Downloads · 30 days
6
14% of all-time downloads
mistral-7b-javelin-med
JAVELINIQ/mistral-7b-javelin-med
mistral-7b-javelin-med is a machine learning model from JAVELINIQ. 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
43
Public
Repo size
6.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other5.1 GB · 73%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jan 10, 2024
- Updated
- Jan 10, 2024
- SHA
- c241c945
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. -->
results
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6561
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 35
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2796 | 0.03 | 1 | 1.9554 |
| 1.9123 | 0.06 | 2 | 1.8254 |
| 1.7373 | 0.1 | 3 | 1.7547 |
| 1.6876 | 0.13 | 4 | 1.7071 |
| 1.5121 | 0.16 | 5 | 1.6439 |
| 1.5555 | 0.19 | 6 | 1.5802 |
| 1.6819 | 0.23 | 7 | 1.5222 |
| 1.5466 | 0.26 | 8 | 1.4651 |
| 1.2546 | 0.29 | 9 | 1.4119 |
| 1.4173 | 0.32 | 10 | 1.3616 |
| 1.289 | 0.35 | 11 | 1.3113 |
| 1.1334 | 0.39 | 12 | 1.2597 |
| 0.998 | 0.42 | 13 | 1.2060 |
| 1.2082 | 0.45 | 14 | 1.1604 |
| 1.1204 | 0.48 | 15 | 1.1122 |
| 0.9308 | 0.52 | 16 | 1.0729 |
| 1.0806 | 0.55 | 17 | 1.0349 |
| 0.9216 | 0.58 | 18 | 1.0002 |
| 1.5421 | 0.61 | 19 | 0.9663 |
| 0.9529 | 0.65 | 20 | 0.9324 |
| 0.9047 | 0.68 | 21 | 0.9058 |
| 0.7054 | 0.71 | 22 | 0.8831 |
| 0.9573 | 0.74 | 23 | 0.8534 |
| 0.7545 | 0.77 | 24 | 0.8271 |
| 0.5951 | 0.81 | 25 | 0.8009 |
| 0.7478 | 0.84 | 26 | 0.7760 |
| 0.5568 | 0.87 | 27 | 0.7524 |
| 0.509 | 0.9 | 28 | 0.7315 |
| 0.5254 | 0.94 | 29 | 0.7106 |
| 0.3855 | 0.97 | 30 | 0.6943 |
| 0.7881 | 1.0 | 31 | 0.6823 |
| 0.5597 | 1.03 | 32 | 0.6724 |
| 0.2829 | 1.06 | 33 | 0.6641 |
| 0.2637 | 1.1 | 34 | 0.6587 |
| 0.396 | 1.13 | 35 | 0.6561 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.0.0
- Datasets 2.16.1
- Tokenizers 0.15.0
- Library
- peft
- License
- apache-2.0
- Created
- Jan 10, 2024
- Updated
- Jan 10, 2024