Merge branch 'main' of github.com:HazyResearch/zoology into main

HazyResearch · Feb 8, 2024 · de4e258 · de4e258
2 parents 9676843 + 1e01588
commit de4e258
Show file tree

Hide file tree

Showing 15 changed files with 1,451 additions and 11 deletions.
diff --git a/LICENSE.md b/LICENSE.md
@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2021 The Meerkat Team.
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
diff --git a/README.md b/README.md
@@ -1,5 +1,5 @@
 <div align="center" >
-    <img src="banner.png" height=150 alt="Meerkat logo" style="margin-bottom:px"/> 
+    <img src="assets/banner.png" height=150 alt="Meerkat logo" style="margin-bottom:px"/> 
 
 [![GitHub](https://img.shields.io/github/license/HazyResearch/meerkat)](https://img.shields.io/github/license/HazyResearch/meerkat)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
@@ -9,7 +9,7 @@
 
 </div>
 
-Zoology provides machine learning researchers with a simple playground for understanding and testing language model architectures on synthetic tasks. This repository can be used to reproduce the results in our paper *[Zoology: Measuring and Improving Recall in Efficient Language Models](https://arxiv.org/abs/2312.04927)*.
+Zoology provides machine learning researchers with a simple playground for understanding and testing language model architectures on synthetic tasks. This repository can be used to reproduce the results in our paper *[Zoology: Measuring and Improving Recall in Efficient Language Models](https://arxiv.org/abs/2312.04927)*. See the section on [reproducing paper experiments](#reproducing-paper-experiments) for details.
 
 ---
 
@@ -30,7 +30,7 @@ pip install -e .[extra,analysis]
 ```
 If you want to keep this install as lightweight as possible; the only required dependencies are: `torch, einops, tqdm, pydantic, wandb`. There is some extra functionality (*e.g.* launching sweeps in parallel with Ray) that require additional dependencies. To install without the optional dependencies, run `pip install -e .`.
 
-Then, try running an example experiments with: 
+Then, try running an example experiment with: 
 ```
 python -m zoology.launch zoology/experiments/examples/basic.py
 ```
@@ -40,6 +40,24 @@ python -m zoology.launch zoology/experiments/examples/basic_sweep.py
 ```
 If you have access to multiple GPUs, you can run the sweep in parallel by adding the `-p` flag.
 
+
+## Reproducing paper experiments
+ In this section, we'll show how to reproduce the results in our paper *[Zoology: Measuring and Improving Recall in Efficient Language Models](https://arxiv.org/abs/2312.04927)* and [blogpost](https://hazyresearch.stanford.edu/blog/2023-12-11-zoology1-analysis).
+
+ The main synthetic data results in our work are summarized in Figure 2. The x-axis is the model dimension and the y-axis is accuracy on Mqar. Increasing the sequence
+length correlates with increased task difficulty. The results shown are the maximum performance for each model over four learning rates.
+<div align="center" >
+    <img src="assets/figure2.png" height=150 alt="Figure 2" style="margin-bottom:px"/> 
+</div>
+
+To reproduce these results, ensure you have WandB setup to log all the results and then run the command:
+```
+python -m zoology.launch zoology/experiments/paper/figure2.py -p
+```
+Note that there are 448 model/data configurations in this sweep, so it takes a while to run. We ran most of our experiments on an 8xA100 with the `-p` flag, which launches configurations in parallel. To run a smaller scale experiment, you can modify the loops in `figure2.py` file to only include a subset of the configurations you're interested in (*e.g.* you can drop some models, sequence lengths, or learning rates). For more details on how the experiments are configured, see the [configuration section](#configuration-experiments-and-sweeps).
+
+To produce the plot after the run, see the plotting code `zoology/analysis/paper/figure2.py`.
+
 ## Configuration, Experiments, and Sweeps
 In this section, we'll walk through how to configure an experiment and launch sweeps. 
 
@@ -169,8 +187,6 @@ When you launch an experiment with this configuration, the `my_data_builder` fun
 **Caching dataset creation.** Sometimes it's useful to cache the dataset creation process, especially if it's expensive. To do so you can pass a `cache_dir` to the `DataConfig`: `DataConfig(..., cache_dir="my_cache_dir")`.
 
