Commit History
Saving weights and logs of step 35000
bc7b998
Saving weights and logs of step 32500
d50e019
Saving weights and logs of step 30000
d5bba1b
Saving weights and logs of step 27500
2e9e4dc
Saving weights and logs of step 25000
f389a77
Saving weights and logs of step 22500
fb09f75
Saving weights and logs of step 20000
80d1da9
Saving weights and logs of step 17500
730ca0d
Saving weights and logs of step 15000
cbfcb64
Saving weights and logs of step 12500
853161d
Saving weights and logs of step 10000
cd7d53d
Saving weights and logs of step 7500
bb9fbf4
Saving weights and logs of step 5000
72f0bfa
Saving weights and logs of step 2500
1a4b666
change run.sh
70704f2
pushing tokenizer
c36ebf7
Add runner, fix some bugs
31bf2aa
Merge remote-tracking branch 'origin/saied' into develop
8918872
Remove junks
a749413
adding remove add and remove tag functions
a32918a
Remove extra file
4350a5a
Add normalization steps, fix som bugs, add tfboard tracker
1809a17
Merge remote-tracking branch 'origin/saied' into develop
9eca64d
Refine saied code
09f9c26
Add normalization steps
a90e731
Add normalization steps
74e88fc
some modification in preprocessing/urls removing
ad582b6
some modification in preprocessing
79fa2a7
editted data_utils-url,html,streched alphabet
95cd35a
Add notebook for data flaws
ec2c00e
Fix rm files
bce7e0a
Add training script with checkpoint and preprocessing + merge scripts
7cfca48
Merge remote-tracking branch 'origin/hooman' into develop
8812e32
adding dataset prepration module
73d5951
adding training demo notebook-flax/jax
be67d26
pushing a template clm training script for gpt2
01ae861
Hooman Sedghamiz
commited on
