Merge branch 'main' of https://github.com/FAIR-Chem/fairchem into eqv…

…2_dens # Conflicts: # src/fairchem/core/common/utils.py # src/fairchem/core/modules/evaluator.py # src/fairchem/core/modules/loss.py # src/fairchem/core/trainers/ocp_trainer.py
FAIR-Chem · Oct 31, 2024 · 6ac0683 · 6ac0683
2 parents ebde98c + fbec2d3
commit 6ac0683
Show file tree

Hide file tree

Showing 26 changed files with 1,876 additions and 262 deletions.
diff --git a/docs/core/datasets/oc20.md b/docs/core/datasets/oc20.md
@@ -134,9 +134,115 @@ Each tarball has README file containing details about file formats, number of st
 
 #### Per-adsorbate trajectories (optional download)
 
-Adsorbate+catalyst trajectories on a per adsorbate basis are provided [here](./DATASET_PER_ADSORBATE.md) to avoid having to download all systems. Note - a few adsorbates are intentionally left out for the test splits.
+Download links are in the table below:
+
+|Adsorbate symbol	|Downloadable path	|size	|MD5 checksum	|
+|---	|---	|---	|---	|
+|*O	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/0.tar	|1006M	|d4151542856b4b6405f276808f75358a	|
+|*H	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/1.tar	|850M	|3697f04faf04251a23da8b88a78209f7	|
+|*OH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/2.tar	|1.6G	|a21081f3f55eb0c98a91021bbe3dac44	|
+|*OH2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/3.tar	|1.8G	|b12b706854f5d899e02a9ae6578b5d45	|
+|*C	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/4.tar	|1.1G	|e4fe9890764fcf59e01e3ceab089b978	|
+|*CH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/6.tar	|1.4G	|ec9aa2c4c4bd4419359438ba7fbb881d	|
+|*CHO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/7.tar	|1.4G	|d32200f74ad5c3bfd42e8835f36d57ab	|
+|*COH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/8.tar	|1.6G	|5418a1b331f6c7689a5405cca4cc8d15	|
+|*CH2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/9.tar	|1.6G	|8ee1066149c305d7c17c219b369c5a73	|
+|*CH2*O	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/10.tar	|1.7G	|960c2450814024b66f3c79121179ac60	|
+|*CHOH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/11.tar	|1.8G	|60ac9f965f9589a3389483e3d1e58144	|
+|*CH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/12.tar	|1.7G	|7e123e6f4fb10d6897be3f47721dfd4a	|
+|*OCH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/13.tar	|1.8G	|0823047bbbe05fa0e63f9d83ec601487	|
+|*CH2OH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/14.tar	|1.9G	|9ac71e198d75b1427182cd34abb73e4d	|
+|*CH4	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/15.tar	|1.9G	|a405ce403018bf8afbd4425d5c0b34d5	|
+|*OHCH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/16.tar	|2.1G	|d3c829f1952db6e4f428273ee05f59b1	|
+|*C*C	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/17.tar	|1.5G	|d687a151345305897b9245af4b0f9967	|
+|*CCO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/18.tar	|1.7G	|214ca96e620c5ec6e8a6ff8144a22a04	|
+|*CCH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/19.tar	|1.6G	|da2268545e80ca1664026449dd2fdd24	|
+|*CHCO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/20.tar	|1.7G	|386c99407fe63080d26cda525dfdd8cd	|
+|*CCHO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/21.tar	|1.8G	|918b20960438494ab160a9dbd9668157	|
+|*COCHO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/22.tar	|1.8G	|84424aa2ad30301e23ece1438ea39923	|
+|*CCHOH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/23.tar	|2.0G	|3cc90425ec042a70085ba7eb2916a79a	|
+|*CCH2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/24.tar	|1.8G	|9dbcf7566e40965dd7f8a186a75a718e	|
+|*CH*CH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/25.tar	|1.7G	|a193b4c72f915ba0b21a41790696b23c	|
+|CH2*CO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/26.tar	|1.8G	|de83cf50247f5556fa4f9f64beff1eeb	|
+|*CHCHO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/27.tar	|1.9G	|1d140aaa2e7b287124ab38911a711d70	|
+|*CH*COH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/28.tar	|1.3G	|682d8a6b05ca5948b34dc5e5f6bbcd61	|
+|*COCH2O	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/29.tar	|1.9G	|c8742faa8ca40e8edb4110069817fa70	|
+|*CHO*CHO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/30.tar	|2.0G	|8cfbb67beb312b98c40fcb891dfa480a	|
+|*COHCHO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/31.tar	|1.9G	|6ffa903a62d8ec3319ecec6a03b06276	|
+|*COHCOH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/32.tar	|2.0G	|caca0058b641bfdc9f8de4527e60feb7	|
+|*CCH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/33.tar	|1.8G	|906543aaefc171edab388ff4f0fe8a20	|
