Commit History

Notebook to encode splitted YFCC100M files.
82fad8c

Pedro Cuenca commited on

change bart-large-cnn to bart-large in demo folder
5801f13

Ritobrata Ghosh commited on

Shift tokens in numpy because the built in shift function stalls.
835ea55

Pedro Cuenca commited on

fix: should be converted to array
945d86c

boris commited on

fix: labels array
6c1f112

boris commited on

fix: typo
678a62f

boris commited on

Merge pull request #17 from borisdayma/fix-model
357779a
unverified

boris commited on

fix: model config
0be4942

boris commited on

fix: correct decoder_input_ids and labels
19946be

boris commited on

Merge pull request #16 from borisdayma/feat-log_model
bf4da91
unverified

boris commited on

feat: don't log model by default
5b79afd

boris commited on

fix: typo
47bc7b9

boris commited on

feat: fix typo
ec8d66b

boris commited on

feat: log model
1c44a7d

boris commited on

doc: fix comment
3073ff4

boris commited on

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