Skip to content

Commit

Permalink
deploy: 3df16ce
Browse files Browse the repository at this point in the history
  • Loading branch information
misko committed May 13, 2024
1 parent df18deb commit df180e7
Show file tree
Hide file tree
Showing 37 changed files with 3,248 additions and 4,866 deletions.
121 changes: 81 additions & 40 deletions _downloads/5fdddbed2260616231dbf7b0d94bb665/train.txt

Large diffs are not rendered by default.

49 changes: 25 additions & 24 deletions _downloads/819e10305ddd6839cd7da05935b17060/mass-inference.txt
Original file line number Diff line number Diff line change
@@ -1,17 +1,17 @@
2024-05-13 17:28:47 (INFO): Project root: /home/runner/work/fairchem/fairchem/src/fairchem
2024-05-13 21:57:54 (INFO): Project root: /home/runner/work/fairchem/fairchem/src/fairchem
/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch/cuda/amp/grad_scaler.py:126: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available. Disabling.
warnings.warn(
2024-05-13 17:28:48 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
2024-05-13 17:28:48 (INFO): amp: true
2024-05-13 21:57:55 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
2024-05-13 21:57:55 (INFO): amp: true
cmd:
checkpoint_dir: ./checkpoints/2024-05-13-17-29-36
commit: db148bb
checkpoint_dir: ./checkpoints/2024-05-13-21-58-24
commit: 3df16ce
identifier: ''
logs_dir: ./logs/tensorboard/2024-05-13-17-29-36
logs_dir: ./logs/tensorboard/2024-05-13-21-58-24
print_every: 10
results_dir: ./results/2024-05-13-17-29-36
results_dir: ./results/2024-05-13-21-58-24
seed: 0
timestamp_id: 2024-05-13-17-29-36
timestamp_id: 2024-05-13-21-58-24
dataset:
a2g_args:
r_energy: false
Expand All @@ -36,6 +36,7 @@ eval_metrics:
- magnitude_error
misc:
- energy_forces_within_threshold
primary_metric: forces_mae
gpus: 0
logger: tensorboard
loss_fns:
Expand Down Expand Up @@ -121,25 +122,25 @@ test_dataset:
trainer: ocp
val_dataset: null