+|*CHCH2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/34.tar	|1.8G	|4dfab479495f76179749c1956046fbd8	|
+|*COCH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/35.tar	|1.9G	|29d1b992715054e920e8bb2afe97b393	|
+|*CHCHOH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/38.tar	|2.0G	|9e5912df6f7b11706d1046cdb9e3087e	|
+|*CCH2OH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/39.tar	|2.1G	|7bcae43cee451306e34ec416588a7f09	|
+|*CHOCHOH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/40.tar	|2.0G	|f98866d08fe3451ae7ebc47bb51599aa	|
+|*COCH2OH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/41.tar	|1.4G	|bfaf689e5827fcf26c51e567bb8dd1be	|
+|*COHCHOH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/42.tar	|2.0G	|236fe4e950aa2fbdde94ef2821fb48d2	|
+|*OCHCH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/44.tar	|2.1G	|66acc5460a999625c3364f0f3bcca871	|
+|*COHCH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/45.tar	|2.1G	|bb4a01956736399c8cee5e219f8c1229	|
+|*CHOHCH2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/46.tar	|2.1G	|e836de4ec146b1b611533f1ef682cace	|
+|*CHCH2OH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/47.tar	|2.0G	|66df44121806debef6dc038df7115d1d	|
+|*OCH2CHOH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/48.tar	|2.2G	|ff6981fdbcd2e65d351505c15d218d76	|
+|*CHOCH2OH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/49.tar	|2.1G	|448f7d352ab6e32f754e24de64ca302a	|
+|*COHCH2OH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/50.tar	|2.1G	|8bff6bf3e10cc84acc4a283a375fcc23	|
+|*CHOHCHOH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/51.tar	|2.0G	|9c9e4d617d306751760a80f1453e71f1	|
+|*CH2CH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/52.tar	|2.0G	|ec1e964d2ee6f468fa5773743e3994a4	|
+|*OCH2CH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/53.tar	|2.1G	|d297b27b02822f9b6af80bdb64aee819	|
+|*CHOHCH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/54.tar	|2.1G	|368de083dafdc3bbdb560d35e2a102c0	|
+|*CH2CH2OH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/55.tar	|2.1G	|3c1aaf790659f7ff89bf1eed8b396b63	|
+|*CHOHCH2OH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/56.tar	|2.2G	|2d71adb9e305e6f3bca49e5df9b5a86a	|
+|*OHCH2CH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/57.tar	|2.3G	|cf51128f8522b7b66fc68d79980d6def	|
+|*NH2N(CH3)2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/58.tar	|1.6G	|36ba974d80c20ff636431f7c0ad225da	|
+|*ONN(CH3)2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/59.tar	|2.3G	|fdc4cd19977496909d61be4aee61c4f1	|
+|*OHNNCH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/60.tar	|2.1G	|50a6ff098f9ba7adbba9ac115726cc5a	|
+|*ONH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/62.tar	|1.8G	|47573199c545afe46c554ff756c3e38f	|
+|*NHNH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/63.tar	|1.7G	|dd456b7e19ef592d9f0308d911b91d7c	|
+|*N*NH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/65.tar	|1.6G	|c05289fd56d64c74306ebf57f1061318	|
+|*NO2NO2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/67.tar	|2.1G	|4822a06f6c5f41bdefd3cbbd8856c11f	|
+|*N*NO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/68.tar	|1.6G	|2a27de122d32917cc5b6ac0a21c63c1c	|
+|*N2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/69.tar	|1.5G	|cc668fecf679b6edaac8fd8fb9cdd404	|
+|*ONNH2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/70.tar	|2.1G	|dff880f1a5baa7f67b52fd3ed745443d	|
+|*NH2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/71.tar	|1.6G	|c7f383b50faa6244e265c9611466cb8f	|
+|*NH3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/72.tar	|1.9G	|2b355741f9300445703270e0e4b8c01c	|
+|*NONH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/73.tar	|1.8G	|48877a0c6f2994baac82cb722711aaa2	|
+|*NH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/74.tar	|1.4G	|7979b9e7ab557d6979b33e352486f0ef	|
+|*NO2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/75.tar	|1.7G	|9f352fbc32bb2b8caf4788aba28b2eb7	|
+|*NO	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/76.tar	|1.4G	|482ee306a5ae2eee78cac40d10059ebc	|
+|*N	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/77.tar	|1.1G	|bfb6e03d4a687987ff68976f0793cc46	|
+|*NO3	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/78.tar	|1.8G	|700834326e789a6e38bf3922d9fcb792	|
+|*OHNH2	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/79.tar	|2.1G	|fa24472e0c02c34d91f3ffe6b77bfb11	|
+|*ONOH	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/80.tar	|1.4G	|4ddcccd62a834a76fe6167461f512529	|
+|*CN	|https://dl.fbaipublicfiles.com/opencatalystproject/data/per_adsorbate_is2res/81.tar	|1.5G	|bc7c55330ece006d09496a5ff01d5d50	|
 
