2 contributors

History: 50 commits

Yeb Havinga

Remove run logs unused for current model

d1dfaf7 over 3 years ago

clean
Update clean/clean.py over 3 years ago
runs
Remove run logs unused for current model over 3 years ago
.gitattributes

737 Bytes

initial commit over 3 years ago
.gitignore

38 Bytes

Saving weights and logs of step 300 over 3 years ago
Determine_batch_size.ipynb

6.45 kB

Saving weights and logs of step 16000 over 3 years ago
Load_preprocessed_dataset.ipynb

13.4 kB

Update weights and scripts over 3 years ago
Load_token_group_dataset.ipynb

34.1 kB

Update scripts. Add dataset load check notebook over 3 years ago
README.md

1.52 kB

Update README.md over 3 years ago
config.json

1.42 kB

Update scripts to work around collator valueerror. Update weights over 3 years ago
create_config.py

148 Bytes

Add config, tokenizer and training script over 3 years ago
flax_model.msgpack

892 MB
LFS

Update weights over 3 years ago
flax_to_pt.py

292 Bytes

Update weights and scripts over 3 years ago
opt_state.msgpack

1.99 MB
LFS

Update weights over 3 years ago
pytorch_model.bin

892 MB
LFS

Update weights and scripts over 3 years ago
run_t5.sh

2.07 kB

Add latest log and script over 3 years ago
run_t5_mlm_flax_custom_dataset.py

44.7 kB

Update weights and scripts over 3 years ago
streaming_dataset_filter_test.py

2.96 kB

Update weights and scripts over 3 years ago
tf_model.h5

892 MB
LFS

Update weights and scripts over 3 years ago
tokenizer.json

1.03 MB

Retrain tokenizer for case sensitive over 3 years ago
train_tokenizer.py

2 kB

Retrain tokenizer for case sensitive over 3 years ago
training_state.json

15 Bytes

Update weights over 3 years ago