2024-05-13 17:28:48 (INFO): Loading dataset: ase_db
2024-05-13 17:28:48 (INFO): rank: 0: Sampler created...
2024-05-13 17:28:48 (INFO): Batch balancing is disabled for single GPU training.
2024-05-13 17:28:48 (INFO): rank: 0: Sampler created...
2024-05-13 17:28:48 (INFO): Batch balancing is disabled for single GPU training.
2024-05-13 17:28:48 (INFO): Loading model: gemnet_t
2024-05-13 17:28:50 (INFO): Loaded GemNetT with 31671825 parameters.
2024-05-13 17:28:50 (WARNING): Model gradient logging to tensorboard not yet supported.
2024-05-13 17:28:50 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gndt_oc22_all_s2ef.pt
2024-05-13 17:28:50 (INFO): Overwriting scaling factors with those loaded from checkpoint. If you're generating predictions with a pretrained checkpoint, this is the correct behavior. To disable this, delete `scale_dict` from the checkpoint.
2024-05-13 17:28:50 (WARNING): Scale factor comment not found in model
2024-05-13 17:28:50 (INFO): Predicting on test.
2024-05-13 21:57:55 (INFO): Loading dataset: ase_db
2024-05-13 21:57:55 (INFO): rank: 0: Sampler created...
2024-05-13 21:57:55 (INFO): Batch balancing is disabled for single GPU training.
2024-05-13 21:57:55 (INFO): rank: 0: Sampler created...
2024-05-13 21:57:55 (INFO): Batch balancing is disabled for single GPU training.
2024-05-13 21:57:55 (INFO): Loading model: gemnet_t
2024-05-13 21:57:57 (INFO): Loaded GemNetT with 31671825 parameters.
2024-05-13 21:57:57 (WARNING): Model gradient logging to tensorboard not yet supported.
2024-05-13 21:57:57 (INFO): Loading checkpoint from: /tmp/ocp_checkpoints/gndt_oc22_all_s2ef.pt
2024-05-13 21:57:58 (INFO): Overwriting scaling factors with those loaded from checkpoint. If you're generating predictions with a pretrained checkpoint, this is the correct behavior. To disable this, delete `scale_dict` from the checkpoint.
2024-05-13 21:57:58 (WARNING): Scale factor comment not found in model
2024-05-13 21:57:58 (INFO): Predicting on test.
device 0: 0%| | 0/3 [00:00<?, ?it/s]/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch_geometric/data/collate.py:145: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
storage = elem.storage()._new_shared(numel)
/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch_geometric/data/collate.py:145: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly. To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
storage = elem.storage()._new_shared(numel)
/opt/hostedtoolcache/Python/3.11.9/x64/lib/python3.11/site-packages/torch/amp/autocast_mode.py:250: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling
warnings.warn(
device 0: 33%|███████████▋ | 1/3 [00:05<00:11, 5.83s/it]device 0: 67%|███████████████████████▎ | 2/3 [00:08<00:03, 3.73s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:11<00:00, 3.38s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:11<00:00, 3.69s/it]
2024-05-13 17:29:02 (INFO): Writing results to ./results/2024-05-13-17-29-36/ocp_predictions.npz
2024-05-13 17:29:02 (INFO): Total time taken: 11.22813892364502
Elapsed time = 17.3 seconds
device 0: 33%|███████████▋ | 1/3 [00:04<00:08, 4.40s/it]device 0: 67%|███████████████████████▎ | 2/3 [00:06<00:02, 2.91s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:07<00:00, 2.29s/it]device 0: 100%|███████████████████████████████████| 3/3 [00:07<00:00, 2.62s/it]
2024-05-13 21:58:05 (INFO): Writing results to ./results/2024-05-13-21-58-24/ocp_predictions.npz
2024-05-13 21:58:05 (INFO): Total time taken: 8.00568413734436
Elapsed time = 14.4 seconds
Expand Down
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Binary file not shown.
6 changes: 3 additions & 3 deletions _sources/legacy_tutorials/OCP_Tutorial.md
Original file line number Diff line number Diff line change
Expand Up @@ -795,9 +795,9 @@ Lets download it locally,

```{code-cell} ipython3
%%bash
https://github.com/FAIR-Chem/fairchem/blob/main/src/fairchem/core/configs/s2ef/all/gemnet/scaling_factors/gemnet-oc-large.pt
wget https://github.com/FAIR-Chem/fairchem/blob/main/configs/s2ef/all/gemnet/scaling_factors/gemnet-oc.pt
wget https://github.com/FAIR-Chem/fairchem/blob/main/configs/s2ef/all/gemnet/scaling_factors/gemnet-dT.json
wget https://github.com/FAIR-Chem/fairchem/raw/main/configs/s2ef/all/gemnet/scaling_factors/gemnet-oc-large.pt
wget https://github.com/FAIR-Chem/fairchem/raw/main/configs/s2ef/all/gemnet/scaling_factors/gemnet-oc.pt
wget https://github.com/FAIR-Chem/fairchem/raw/main/configs/s2ef/all/gemnet/scaling_factors/gemnet-dT.json
```


