr_loss, exp_average_loss = 0, 0, None

examples/contrib/run_swag.py

@@ -42,7 +42,7 @@ from tqdm import tqdm, trange
 from transformers import (WEIGHTS_NAME, BertConfig,
                                   BertForMultipleChoice, BertTokenizer)
 
-from transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, get_linear_schedule_with_warmup
 
 logger = logging.getLogger(__name__)
 
@@ -322,7 +322,7 @@ def train(args, train_dataset, model, tokenizer):
         {'params': [p for n, p in model.named_parameters() 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=t_total)
+    scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total)
     if args.fp16:
         try:
             from apex import amp

examples/distillation/distiller.py

@@ -35,7 +35,7 @@ try:
 except:
     from tensorboardX import SummaryWriter
 
-from transformers import WarmupLinearSchedule
+from transformers import get_linear_schedule_with_warmup
 
 from utils import logger
 from lm_seqs_dataset import LmSeqsDataset
@@ -137,9 +137,9 @@ class Distiller:
                                betas=(0.9, 0.98))
 
         warmup_steps = math.ceil(num_train_optimization_steps * params.warmup_prop)
-        self.scheduler = WarmupLinearSchedule(self.optimizer,
-                                                warmup_steps=warmup_steps,
-                                                t_total=num_train_optimization_steps)
+        self.scheduler = get_linear_schedule_with_warmup(self.optimizer,
+                                                num_warmup_steps=warmup_steps,
+                                                num_training_steps=num_train_optimization_steps)
 
         if self.fp16:
             try:

examples/distillation/run_squad_w_distillation.py

@@ -46,7 +46,7 @@ from transformers import (WEIGHTS_NAME, BertConfig,
                                   XLNetTokenizer,
                                   DistilBertConfig, DistilBertForQuestionAnswering, DistilBertTokenizer)
 
-from transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, get_linear_schedule_with_warmup
 
 from ..utils_squad import (read_squad_examples, convert_examples_to_features,
                          RawResult, write_predictions,
@@ -101,7 +101,7 @@ def train(args, train_dataset, model, tokenizer, teacher=None):
         {'params': [p for n, p in model.named_parameters() 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=t_total)
+    scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total)
     if args.fp16:
         try:
             from apex import amp

examples/run_glue.py

@@ -49,7 +49,7 @@ from transformers import (WEIGHTS_NAME, BertConfig,
                                   DistilBertForSequenceClassification,
                                   DistilBertTokenizer)
 
-from transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, get_linear_schedule_with_warmup
 
 from transformers import glue_compute_metrics as compute_metrics
 from transformers import glue_output_modes as output_modes
@@ -100,7 +100,7 @@ def train(args, train_dataset, model, tokenizer):
         {'params': [p for n, p in model.named_parameters() 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=t_total)
+    scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total)
     if args.fp16:
         try:
             from apex import amp

examples/run_lm_finetuning.py

@@ -42,7 +42,7 @@ except:
 
 from tqdm import tqdm, trange
 
-from transformers import (WEIGHTS_NAME, AdamW, WarmupLinearSchedule,
+from transformers import (WEIGHTS_NAME, AdamW, get_linear_schedule_with_warmup,
                                   BertConfig, BertForMaskedLM, BertTokenizer,
                                   GPT2Config, GPT2LMHeadModel, GPT2Tokenizer,
                                   OpenAIGPTConfig, OpenAIGPTLMHeadModel, OpenAIGPTTokenizer,
@@ -185,7 +185,7 @@ def train(args, train_dataset, model, tokenizer):
         {'params': [p for n, p in model.named_parameters() 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=t_total)
+    scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total)
     if args.fp16:
         try:
             from apex import amp

examples/run_multiple_choice.py

@@ -43,7 +43,7 @@ from transformers import (WEIGHTS_NAME, BertConfig,
                                   XLNetTokenizer, RobertaConfig,
                                   RobertaForMultipleChoice, RobertaTokenizer)
 
-from transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, get_linear_schedule_with_warmup
 
 from utils_multiple_choice import (convert_examples_to_features, processors)
 
@@ -101,7 +101,7 @@ def train(args, train_dataset, model, tokenizer):
         {'params': [p for n, p in model.named_parameters() 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=t_total)
+    scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total)
     if args.fp16:
         try:
             from apex import amp

examples/run_ner.py

@@ -33,7 +33,7 @@ from torch.utils.data.distributed import DistributedSampler
 from tqdm import tqdm, trange
 from utils_ner import convert_examples_to_features, get_labels, read_examples_from_file
 
-from transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, get_linear_schedule_with_warmup
 from transformers import WEIGHTS_NAME, BertConfig, BertForTokenClassification, BertTokenizer
 from transformers import RobertaConfig, RobertaForTokenClassification, RobertaTokenizer
 
@@ -80,7 +80,7 @@ def train(args, train_dataset, model, tokenizer, labels, pad_token_label_id):
         {"params": [p for n, p in model.named_parameters() 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=t_total)
+    scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total)
     if args.fp16:
         try:
             from apex import amp

examples/run_squad.py

@@ -45,7 +45,7 @@ from transformers import (WEIGHTS_NAME, BertConfig,
                                   XLNetTokenizer,
                                   DistilBertConfig, DistilBertForQuestionAnswering, DistilBertTokenizer)
 
-from transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, get_linear_schedule_with_warmup
 
 from utils_squad import (read_squad_examples, convert_examples_to_features,
                          RawResult, write_predictions,
@@ -100,7 +100,7 @@ def train(args, train_dataset, model, tokenizer):
         {'params': [p for n, p in model.named_parameters() 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=t_total)
+    scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total)
     if args.fp16:
         try:
             from apex import amp

templates/adding_a_new_example_script/run_xxx.py

@@ -43,7 +43,7 @@ from transformers import (WEIGHTS_NAME, BertConfig,
                                   XLNetTokenizer,
                                   DistilBertConfig, DistilBertForQuestionAnswering, DistilBertTokenizer)
 
-from transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, get_linear_schedule_with_warmup
 
 from utils_squad import (read_squad_examples, convert_examples_to_features,
                          RawResult, write_predictions,
@@ -98,7 +98,7 @@ def train(args, train_dataset, model, tokenizer):
         {'params': [p for n, p in model.named_parameters() 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=t_total)
+    scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=args.warmup_steps, num_training_steps=t_total)
     if args.fp16:
         try:
             from apex import amp