File size: 5,306 Bytes
f8946de 218eab5 f8946de ba23b3d f8946de 218eab5 f8946de 218eab5 f8946de 218eab5 f8946de 218eab5 f8946de 218eab5 f8946de 218eab5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
---
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: storage/context
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)
# storage/context
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the mhenrichsen/context-aware-splits-english dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0253
## Model description
- This model is used to split texts in a context aware way. Used for RAG applications.
- This model is an adapter for Mistral 7b.
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.'}
```
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.1557 | 0.01 | 1 | 0.1552 |
| 0.0936 | 0.05 | 6 | 0.0695 |
| 0.0447 | 0.1 | 12 | 0.0413 |
| 0.0347 | 0.16 | 18 | 0.0357 |
| 0.0314 | 0.21 | 24 | 0.0324 |
| 0.0306 | 0.26 | 30 | 0.0309 |
| 0.0276 | 0.31 | 36 | 0.0294 |
| 0.028 | 0.36 | 42 | 0.0284 |
| 0.0307 | 0.41 | 48 | 0.0281 |
| 0.0276 | 0.47 | 54 | 0.0274 |
| 0.0251 | 0.52 | 60 | 0.0267 |
| 0.0244 | 0.57 | 66 | 0.0269 |
| 0.0268 | 0.62 | 72 | 0.0263 |
| 0.0249 | 0.67 | 78 | 0.0262 |
| 0.0252 | 0.73 | 84 | 0.0258 |
| 0.0259 | 0.78 | 90 | 0.0257 |
| 0.0241 | 0.83 | 96 | 0.0255 |
| 0.0241 | 0.88 | 102 | 0.0254 |
| 0.0253 | 0.93 | 108 | 0.0254 |
| 0.0234 | 0.98 | 114 | 0.0253 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0 |