Ensure tokenizer is on GPU

Diagnostics

Diagnostics

Moved device assignement to beginning of function

Corrected typo

Ensure consistency of device assignment when training

Ensure consistency of device assignment when training

Clear cuda cache

Google Colab imports

Training on Colab. Half a crawler

Download training data from S3

Removed unnecessary import

Removed train_base_models task. Not needed with RoBERTa models

Configured gradio app for training

Created HuggingFace Space

Removed diagnostic

Ensure consitency value is 32 bit

Removed diagnostics

Wrap CrossEntropyLoss in callable that makes it appplicable to sequences

Using torch.nn.CosineSimilarity to simplify code

Use builtin sum rather than torch.sum for a generator

Use keepdim option when normalising vectors

Make EPSILON a tensor

torch.maximum, not torch.max

Learning rate scheduler

Fixed typo

Minor error in setting up tokenizer

PyTorch implementation of HugggingFace PreTrainedModel class does not allow direct setting of base_model. Rejig constructors accordingly

Modified training scripts to use PyTorch

Removed diagnostics

Use dictionary coprehensions to do padding and return dictionaries instead of default dictionaries

Completed script for testing consistency

Fixed name of argument

Tensor is logits

Incoplete testing script for consistency. Fixed typo

Testing script for reasoning

Testing scripts

Attention masks, generation, and testing script

Invoke class, not module

Superclass __init__

Fix typo

Authentication

Training script

Training script

Bug fixes

Bug fixes

Bug fixes

Script for preparing training datasets

Coreference Resolution for WikiQA dataset

Data preparation for WikiQA