if config.birnn:
config.n_cells *= 2
if args.resume_snapshot:
model = torch.load(
args.resume_snapshot,
map_location=lambda storage, location: storage.cuda(args.gpu))
else:
model = LSTMSentiment(config)
if args.word_vectors:
model.embed.weight.data = inputs.vocab.vectors
model.cuda()
criterion = nn.CrossEntropyLoss()
opt = O.Adam(model.parameters()) # , lr=args.lr)
# model.embed.requires_grad = False
iterations = 0
start_time = time.time()
best_dev_acc = -1
train_iter.repeat = False
header = ' Time Epoch Loss Dev/Loss CD Loss Accuracy Dev/Accuracy'
dev_log_template = ' '.join(
'{:6.0f},{:5.0f},{:9.4f},{:8.6f},{:8.6f},{:12.4f},{:12.4f}'.split(','))
print(len(train))
print(header)
for epoch in range(p.num_iters):
if config.birnn:
config.n_cells *= 2
if args.resume_snapshot:
model = torch.load(
args.resume_snapshot,
map_location=lambda storage, location: storage.cuda(args.gpu))
else:
model = LSTMSentiment(config)
if args.word_vectors:
model.embed.weight.data = inputs.vocab.vectors
model.cuda()
criterion = nn.CrossEntropyLoss()
opt = O.Adam(model.parameters())
# model.embed.requires_grad = False
iterations = 0
start_time = time.time()
best_dev_acc = -1
train_iter.repeat = False
header = ' Time Epoch Loss Dev/Loss CD Loss Accuracy Dev/Accuracy'
dev_log_template = ' '.join(
'{:6.0f},{:5.0f},{:9.4f},{:8.6f},{:8.6f},{:12.4f},{:12.4f}'.split(','))
print(len(train))
print(header)
best_model_weights = None
best_dev_loss = 100000
model = LSTMSentiment(embedding_dim=300,
hidden_dim=168,
vocab_size=300,
label_size=2,
gpu_device=DEVICE)
model.word_embeddings.weight.data = inputs.vocab.vectors
model.cuda(device=DEVICE)
# Load previously checkpointed model if it exists
model_path = "model.pt"
if os.path.exists(model_path) and RESUME_CKPT:
print("Loading previously stored model")
model = torch.load(model_path)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)
#############################################
# TRAINING
print("Beginning training")
early_stop_test = 0
tqdm_epoch = tqdm(range(5), desc="Epoch")
for epoch in tqdm_epoch:
train_iter.init_epoch()
tqdm_batch = tqdm(train_iter, desc="Batch")
loss = None
for b_id, batch in enumerate(tqdm_batch):
model.train()
optimizer.zero_grad()