Expand Down
14 changes: 7 additions & 7 deletions core/fine-tuning/fine-tuning-oxides.html
Original file line number Diff line number Diff line change
Expand Up @@ -818,7 +818,7 @@ <h1>Fine tuning a model<a class="headerlink" href="#fine-tuning-a-model" title="
warnings.warn(
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Elapsed time 67.6 seconds.
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Elapsed time 67.9 seconds.
</pre></div>
</div>
<img alt="../../_images/92bd7f94dd548c8cfc2744eb5890cd23fada1ff98e8dc907657e2eb109af0402.png" src="../../_images/92bd7f94dd548c8cfc2744eb5890cd23fada1ff98e8dc907657e2eb109af0402.png" />
Expand Down Expand Up @@ -1036,7 +1036,7 @@ <h2>Setting up the configuration yaml file<a class="headerlink" href="#setting-u
r_energy: true
r_forces: true
src: val.db
eval_metrics:
evaluation_metrics:
metrics:
energy:
- mae
Expand Down Expand Up @@ -1183,7 +1183,7 @@ <h2>Running the training job<a class="headerlink" href="#running-the-training-jo
<span class="expanded">Hide code cell output</span>
</summary>
<div class="cell_output docutils container">
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Elapsed time = 38.6 seconds
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Elapsed time = 207.6 seconds
</pre></div>
</div>
</div>
Expand All @@ -1199,7 +1199,7 @@ <h2>Running the training job<a class="headerlink" href="#running-the-training-jo
</div>
</div>
<div class="cell_output docutils container">
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>&#39;fine-tuning/checkpoints/2024-05-13-17-25-20-ft-oxides&#39;
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>&#39;fine-tuning/checkpoints/2024-05-13-21-52-00-ft-oxides&#39;
</pre></div>
</div>
</div>
Expand Down Expand Up @@ -1264,7 +1264,7 @@ <h2>Running the training job<a class="headerlink" href="#running-the-training-jo
warnings.warn(
</pre></div>
</div>
<img alt="../../_images/63a5f1d908808b57026d9a50d0b0ba827fb7ec964f105322b18a0738c5c88c0c.png" src="../../_images/63a5f1d908808b57026d9a50d0b0ba827fb7ec964f105322b18a0738c5c88c0c.png" />
<img alt="../../_images/a1eb81a787e4c7318422b93c686c36e23de6049d49ca949fea3ebe2f15ea5a68.png" src="../../_images/a1eb81a787e4c7318422b93c686c36e23de6049d49ca949fea3ebe2f15ea5a68.png" />
</div>
</div>
<div class="cell docutils container">
Expand All @@ -1275,7 +1275,7 @@ <h2>Running the training job<a class="headerlink" href="#running-the-training-jo
</div>
</div>
<div class="cell_output docutils container">
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>New MAE = 0.686 eV/atom
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>New MAE = 0.215 eV/atom
</pre></div>
</div>
</div>
Expand All @@ -1294,7 +1294,7 @@ <h2>Running the training job<a class="headerlink" href="#running-the-training-jo
</div>
</div>
<div class="cell_output docutils container">
<img alt="../../_images/bf74a5757a49a023060d744464527b5b70bb87f87fbeb750897bc2c22013dc50.png" src="../../_images/bf74a5757a49a023060d744464527b5b70bb87f87fbeb750897bc2c22013dc50.png" />
<img alt="../../_images/22815deebf21a31b5b0a110c41bf2e418ca25f6aecbd1dc17e3d9990f3848363.png" src="../../_images/22815deebf21a31b5b0a110c41bf2e418ca25f6aecbd1dc17e3d9990f3848363.png" />
</div>
</div>
<p>It is possible to continue refining the fit. The simple things to do are to use more epochs of training. Eventually the MAE will stabilize, and then it may be necessary to adjust other optimization parameters like the learning rate (usually you decrease it).</p>
Expand Down
28 changes: 14 additions & 14 deletions core/gotchas.html
Original file line number Diff line number Diff line change
Expand Up @@ -987,7 +987,7 @@ <h1>I get wildly different energies from the different models<a class="headerlin
warnings.warn(
</pre></div>
</div>
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>1.6787405014038086
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>1.675635576248169
</pre></div>
</div>
</div>
Expand Down Expand Up @@ -1500,7 +1500,7 @@ <h1>To tag or not?<a class="headerlink" href="#to-tag-or-not" title="Link to thi
warnings.warn(
</pre></div>
</div>
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.429736852645874
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.42973706126213074
</pre></div>
</div>
</div>
Expand Down Expand Up @@ -1555,17 +1555,17 @@ <h1>Stochastic simulation results<a class="headerlink" href="#stochastic-simulat
warnings.warn(
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>1.213986325263977 1.784320568281904e-06
1.2139856815338135
1.2139854431152344
1.2139854431152344
1.2139906883239746
1.2139859199523926
1.2139856815338135
1.2139880657196045
1.2139840126037598
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>1.2139862775802612 1.2491404435567604e-06
1.2139852046966553
1.213987112045288
1.213986873626709
1.2139861583709717
1.2139854431152344
1.213986873626709
1.2139849662780762
1.213986873626709
1.2139875888824463
1.2139842510223389
1.2139885425567627
</pre></div>
</div>
</div>
Expand Down Expand Up @@ -1611,7 +1611,7 @@ <h1>The forces don’t sum to zero<a class="headerlink" href="#the-forces-don-t-
warnings.warn(
</pre></div>
</div>
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>array([ 0.00848023, 0.01409696, -0.05882549], dtype=float32)
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>array([ 0.00848408, 0.01409468, -0.05882645], dtype=float32)
</pre></div>
</div>
</div>
Expand All @@ -1624,7 +1624,7 @@ <h1>The forces don’t sum to zero<a class="headerlink" href="#the-forces-don-t-
</div>
</div>
<div class="cell_output docutils container">
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>array([9.9942554e-08, 7.0082024e-08, 4.7683716e-07], dtype=float32)
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>array([ 5.9837475e-08, 1.5040860e-07, -1.1920929e-07], dtype=float32)
</pre></div>
</div>
</div>
Expand Down
Loading

0 comments on commit df180e7

Please sign in to comment.