evaluate(model,data_loader_test,model_name=config.model,ty='test',verbose=True,log=True)
exit(0)
model = Transformer(p.vocab)
print("MODEL USED",config.model)
print("TRAINABLE PARAMETERS",count_parameters(model))
best_ppl = 1000
cnt = 0
for e in range(config.epochs):
print("Epoch", e)
p, l = [],[]
pbar = tqdm(enumerate(data_loader_tr),total=len(data_loader_tr))
for i, d in pbar:
torch.cuda.empty_cache()
loss, ppl, _ = model.train_one_batch(d)
l.append(loss)
p.append(ppl)
pbar.set_description("loss:{:.4f} ppl:{:.1f}".format(np.mean(l),np.mean(p)))
#pbar.set_description("loss:{:.4f} ppl:{:.1f}".format(loss,ppl))
torch.cuda.empty_cache()
#break
loss,ppl_val,ent_b,bleu_score_b = evaluate(model,data_loader_val,model_name=config.model,ty="valid", verbose=True)
if(ppl_val <= best_ppl):
best_ppl = ppl_val
cnt = 0
model.save_model(best_ppl,e,0,0,bleu_score_b,ent_b)
else:
cnt += 1
if(cnt > 10): break
xavier_uniform_(p)
print("MODEL USED", config.model)
print("TRAINABLE PARAMETERS", count_parameters(model))
check_iter = 2000
try:
if (config.USE_CUDA):
model.cuda()
model = model.train()
best_ppl = 1000
patient = 0
writer = SummaryWriter(log_dir=config.save_path)
weights_best = deepcopy(model.state_dict())
data_iter = make_infinite(data_loader_tra)
for n_iter in tqdm(range(1000000)):
loss, ppl, bce, acc = model.train_one_batch(next(data_iter), n_iter)
writer.add_scalars('loss', {'loss_train': loss}, n_iter)
writer.add_scalars('ppl', {'ppl_train': ppl}, n_iter)
writer.add_scalars('bce', {'bce_train': bce}, n_iter)
writer.add_scalars('accuracy', {'acc_train': acc}, n_iter)
if (config.noam):
writer.add_scalars('lr', {'learning_rata': model.optimizer._rate},
n_iter)
if ((n_iter + 1) % check_iter == 0):
model = model.eval()
model.epoch = n_iter
model.__id__logger = 0
loss_val, ppl_val, bce_val, acc_val, bleu_score_g, bleu_score_b = evaluate(
model, data_loader_val, ty="valid", max_dec_step=50)
writer.add_scalars('loss', {'loss_valid': loss_val}, n_iter)
