|
--- |
|
license: apache-2.0 |
|
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Context aware splitter 1.1b |
|
results: [] |
|
datasets: |
|
- mhenrichsen/context-aware-splits-english |
|
language: |
|
- en |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
# Context aware splitter 1.1b |
|
|
|
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0598 |
|
|
|
## Model description |
|
- This model is used to split texts in a context aware way. Used for RAG applications. |
|
- This model is based off TinyLLaMA 1.1b |
|
It uses the Alpaca format: |
|
|
|
``` |
|
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. |
|
|
|
### Instruction: |
|
Your task is to segment text into smaller blocks. Split the text where it makes sense and be vary of the context. The ideal split should be close to {WORD_COUNT} words. |
|
|
|
### Input: |
|
Q: Information/File Manager I'm looking for a file manager application which helps to organize a large amount of movies, pictures, music, text documents, databases, audio-books and ebooks. Right now I only use the Finder which doesn't work well, because I really need a function to put single files into multiple categories. Simply using the file system for this creates a confusing nesting of files. A: Depending on the number of categories you require to handle, you could always use a combination of the finder with the built in label functionality, thus a movie can be held in one area (movies directory, for example), but "tagged" as something else. Using smart directories and saved searches you can view your files by a combination of the attributes (location, label, media type) to create custom views. All without purchasing software. Cheap and cheerful, but may be suitable to your needs. A: Maybe use a file manager that supports Open Meta. Or use symbolic links for organizing all your media files. Or even use hardlinked files if you dare. |
|
|
|
### Response: |
|
``` |
|
|
|
Response: |
|
``` |
|
{'splits': ["Q: Information/File Manager I'm looking for a file manager application which helps to organize a large amount of movies, pictures, music, text documents, databases, audio-books and ebooks. Right now I only use the Finder which doesn't work well, because I really need a function to put single files into multiple categories. Simply using the file system for this creates a confusing nesting of files.", 'A: Depending on the number of categories you require to handle, you could always use a combination of the finder with the built in label functionality, thus a movie can be held in one area (movies directory, for example), but "tagged" as something else. Using smart directories and saved searches you can view your files by a combination of the attributes (location, label, media type) to create custom views. All without purchasing software. Cheap and cheerful, but may be suitable to your needs.', 'A: Maybe use a file manager that supports Open Meta. Or use symbolic links for organizing all your media files. Or even use hardlinked files if you dare.'], 'topic': 'Discussion on file manager applications for organizing large amount of media files.'} |
|
``` |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 0.0002 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 10 |
|
- num_epochs: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.9849 | 0.03 | 1 | 2.0811 | |
|
| 1.3107 | 0.17 | 5 | 1.1992 | |
|
| 0.6399 | 0.34 | 10 | 0.6359 | |
|
| 0.2779 | 0.51 | 15 | 0.2862 | |
|
| 0.1807 | 0.68 | 20 | 0.1634 | |
|
| 0.1256 | 0.85 | 25 | 0.1177 | |
|
| 0.097 | 1.0 | 30 | 0.0891 | |
|
| 0.1063 | 1.17 | 35 | 0.0734 | |
|
| 0.0769 | 1.34 | 40 | 0.0723 | |
|
| 0.0694 | 1.51 | 45 | 0.0633 | |
|
| 0.0687 | 1.69 | 50 | 0.0624 | |
|
| 0.0575 | 1.86 | 55 | 0.0622 | |
|
| 0.0516 | 2.01 | 60 | 0.0609 | |
|
| 0.0582 | 2.18 | 65 | 0.0603 | |
|
| 0.0611 | 2.35 | 70 | 0.0600 | |
|
| 0.0515 | 2.52 | 75 | 0.0598 | |
|
| 0.0704 | 2.69 | 80 | 0.0598 | |
|
| 0.0525 | 2.86 | 85 | 0.0598 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |