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

Evaluation code fixed.

Browse Source
This commit is contained in:
altsoph
2019-10-25 13:22:58 +03:00
committed by Lysandre Debut
parent ae1d03fc51
commit 438f2730a0
1 changed files with 6 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/run_lm_finetuning.py
View File

@@ -86,6 +86,7 @@ class TextDataset(Dataset):
# Note that we are loosing the last truncated example here for the sake of simplicity (no padding) # Note that we are loosing the last truncated example here for the sake of simplicity (no padding)
# If your dataset is small, first you should loook for a bigger one :-) and second you # If your dataset is small, first you should loook for a bigger one :-) and second you
# can change this behavior by adding (model specific) padding. # can change this behavior by adding (model specific) padding.
self.examples.append(tokenizer.build_inputs_with_special_tokens(tokenized_text[-block_size:])) # DIRTY!
logger.info("Saving features into cached file %s", cached_features_file) logger.info("Saving features into cached file %s", cached_features_file)
with open(cached_features_file, 'wb') as handle: with open(cached_features_file, 'wb') as handle:
@@ -309,10 +310,12 @@ def evaluate(args, model, tokenizer, prefix=""):
model.eval() model.eval()
for batch in tqdm(eval_dataloader, desc="Evaluating"): for batch in tqdm(eval_dataloader, desc="Evaluating"):
batch = batch.to(args.device) inputs, labels = mask_tokens(batch, tokenizer, args) if args.mlm else (batch, batch)
inputs = inputs.to(args.device)
labels = labels.to(args.device)
with torch.no_grad(): with torch.no_grad():
outputs = model(batch, masked_lm_labels=batch) if args.mlm else model(batch, labels=batch) outputs = model(inputs, masked_lm_labels=labels) if args.mlm else model(inputs, labels=labels)
lm_loss = outputs[0] lm_loss = outputs[0]
eval_loss += lm_loss.mean().item() eval_loss += lm_loss.mean().item()
nb_eval_steps += 1 nb_eval_steps += 1