Downloads · 30 days
7
13% of all-time downloads
mistral-7b-legal-lora
aarushidicious1/mistral-7b-legal-lora
mistral-7b-legal-lora is a machine learning model from aarushidicious1. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
52
Public
Parameters
7.2B
16 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.7 GB · 100%
At a glance
- Library
- peft
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Feb 7, 2025
- Updated
- Mar 7, 2025
- SHA
- ece51ec0
Base models
Model card
From the Hugging Face model README
<!-- 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. -->
mistral-7b-legal-lora
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3576
Model description
More information needed
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: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3309 | 0.3929 | 100 | 1.5693 |
| 1.1568 | 0.7859 | 200 | 1.0259 |
| 0.769 | 1.1768 | 300 | 0.7513 |
| 0.6402 | 1.5697 | 400 | 0.6505 |
| 0.5844 | 1.9627 | 500 | 0.5912 |
| 0.544 | 2.3536 | 600 | 0.5423 |
| 0.5056 | 2.7466 | 700 | 0.5103 |
| 0.4821 | 3.1375 | 800 | 0.4866 |
| 0.4416 | 3.5305 | 900 | 0.4645 |
| 0.4135 | 3.9234 | 1000 | 0.4332 |
| 0.3833 | 4.3143 | 1100 | 0.4058 |
| 0.3734 | 4.7073 | 1200 | 0.3918 |
| 0.3546 | 5.0982 | 1300 | 0.3831 |
| 0.367 | 5.4912 | 1400 | 0.3771 |
| 0.3376 | 5.8841 | 1500 | 0.3712 |
| 0.3317 | 6.2750 | 1600 | 0.3695 |
| 0.3376 | 6.6680 | 1700 | 0.3665 |
| 0.3405 | 7.0589 | 1800 | 0.3646 |
| 0.3312 | 7.4519 | 1900 | 0.3628 |
| 0.3304 | 7.8448 | 2000 | 0.3618 |
| 0.3077 | 8.2358 | 2100 | 0.3604 |
| 0.3378 | 8.6287 | 2200 | 0.3589 |
| 0.3269 | 9.0196 | 2300 | 0.3580 |
| 0.3198 | 9.4126 | 2400 | 0.3580 |
| 0.3208 | 9.8055 | 2500 | 0.3576 |
Framework versions
- PEFT 0.14.0
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
- Library
- peft
- Type
- mistral
- License
- apache-2.0
- Created
- Feb 7, 2025
- Updated
- Mar 7, 2025