5cf3feb507
Added checkpoints to gitignore
2024-09-12 12:09:54 +01:00
9961737481
Removed HTML results, as GFM doesnt allow plotly plots to work.
2024-09-12 12:08:26 +01:00
594f698ba2
removed expt3 from main (for now)
2024-09-12 09:05:08 +01:00
f54885ba16
removed accidentally committed files
2024-09-12 09:04:26 +01:00
3b2ca2b1a5
Updated .gitignore
2024-09-12 09:00:04 +01:00
9a32c8fd04
Added accuracy to expt1 metrics
2024-09-11 17:13:51 +01:00
1454a701e0
Aded confusion matrices to experiments
2024-09-11 16:52:04 +01:00
546e235b09
Moved to rye instead of poetry, to avoid linking problems
2024-09-11 14:30:37 +01:00
4036364ea0
Added local experiment for private tests that shouldnt be pushed.
2024-09-11 10:57:48 +01:00
2c1e9aada0
minor tweak to expt3 plan
2024-06-28 14:13:19 +01:00
d40176a856
Added description of expt3
2024-06-27 18:06:21 +01:00
129092f610
Updated expt1 title to be more accurate
2024-06-27 16:47:31 +01:00
78e9a02bf1
minor correction to readme.md
2024-06-18 14:14:09 +01:00
8d81ea2008
Fixed TeX mistake in expt2
2024-06-18 14:12:26 +01:00
cb74559222
Updated readme use effectively as a lab journal
2024-06-18 14:09:31 +01:00
b113c21862
Generated plots of results for expt 1 and 2
2024-06-18 13:00:45 +01:00
85c6ba42a1
Tweaaks after re-running expt1
2024-06-17 17:31:00 +01:00
c6a1b7207a
Final attempt at Expt2
2024-06-17 16:47:10 +01:00
8bf53fb560
Working attempt at semantic loss based on RFR
...
Attempt at semantic loss driven by self optimising loss funtion using a
random forest regerssor for optimisation of semantic expressions
2024-06-14 13:09:42 +01:00
dd4effc690
changes to logging to sync frequency
2024-06-11 19:57:48 +01:00
6d0682bbed
re-enabled expt2 test1
2024-06-11 14:22:16 +01:00
85363021be
Added trainable residual penalty & logging for it
2024-06-11 14:18:56 +01:00
a14babd58a
New attempt at expt2 semantic loss
2024-06-10 16:12:02 +01:00
888fe9f2e8
Added automatic enabling of tensor cores
2024-06-10 12:58:19 +01:00
08fe32302c
Made model smaller to avoid overfitting
2024-06-07 16:09:51 +01:00
c7133a8bb1
Switched loss in expt2 to smooth_l1
...
Switched from mse_loss to smooth_l1_loss to avoid exploding gradient and
NaNs when using mse_loss.
2024-06-07 11:48:36 +01:00
1c21ee25d7
Added separate loss funcs for train, val, and test
2024-06-06 22:33:01 +01:00
ea77a055f8
Update README.md
...
Fixed typo
2024-06-06 15:12:25 +01:00
f10aa2fd19
Refactor of experiment2 for convenience
2024-06-06 15:02:39 +01:00
165ef045ea
First working attempt at semantic loss for expt2
2024-06-06 12:40:41 +01:00
d2ec5c0c1a
Added ability to train on submodules in expt2
2024-05-30 17:34:53 +01:00
52fb30a9ed
Completely implemented baseline for expt2
2024-05-30 16:02:46 +01:00
2720887f88
Added cli for configuring/launching experiments
2024-05-23 11:06:11 +01:00
9536beea04
Refactored to lay groundwork for TUI
2024-05-23 09:50:01 +01:00
02b9e43f4d
Made loggers togglable from top level
2024-05-23 09:21:48 +01:00
1be0fa1020
Added overview and plan for expt 2
2024-05-22 15:40:24 +01:00
c3dba79a0b
Refactored slightly to allow other experiments
2024-05-22 10:35:14 +01:00
ae14a1d7c0
Added a garbage semantic function
...
Added a semantic function where the injected "knowledge" is just random
garbage. This function was written to isolate the "knowledge" component
of the other semantic functions, basically to ensure it's the matrices
and not the rest of the process that is making the difference in
training.
2024-05-15 19:01:35 +01:00
e3690b0425
Added wandb.finish to properly start new runs
2024-05-15 18:40:20 +01:00
8a87e864fb
Fixed wandb logging mistake
2024-05-15 18:39:42 +01:00
4212c543f8
Update before first push to remote
2024-05-15 16:38:40 +01:00
15a57cc229
Added wandb logging
2024-05-15 16:37:53 +01:00
6600a79f71
Added more varied semantic loss functions
2024-05-15 16:37:53 +01:00
01127de4b3
Added testing step at end of training
2024-05-15 16:37:53 +01:00
62649a39da
Modified model to use SGD for less optimal training
...
There's no point having a loss function testing sandbox where the baseling trains perfectly in 2 epochs. I've DEoptimised the training in this commit to ensure the testing sandbox is actually useful.
2024-05-15 16:37:53 +01:00
389c47ef28
Fixed similarity matrix normalization
2024-05-15 16:37:53 +01:00
66b23a8e76
Minimized model and prepared for testing new loss functions
2024-05-15 16:37:53 +01:00
708f9952b3
First functional training loop
2024-05-15 16:37:53 +01:00
674175b260
Added trainer and made dataset hot-swappable
2024-05-15 16:37:53 +01:00
63bea4d355
Updated dataloader to default to tensor transform
2024-05-15 16:37:53 +01:00
