grammatical / pretraining-bea2019 Goto Github PK

That's an awesome work, Thanks for sharing this code, Can you please give us the data you describe in the README? Thank you.

There is no documentation on how to train the model.

Inference on even one sentence (with the example code) fails. I used no GPU, and it seems the code doesn't support CPU inference, suppose it is better to note that if that is an expected behaviour.

[2019-10-22 08:57:51] [data] Loading SentencePiece vocabulary from file /cs/snapless/oabend/borgr/UEDIN2019/systems/model.restricted/vocab.spm
[2019-10-22 08:57:51] Error: Curand error 203 - /cs/snapless/oabend/borgr/UEDIN2019/systems/tools/marian-dev/src/tensors/rand.cpp:75: curandCreateGenerator(&generator_, CURAND_RNG_PSEUDO_DEFAULT)
[2019-10-22 08:57:51] Error: Curand error 203 - /cs/snapless/oabend/borgr/UEDIN2019/systems/tools/marian-dev/src/tensors/rand.cpp:75: curandCreateGenerator(&generator_, CURAND_RNG_PSEUDO_DEFAULT)
[2019-10-22 08:57:51] Error: Aborted from marian::CurandRandomGenerator::CurandRandomGenerator(size_t, marian::DeviceId) in /cs/snapless/oabend/borgr/UEDIN2019/systems/tools/marian-dev/src/tensors/rand.cpp:75
Aborted from marian::CurandRandomGenerator::CurandRandomGenerator(size_t, marian::DeviceId) in /cs/snapless/oabend/borgr/UEDIN2019/systems/tools/marian-dev/src/tensors/rand.cpp:75

After running the code given following the steps mentioned, getting this error in the test.out.nbest.logs

[2023-02-11 11:35:41] Vocabulary file model.restricted/vocab.spm must not contain empty lines

We would like to reproduce your system results. Do you have any ETA when the training scripts and scripts for synthetic data generation will be released?

The README suggests that the code would be posted in July. Any updates? Thank you.

Hi guys,
I fear that I cannot reproduce your impressive results as mentioned in your paper. May I know if your team can share the dev and test set outputs please?
Thank you.