deploy: 87e111f

_downloads/5fdddbed2260616231dbf7b0d94bb665/train.txt

@@ -1,17 +1,17 @@
-2024-04-14 18:46:02 (INFO): Project root: /home/runner/work/ocp/ocp
+2024-04-14 19:19:53 (INFO): Project root: /home/runner/work/ocp/ocp
 /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(
-2024-04-14 18:46:03 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
-2024-04-14 18:46:03 (INFO): amp: true
+2024-04-14 19:19:54 (WARNING): Detected old config, converting to new format. Consider updating to avoid potential incompatibilities.
+2024-04-14 19:19:54 (INFO): amp: true
 cmd:
-  checkpoint_dir: fine-tuning/checkpoints/2024-04-14-18-46-24-ft-oxides
-  commit: 962bffa
+  checkpoint_dir: fine-tuning/checkpoints/2024-04-14-19-20-32-ft-oxides
+  commit: 87e111f
   identifier: ft-oxides
-  logs_dir: fine-tuning/logs/wandb/2024-04-14-18-46-24-ft-oxides
+  logs_dir: fine-tuning/logs/wandb/2024-04-14-19-20-32-ft-oxides
   print_every: 10
-  results_dir: fine-tuning/results/2024-04-14-18-46-24-ft-oxides
+  results_dir: fine-tuning/results/2024-04-14-19-20-32-ft-oxides
   seed: 0
-  timestamp_id: 2024-04-14-18-46-24-ft-oxides
+  timestamp_id: 2024-04-14-19-20-32-ft-oxides
 dataset:
   a2g_args:
     r_energy: true

_sources/tutorials/advanced/embeddings.md

@@ -32,14 +32,16 @@ We provide 5 different kinds of embeddings:
 4. 'x_E sum' - summed over atoms
 5. 'x_F sum' - This is related to the forces
 
-In principle other models could be adapted in a similar way. See [embedding-monkeypatch.py](./embedding-monkeypatch.py) for details on the patch. We simply run this notebook below to load it.
+In principle other models could be adapted in a similar way. See [embedding-monkeypatch.py](./embedding-monkeypatch.py) for details on the patch. We simply load the module to monkeypatch GemNet-OC.
 
-The OCP project is still under active development, and it is not yet clear what the best way to access these embeddings are, so this code is not yet part of the main development branch. This code was adapted from a branch at https://github.com/Open-Catalyst-Project/ocp/blob/gnoc-embeddings.
 
 ```{code-cell} ipython3
 import embedding_monkeypatch
 ```
 
+The OCP project is still under active development, and it is not yet clear what the best way to access these embeddings are, so this code is not yet part of the main development branch. This code was adapted from a branch at https://github.com/Open-Catalyst-Project/ocp/blob/gnoc-embeddings.
+
+
 # A diagnostic example
 
 Here we will look at an equation of state for bulk fcc Cu.
@@ -109,6 +111,8 @@ x1, x2, x3 = out['h sum'], out['x_E sum'], out['x_F sum']
 Next, we loop over a grid of lattice constants, and we compare the cosine similarity of the embeddings for each one to the reference embeddings above. A similarity of 1 means they are the same, and as the similarity decreases it means the embbedings are more and more different (and so is the energy).
 
 ```{code-cell} ipython3
+import torch
+
 E = []
 
 LC = np.linspace(0.95 * a0, 1.05 * a0, 200)
@@ -192,11 +196,6 @@ embeddings = np.array(embeddings)
 embeddings.shape
 ```
 
-```{code-cell} ipython3
-%%capture
-! pip install umap-learn
-```
-
 Now we use a tool like umap. This will take the 40 vectors with 256 dimensions each, and reduce these to two dimennsions where similar embeddings remain close together. You should see two clusters. The one labeled 1 with 40 points is the bulk set.
 
 ```{code-cell} ipython3
@@ -261,9 +260,6 @@ Our database is very small, it only contains embeddings for ethanol and ethane.
 
 Note in this example, we have to tag all the atoms with 1 for GemnetOC to work.
 
-```{code-cell} ipython3
-! pip install vdict 2&>1 /devnull
-```
 
 Here we set up the simple database. Each row, or entry, is the actual embedding vector for an atom. That is the key that points to the atom index and the atoms object. I use cosine similarity here. If you use the default (l2) then you may not find anything close enough.
 

core/fine-tuning/fine-tuning-oxides.html

@@ -769,7 +769,7 @@ <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 71.2 seconds.
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Elapsed time 67.3 seconds.
 </pre></div>
 </div>
 <img alt="../../_images/92bd7f94dd548c8cfc2744eb5890cd23fada1ff98e8dc907657e2eb109af0402.png" src="../../_images/92bd7f94dd548c8cfc2744eb5890cd23fada1ff98e8dc907657e2eb109af0402.png" />
@@ -1128,7 +1128,7 @@ <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 = 5.1 seconds
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Elapsed time = 4.7 seconds
 </pre></div>
 </div>
 </div>
@@ -1144,7 +1144,7 @@ <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/2024-04-14-18-46-24-ft-oxides&#39;
+<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>&#39;fine-tuning/checkpoints/2024-04-14-19-20-32-ft-oxides&#39;
 </pre></div>
 </div>
 </div>
@@ -1194,7 +1194,7 @@ <h2>Running the training job<a class="headerlink" href="#running-the-training-jo
 <span class="g g-Whitespace">    </span><span class="mi">425</span> <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">mode</span><span class="p">):</span>
 <span class="ne">--&gt; </span><span class="mi">426</span>     <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="nb">open</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">mode</span><span class="p">))</span>
 
-<span class="ne">FileNotFoundError</span>: [Errno 2] No such file or directory: &#39;fine-tuning/checkpoints/2024-04-14-18-46-24-ft-oxides/checkpoint.pt&#39;
+<span class="ne">FileNotFoundError</span>: [Errno 2] No such file or directory: &#39;fine-tuning/checkpoints/2024-04-14-19-20-32-ft-oxides/checkpoint.pt&#39;
 </pre></div>
 </div>
 </div>

core/gotchas.html

@@ -929,7 +929,7 @@ <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>1.6722240447998047
+<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>1.6726934909820557
 </pre></div>
 </div>
 </div>
@@ -1433,7 +1433,7 @@ <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>-0.42973750829696655
+<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.4297369718551636
 </pre></div>
 </div>
 </div>
@@ -1483,17 +1483,17 @@ <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>1.213987445831299 1.0936112347774234e-06
-1.2139878273010254
-1.2139873504638672
-1.2139878273010254
-1.2139873504638672
-1.2139885425567627
-1.2139897346496582
-1.213987112045288
+<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>1.2139864683151245 1.2206006752176479e-06
+1.213986873626709
+1.2139849662780762
+1.2139849662780762
+1.2139880657196045
+1.213984489440918
 1.213986873626709
-1.2139856815338135
 1.2139861583709717
+1.2139873504638672
+1.213986873626709
+1.2139880657196045
 </pre></div>
 </div>
 </div>
@@ -1536,7 +1536,7 @@ <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([ 0.00847837,  0.01409242, -0.05882645], dtype=float32)
+<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>array([ 0.00847878,  0.01409772, -0.05882716], dtype=float32)
 </pre></div>
 </div>
 </div>
@@ -1549,7 +1549,7 @@ <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([-6.1525498e-08,  1.7229468e-08, -3.5762787e-07], dtype=float32)
+<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>array([ 5.1339157e-08,  4.6449713e-08, -1.1920929e-07], dtype=float32)
 </pre></div>
 </div>
 </div>