 
-
-
 ## About 
 
 This repo is being developed by members of the HazyResearch group. 

diff --git a/banner.png → assets/banner.png b/banner.png → assets/banner.png
diff --git a/assets/figure2.png b/assets/figure2.png
diff --git a/zoology/analysis/paper/figure2.py b/zoology/analysis/paper/figure2.py
@@ -0,0 +1,71 @@
+import os
+
+import pandas as pd
+from tqdm import tqdm
+import numpy as np
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+from zoology.analysis.utils import fetch_wandb_runs
+
+
+
+
+def plot(
+    df: pd.DataFrame,
+    max_seq_len: int = 512,
+):
+
+    plot_df = df.groupby([
+        "model.sequence_mixer.name",
+        "model.d_model",
+        "data.input_seq_len",
+    ])["valid/accuracy"].max().reset_index()
+
+    run_dir = "/var/cr05_data/sim_data/code/petting-zoo/"
+    sns.set_theme(style="whitegrid")
+    g = sns.relplot(
+        data=plot_df[plot_df["data.input_seq_len"] <= max_seq_len],
+        y="valid/accuracy",
+        col="data.input_seq_len",
+        x="model.d_model",
+        hue="model.sequence_mixer.name",
+        kind="line",
+        marker="o",
+        height=2.25,
+        aspect=1,
+    )
+    g.set(xscale="log", ylabel="Accuracy", xlabel="Model dimension")
+
+    # Set custom x-ticks
+    ticks = [64, 128, 256, 512] # Modify this list as needed
+    for ax in g.axes.flat:
+        ax.set_xticks(ticks)
+        ax.get_xaxis().set_major_formatter(plt.ScalarFormatter()) # This will keep the tick labels as integers rather than in scientific notation
+
+    # Set custom y-ticks
+    y_ticks = [0, 0.25, 0.5, 0.75, 1.0]
+    for ax in g.axes.flat:
+        ax.set_yticks(y_ticks)
+
+    for ax, title in zip(g.axes.flat, g.col_names):
+        ax.set_title(f"Sequence Length: {title}")
+
+
+if __name__ == "__main__" :
+    df = fetch_wandb_runs(
+        launch_id=[
+            "default-2023-10-25-22-20-38", 
+            "default-2023-10-26-19-09-31",
+            "default-2023-10-27-04-13-56",
+            "default-2023-10-29-17-31-26",
+            "default-2023-11-12-00-31-44",
+            "default-2023-11-13-00-31-15",
+            "default-2023-11-13-00-42-27"
+        ], 
+        project_name="zoology"
+    )
+
+    df["data.input_seq_len"] = df["data.input_seq_len"].fillna(df["data.0.input_seq_len"])
+    plot(df=df, max_seq_len=1024)
+    plt.savefig("results.pdf")
diff --git a/zoology/data/associative_recall.py b/zoology/data/associative_recall.py
@@ -136,7 +136,7 @@ def _ar(
     inputs[:, 0:context_size] = kvs
 
     # create a matrix of indices, which is needed to index correctly below 
-    rows = np.tile(np.arange(num_examples), (3, 1)).T  
+    rows = np.tile(np.arange(num_examples), (num_queries, 1)).T  
 
     # sample random kv pairs to use for the queries
     kv_idx_choices = np.arange(0, num_kv_pairs)

diff --git a/zoology/experiments/mqar_d_model.py → zoology/experiments/mqar_dmodel.py b/zoology/experiments/mqar_d_model.py → zoology/experiments/mqar_dmodel.py
@@ -72,6 +72,12 @@
                         "l_max": input_seq_len,
                     },
                 ),
+                "rwkv5": dict(
+                    name="zoology.mixers.rwkv5.RWKVTimeMixer",
+                    kwargs={
+                        "l_max": input_seq_len,
+                    },
+                ),
                 "base_conv": dict(
                     name="zoology.mixers.base_conv.BaseConv",
                     kwargs={