Commit History

feat: update default parameters
dbe8c41

boris commited on

feat: output_length considers bos and eos
8bb2236

boris commited on

fix: missing arg
bc01f78

boris commited on

[WIP] Encoding YFC100M dataset.
b4dfea0

Pedro Cuenca commited on

Merge pull request #15 from borisdayma/feat-fix-lr
dc5ae57
unverified

boris commited on

feat: requirements for tb logging
8884d40

boris commited on

feat: shared cache folder
42ce7dd

boris commited on

feat: update lr range
dbbd01a

boris commited on

fix: accumulation vs lr
4d55db6

boris commited on

Move generate nb by @ghosh-r to demo
dcbf091

Pedro Cuenca commited on

Merge pull request #14 from khalidsaifullaah/main
66bfb99
unverified

boris commited on

Merge pull request #13 from borisdayma/model-generate-notebook
894a546
unverified

boris commited on

Updated with train_file flag to resolve the error
8f058ae
unverified

khalidsaifullaah commited on

notebook example for model.generate
67221fc

Ritobrata Ghosh commited on

text-heneration-notebook
1c2552a

Ritobrata Ghosh commited on

feat: update sweep parameters
2f69241

boris commited on

feat: update script
650ecb1

boris commited on

fix: wandb logging with sync_tensorboard
8ba598c

boris commited on

Merge pull request #12 from borisdayma/feat-sweeps
06f1345
unverified

boris commited on

feat: add sweep for parameter search
dad6d93

boris commited on

feat: lower default source length
48c07ca

boris commited on

Merge pull request #11 from borisdayma/feat-cumul
ba73e00
unverified

boris commited on

fix: typos
5960e87

boris commited on

feat: gradient accumulation
c9e9575

boris commited on

Merge pull request #10 from borisdayma/feat-loss
cbeacb9
unverified

boris commited on

feat: simplify loss function
9db361a

boris commited on

feat: padding mask not required
d61405b

boris commited on

Merge pull request #9 from borisdayma/feat--wandb-search
61f888f
unverified

boris commited on

fix: typo
833a2d5

boris commited on

feat: default to 1000 warmup steps
b66b951

boris commited on

feat: add adafactor
600ad79

boris commited on

feat: log metrics more frequently
498559f

boris commited on

* Make padding mask optional.
ecafe5e

Pedro Cuenca commited on

* Only perform validation if requested
32dc2d8

Pedro Cuenca commited on

Preprocessing: return "labels", "decoder_input_ids" and
df3c7bd

Pedro Cuenca commited on

Decoder: set eos to an unreachable value, set min_length=max_length to
a841a4c

Pedro Cuenca commited on

accept tsv files as inputs.
a104edb

Pedro Cuenca commited on

val_max_target_length set to OUTPUT_LENGTH
6c27b0d

Pedro Cuenca commited on

use pylogging to refer to logging.
d9f5a35

Pedro Cuenca commited on

fix typos and update requirements
de74f11

Pedro Cuenca commited on

Merge pull request #8 from pcuenca/main
9c0e5c9
unverified

boris commited on

feat: adjust seq2seq script for dalle
3f0364c

boris commited on

feat: add seq2seq requirements
fad333f

boris commited on

feat: add run_seq2seq_flax
46cb01f

boris commited on

* Prepend [bos] to image encodings, rename to "labels".
86ba774

Pedro Cuenca commited on

* Data preprocessing pipeline proof of concept.
95d2faf

Pedro Cuenca commited on

* Notebook that processes CC12M and creates a version with encodings.
16f038a

Pedro Cuenca commited on

* dalle_mini package with models and utilities:
150ed18

Pedro Cuenca commited on

* Ignore __pycache__
550b472

Pedro Cuenca commited on

* JIT outside the loop.
4b8c3a8

Pedro Cuenca commited on