def load_classification_model():
global trainer
global tokenizer
mod = 'mtn_models/pytorch_model.bin'
tok = 'mtn_models/vocab.txt'
conf = 'mtn_models/config.json'
tokenizer = BertTokenizer.from_pretrained(tok,
do_lower_case=False,
do_basic_tokenize=True,
never_split=never_split_tokens,
truncation=True)
config = PretrainedConfig.from_pretrained(conf, num_labels=6)
model = BertForSequenceClassification.from_pretrained(mod, config=config)
training_args = TrainingArguments("./train")
training_args.do_train = True
training_args.evaluate_during_training = True
training_args.adam_epsilon = 1e-8
training_args.learning_rate = 2e-5
training_args.warmup_steps = 0
training_args.per_gpu_train_batch_size = 16
training_args.per_gpu_eval_batch_size = 16
training_args.num_train_epochs = 3
#training_args.logging_steps = (len(train_features) - 1) // training_args.per_gpu_train_batch_size + 1
training_args.save_steps = training_args.logging_steps
training_args.seed = 42
trainer = Trainer(model=model, args=training_args)
help="The embedding file to swap.")
try:
get_ipython().run_line_magic('matplotlib', 'inline')
args = parser.parse_args([])
except:
args = parser.parse_args()
# os.environ["WANDB_DISABLED"] = "false" if args.is_tensorboard else "true"
os.environ["TRANSFORMERS_CACHE"] = "../huggingface_cache/"
# if cache does not exist, create one
if not os.path.exists(os.environ["TRANSFORMERS_CACHE"]):
os.makedirs(os.environ["TRANSFORMERS_CACHE"])
training_args = TrainingArguments("tmp_trainer")
training_args.no_cuda = args.no_cuda
training_args.per_device_eval_batch_size = args.per_device_eval_batch_size
training_args.per_gpu_eval_batch_size = args.per_device_eval_batch_size
training_args_dict = training_args.to_dict()
_n_gpu = training_args_dict["_n_gpu"]
del training_args_dict["_n_gpu"]
training_args_dict["n_gpu"] = _n_gpu
HfParser = HfArgumentParser((TrainingArguments))
training_args = HfParser.parse_dict(training_args_dict)[0]
TASK_CONFIG = {"classification": ("text", None)}
# Load pretrained model and tokenizer
NUM_LABELS = 3
MAX_SEQ_LEN = 128
config = AutoConfig.from_pretrained(args.model_type,
num_labels=3,
finetuning_task=args.task_name,