 
+Note - A few adsorbates are intentionally left out for the test splits.
+
+Downloading any of the above and extracting will result in a folder :
+
+`<index>/`
+
+* `system.txt` Text file containing information about the different adsorbate+catalyst system names. In total there are N systems. More details described below.
+* `<index>/`
+    * This contains N compressed trajectory files of the format `.extxyz.xz`.
+    * Files are named as  `<system_id>.extxyz.xz` (where `system_id` is defined below).
+
+
+where, `<index>` can be 0 to 81. N is dependent on which adsorbate index is chosen.
+
+
+
+The file  `system.txt`  has information in the following format:
+`system_id,reference_energy`
+
+where:
+
+* `system_id `- Internal random ID corresponding to an adsorbate+catalyst system.
+* `reference_energy` - Energy used to reference system energies to bare catalyst+gas reference energies. Used for adsorption energy calculations.
+
+
+The `.extxyz.xz` files are LZMA compressed `.extxyz` trajectory files. Each trajectory corresponds to a relaxation trajectory of a different adsorbate+catalyst system. Information about the `.extxyz` trajectory file format may be found at https://wiki.fysik.dtu.dk/ase/dev/ase/io/formatoptions.html#extxyz .
+
+In order to uncompress the files, `uncompress.py` provides a multi-core implementation which could be used.
 
 ### Catalyst system trajectories (optional download)
 

diff --git a/packages/fairchem-core/pyproject.toml b/packages/fairchem-core/pyproject.toml
@@ -22,7 +22,8 @@ dependencies = [
     "requests",
     "orjson",
     "tqdm",
-    "submitit"
+    "submitit",
+    "hydra-core"
 ]
 
 [project.optional-dependencies]  # add optional dependencies to be installed as pip install fairchem.core[dev]

diff --git a/packages/requirements-optional.txt b/packages/requirements-optional.txt
@@ -1,4 +1,4 @@
-torch_geometric==2.6.0
+torch_geometric==2.6.1
 -f https://data.pyg.org/whl/torch-2.4.0+cpu.html
 torch_scatter==2.1.2
 torch_sparse==0.6.18