add preload dataset in Dockerfile

Dockerfile

@@ -1,8 +1,17 @@
+# build with: docker build . --tag sctg/roco-idefics3:0.0.2 --tag sctg/roco-idefics3:latest --push
 FROM ovhcom/ai-training-pytorch:latest
 RUN source /workspace/.miniconda3/bin/activate \
-    && pip install -U "safetensors>=0.4.5" \
+    && pip install -U "safetensors>=0.4.5" bitsandbytes\
     && pip install -U git+https://github.com/huggingface/transformers.git\
     && pip install huggingface_hub accelerate datasets peft\
     && pip install -U Pillow
 COPY --chmod=777 start.sh /start.sh
 COPY learn.py /learn.py
+COPY preload.py /preload.py
+# Mandatory to run the jobs in rootless mode
+USER root
+RUN chown -R 42420:42420 /workspace
+USER 42420
+RUN source /workspace/.miniconda3/bin/activate \
+    && mkdir -p /workspace/data \
+    && python /preload.py

LICENSE.md

@@ -0,0 +1,194 @@
+Apache License
+==============
+
+_Version 2.0, January 2004_  
+_&lt;<http://www.apache.org/licenses/>&gt;_
+
+### 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 2024 Ronan Le Meillat
+    
+    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.

README.md

@@ -23,11 +23,11 @@ This repository contains a fine-tuned version of the Hugging Face [Idefics3-8B-L
 * **Base Model:** Idefics3-8B-Llama3
 * **Fine-tuning Dataset:** Radiology Objects in Context (ROCO)
 * **License:** Apache-2.0
-* **Current Status:** Fine-tuning process is currently halted at checkpoint 2350 (out of 12,267) due to limitations with Colab Free T4 GPU unit. Contributions to complete the fine-tuning process are welcome!
+* **Current Status:** Fine-tuning process is currently halted at checkpoint 2350 (out of 12,267) (in branch bug-restart) due to limitations with Colab Free T4 GPU unit. Contributions to complete the fine-tuning process are welcome!
 
 ### Training Progress Status
 
-* Current checkpoint: 2350/12267 (~19% completed)
+* Current checkpoint: 2350/12267 (~19% completed) (in branch bug-restart)
 * Estimated remaining GPU time: ~57 hours
 * Hardware requirements: T4 GPU with >16GB VRAM
 * Last update: november, 8th 2024
@@ -60,12 +60,22 @@ If you use this model in your work, please cite the original Idefics3 model and
 
 2. **Getting Started**
    * Fork the repository
-   * Resume from checkpoint 2350/12267
+   * Resume from checkpoint 2350/12267 (in branch bug-restart)
    * Follow instructions in [ROCO-idefics3.ipynb](https://huggingface.co/eltorio/IDEFICS3_ROCO/blob/main/ROCO-idefics3.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/#fileId=https://huggingface.co/eltorio/IDEFICS3_ROCO/blob/main/ROCO-idefics3.ipynb)
 
 3. **Contact**
    * For questions: [link to issues/discussions](https://huggingface.co/eltorio/IDEFICS3_ROCO/discussions)
 
+### Docker Image
+
+A AI training docker image is available for this model. The image and includes all necessary dependencies to run the fine-tuning process. The image is available on Docker Hub:  
+
+```bash
+docker run --user=42420:42420 -it sctg/roco-idefics3:latest /start.sh hf_TOKEN
+```
+
+The Dockerfile is available in the [IDEFICS_ROCO repository](https://huggingface.co/eltorio/IDEFICS3_ROCO/blob/main/Dockerfile).
+
 ### Acknowledgments
 
 This work was made possible by the [Hugging Face Transformers](https://huggingface.co/) library and the [ROCO-radiology dataset](https://huggingface.co/datasets/eltorio/ROCO-radiology).

learn.py

@@ -1,3 +1,6 @@
+# Copyright (C) 2024 Ronan Le Meillat
+# License: Apache License 2.0
+# Description: Train the model on the dataset
 import os
 import torch
 
@@ -5,6 +8,8 @@ from huggingface_hub import login as hf_login
 from datasets import load_dataset
 from peft import LoraConfig
 from transformers import AutoProcessor, BitsAndBytesConfig, Idefics3ForConditionalGeneration, TrainingArguments, Trainer
+from datasets.utils.logging import disable_progress_bar
+disable_progress_bar()
 
 HF_TOKEN = ""
 
@@ -21,8 +26,8 @@ prompt= "You are an expert radiologist certified with over 15 years of experienc
 source_model_id = "HuggingFaceM4/Idefics3-8B-Llama3"
 destination_model_id = "eltorio/ROCO-idefics3-8B"
 output_dir = "IDEFICS3_ROCO"
-
-train_dataset = load_dataset(dataset_id, split="train")
+cache_dir = "/workspace/data"
+train_dataset = load_dataset(dataset_id, split="train", cache_dir=cache_dir)
 
 DEVICE = "cuda:0"
 USE_LORA = False

preload.py

@@ -0,0 +1,6 @@
+# Description: Preload the dataset to cache_dir
+# Copyright (C) 2024 Ronan Le Meillat
+# License: Apache License 2.0
+from datasets import load_dataset
+dataset_id = "eltorio/ROCO-radiology"
+train_dataset = load_dataset(dataset_id, split="train", cache_dir=cache_dir)